CN111462379A - Access control management method, system and medium containing palm vein and face recognition - Google Patents
Access control management method, system and medium containing palm vein and face recognition Download PDFInfo
- Publication number
- CN111462379A CN111462379A CN202010189226.6A CN202010189226A CN111462379A CN 111462379 A CN111462379 A CN 111462379A CN 202010189226 A CN202010189226 A CN 202010189226A CN 111462379 A CN111462379 A CN 111462379A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- palm vein
- feature
- palm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/161—Detection; Localisation; Normalisation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses an access control management method, a system and a medium containing palm veins and face recognition, wherein the method comprises the following steps: the method comprises the steps of collecting a face image and a palm vein image of a current user through an image collection module, then preprocessing the face image and the palm vein image, and carrying out in-vivo detection according to difference analysis; after the living body detection is carried out, respectively carrying out feature analysis on the collected face image and the collected palm vein image, and extracting to obtain a corresponding face feature image and a corresponding palm vein feature map; after the characteristic analysis is finished, respectively matching with a user identity template in a database according to the face characteristic image and the palm vein characteristic map to finally obtain an identity recognition result so as to control an access control system according to the identity recognition result; the user identity template comprises a face feature template and a palm vein feature template. The invention effectively improves the safety, reliability and practicability of the access control system by combining palm vein recognition, face recognition and living body detection.
Description
Technical Field
The invention relates to the technical field of security authentication, in particular to an access control management method, system and medium containing palm vein and face recognition.
Background
Along with scientific and technical progress, more and more occasions select to use entrance guard's equipment to promote the security in each aspect, and the mode of unblanking also is diversified, no longer limits to and uses traditional key to unblank, more uses electronic entrance guard's equipment to play the safety protection work. The existing electronic access control system mainly comprises IC card authentication, wearable equipment authentication, fingerprint authentication, face identification authentication and the like.
However, in the course of research and practice on the prior art, the inventors of the present invention found that the prior art has the following disadvantages: for example, external devices (IC cards, wearable devices, etc.) are inconvenient to carry, easy to lose, and easy to copy and steal; the accuracy of the fingerprint identification system is not high, the identification success rate is low in low-temperature and dry environments and the like, and the fingerprint identification system is easily influenced by the change of fingerprints; the face recognition system cannot achieve the purpose of completely accurately distinguishing whether the currently recognized image is a living organism or not, or the mounting position is too high, so that children or people with short heights cannot be conveniently used. Therefore, there is a need for an entrance guard management system that can improve security and utility in user identification.
Disclosure of Invention
The technical problem to be solved by the embodiments of the present invention is to provide a method, a system and a medium for door access management including palm vein and face recognition, which are suitable for operating on a face recognition intelligent lock device including palm vein recognition, and can perform living body detection on a recognition image, thereby improving the safety and reliability of a door access system.
In order to solve the above problems, an embodiment of the present invention provides an access control method including palm vein and face recognition, including at least the following steps:
acquiring a face image and a palm vein image of a current user through an image acquisition module;
respectively preprocessing the acquired face image and palm vein image, and performing in-vivo detection according to a difference analysis method;
after the living body detection is carried out, respectively carrying out feature analysis on the collected face image and the collected palm vein image, and extracting to obtain a corresponding face feature image and a corresponding palm vein feature map;
after the characteristic analysis is finished, respectively matching with a user identity template in a database according to the face characteristic image and the palm vein characteristic map to finally obtain an identity recognition result so as to control an access control system according to the identity recognition result; the user identity template comprises a face feature template and a palm vein feature template.
Further, the access control management method including palm vein and face recognition further includes:
and carrying out face registration and palm vein registration on the user in advance, and storing a registration result into a database.
Further, the access control management method including palm vein and face recognition further includes:
and presetting an identity authentication mode of the user.
Further, the access control management method including the palm vein and the face recognition respectively preprocesses the acquired face image and the palm vein image, and specifically includes:
detecting whether a face image exists in the shot picture, if so, extracting a corresponding face characteristic image from the shot picture according to the face common characteristic, and evaluating the quality of the face image;
detecting whether a palm vein image exists in a shot picture, if so, extracting texture features of the palm vein image to form a palm vein feature map after image binarization, image contour extraction, finger heel position positioning, effective region extraction, image normalization, image enhancement and denoising processing are carried out on the palm vein image.
Further, the entrance guard management method including palm vein and face recognition performs living body detection according to a difference analysis method, specifically including:
adopting an analysis method of texture features based on an infrared image and a CNN method based on the infrared image and an RGB image to carry out living body detection on the human face feature image;
and judging whether the current shooting palm is a living body or not according to the absorption characteristic of the heme to the near infrared light and the palm vein feature map.
Further, the face registration specifically includes:
acquiring a face image of a user through an image acquisition module in advance, and performing face detection and capturing to obtain a face feature image;
carrying out face image quality evaluation on the face feature image, wherein the quality evaluation comprises the evaluation of image brightness and noise points, whether a face exists, the size of a face area, the distance value between two eyes of the face and face angle data;
distinguishing the significant difference characteristics of a real face and a false face by a deep neural network method, judging whether the detected person is a live person, and if so, executing the next step;
and performing face feature analysis and analog-to-digital conversion on the shape, position, distance and textural features of facial features of the facial region in the face feature image, establishing face feature templates corresponding to different users and storing the face feature templates in a database.
Further, the palm vein registration specifically includes:
irradiating the palm of the user by using a near-infrared light source, and acquiring a vein grain distribution image under the palm of the user;
preprocessing the vein grain distribution image by adopting a filtering, image binarization and refinement analysis method, and then extracting the palm vein features to obtain a palm vein feature map;
performing living body detection according to the palm vein feature map, and executing the next step after detecting that the palm collected currently is a living body;
and carrying out spectrum analysis and feature extraction on the palm vein feature spectrum, establishing palm vein feature templates corresponding to different users, and storing the palm vein feature templates in a database.
One embodiment of the present invention provides an access control system including a palm vein and a face recognition, including:
the acquisition module is used for acquiring a face image and a palm vein image of a current user through the image acquisition module;
the living body detection module is used for respectively preprocessing the acquired face image and the palm vein image and carrying out living body detection according to a difference analysis method;
the characteristic analysis module is used for respectively carrying out characteristic analysis on the acquired face image and the palm vein image after the living body detection is passed, and extracting to obtain a corresponding face characteristic image and a corresponding palm vein characteristic map;
the identification module is used for respectively matching the face characteristic image and the palm vein characteristic map with a user identity template in a database after the characteristic analysis is finished, and finally obtaining an identity identification result so as to control the access control system according to the identity identification result; the user identity template comprises a face feature template and a palm vein feature template.
Further, the entrance guard management system who contains palm vein and face identification still includes:
the user registration module is used for carrying out face registration and palm vein registration on a user in advance and storing a registration result into a database;
and the authentication mode setting module is used for presetting the identity authentication mode of the user.
Another embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the above-mentioned access control management method including palm vein and face recognition.
The embodiment of the invention has the following beneficial effects:
the embodiment of the invention provides an access control management method, a system and a medium containing palm veins and face recognition, wherein the method comprises the following steps: acquiring a face image and a palm vein image of a current user through an image acquisition module; respectively preprocessing the acquired face image and palm vein image, and performing in-vivo detection according to a difference analysis method; after the living body detection is carried out, respectively carrying out feature analysis on the collected face image and the collected palm vein image, and extracting to obtain a corresponding face feature image and a corresponding palm vein feature map; after the characteristic analysis is finished, respectively matching with a user identity template in a database according to the face characteristic image and the palm vein characteristic map to finally obtain an identity recognition result so as to control an access control system according to the identity recognition result; the user identity template comprises a face feature template and a palm vein feature template. The invention combines palm vein recognition, face recognition and living body detection, avoids the defect that the access control system can be unlocked by using a face picture, improves the identity recognition accuracy of the access control system, effectively improves the safety, reliability and practicability of the access control system, and improves the flexibility of the access control management system by a multi-mode biological recognition verification mode.
Drawings
Fig. 1 is a schematic flow chart of a door access management method including palm vein and face recognition according to a first embodiment of the present invention;
fig. 2 is a schematic flow chart of another access control management method including palm vein and face recognition according to the first embodiment of the present invention;
fig. 3 is a schematic flow chart of a face recognition access control method according to a first embodiment of the present invention;
fig. 4 is a schematic flow chart of a palm vein recognition access control method according to a first embodiment of the present invention;
fig. 5 is a schematic flow chart of face registration according to a first embodiment of the present invention;
fig. 6 is a schematic flow chart of palm vein registration according to a first embodiment of the present invention;
fig. 7 is a schematic structural diagram of an access control system including a palm vein and face recognition according to a second embodiment of the present invention;
fig. 8 is a schematic structural diagram of another access control system with palm veins and face recognition according to a second embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Firstly, the application scenario provided by the invention is introduced, for example, the identity of a user is verified by a face recognition intelligent lock containing palm vein recognition.
The first embodiment of the present invention:
please refer to fig. 1-6.
As shown in fig. 1, the present embodiment provides an access control method including palm vein and face recognition, which is suitable for operating on an intelligent face recognition lock device including palm vein recognition, and at least includes the following steps:
s101, acquiring a face image and a palm vein image of a current user through an image acquisition module;
specifically, for step S101, when the user needs to open the door, the access control system first captures a face image of the current user through the image capture module and irradiates the palm of the user with near-infrared light to obtain a palm vein image, in this embodiment, the image capture module and the near-infrared L ED that are captured by face recognition can perform a palm vein recognition function in addition to the face recognition function, and a palm vein distribution map can be obtained by using the light absorption characteristics of human hemoglobin.
It should be noted that, when the image acquisition module acquires an image, it first automatically identifies whether the image is a human face or a palm; when the current collected image is identified as a human face, automatically calling a human face identification program and a template for comparison and identification; when the currently acquired image is identified as the palm, a palm vein identification program and a template are automatically called for comparison and identification, and the efficiency and accuracy of user identity authentication are improved by identifying the object of the acquired image in advance.
In the embodiment, the image acquisition module for acquiring the face image and the palm vein image is substantially the same set of acquisition device, so that the structure of the device is simplified, and the cost is saved. The image acquisition module comprises a visible light camera and a near-infrared camera, can shoot visible light images and infrared images of the same target at the same time, and can respectively model and identify the two images. Due to the adoption of the infrared sampling technology, the method has strong adaptability to the change of the external light environment, is very stable, and can still normally identify even a completely black environment. Meanwhile, the camera adopts a near-infrared high-sensitivity light sensing technology, can accurately capture the human face characteristics of the living body, and effectively prevents pictures, screen videos and the like from being mistaken for the living body of the real person.
The visible light (RGB) camera and the Near Infrared (NIR) camera are used for shooting the same target respectively, the shot visible light image and the shot near infrared image are respectively subjected to preprocessing and quality evaluation, and after the screened face image is subjected to in-vivo detection, the visible light face image and the infrared face image can be respectively subjected to feature analysis, extraction and modeling. The human face feature templates of visible light and infrared light collected by the same target at the same time point can be mutually verified.
Two templates built up from two different light images can be used for different applications, respectively. For example, the picture of the identity card is a color RGB picture, and the visible light template has good applicability when the identity card is checked by people; as remote registration generally uses visible light photos, modeling and comparison recognition of visible light images are required. While infrared acquisition, modeling and identification can be used for on-site registration and on-site identification.
S102, preprocessing the acquired face image and palm vein image respectively, and carrying out in-vivo detection according to a difference analysis method;
specifically, in step S102, the presence or absence of a face image is detected from the captured image, which is called face detection or face capture, and if the presence of a face image is detected, the face image is extracted. The face recognition method is a primary processing step of a shot image in a face recognition algorithm, can automatically and quickly detect the face of a person from the shot image by utilizing the face common characteristic of biometrics, and can accurately capture the face even in a complex background. Meanwhile, the palm vein image is preprocessed, so that interference factors such as noise in the image are mainly eliminated, palm vein features in the image are enhanced, effective regions of the palm veins are extracted subsequently, accurate data support is provided for subsequent feature extraction and analysis by preprocessing the face image and the palm vein image, and accuracy of feature extraction and analysis is improved.
Meanwhile, in order to avoid the situation that the user is falsely opened by utilizing the photo, the scheme is additionally provided with a step of carrying out living body detection according to the human face characteristic image and the palm vein characteristic map, and the accuracy and the reliability of the access control management system for user identity verification are further improved by judging whether the detected person is a real person or not.
In this embodiment, the method for performing living body detection according to the face feature image includes an analysis method based on the texture feature of the infrared image, and a CNN method based on the infrared image and the RGB image.
The method comprises the steps of extracting the characteristics of an infrared face image by using an L BP operator, inputting the calculated L BP characteristics into an SVM classifier to train, and judging whether the input face image is a real living face or not.
The CNN method based on the infrared image and the RGB image can learn more discriminative characteristics through multilayer nonlinear mapping. Because the data volume of the in-vivo detection task is small, the algorithm is based on a shallow 4-layer CNN model; the model takes an infrared image and an RGB image which are simultaneously shot by two cameras as input, respectively extracts the characteristics of the infrared image and the RGB image through a shared convolution layer and a full-link layer, and finally fuses the characteristics together and outputs the characteristics through a full-link layer and a Softmax layer for classification. The infrared image and the RGB image are used simultaneously, so that the algorithm can distinguish the difference between a real face and a fake face under the two cameras, and the algorithm has distinguishing capability.
On the other hand, for the living body detection of the palm vein feature map, because the deoxyhemoglobin has the characteristic of relatively sensitive absorption to near infrared light with a specific wavelength (700-1100 nm), after the palm of a human body is irradiated by a near infrared light source, a vein line distribution image under the palm skin is obtained. Hemoglobin flowing into the venous red blood cells absorbs near infrared rays having a wavelength of around 760nm, resulting in less reflection at the vein portion and a vein pattern on the image. The palm vein image can obtain the image characteristics only when the palm is a living body, and the palm which is not a living body can not obtain the vein image characteristics. Therefore, whether the palm is a living body or not can be known by analyzing the palm vein feature map.
S103, after the living body detection is carried out, respectively carrying out feature analysis on the collected face image and the collected palm vein image, and extracting to obtain a corresponding face feature image and a corresponding palm vein feature map;
specifically, in step S103, when performing facial image feature analysis, analysis is performed according to the shape, position, distance, texture feature, and the like of facial features in a facial region in a facial feature image, analog-to-digital conversion is performed on these feature values, a corresponding digital model is established, and a template capable of representing unique features of each person is formed through deep learning analysis and training.
When the palm vein image feature analysis is carried out, the feature values of the palm vein feature image in different block multi-scale and multi-direction are extracted by utilizing the characteristic that the thickness and the extending direction of blood vessels in the vein structure are different, a coding sequence is formed through analog-to-digital conversion and serves as a template for representing the palm vein feature, image preprocessing and feature extraction are carried out on the currently collected palm vein image of the user, and feature data of the current palm vein of the user are obtained. The specific process is as follows:
(1) the method comprises the steps of collecting palm vein images, wherein deoxyhemoglobin has the characteristic of relatively sensitive absorption to near infrared light with a specific wavelength (700-1100 nm), as shown in the figure, the deoxyhemoglobin has good absorption response to the band range of 760 nm-940 nm, a small absorption peak is arranged at the position of 760nm approximately, and the band range of 800 nm-940 nm is almost unchanged.
(2) And (5) palm vein image preprocessing. The purpose of preprocessing is mainly to eliminate noise and other interference factors in the image, enhance the palm vein features in the image and extract the effective region of the palm vein. The palm vein image preprocessing steps mainly comprise: image binarization, image contour extraction, finger root point positioning, effective region extraction, image normalization, image enhancement, denoising and the like. The series of steps are preprocessing steps of the palm vein image, and aim to accurately position the palm image so as to obtain an effective palm vein area image. Image binarization: converting the palm vein image into a binary image only with black and white to obtain a palm outline image, then obtaining coordinates through finger root positioning, correcting the palm orientation, and further dividing an effective vein region image (ROI (region of interest) region image) from the original palm vein image. And then, carrying out normalization processing, scale normalization and gray level normalization on the ROI image, so that the ROI image has uniform size and balanced gray level values. And then the vein lines of the image are clear through image enhancement and filtering denoising processing, so that subsequent feature extraction and identification are facilitated.
(3) After the palm vein image is preprocessed and enhanced, the textural features of the palm vein are extracted to form a feature map, the feature values of the palm vein image in blocks and in multiple scales and multiple directions are extracted by utilizing the characteristic that the thickness and the extending direction of blood vessels in the vein structure are different, and a coding sequence is formed through analog-to-digital conversion and serves as a template for representing the palm vein features.
(4) The palm vein collection processing method is applied to 2 main processes, one is a registration stage, and a feature template obtained by performing feature extraction after pretreatment is stored in a template database and is used as an identification sample; and secondly, in the identification stage, image preprocessing and feature extraction are carried out on the currently acquired palm vein image of the user to obtain feature data of the current palm vein of the user, and the feature data are matched with the template in the database to identify a final result.
S104, after the characteristic analysis is finished, respectively matching the face characteristic image and the palm vein characteristic map with a user identity template in a database to finally obtain an identity recognition result so as to control the access control system according to the identity recognition result; the user identity template comprises a face feature template and a palm vein feature template.
Specifically, in step S104, user identity templates of different users during registration, including a face feature template and a palm vein feature template, are pre-stored in the database of the access control system. After the user passes the living body detection and the feature analysis, the face feature image and the palm vein feature map are respectively matched with a user identity template in a database, so that an identity recognition result is obtained, and the identity authentication can be confirmed to be qualified only when the face feature image and the palm vein are detected. In order to improve the accuracy and the safety of identity identification, the embodiment identifies the identity of a person by combining a plurality of biological characteristics, namely multi-mode biological characteristic identification, and avoids the defect of low identity identification precision caused by the limitation of single biological characteristic identification.
In a preferred embodiment, as shown in fig. 2, the access control method including palm vein and face recognition further includes:
and carrying out face registration and palm vein registration on the user in advance, and storing a registration result into a database.
Specifically, identity registration including face registration and palm vein registration is performed on users of the access control management system in advance, and an identity registration result corresponding to each user is stored in a database.
The palm vein recognition method has the advantages that the palm vein belongs to the biological characteristic that the inside of a human body is not visible to naked eyes, the vein blood vessel is hidden under the skin and is not easy to see by human eyes, and compared with other parts of the human body, the palm vein recognition method is difficult to obtain, is not easy to steal, and cannot be copied and counterfeited. And vein radiography can be realized only in a living body, and the false body cannot be utilized. Meanwhile, the vein blood vessels form a net structure under the skin of a person, the net structure has rich characteristics and information content, each person has unique vein line characteristics, the vein structures of the same parts of different persons are different, even if the vein lines of twins are different, the net structure has good uniqueness. On the other hand, the palm vein recognition has the advantages of non-contact use and is more sanitary. The requirements on ambient light and the position and the posture of a user are almost not limited, and the device is easier to use and more reliable.
In a preferred embodiment, as shown in fig. 2, the access control method including palm vein and face recognition further includes:
and presetting an identity authentication mode of the user.
Specifically, by presetting the identity authentication mode of the user, what authentication mode is adopted by each different user can be set, and the corresponding setting can be carried out according to the requirements of the use occasion or the specific personal condition. For example, as shown in fig. 3, it is set to use only face recognition; the setting as shown in fig. 4 is to use only the palm vein recognition. In specific situations, for example, it is possible to set a mode of authentication using face recognition alone for adults, face recognition or palm vein recognition for children or people with insufficient height, and in some important situations, such as a key laboratory, a key cultural relic room, a file repository, etc., it is also possible to set a mode of authentication using multi-modal biometric recognition, such as face recognition and palm vein recognition. The two biological characteristics are respectively used for each person to carry out comparison and matching, and the identity authentication is successfully confirmed only when the two biological characteristics are successfully matched, so that the identification accuracy is improved in a geometric series manner.
In a preferred embodiment, the access control management method including the palm vein and the face recognition respectively preprocesses the acquired face image and the collected palm vein image, specifically:
detecting whether a face image exists in the shot picture, if so, extracting a corresponding face characteristic image from the shot picture according to the face common characteristic, and evaluating the quality of the face image;
detecting whether a palm vein image exists in a shot picture, if so, extracting texture features of the palm vein image to form a palm vein feature map after image binarization, image contour extraction, finger heel position positioning, effective region extraction, image normalization, image enhancement and denoising processing are carried out on the palm vein image.
In a preferred embodiment, the entrance guard management method including palm vein and face recognition performs living body detection according to a difference analysis method, specifically including:
adopting an analysis method of texture features based on an infrared image and a CNN method based on the infrared image and an RGB image to carry out living body detection on the human face feature image;
and judging whether the current shooting palm is a living body or not according to the absorption characteristic of the heme to the near infrared light and the palm vein feature map.
In a preferred embodiment, as shown in fig. 5, the face registration specifically includes:
acquiring a face image of a user through an image acquisition module in advance, and performing face detection and capturing to obtain a face feature image;
carrying out face image quality evaluation on the face feature image, wherein the quality evaluation comprises the evaluation of image brightness and noise points, whether a face exists, the size of a face area, the distance value between two eyes of the face and face angle data;
distinguishing the significant difference characteristics of a real face and a false face by a deep neural network method, judging whether the detected person is a live person, and if so, executing the next step;
and performing face feature analysis and analog-to-digital conversion on the shape, position, distance and textural features of facial features of the facial region in the face feature image, establishing face feature templates corresponding to different users and storing the face feature templates in a database.
Specifically, the face registration process specifically includes:
(1) face detection and capture: the detection of the existence of the human face image from the shot picture is called human face detection or human face capture, and if the human face image is detected, the human face image is extracted. The method is a primary processing step of a shot image in a face recognition algorithm, can automatically and quickly detect the face of a person from the shot image by utilizing the face common characteristic of biometrics, and can accurately capture the face even in a complex background.
(2) Evaluating the quality of the face image: the method comprises the steps of evaluating the brightness and noise of an image, the existence of a human face, the size of a human face region, the distance between two eyes, the angle of the human face and the like.
(3) And (3) living body detection: distinguishing the significant difference characteristics of a real face and a false face through the learning of a deep neural network method through the significant difference between a living face and a non-living face of a face image shot by infrared rays; the image shot by infrared light has great correlation with the reflection attribute of a shot object, the image formed by the living human face and the non-living human face (such as a photo or a mobile phone video) has obvious difference, and whether the input image is a real human face or not can be judged through the training of an SVM classifier. Meanwhile, the scheme is based on the characteristics of the infrared image and the visible light image, a Convolutional Neural Network (CNN) method is adopted, the infrared image and the RGB image which are simultaneously shot by the two-way camera are used as input, the characteristics of the infrared image and the RGB image are respectively extracted through the shared convolution layer and the full-connection layer, and the convolution layer and the full-connection layer are fused together and output through the full-connection layer and the Softmax layer to be classified. The infrared image and the RGB image are used simultaneously, so that the algorithm can distinguish the difference between a real face and a fake face under the two cameras, and the algorithm has distinguishing capability. Thereby judging whether the detected person is a real person. If the face is not the face of the living body, the next identification process is not allowed to be carried out; and if the face is the living body face, further sending the face to the next recognition processing.
(4) Analyzing and modeling the human face features: the method comprises the steps of analyzing the shape, position, distance, textural features and the like of five sense organs in a face area, enabling each person to have unique structural features, conducting analog-to-digital conversion on feature values, establishing a corresponding digital model, forming templates capable of reflecting the unique features of each person through deep learning analysis and training, and enabling the templates to serve as bases for identifying faces.
In a preferred embodiment, as shown in fig. 6, the palm vein registration specifically includes:
irradiating the palm of the user by using a near-infrared light source, and acquiring a vein grain distribution image under the palm of the user;
preprocessing the vein grain distribution image by adopting a filtering, image binarization and refinement analysis method, and then extracting the palm vein features to obtain a palm vein feature map;
performing living body detection according to the palm vein feature map, and executing the next step after detecting that the palm collected currently is a living body;
and carrying out spectrum analysis and feature extraction on the palm vein feature spectrum, establishing palm vein feature templates corresponding to different users, and storing the palm vein feature templates in a database.
Specifically, the specific process of the palm vein registration is as follows:
(1) obtaining a palm vein image: the palm of the human body is irradiated by a near-infrared light source, and the vein grain distribution image under the palm skin is obtained by utilizing the strong absorption characteristic of heme in blood to the near-infrared light. Hemoglobin flowing into the venous red blood cells absorbs near infrared rays having a wavelength of around 760nm, resulting in less reflection at the vein portion and a vein pattern on the image.
(2) Vein image preprocessing: and processing the vein image and extracting features by using methods such as filtering, image binarization, thinning analysis and the like.
(3) Judging the living body: since the palm vein can acquire its image features only when the palm is a living body, the palm that is not a living body cannot acquire the vein image features.
(4) Extracting characteristics and modeling: the palm vein distribution, trend and texture of each person have unique characteristics, the characteristics are analyzed and extracted, a corresponding digital model is established, namely the palm vein characteristic template unique to each person is formed, and the digital model is stored in the recognition machine. When palm vein recognition is carried out in future, the collected on-site palm vein images can be compared and matched with the stored characteristic template through a recognition matching algorithm, and therefore the identity of the detected person is identified.
The embodiment of the invention has the following beneficial effects:
the embodiment provides an access control management method including palm vein and face recognition, which comprises the following steps: acquiring a face image and a palm vein image of a current user through an image acquisition module; respectively preprocessing the acquired face image and palm vein image, and performing in-vivo detection according to a difference analysis method; after the living body detection is carried out, respectively carrying out feature analysis on the collected face image and the collected palm vein image, and extracting to obtain a corresponding face feature image and a corresponding palm vein feature map; after the characteristic analysis is finished, respectively matching with a user identity template in a database according to the face characteristic image and the palm vein characteristic map to finally obtain an identity recognition result so as to control an access control system according to the identity recognition result; the user identity template comprises a face feature template and a palm vein feature template. The invention combines palm vein recognition, face recognition and living body detection, avoids the defect that the access control system can be unlocked by using a face picture, improves the identity recognition accuracy of the access control system, effectively improves the safety, reliability and practicability of the access control system, and improves the flexibility of the access control management system by a multi-mode biological recognition verification mode.
Second embodiment of the invention:
please refer to fig. 7-8.
As shown in fig. 7, this embodiment provides an entrance guard management system including palm veins and face recognition, which is suitable for operating on a face recognition intelligent lock device including palm veins, and the system includes:
the acquisition module 100 is used for acquiring a face image and a palm vein image of a current user through an image acquisition module;
specifically, for the acquisition module 100, when the user needs to open the door, the access control system first captures a face image of the current user through the image acquisition module and irradiates the palm of the user with near-infrared light to obtain a palm vein image, in this embodiment, the image capture module and the near-infrared L ED, which are acquired by face recognition, can perform a palm vein recognition function in addition to the face recognition function, and can obtain a palm vein distribution map by using the light absorption characteristics of human hemoglobin,
it should be noted that, when the acquisition module 100 acquires an image, it first automatically identifies whether the image is a human face or a palm; when the current collected image is identified as a human face, automatically calling a human face identification program and a template for comparison and identification; when the currently acquired image is identified as the palm, a palm vein identification program and a template are automatically called for comparison and identification, and the efficiency and accuracy of user identity authentication are improved by identifying the object of the acquired image in advance.
In the embodiment, the acquisition module 100 for acquiring the facial image and the palm vein image is substantially the same set of acquisition device, which not only simplifies the structure of the device, but also saves the cost. The acquisition module 100 comprises a visible light camera and a near infrared camera, and can shoot visible light images and infrared images of the same target at the same time, and the two images can be modeled and identified respectively. Due to the adoption of the infrared sampling technology, the method has strong adaptability to the change of the external light environment, is very stable, and can still normally identify even a completely black environment. Meanwhile, the camera adopts a near-infrared high-sensitivity light sensing technology, can accurately capture the human face characteristics of the living body, and effectively prevents pictures, screen videos and the like from being mistaken for the living body of the real person.
The living body detection module 200 is used for respectively preprocessing the acquired face image and the palm vein image and carrying out living body detection according to a difference analysis method;
specifically, the living body detection module 200 detects the presence or absence of a face image from a captured image, which is called face detection or face capture, and extracts the face image if the presence of the face image is detected. The face recognition method is a primary processing step of a shot image in a face recognition algorithm, can automatically and quickly detect the face of a person from the shot image by utilizing the face common characteristic of biometrics, and can accurately capture the face even in a complex background. Meanwhile, the palm vein image is preprocessed, so that interference factors such as noise in the image are mainly eliminated, palm vein features in the image are enhanced, effective regions of the palm veins are extracted subsequently, accurate data support is provided for subsequent feature extraction and analysis by preprocessing the face image and the palm vein image, and accuracy of feature extraction and analysis is improved.
In order to avoid the situation that the user is falsely opened by using the photo, the scheme is additionally provided with a step of carrying out living body detection according to the human face characteristic image and the palm vein characteristic map, and the accuracy and the reliability of the access control management system for user identity verification are further improved by judging whether the detected person is a real person or not.
The feature analysis module 300 is configured to perform feature analysis on the acquired face image and the collected palm vein image respectively after the living body detection is passed, and extract a corresponding face feature image and a corresponding palm vein feature map;
specifically, for the feature analysis module 300, when performing face image feature analysis, analysis is performed according to the shape, position, distance, texture feature, and the like of facial features in a face region in a face feature image, analog-to-digital conversion is performed on these feature values, a corresponding digital model is established, and a template capable of representing unique features of each person is formed through analysis and training of deep learning.
When the palm vein image feature analysis is carried out, the feature values of the palm vein feature image in different block multi-scale and multi-direction are extracted by utilizing the characteristic that the thickness and the extending direction of blood vessels in the vein structure are different, a coding sequence is formed through analog-to-digital conversion and serves as a template for representing the palm vein feature, image preprocessing and feature extraction are carried out on the currently collected palm vein image of the user, and feature data of the current palm vein of the user are obtained.
The recognition module 400 is configured to match the face feature image and the palm vein feature map with a user identity template in a database respectively according to the feature analysis, and finally obtain an identity recognition result, so that the access control system is controlled according to the identity recognition result; the user identity template comprises a face feature template and a palm vein feature template.
Specifically, for the recognition module 400, user identity templates of different users during registration, including a face feature template and a palm vein feature template, are pre-stored in a database of the access control management system. After the user passes the living body detection, respectively matching with a user identity template in a database according to the face feature image and the palm vein feature map so as to obtain an identity recognition result, and only when the face feature image and the palm vein are matched to be qualified, the identity authentication can be confirmed to be qualified. In order to improve the accuracy and the safety of identity identification, the embodiment identifies the identity of a person by combining a plurality of biological characteristics, namely multi-mode biological characteristic identification, and avoids the defect of low identity identification precision caused by the limitation of single biological characteristic identification.
In a preferred embodiment, as shown in fig. 8, the access control system including a palm vein and face recognition further includes:
the user registration module 500 is used for performing face registration and palm vein registration on a user in advance and storing a registration result into a database;
specifically, for the user registration module 500, the identity registration including face registration and palm vein registration is performed in advance for the user of the access control management system, and the identity registration result corresponding to each user is stored in the database.
In a preferred embodiment, as shown in fig. 8, the access control system including a palm vein and face recognition further includes:
an authentication mode setting module 600 is configured to set an identity authentication mode of a user in advance.
Specifically, for the authentication mode setting module 600, by presetting the identity authentication mode of the user, what authentication mode is adopted for each different user can be set, and the corresponding setting can be performed according to the requirement of the use occasion or the specific situation of the individual. The method comprises the following steps: the face recognition is set to be applied only and the palm vein recognition is set to be used only. In specific situations, for example, it is possible to set a mode of authentication using face recognition alone for adults, face recognition or palm vein recognition for children or people with insufficient height, and in some important situations, such as a key laboratory, a key cultural relic room, a file repository, etc., it is also possible to set a mode of authentication using multi-modal biometric recognition, such as face recognition and palm vein recognition. The two biological characteristics are respectively used for each person to carry out comparison and matching, and the identity authentication is successfully confirmed only when the two biological characteristics are successfully matched, so that the identification accuracy is improved in a geometric series manner.
The embodiment of the invention has the following beneficial effects:
this embodiment provides an entrance guard management system who contains palm vein and face identification, includes: the acquisition module 100 is used for acquiring a face image and a palm vein image of a current user through an image acquisition module; the living body detection module 200 is used for respectively preprocessing the acquired face image and the palm vein image and carrying out living body detection according to a difference analysis method; the feature analysis module 300 is configured to perform feature analysis on the acquired face image and the collected palm vein image respectively after the living body detection is passed, and extract a corresponding face feature image and a corresponding palm vein feature map; the recognition module 400 is configured to match the face feature image and the palm vein feature map with a user identity template in a database respectively according to the feature analysis, and finally obtain an identity recognition result, so that the access control system is controlled according to the identity recognition result; the user identity template comprises a face feature template and a palm vein feature template. The invention combines palm vein recognition, face recognition and living body detection, avoids the defect that the access control system can be unlocked by using a face picture, improves the identity recognition accuracy of the access control system, effectively improves the safety, reliability and practicability of the access control system, and improves the flexibility of the access control management system by a multi-mode biological recognition verification mode.
Another embodiment of the present invention further provides a computer-readable storage medium, where the computer-readable storage medium includes a stored computer program, where when the computer program runs, the apparatus where the computer-readable storage medium is located is controlled to execute the above-mentioned access control management method including palm vein and face recognition.
In the above embodiments of the present invention, the descriptions of the respective embodiments have respective emphasis, and for parts that are not described in detail in a certain embodiment, reference may be made to related descriptions of other embodiments.
In the embodiments provided in the present application, it should be understood that the disclosed technology can be implemented in other ways. The above-described embodiments of the apparatus are merely illustrative, and for example, the division of the modules may be a logical division, and in actual implementation, there may be another division, for example, multiple modules or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, units or modules, and may be in an electrical or other form.
The modules described as separate parts may or may not be physically separate, and parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment.
In addition, functional modules in the embodiments of the present invention may be integrated into one processing module, or each of the modules may exist alone physically, or two or more modules are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode.
The foregoing is directed to the preferred embodiment of the present invention, and it is understood that various changes and modifications may be made by one skilled in the art without departing from the spirit of the invention, and it is intended that such changes and modifications be considered as within the scope of the invention.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), or the like.
Claims (10)
1. An entrance guard management method containing palm veins and face recognition is characterized by at least comprising the following steps:
acquiring a face image and a palm vein image of a current user through an image acquisition module;
respectively preprocessing the acquired face image and palm vein image, and performing in-vivo detection according to a difference analysis method;
after the living body detection is carried out, respectively carrying out feature analysis on the collected face image and the collected palm vein image, and extracting to obtain a corresponding face feature image and a corresponding palm vein feature map;
after the characteristic analysis is finished, respectively matching with a user identity template in a database according to the face characteristic image and the palm vein characteristic map to finally obtain an identity recognition result so as to control an access control system according to the identity recognition result; the user identity template comprises a face feature template and a palm vein feature template.
2. The access control management method containing the palm vein and the face recognition according to claim 1, further comprising:
and carrying out face registration and palm vein registration on the user in advance, and storing a registration result into a database.
3. The access control management method containing the palm vein and the face recognition according to claim 1, further comprising:
and presetting an identity authentication mode of the user.
4. The access control management method containing the palm vein and the face recognition according to claim 1, wherein the preprocessing is performed on the acquired face image and the collected palm vein image respectively, specifically:
detecting whether a face image exists in the shot picture, if so, extracting a corresponding face characteristic image from the shot picture according to the face common characteristic, and evaluating the quality of the face image;
detecting whether a palm vein image exists in a shot picture, if so, extracting texture features of the palm vein image to form a palm vein feature map after image binarization, image contour extraction, finger heel position positioning, effective region extraction, image normalization, image enhancement and denoising processing are carried out on the palm vein image.
5. The entrance guard management method containing palm veins and face recognition according to claim 1, characterized in that the in vivo detection is performed according to a difference analysis method, specifically:
adopting an analysis method of texture features based on an infrared image and a CNN method based on the infrared image and an RGB image to carry out living body detection on the human face feature image;
and judging whether the current shooting palm is a living body or not according to the absorption characteristic of the heme to the near infrared light and the palm vein feature map.
6. The access control management method containing the palm vein and the face recognition according to claim 2, wherein the face registration specifically comprises:
acquiring a face image of a user through an image acquisition module in advance, and performing face detection and capturing to obtain a face feature image;
carrying out face image quality evaluation on the face feature image, wherein the quality evaluation comprises the evaluation of image brightness and noise points, whether a face exists, the size of a face area, the distance value between two eyes of the face and face angle data;
distinguishing the significant difference characteristics of a real face and a false face by a deep neural network method, judging whether the detected person is a live person, and if so, executing the next step;
and performing face feature analysis and analog-to-digital conversion on the shape, position, distance and textural features of facial features of the facial region in the face feature image, establishing face feature templates corresponding to different users and storing the face feature templates in a database.
7. The entrance guard management method containing the palm vein and the face recognition according to claim 2, wherein the palm vein registration specifically comprises:
irradiating the palm of the user by using a near-infrared light source, and acquiring a vein grain distribution image under the palm of the user;
preprocessing the vein grain distribution image by adopting a filtering, image binarization and refinement analysis method, and then extracting the palm vein features to obtain a palm vein feature map;
performing living body detection according to the palm vein feature map, and executing the next step after detecting that the palm collected currently is a living body;
and carrying out spectrum analysis and feature extraction on the palm vein feature spectrum, establishing palm vein feature templates corresponding to different users, and storing the palm vein feature templates in a database.
8. The utility model provides an entrance guard management system who contains palm vein and face identification which characterized in that includes:
the acquisition module is used for acquiring a face image and a palm vein image of a current user through the image acquisition module;
the living body detection module is used for respectively preprocessing the acquired face image and the palm vein image and carrying out living body detection according to a difference analysis method;
the characteristic analysis module is used for respectively carrying out characteristic analysis on the acquired face image and the palm vein image after the living body detection is passed, and extracting to obtain a corresponding face characteristic image and a corresponding palm vein characteristic map;
the identification module is used for respectively matching the face characteristic image and the palm vein characteristic map with a user identity template in a database after the characteristic analysis is finished, and finally obtaining an identity identification result so as to control the access control system according to the identity identification result; the user identity template comprises a face feature template and a palm vein feature template.
9. The entrance guard management system containing the palm vein and the face recognition according to claim 8, further comprising:
the user registration module is used for carrying out face registration and palm vein registration on a user in advance and storing a registration result into a database;
and the authentication mode setting module is used for presetting the identity authentication mode of the user.
10. A computer-readable storage medium, comprising a stored computer program, wherein when the computer program runs, the computer-readable storage medium is controlled to execute the access control management method including palm vein and face recognition according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010189226.6A CN111462379A (en) | 2020-03-17 | 2020-03-17 | Access control management method, system and medium containing palm vein and face recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010189226.6A CN111462379A (en) | 2020-03-17 | 2020-03-17 | Access control management method, system and medium containing palm vein and face recognition |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111462379A true CN111462379A (en) | 2020-07-28 |
Family
ID=71682101
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010189226.6A Pending CN111462379A (en) | 2020-03-17 | 2020-03-17 | Access control management method, system and medium containing palm vein and face recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111462379A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112183327A (en) * | 2020-09-27 | 2021-01-05 | 烟台艾睿光电科技有限公司 | Face recognition method, device and system |
| CN112241680A (en) * | 2020-09-14 | 2021-01-19 | 中国矿业大学 | Multi-mode identity authentication method based on vein similar image knowledge migration network |
| CN112418150A (en) * | 2020-12-03 | 2021-02-26 | 佳都新太科技股份有限公司 | Palm vein image evaluation method and device, computer equipment and storage medium |
| CN112465999A (en) * | 2020-12-29 | 2021-03-09 | 天津科技大学 | Attendance checking equipment and attendance checking system based on face and finger vein fusion recognition |
| CN112487389A (en) * | 2020-12-16 | 2021-03-12 | 熵基科技股份有限公司 | Identity authentication method, device and equipment |
| CN112530072A (en) * | 2020-12-19 | 2021-03-19 | 韦立有 | Intelligent access control system |
| CN113065463A (en) * | 2021-04-01 | 2021-07-02 | 江苏芯灵智能科技有限公司 | High-safety identity authentication system |
| CN113420582A (en) * | 2020-11-04 | 2021-09-21 | 中国银联股份有限公司 | Anti-counterfeiting detection method and system for palm vein recognition |
| WO2022095092A1 (en) * | 2020-11-05 | 2022-05-12 | 常熟安智生物识别技术有限公司 | Access control system based on palm vein recognition |
| CN115394001A (en) * | 2022-07-29 | 2022-11-25 | 北京旷视科技有限公司 | Identity authentication system, method, electronic device, and computer-readable medium |
| CN116543438A (en) * | 2023-05-05 | 2023-08-04 | 深圳市齐胜达科技有限公司 | Accurate identification method for dynamically tracking and capturing human face |
| CN118470809A (en) * | 2023-10-30 | 2024-08-09 | 杭州名光微电子科技有限公司 | Object recognition system and method for fusing human face and living palm vein |
| CN118486064A (en) * | 2023-10-27 | 2024-08-13 | 杭州名光微电子科技有限公司 | Object recognition system and method based on fusion of human face and palm vein |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101196987A (en) * | 2007-12-25 | 2008-06-11 | 哈尔滨工业大学 | On-line palm print, palm vein image personal identification method and its special capturing instrument |
| CN202041967U (en) * | 2011-04-08 | 2011-11-16 | 中国矿业大学 | Palm vein and human face bimodal biological identification instrument |
| CN102332093A (en) * | 2011-09-19 | 2012-01-25 | 汉王科技股份有限公司 | Identity authentication method and device adopting palmprint and human face fusion recognition |
| CN103902969A (en) * | 2014-02-27 | 2014-07-02 | 中国科学院自动化研究所 | Device for simultaneously shooting palm print image and palm vein image |
| CN106372611A (en) * | 2016-09-09 | 2017-02-01 | 康佳集团股份有限公司 | Identity identification method and system based on palm vein features, and image acquisition apparatus |
| CN107256395A (en) * | 2017-06-12 | 2017-10-17 | 成都芯软科技股份公司 | Vena metacarpea extracting method and device |
| CN107274517A (en) * | 2017-04-25 | 2017-10-20 | 合肥中科奔巴科技有限公司 | Merge the intelligent access control system that three-dimensional face is recognized with vena metacarpea |
| CN107292217A (en) * | 2016-04-01 | 2017-10-24 | 江苏星蓝宇信息技术有限公司 | A kind of Dual-factor identity authentication system based on recognition of face Yu vena metacarpea technology |
| US20180225669A1 (en) * | 2015-08-03 | 2018-08-09 | All It Top Co., Ltd. | Financial transaction relay system having multi-safety lock function of processing user authentication by scanning both finger pulse and fingerprint, and processing method therefore |
| CN108985231A (en) * | 2018-07-12 | 2018-12-11 | 广州麦仑信息科技有限公司 | A kind of vena metacarpea feature extracting method based on multiple dimensioned convolution kernel |
| CN109583279A (en) * | 2017-09-29 | 2019-04-05 | 山西圣点世纪科技股份有限公司 | A kind of fingerprint and refer to that vein combines recognizer |
| CN109614910A (en) * | 2018-12-04 | 2019-04-12 | 青岛小鸟看看科技有限公司 | A kind of face identification method and device |
| CN110718008A (en) * | 2019-11-15 | 2020-01-21 | 杭州艾芯智能科技有限公司 | 3D face identification module, lock and door |
-
2020
- 2020-03-17 CN CN202010189226.6A patent/CN111462379A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101196987A (en) * | 2007-12-25 | 2008-06-11 | 哈尔滨工业大学 | On-line palm print, palm vein image personal identification method and its special capturing instrument |
| CN202041967U (en) * | 2011-04-08 | 2011-11-16 | 中国矿业大学 | Palm vein and human face bimodal biological identification instrument |
| CN102332093A (en) * | 2011-09-19 | 2012-01-25 | 汉王科技股份有限公司 | Identity authentication method and device adopting palmprint and human face fusion recognition |
| CN103902969A (en) * | 2014-02-27 | 2014-07-02 | 中国科学院自动化研究所 | Device for simultaneously shooting palm print image and palm vein image |
| US20180225669A1 (en) * | 2015-08-03 | 2018-08-09 | All It Top Co., Ltd. | Financial transaction relay system having multi-safety lock function of processing user authentication by scanning both finger pulse and fingerprint, and processing method therefore |
| CN107292217A (en) * | 2016-04-01 | 2017-10-24 | 江苏星蓝宇信息技术有限公司 | A kind of Dual-factor identity authentication system based on recognition of face Yu vena metacarpea technology |
| CN106372611A (en) * | 2016-09-09 | 2017-02-01 | 康佳集团股份有限公司 | Identity identification method and system based on palm vein features, and image acquisition apparatus |
| CN107274517A (en) * | 2017-04-25 | 2017-10-20 | 合肥中科奔巴科技有限公司 | Merge the intelligent access control system that three-dimensional face is recognized with vena metacarpea |
| CN107256395A (en) * | 2017-06-12 | 2017-10-17 | 成都芯软科技股份公司 | Vena metacarpea extracting method and device |
| CN109583279A (en) * | 2017-09-29 | 2019-04-05 | 山西圣点世纪科技股份有限公司 | A kind of fingerprint and refer to that vein combines recognizer |
| CN108985231A (en) * | 2018-07-12 | 2018-12-11 | 广州麦仑信息科技有限公司 | A kind of vena metacarpea feature extracting method based on multiple dimensioned convolution kernel |
| CN109614910A (en) * | 2018-12-04 | 2019-04-12 | 青岛小鸟看看科技有限公司 | A kind of face identification method and device |
| CN110718008A (en) * | 2019-11-15 | 2020-01-21 | 杭州艾芯智能科技有限公司 | 3D face identification module, lock and door |
Non-Patent Citations (1)
| Title |
|---|
| 刘邦奇，孙曙辉: "《数字化校园理念、设计与实现》", 31 January 2014, 中国科学技术大学出版社 * |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112241680A (en) * | 2020-09-14 | 2021-01-19 | 中国矿业大学 | Multi-mode identity authentication method based on vein similar image knowledge migration network |
| CN112183327B (en) * | 2020-09-27 | 2023-07-18 | 烟台艾睿光电科技有限公司 | Face recognition method, device and system |
| CN112183327A (en) * | 2020-09-27 | 2021-01-05 | 烟台艾睿光电科技有限公司 | Face recognition method, device and system |
| CN113420582A (en) * | 2020-11-04 | 2021-09-21 | 中国银联股份有限公司 | Anti-counterfeiting detection method and system for palm vein recognition |
| CN113420582B (en) * | 2020-11-04 | 2023-09-05 | 中国银联股份有限公司 | Anti-fake detection method and system for palm vein recognition |
| WO2022095092A1 (en) * | 2020-11-05 | 2022-05-12 | 常熟安智生物识别技术有限公司 | Access control system based on palm vein recognition |
| CN112418150A (en) * | 2020-12-03 | 2021-02-26 | 佳都新太科技股份有限公司 | Palm vein image evaluation method and device, computer equipment and storage medium |
| CN112487389A (en) * | 2020-12-16 | 2021-03-12 | 熵基科技股份有限公司 | Identity authentication method, device and equipment |
| CN112530072A (en) * | 2020-12-19 | 2021-03-19 | 韦立有 | Intelligent access control system |
| CN112465999A (en) * | 2020-12-29 | 2021-03-09 | 天津科技大学 | Attendance checking equipment and attendance checking system based on face and finger vein fusion recognition |
| CN113065463A (en) * | 2021-04-01 | 2021-07-02 | 江苏芯灵智能科技有限公司 | High-safety identity authentication system |
| CN115394001A (en) * | 2022-07-29 | 2022-11-25 | 北京旷视科技有限公司 | Identity authentication system, method, electronic device, and computer-readable medium |
| CN116543438A (en) * | 2023-05-05 | 2023-08-04 | 深圳市齐胜达科技有限公司 | Accurate identification method for dynamically tracking and capturing human face |
| CN116543438B (en) * | 2023-05-05 | 2024-10-01 | 深圳市齐胜达科技有限公司 | Accurate identification method for dynamically tracking and capturing human face |
| CN118486064A (en) * | 2023-10-27 | 2024-08-13 | 杭州名光微电子科技有限公司 | Object recognition system and method based on fusion of human face and palm vein |
| CN118470809A (en) * | 2023-10-30 | 2024-08-09 | 杭州名光微电子科技有限公司 | Object recognition system and method for fusing human face and living palm vein |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111462379A (en) | Access control management method, system and medium containing palm vein and face recognition | |
| Lee | A novel biometric system based on palm vein image | |
| CN108985134B (en) | Face living body detection and face brushing transaction method and system based on binocular camera | |
| Wang et al. | Infrared imaging of hand vein patterns for biometric purposes | |
| Han et al. | Palm vein recognition using adaptive Gabor filter | |
| Wang et al. | Near-and far-infrared imaging for vein pattern biometrics | |
| Cross et al. | Thermographic imaging of the subcutaneous vascular network of the back of the hand for biometric identification | |
| CN102542281B (en) | Non-contact biometric feature identification method and system | |
| CN110516576A (en) | Near-infrared living body faces recognition methods based on deep neural network | |
| CN1898678A (en) | Method for acquiring face image and face recognition method and system | |
| CN113469143A (en) | Finger vein image identification method based on neural network learning | |
| CN108846269A (en) | One kind is towards manifold identity identifying method and identification authentication system | |
| Seal et al. | Minutiae based thermal face recognition using blood perfusion data | |
| CN106203322A (en) | A kind of identity authorization system based on hand back vein and palmmprint fusion image and method | |
| CN114218543A (en) | Encryption and unlocking system and method based on multi-scene expression recognition | |
| Deepika et al. | An algorithm for improved accuracy in unimodal biometric systems through fusion of multiple feature sets | |
| Pal et al. | Implementation of hand vein structure authentication based system | |
| Estacio et al. | A rotation invariant algorithm for bimodal hand vein recognition system | |
| Villariña et al. | Palm vein recognition system using directional coding and back-propagation neural network | |
| Yang et al. | $\alpha $-Trimmed Weber Representation and Cross Section Asymmetrical Coding for Human Identification Using Finger Images | |
| CN110866235B (en) | Identity recognition method and device for simultaneously capturing human pulse and vein images | |
| Zayed et al. | A comprehensive survey on finger vein biometric | |
| Gayathri et al. | Low cost hand vein authentication system on embedded linux platform | |
| Seal et al. | Minutiae based thermal human face recognition using label connected component algorithm | |
| KR101767051B1 (en) | Method and apparatus for extracting finger vein image based on fuzzy inference |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200728 |