CN111368803A - Face recognition method and system - Google Patents
Face recognition method and system Download PDFInfo
- Publication number
- CN111368803A CN111368803A CN202010232719.3A CN202010232719A CN111368803A CN 111368803 A CN111368803 A CN 111368803A CN 202010232719 A CN202010232719 A CN 202010232719A CN 111368803 A CN111368803 A CN 111368803A
- Authority
- CN
- China
- Prior art keywords
- face
- human face
- target
- module
- features
- 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
- 238000000034 method Methods 0.000 title claims abstract description 19
- 238000001514 detection method Methods 0.000 claims abstract description 24
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 17
- 210000000988 bone and bone Anatomy 0.000 claims abstract description 8
- 238000005065 mining Methods 0.000 claims abstract description 8
- 230000004927 fusion Effects 0.000 claims abstract description 6
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 239000011521 glass Substances 0.000 claims description 22
- 238000013528 artificial neural network Methods 0.000 claims description 8
- 230000000977 initiatory effect Effects 0.000 claims description 8
- 230000008859 change Effects 0.000 abstract description 3
- 238000005286 illumination Methods 0.000 abstract description 3
- 238000012549 training Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000000513 principal component analysis Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000001815 facial effect Effects 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
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
- G06V40/168—Feature extraction; Face representation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/25—Fusion techniques
- G06F18/253—Fusion techniques of extracted features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- 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
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Oral & Maxillofacial Surgery (AREA)
- General Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a face recognition method and a system, wherein the system comprises the following steps: the face target detection module is used for mining a face target in the image based on a pyramidBox algorithm; the feature extraction module is used for extracting LBPH, SIFT and human face skeleton features of the human face target; the feature fusion module is used for fusing the extracted human face bone features, SIFT and LBPH3 features according to the weight of 3: 1: 5 to obtain a human face feature vector; and the face recognition module is used for recognizing the face by adopting a nearest neighbor classifier based on the face feature vector. The invention uses the fusion of various characteristics to recognize the face, can effectively improve the influence of single characteristics on the recognition due to the illumination, the angle and the scale change, improves the recognition rate, realizes the automatic locking of the unrecognized face, thereby reducing the recognition loophole and being convenient for a user to lock a suspicious object quickly.
Description
Technical Field
The invention relates to a face recognition system, in particular to a face recognition method and a face recognition system.
Background
Face recognition is a biometric technique for performing identity authentication based on facial feature information of a person. The method comprises the steps of collecting images or video streams containing human faces through a camera or a camera, automatically detecting and tracking the human faces in the images, and further matching and identifying the detected human faces.
The application field of the face recognition is very wide, especially the face recognition plays an important role in a plurality of fields such as security anti-terrorism, financial payment, access control attendance, identity recognition and the like, and the related field knowledge comprises biomedicine, pattern recognition, image processing, machine learning and the like.
At present, the face recognition algorithm mainly comprises: (1) the template matching method mainly utilizes the texture and the gray characteristic of the human face, adopts a nearest neighbor classifier,
and matching the image to be identified with all templates in the data set, and further finding out the most similar template. The main problems with this approach are that if the data set is large enough, time is consumed in matching and accuracy is reduced.
(2) Principal Component Analysis (PCA) in short, the image of the original image library is represented by a low-dimensional feature, which is generally required to represent more than 90% of the whole image, and the calculation amount can be greatly reduced. However, the algorithm is sensitive to the external environment, and the number of the initial characteristic quantities is difficult to determine in advance in the identification process.
(3) The Support Vector Machine (SVM) is a classifier with strong capability, and the accuracy of an algorithm adopting the classifier is high in general. When the number of the face samples is large, the time complexity and the space complexity of the algorithm are high.
(4) Linear Discriminant Analysis (LDA) projects high-dimensional pattern samples into an optimal discriminant vector space to achieve the effects of extracting classification information and compressing feature space dimensions, and ensures that the pattern samples have the maximum inter-class distance and the minimum intra-class distance in a new subspace after projection. The fact that the class spacing is large and the feature with the small class spacing is ignored is over emphasized, and finally, a large amount of overlapping of classes with the small class spacing can be caused, so that the final recognition accuracy is not high.
Disclosure of Invention
In order to solve the problem of low recognition rate caused by the fact that a face recognition method is only based on one feature and the recognition method is single, the invention provides the face recognition method and the face recognition system, which are used for carrying out face recognition by fusing multiple features, can effectively improve the influence of single feature on recognition due to illumination, angle and scale change, and improve the recognition rate.
In order to achieve the purpose, the invention adopts the technical scheme that:
a face recognition system comprising:
the face target detection module is used for mining a face target in the image based on a pyramidBox algorithm;
the feature extraction module is used for extracting LBPH, SIFT and human face skeleton features of the human face target;
the feature fusion module is used for fusing the extracted human face bone features, SIFT and LBPH3 features according to the weight of 3: 1: 5 to obtain a human face feature vector;
and the face recognition module is used for recognizing the face by adopting a nearest neighbor classifier based on the face feature vector.
Further, the human face skeleton features are extracted based on a Kinect depth sensor.
Further, still include:
and the human face target hiding module is used for hiding the human face target which is subjected to the human face recognition in the image.
Further, still include:
the glasses, mask and hat detection module is used for detecting glasses, masks and hats in the image processed by the face target hiding module based on the ssd _ acceptance _ v2_ coco model;
and the glasses, the mask and the hat delineating module are used for marking a position frame in the image processed by the face target hiding module according to the detection results of the glasses, the mask and the hat detection module.
Furthermore, the ssd _ initiation _ v2_ coco adopts the ssd target detection algorithm, pre-trains the initiation v2 deep neural network with the coco data set, then trains the model with the previously prepared data set, finely adjusts various parameters in the deep neural network, and finally obtains the appropriate target detection model for glasses, masks and hats.
The invention also provides a face recognition method, which is realized based on the face recognition system and comprises the following steps:
s1, mining the human face target in the target image based on a pyramidBox algorithm;
s2, extracting LBPH, SIFT and human face skeleton characteristics of the human face target;
s3, fusing the extracted human face bone features, SIFT and LBPH3 features according to the weight of 3: 1: 5 to obtain human face features;
and S4, recognizing the human face by adopting a nearest neighbor classifier based on the human face features.
Further, the method also comprises the following steps:
s5, hiding the face target which is subjected to face recognition in the image based on the face target hiding module;
s6, detecting glasses, masks and hats in the image processed by the human face target hiding module based on the ssd _ acceptance _ v2_ coco model;
s7, marking a position frame in the image processed by the human face target hiding module according to the detection results of the glasses, the mask and the hat;
and S8, observing, comparing and tracking the object in the position marking frame through human operation.
The invention has the following beneficial effects:
1) the face target can be efficiently mined based on the pyramidBox algorithm, face recognition is performed based on the fusion of LBPH, SIFT and face skeleton characteristics, the influence of single characteristics on recognition due to illumination, angle and scale change can be effectively improved, and the recognition rate is improved.
2) The automatic locking of the unidentified face is realized, so that identification holes can be reduced, and the user can lock the suspicious object quickly.
Drawings
Fig. 1 is a system block diagram of a face recognition system according to an embodiment of the present invention.
Fig. 2 is a flowchart of a face recognition method in embodiment 2 of the present invention.
FIG. 3 is a flowchart of a face recognition method in embodiment 3 of the present invention
Detailed Description
In order that the objects and advantages of the invention will be more clearly understood, the invention is further described in detail below with reference to examples. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
Example 1
As shown in fig. 1, an embodiment of the present invention provides a face recognition system, including:
the face target detection module is used for mining a face target in the image based on a pyramidBox algorithm;
the feature extraction module is used for extracting LBPH, SIFT and human face skeleton features of the human face target; extracting the human face skeleton characteristics based on a Kinect depth sensor;
the feature fusion module is used for fusing the extracted human face bone features, SIFT and LBPH3 features according to the weight of 3: 1: 5 to obtain a human face feature vector;
the face recognition module is used for recognizing the face by adopting a nearest neighbor classifier based on the face feature vector;
the human face target hiding module is used for hiding the human face target of which the human face recognition is finished in the image;
the glasses, mask and hat detection module is used for detecting glasses, masks and hats in the image processed by the face target hiding module based on the ssd _ acceptance _ v2_ coco model; the ssd _ initiation _ v2_ coco adopts an ssd target detection algorithm, a coco data set is used for pre-training an initiation v2 deep neural network, then a previously prepared data set is used for training the model, various parameters in the deep neural network are finely adjusted, and finally a suitable target detection model for glasses, a mask and a hat is obtained;
and the glasses, the mask and the hat delineating module are used for marking a position frame in the image processed by the face target hiding module according to the detection results of the glasses, the mask and the hat detection module.
Example 2
As shown in fig. 2, an embodiment of the present invention further provides a face recognition method, including the following steps:
s1, mining the human face target in the target image based on a pyramidBox algorithm;
s2, extracting LBPH, SIFT and human face skeleton characteristics of the human face target;
s3, fusing the extracted human face bone features, SIFT and LBPH3 features according to the weight of 3: 1: 5 to obtain human face features;
and S4, recognizing the human face by adopting a nearest neighbor classifier based on the human face features.
Example 3
As shown in fig. 3, an embodiment of the present invention further provides a face recognition method, including the following steps:
s1, mining the human face target in the target image based on a pyramidBox algorithm;
s2, extracting LBPH, SIFT and human face skeleton characteristics of the human face target;
s3, fusing the extracted human face bone features, SIFT and LBPH3 features according to the weight of 3: 1: 5 to obtain human face features;
s4, recognizing the human face by adopting a nearest neighbor classifier based on the human face features;
s5, hiding the face target which is subjected to face recognition in the image based on the face target hiding module;
s6, detecting glasses, masks and hats in the image processed by the human face target hiding module based on the ssd _ acceptance _ v2_ coco model; the ssd _ initiation _ v2_ coco adopts an ssd target detection algorithm, a coco data set is used for pre-training an initiation v2 deep neural network, then a previously prepared data set is used for training the model, various parameters in the deep neural network are finely adjusted, and finally a suitable target detection model for glasses, a mask and a hat is obtained;
s7, marking a position frame in the image processed by the human face target hiding module according to the detection results of the glasses, the mask and the hat;
and S8, observing, comparing and tracking the object in the position marking frame through human operation.
The foregoing is only a preferred embodiment of the present invention, and it should be noted that those skilled in the art can make various improvements and modifications without departing from the principle of the present invention, and these improvements and modifications should also be construed as the protection scope of the present invention.
Claims (7)
1. A face recognition system, comprising:
the face target detection module is used for mining a face target in the image based on a pyramidBox algorithm;
the feature extraction module is used for extracting LBPH, SIFT and human face skeleton features of the human face target;
the feature fusion module is used for fusing the extracted human face bone features, SIFT and LBPH3 features according to the weight of 3: 1: 5 to obtain a human face feature vector;
and the face recognition module is used for recognizing the face by adopting a nearest neighbor classifier based on the face feature vector.
2. A face recognition system according to claim 1, wherein: the human face skeleton features are extracted based on a Kinect depth sensor.
3. A face recognition system according to claim 1, wherein: further comprising:
and the human face target hiding module is used for hiding the human face target which is subjected to the human face recognition in the image.
4. A face recognition system according to claim 1, wherein: further comprising:
the glasses, mask and hat detection module is used for detecting glasses, masks and hats in the image processed by the face target hiding module based on the ssd _ acceptance _ v2_ coco model;
and the glasses, the mask and the hat delineating module are used for marking a position frame in the image processed by the face target hiding module according to the detection results of the glasses, the mask and the hat detection module.
5. The face recognition system of claim 4, wherein: the ssd _ initiation _ v2_ coco adopts an ssd target detection algorithm, pre-trains an initiation v2 deep neural network by using a coco data set, then trains the model by using a previously prepared data set, finely adjusts various parameters in the deep neural network, and finally obtains a suitable target detection model for glasses, a mask and a hat.
6. A face recognition method is characterized in that: the face recognition system implementation according to any one of claims 1 to 5, comprising the steps of:
s1, mining the human face target in the target image based on a pyramidBox algorithm;
s2, extracting LBPH, SIFT and human face skeleton characteristics of the human face target;
s3, fusing the extracted human face bone features, SIFT and LBPH3 features according to the weight of 3: 1: 5 to obtain human face features;
and S4, recognizing the human face by adopting a nearest neighbor classifier based on the human face features.
7. The face recognition method of claim 6, wherein: also comprises the following steps:
s5, hiding the face target which is subjected to face recognition in the image based on the face target hiding module;
s6, detecting glasses, masks and hats in the image processed by the human face target hiding module based on the ssd _ acceptance _ v2_ coco model;
s7, marking a position frame in the image processed by the human face target hiding module according to the detection results of the glasses, the mask and the hat;
and S8, observing, comparing and tracking the object in the position marking frame through human operation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010232719.3A CN111368803A (en) | 2020-03-28 | 2020-03-28 | Face recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010232719.3A CN111368803A (en) | 2020-03-28 | 2020-03-28 | Face recognition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111368803A true CN111368803A (en) | 2020-07-03 |
Family
ID=71210626
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010232719.3A Pending CN111368803A (en) | 2020-03-28 | 2020-03-28 | Face recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111368803A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287863A (en) * | 2020-11-09 | 2021-01-29 | 九江职业技术学院 | Computer portrait recognition system |
| CN112507967A (en) * | 2020-12-23 | 2021-03-16 | 河南应用技术职业学院 | Image processing system based on artificial intelligence recognition |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019071664A1 (en) * | 2017-10-09 | 2019-04-18 | 平安科技（深圳）有限公司 | Human face recognition method and apparatus combined with depth information, and storage medium |
| CN110472516A (en) * | 2019-07-23 | 2019-11-19 | 腾讯科技（深圳）有限公司 | A kind of construction method, device, equipment and the system of character image identifying system |
-
2020
- 2020-03-28 CN CN202010232719.3A patent/CN111368803A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019071664A1 (en) * | 2017-10-09 | 2019-04-18 | 平安科技（深圳）有限公司 | Human face recognition method and apparatus combined with depth information, and storage medium |
| CN110472516A (en) * | 2019-07-23 | 2019-11-19 | 腾讯科技（深圳）有限公司 | A kind of construction method, device, equipment and the system of character image identifying system |
Non-Patent Citations (3)
| Title |
|---|
| DOGNERY SINALY SILUE: "基于多特征融合的人脸识别方法", 《电子测量技术》 * |
| XU TANG等: "Pyramidbox：A Context-assisted Single Shot Face Detector", 《ECCV2018》 * |
| 庄建等: "《深度学习图像识别技术》", 28 February 2020 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112287863A (en) * | 2020-11-09 | 2021-01-29 | 九江职业技术学院 | Computer portrait recognition system |
| CN112507967A (en) * | 2020-12-23 | 2021-03-16 | 河南应用技术职业学院 | Image processing system based on artificial intelligence recognition |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104517104B (en) | A kind of face identification method and system based under monitoring scene | |
| Bansal et al. | Face recognition using PCA and LDA algorithm | |
| KR101185525B1 (en) | Automatic biometric identification based on face recognition and support vector machines | |
| US6661907B2 (en) | Face detection in digital images | |
| CN101510257B (en) | Human face similarity degree matching method and device | |
| Kumar et al. | Real time face recognition using adaboost improved fast PCA algorithm | |
| Barnouti | Improve face recognition rate using different image pre-processing techniques | |
| JP2008146539A (en) | Face authentication device | |
| CN109800643A (en) | A kind of personal identification method of living body faces multi-angle | |
| CN103914676A (en) | Method and apparatus for use in face recognition | |
| Saleem et al. | Face recognition using facial features | |
| Tathe et al. | Face detection and recognition in videos | |
| Bouhabba et al. | Support vector machine for face emotion detection on real time basis | |
| CN111368803A (en) | Face recognition method and system | |
| Sudhakar et al. | Facial identification of twins based on fusion score method | |
| del Rio et al. | Face-based recognition systems in the ABC e-gates | |
| Sharma et al. | Face recognition using haar cascade and local binary pattern histogram in opencv | |
| Sutoyo et al. | Unlock screen application design using face expression on android smartphone | |
| Hutagalung et al. | The effectiveness of opencv based face detection in low-light environments | |
| Singh et al. | Student Surveillance System using Face Recognition | |
| Lee et al. | Facial affect recognition using regularized discriminant analysis-based algorithms | |
| Hbali et al. | Object detection based on HOG features: Faces and dual-eyes augmented reality | |
| Monwar et al. | A real-time face recognition approach from video sequence using skin color model and eigenface method | |
| Sun et al. | Dual camera based feature for face spoofing detection | |
| Mekami et al. | Towards a new approach for real time face detection and normalization |
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: 20200703 |