[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

CN101504724B - Fingerprint alignment method, fingerprint collection apparatus, fingerprint alignment apparatus - Google Patents

Fingerprint alignment method, fingerprint collection apparatus, fingerprint alignment apparatus Download PDF

Info

Publication number
CN101504724B
CN101504724B CN200910080386.0A CN200910080386A CN101504724B CN 101504724 B CN101504724 B CN 101504724B CN 200910080386 A CN200910080386 A CN 200910080386A CN 101504724 B CN101504724 B CN 101504724B
Authority
CN
China
Prior art keywords
fingerprint
line
digitorum manus
articulations digitorum
alignment
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.)
Active
Application number
CN200910080386.0A
Other languages
Chinese (zh)
Other versions
CN101504724A (en
Inventor
舒予
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Mid Star Technology Ltd By Share Ltd
Original Assignee
Vimicro Corp
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Vimicro Corp filed Critical Vimicro Corp
Priority to CN200910080386.0A priority Critical patent/CN101504724B/en
Publication of CN101504724A publication Critical patent/CN101504724A/en
Application granted granted Critical
Publication of CN101504724B publication Critical patent/CN101504724B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Landscapes

  • Collating Specific Patterns (AREA)

Abstract

The invention provides a method for fingerprint alignment, a fingerprint acquisition device and a fingerprint alignment device, wherein the method for the fingerprint alignment comprises the following steps of: extracting a knuckle line from a two-dimensional fingerprint image; calculating a position relation between the extracted knuckle line and a prestored knuckle line; and aligning the extracted knuckle line with the prestored knuckle line according to the position relation so that a fingerprint containing knuckle texture aligns with a prestored fingerprint. The method for the fingerprint alignment performs contrast calculation on the extracted knuckle line and the prestored knuckle line by extracting the knuckle line, and acquires an angle between the extracted knuckle line and the prestored knuckle line, thereby achieving the aim of aligning fingerprints by rotating the angle. The method only needs to realize the coincidence of the extracted knuckle line and the prestored knuckle line, avoids the complexity of the process that the prior method for the fingerprint alignment needs to match minutiaes, shortens the time of the fingerprint alignment, and improves the efficiency of the fingerprint alignment.

Description

Method, fingerprint acquisition device, fingerprint alignment device that a kind of fingerprint is aimed at
Technical field
The present invention relates to fingerprint technique, relate in particular to method, fingerprint acquisition device, fingerprint alignment device that a kind of fingerprint is aimed at.
Background technology
Before carrying out fingerprint recognition, conventionally all to first the fingerprint of collection be aimed at the fingerprint prestoring at present.Because in fingerprint collecting process, the fingerprint of this collection might not just in time be aimed at the fingerprint prestoring, and with reference to figure 1, Fig. 1 is the schematic diagram that there is no the fingerprint of aiming at that does not comprise articulations digitorum manus line.Therefore, the fingerprint of this collection need to be rotated to translation, after the fingerprint of this collection is aimed at the fingerprint prestoring, just can carry out the identification of fingerprint.
Existing fingerprint alignment methods is the minutiae point in the fingerprint finding in the finger belly that existing fingerprint acquisition device collects, then by certain algorithm, the minutiae point in the fingerprint collecting is mated with the minutiae point of the fingerprint that prestores, thereby reach the object that fingerprint is aimed at.But the fingerprint that existing fingerprint acquisition device collects is the fingerprint in finger belly, and by the coupling of minutiae point realize fingerprint aim at method need to carry out a large amount of calculating, taken most times of whole fingerprint recognition process, waste time and energy.
Summary of the invention
The object of this invention is to provide method, fingerprint acquisition device, fingerprint alignment device that a kind of fingerprint is aimed at, only gather the texture in finger belly to solve existing fingerprint acquisition device, and utilize the texture in finger belly to carry out the problem that fingerprint alignment procedures is more complicated.The method that fingerprint of the present invention is aimed at, for the fingerprint that comprises articulations digitorum manus texture collecting is aimed at, comprises the following steps:
From two-dimentional fingerprint image, extract articulations digitorum manus line;
Calculate the position relationship of the articulations digitorum manus line extracting and the articulations digitorum manus line prestoring;
According to described position relationship by the articulations digitorum manus line of described extraction with described in the articulations digitorum manus line that prestores aim at so that described in comprise articulations digitorum manus texture fingerprint aim at the fingerprint prestoring.
Before the described step of extracting articulations digitorum manus line from pretreated fingerprint, also comprise step:
The fingerprint that comprises articulations digitorum manus texture collecting is passed through to default Fingerprint Model, generating three-dimensional fingerprint image;
Described three-dimensional fingerprint image is mapped on two dimensional surface, obtains two-dimentional fingerprint image.
Described position relationship comprises: the angle and distance between the articulations digitorum manus line of described extraction and the articulations digitorum manus line prestoring.
The present invention also provides a kind of fingerprint acquisition device, comprising:
Spatial accommodation;
Be arranged on the opening on described spatial accommodation;
Be arranged on the contactor control device of described spatial accommodation inside, send control command when being subject to touching;
Be arranged on the image collecting device of described spatial accommodation inside, for starting according to described control command, gather the fingerprint that comprises articulations digitorum manus texture.
Described contactor control device is touch-type switch.
Described image collector is set to camera.
Described camera is 3, is positioned at same profile, and any one and finger line in adjacent two of described camera are 45 degree with another and the angle pointed between line.
The present invention also provides a kind of fingerprint alignment device, and described fingerprint alignment device, for the fingerprint that comprises articulations digitorum manus texture is aimed at, comprising:
Articulations digitorum manus line drawing module, for extracting articulations digitorum manus line from two-dimentional fingerprint image;
Computing module, for calculating the articulations digitorum manus line of extraction and the position relationship of the articulations digitorum manus line prestoring;
Alignment modules, for according to described position relationship, the articulations digitorum manus line of described extraction being aimed at the articulations digitorum manus line prestoring so that described in comprise articulations digitorum manus texture fingerprint aim at the fingerprint prestoring.
Described position relationship comprises: the angle and distance between the articulations digitorum manus line of described extraction and the articulations digitorum manus line prestoring.
The method of the described articulations digitorum manus line of described extraction is Hough transformation.
Compared with prior art, the present invention has following beneficial effect:
On fingerprint acquisition device of the present invention, adopt touching device, in the time being subject to touching, just started to gather fingerprint, can collect the complete fingerprint of finger tip to first articulations digitorum manus.Fingerprint alignment methods of the present invention is by extracting articulations digitorum manus line, the articulations digitorum manus line of extraction and the articulations digitorum manus line prestoring are carried out to comparing calculation, obtain the angle between the articulations digitorum manus line extracting and the articulations digitorum manus line prestoring, thereby by rotating this angle to reach the object of alignment fingerprint.As long as realize, the finger extracting closes line to method of the present invention and default articulations digitorum manus line overlaps, and has avoided the complexity of the process that will mate minutiae point in existing fingerprint alignment methods, has shortened the time that fingerprint is aimed at, and has improved the efficiency that fingerprint is aimed at.
Brief description of the drawings
Fig. 1 is the schematic diagram that there is no the fingerprint of aiming at that does not comprise articulations digitorum manus line;
Fig. 2 is a 3D fingerprint acquisition device schematic diagram of the present invention;
Fig. 3 is three position relationship schematic diagram between camera;
Fig. 4 is fingerprint recognition system schematic diagram of the present invention;
Fig. 5 is fingerprint alignment methods process flow diagram of the present invention;
Fig. 6 is the schematic diagram that there is no the fingerprint of aiming at that comprises articulations digitorum manus line of the present invention.
Embodiment
Whole fingerprint recognition process of the present invention comprises: the process that gathers 3D fingerprint; The 3D fingerprint of collection is mapped to two dimensional surface, obtains the process of 2D fingerprint; The process that 2D fingerprint is aimed at default fingerprint; The process that fingerprint after aiming at is identified.
The present invention mainly improves gathering the process of 3D fingerprint and the process that 2D fingerprint is aimed at default fingerprint, to solve the problem of prior art.
Proposed collection 3D fingerprint in " gathering the process of 3D fingerprint " time, take touch-type switch to carry out capture.
Fingerprint alignment methods of the present invention is mapped to the articulations digitorum manus line of the 3D fingerprint of plane by extraction, adjust articulations digitorum manus direction vector and and the articulations digitorum manus line that prestores between distance, thereby reach the object that fingerprint image is aimed at more accurately.Fingerprint alignment procedures is mainly that articulations digitorum manus line is aimed at, thereby has greatly shortened the time that fingerprint is aimed at.
Below in conjunction with accompanying drawing, the specific embodiment of the present invention is described in further detail.
With reference to figure 2, Fig. 2 is a 3D fingerprint acquisition device schematic diagram of the present invention.3D fingerprint acquisition device of the present invention has adopted a box-like device, in two sides of its correspondence, has a finger insert port on a side, and the inside of another side has a touch-type switch.For can be complete collect finger tip to the image of first articulations digitorum manus, just ensure that going deep into sufficiently long position at finger starts to gather fingerprint, should at least be greater than the length of finger tip to first articulations digitorum manus from pointing insert port to the length D touch-type switch.Because everyone finger length is different, therefore, length D can meet most people's finger tip to the length of first articulations digitorum manus.
There are three cameras bottom surface, is used for respectively fingerprint being gathered from 3 different angles.Adopting three cameras to gather from different perspectives fingerprint image is preferably embodiment of one, can ensure that all fingerprint collectings are all complete fingerprints, has solved in traditional fingerprint collecting process the imperfect or unclear problem of the fingerprint of collection.
Position relationship schematic diagram between three cameras is with reference to shown in figure 3, and three cameras are on a section.Three small circles in figure represent respectively three cameras, and the pentagon in the middle of big circumference (finger insert port) represents finger, the angle of the direction indication camera of arrow points.Angle between the line of any one camera in adjacent two cameras and the line of finger and another and finger is 45 degree.Adopt the position that three cameras is set with upper type can not only ensure to collect complete fingerprint, and it is also more simple to utilize the fingerprint image collecting with upper type to carry out the process of reconstruct two dimension fingerprint image.
Certainly, the quantity of camera is not limited to embodiments of the invention, also can use a camera, in the time pointing the position suitable of placing, also can collect complete two-dimentional fingerprint image.
Finger inserts before this device, and camera is closed, only have after finger inserts and touch touch-type switch, and touch-type switch activator camera, camera just starts fingerprint to gather.
Said structure is just realized a kind of mode of fingerprint collecting, as long as adopt this similar structure, the device that can collect articulations digitorum manus texture is all protection scope of the present invention.
With reference to figure 4, Fig. 4 is fingerprint recognition system schematic diagram of the present invention, comprising: fingerprint acquisition device, fingerprint mapping device, fingerprint alignment device and fingerprint identification device.Fingerprint acquisition device can be camera.Fingerprint mapping device comprises three-dimensional fingerprint generation module, Fingerprint Model preservation module and fingerprint mapping block.Fingerprint alignment device comprises: articulations digitorum manus line drawing module, computing module and alignment modules.
Fingerprint acquisition device is used for gathering fingerprint, then the three-dimensional fingerprint generation module of fingerprint mapping device is preserved module generating three-dimensional (3D) fingerprint image by the fingerprint collecting by Fingerprint Model, fingerprint mapping block is processed the fingerprint image of 3D, be mapped on two dimensional surface, to obtain pretreated fingerprint.Here the fingerprint obtaining not only comprises the texture in usually said finger belly, also comprises the texture of articulations digitorum manus.
The articulations digitorum manus line drawing module of fingerprint alignment device is used the methods such as Hough transformation from pretreated fingerprint, to extract articulations digitorum manus line.
Computing module calculates the position relationship of the articulations digitorum manus line extracting and the articulations digitorum manus line prestoring.Position relationship comprise the articulations digitorum manus line of extraction and the articulations digitorum manus line that prestores between angle and distance.
Alignment modules is rotated or translation according to above-mentioned position relationship, and the articulations digitorum manus line extracting is aimed at the articulations digitorum manus line prestoring.In the time that the articulations digitorum manus line extracting is 0 with the angle between the articulations digitorum manus line that prestores, do not need to rotate.Adopt the method for starting point alignment, the approximate distance obtaining between two straight lines, just can realize aligning by translation;
In the time there is certain angle between the articulations digitorum manus line extracting and the articulations digitorum manus line that prestores, rotate this angle, if rotation also exists distance afterwards, realize aligning by translation.
Fingerprint identification module utilizes existing fingerprint identification technology, according to the fingerprint prestoring, pretreated fingerprint is carried out to fingerprint recognition.
With reference to figure 5, Fig. 5 is fingerprint alignment methods process flow diagram of the present invention, comprises step:
Step 1 is extracted articulations digitorum manus line from two-dimentional fingerprint image;
The processing procedure of the two-dimentional fingerprint image in this step is prior art, and existing brief description is as follows:
First gather fingerprint, then the fingerprint collecting is generated to the fingerprint image of 3D by default Fingerprint Model, last, the fingerprint image of 3D is mapped on two dimensional surface, to obtain two dimension (2D) fingerprint.Here the 2D fingerprint obtaining not only comprises the texture in usually said finger belly, also comprises the texture on articulations digitorum manus.Comprise that the schematic diagram that there is no the fingerprint of aiming at of articulations digitorum manus line is with reference to shown in figure 6.
The method of extracting articulations digitorum manus line can be used the methods such as existing Hough transformation, specific as follows:
By the 2D obtaining for fingerprint edge detection algorithm (as Canny algorithm) detect edge, form bianry image;
Bianry image is detected to articulations digitorum manus line (be similar to and regard straight line segment as) with Hough conversion (Hough transformation).
Step 2, calculates the articulations digitorum manus line of the fingerprint extracting and the position relationship of the articulations digitorum manus line prestoring;
The articulations digitorum manus line of the fingerprint of extraction and the articulations digitorum manus line of the fingerprint prestoring are carried out to proportioning, can first use least square fitting straight line, can obtain respectively like this slope of two straight lines, and obtain thus two angles between straight line.Judge and need the left-handed or concrete number of degrees of dextrorotation according to the angle between two straight lines.Meanwhile, adopt the method for starting point alignment, the approximate distance obtaining between two straight lines, makes two adjustings to a line by translation.
Step 3, is rotated or translation according to above-mentioned position relationship, and the articulations digitorum manus line extracting is aimed at the articulations digitorum manus line prestoring;
In the time that the articulations digitorum manus line extracting is 0 with the angle of the articulations digitorum manus line prestoring, do not need rotation, just can realize aligning by translation;
In the time there is certain angle between the articulations digitorum manus line extracting and the articulations digitorum manus line that prestores, rotate this angle, if rotation also exists distance afterwards, realize aligning by translation.
After the articulations digitorum manus line extracting is aimed at the articulations digitorum manus line prestoring, the fingerprint of extraction has just been aimed at the fingerprint prestoring accordingly.
Step 4, carries out fingerprint recognition according to the fingerprint prestoring to two-dimentional fingerprint image.
The process of fingerprint recognition is same as the prior art, no longer describes here.
In sum, the present invention proposes the harvester to 3D fingerprint that comprises touch-type switch, ensured the collection of articulations digitorum manus fingerprint.
And, utilize method of the present invention, the method that traditional passing through searched to minutiae point alignment is converted into the coincidence of two straight lines of simple articulations digitorum manus.Two straight-line passes that articulations digitorum manus are mapped to plane simply contrast, thereby just can know it is to anticlockwise or to right rotation.The angle of rotation also can obtain easily simultaneously.So just be easy to reach the effect of fingerprint rotation alignment, shortened the time of spending on fingerprint is aimed at
The above is only the preferred embodiment of the present invention; it should be pointed out that for those skilled in the art, under the premise without departing from the principles of the invention; can also make some improvements and modifications, these improvements and modifications also should be considered as protection scope of the present invention.

Claims (8)

1. the method that fingerprint is aimed at, is characterized in that, for the fingerprint that comprises articulations digitorum manus texture collecting is aimed at, comprises the following steps:
From two-dimentional fingerprint image, extract articulations digitorum manus line;
Calculate the position relationship of the articulations digitorum manus line extracting and the articulations digitorum manus line that prestores, described position relationship comprise the articulations digitorum manus line of described extraction and the articulations digitorum manus line that prestores between angle and distance;
According to described position relationship by the articulations digitorum manus line of described extraction with described in the articulations digitorum manus line that prestores aim at, so that described in comprise articulations digitorum manus texture fingerprint aim at the fingerprint prestoring, specifically: the articulations digitorum manus line of the fingerprint of extraction and the articulations digitorum manus line of the fingerprint prestoring are carried out to proportioning, utilize least square fitting straight line to obtain respectively the slope of two straight lines, and obtain thus two angles between straight line, in the time there is certain angle between the articulations digitorum manus line extracting and the articulations digitorum manus line that prestores, rotate this angle, if also there is distance after rotation, realize aligning by translation.
2. the method that fingerprint as claimed in claim 1 is aimed at, is characterized in that, the described step of extracting articulations digitorum manus line from two-dimentional fingerprint image comprises:
The fingerprint that comprises articulations digitorum manus texture collecting is passed through to default Fingerprint Model, generating three-dimensional fingerprint image;
Described three-dimensional fingerprint image is mapped on two dimensional surface, obtains two-dimentional fingerprint image.
3. a fingerprint alignment device, is characterized in that, described fingerprint alignment device, for the fingerprint that comprises articulations digitorum manus texture is aimed at, comprising:
Articulations digitorum manus line drawing module, for extracting articulations digitorum manus line from two-dimentional fingerprint image;
Computing module, for the position relationship of the articulations digitorum manus line that calculates extraction and the articulations digitorum manus line prestoring, described position relationship comprise the articulations digitorum manus line of described extraction and the articulations digitorum manus line that prestores between angle and distance;
Alignment modules, for the articulations digitorum manus line of described extraction being aimed at the articulations digitorum manus line prestoring according to described position relationship, so that described in comprise articulations digitorum manus texture fingerprint aim at the fingerprint prestoring, specifically: the articulations digitorum manus line of the fingerprint of extraction and the articulations digitorum manus line of the fingerprint prestoring are carried out to proportioning, utilize least square fitting straight line to obtain respectively the slope of two straight lines, and obtain thus two angles between straight line, in the time there is certain angle between the articulations digitorum manus line extracting and the articulations digitorum manus line that prestores, rotate this angle, if also there is distance after rotation, realize aligning by translation.
4. fingerprint alignment device as claimed in claim 3, is characterized in that, the method for the described articulations digitorum manus line of described extraction is Hough transformation.
5. fingerprint alignment device as claimed in claim 3, is characterized in that, the 3D fingerprint mapping that described two-dimentional fingerprint image is gathered by fingerprint acquisition device forms, and described fingerprint acquisition device comprises:
Spatial accommodation;
Be arranged on the opening on described spatial accommodation;
Be arranged on the contactor control device of described spatial accommodation inside, send control command when being subject to touching;
Be arranged on the image collecting device of described spatial accommodation inside, for starting according to described control command, gather the fingerprint that comprises articulations digitorum manus texture.
6. fingerprint alignment device as claimed in claim 5, is characterized in that, described contactor control device is touch-type switch.
7. fingerprint alignment device as claimed in claim 5, is characterized in that, described image collector is set to camera.
8. fingerprint alignment device as claimed in claim 7, is characterized in that, described camera is 3, is positioned at same profile, and any one and finger line in adjacent two of described camera are 45 degree with another and the angle pointed between line.
CN200910080386.0A 2009-03-20 2009-03-20 Fingerprint alignment method, fingerprint collection apparatus, fingerprint alignment apparatus Active CN101504724B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN200910080386.0A CN101504724B (en) 2009-03-20 2009-03-20 Fingerprint alignment method, fingerprint collection apparatus, fingerprint alignment apparatus

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN200910080386.0A CN101504724B (en) 2009-03-20 2009-03-20 Fingerprint alignment method, fingerprint collection apparatus, fingerprint alignment apparatus

Publications (2)

Publication Number Publication Date
CN101504724A CN101504724A (en) 2009-08-12
CN101504724B true CN101504724B (en) 2014-07-30

Family

ID=40976964

Family Applications (1)

Application Number Title Priority Date Filing Date
CN200910080386.0A Active CN101504724B (en) 2009-03-20 2009-03-20 Fingerprint alignment method, fingerprint collection apparatus, fingerprint alignment apparatus

Country Status (1)

Country Link
CN (1) CN101504724B (en)

Families Citing this family (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101854522B (en) * 2010-05-06 2012-02-22 福建鑫诺通讯技术有限公司 Home wireless intelligent monitoring method
CN105787417A (en) * 2014-12-19 2016-07-20 上海箩箕技术有限公司 Optical fingerprint imaging system and optical fingerprint imaging method
CN105046233B (en) * 2015-07-27 2018-07-20 浪潮软件集团有限公司 Method and device for acquiring fingerprint data and fingerprint identification method and device
CN106384336A (en) * 2015-08-07 2017-02-08 中云智慧(北京)科技有限公司 An X-ray image processing method, system and device
CN106127172B (en) 2016-06-29 2019-08-09 中控智慧科技股份有限公司 A kind of device and method of non-contact 3D fingerprint collecting
CN108492330B (en) * 2018-02-14 2019-04-05 天目爱视(北京)科技有限公司 A kind of multi-vision visual depth computing method and device
CN108388893A (en) * 2018-05-18 2018-08-10 清华大学深圳研究生院 A kind of fingerprint acquisition instrument
CN112232155B (en) * 2020-09-30 2021-12-17 墨奇科技(北京)有限公司 Non-contact fingerprint identification method and device, terminal and storage medium
WO2022068931A1 (en) * 2020-09-30 2022-04-07 墨奇科技(北京)有限公司 Non-contact fingerprint recognition method and apparatus, terminal, and storage medium
CN112016525A (en) * 2020-09-30 2020-12-01 墨奇科技(北京)有限公司 Non-contact fingerprint acquisition method and device
CN112232157B (en) * 2020-09-30 2022-03-18 墨奇科技(北京)有限公司 Fingerprint area detection method, device, equipment and storage medium
CN113486826A (en) * 2021-07-12 2021-10-08 北京集创北方科技股份有限公司 Capacitance fingerprint identification method and device, finger sensing equipment, terminal equipment and storage medium

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1131776A (en) * 1994-12-27 1996-09-25 三菱电机株式会社 Individual person identifying apparatus
CN1710593A (en) * 2005-06-27 2005-12-21 北京交通大学 A Hand Feature Fusion Authentication Method Based on Feature Relationship Measurement
CN101464945A (en) * 2008-11-14 2009-06-24 清华大学深圳研究生院 Identification characteristic identification method based on finger back arthrosis veins

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN1131776A (en) * 1994-12-27 1996-09-25 三菱电机株式会社 Individual person identifying apparatus
CN1710593A (en) * 2005-06-27 2005-12-21 北京交通大学 A Hand Feature Fusion Authentication Method Based on Feature Relationship Measurement
CN101464945A (en) * 2008-11-14 2009-06-24 清华大学深圳研究生院 Identification characteristic identification method based on finger back arthrosis veins

Also Published As

Publication number Publication date
CN101504724A (en) 2009-08-12

Similar Documents

Publication Publication Date Title
CN101504724B (en) Fingerprint alignment method, fingerprint collection apparatus, fingerprint alignment apparatus
CN105225482B (en) Vehicle detecting system and method based on binocular stereo vision
CN107833181B (en) Three-dimensional panoramic image generation method based on zoom stereo vision
CN104463108B (en) A kind of monocular real time target recognitio and pose measuring method
CN102663393B (en) Method for extracting region of interest of finger vein image based on correction of rotation
WO2019080580A1 (en) 3d face identity authentication method and apparatus
CN101957194A (en) Rapid visual orientation and remote monitoring system and method based on embedded mobile robot
CN111266315A (en) On-line sorting system and method for ore materials based on visual analysis
CN104598870A (en) Living fingerprint detection method based on intelligent mobile information equipment
CN104400265B (en) A kind of extracting method of the welding robot corner connection characteristics of weld seam of laser vision guiding
Huang et al. Local feature approach to dorsal hand vein recognition by centroid-based circular key-point grid and fine-grained matching
CN102654902A (en) Contour vector feature-based embedded real-time image matching method
CN105740899A (en) Machine vision image characteristic point detection and matching combination optimization method
CN106679567A (en) Contact net and strut geometric parameter detecting measuring system based on binocular stereoscopic vision
CN101556647A (en) mobile robot visual orientation method based on improved SIFT algorithm
CN104751040A (en) Fingerprint detection method based on intelligent mobile information equipment
WO2022022365A1 (en) Image matching method applied to fingerprint recognition and related device
CN101923641A (en) An Improved Face Recognition Method
CN107122700A (en) A kind of palm print and palm vein combined registering and recognition methods based on video
CN109523528A (en) A kind of transmission line of electricity extracting method based on unmanned plane binocular vision SGC algorithm
CN107845059A (en) Human meridian point's state dynamically normalized digital analysis system and method
CN104732212A (en) Direction control method, direction control system and terminal
CN111536981A (en) Embedded binocular non-cooperative target relative pose measuring method
CN107480654A (en) A three-dimensional vein recognition device applied to wearable devices
CN110532933A (en) A kind of living body faces detection head pose returns the acquisition methods and detection method of device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
TR01 Transfer of patent right
TR01 Transfer of patent right

Effective date of registration: 20180202

Address after: 519031 Guangdong city of Zhuhai province Hengqin Baohua Road No. 6, room 105, -23898 (central office)

Patentee after: Zhongxing Technology Co., Ltd.

Address before: 100083, Haidian District, Xueyuan Road, Beijing No. 35, Nanjing Ning building, 15 Floor

Patentee before: Beijing Vimicro Corporation

CP01 Change in the name or title of a patent holder
CP01 Change in the name or title of a patent holder

Address after: 519031 -23898, 105 room 6, Baohua Road, Hengqin New District, Zhuhai, Guangdong (centralized office area)

Patentee after: Mid Star Technology Limited by Share Ltd

Address before: 519031 -23898, 105 room 6, Baohua Road, Hengqin New District, Zhuhai, Guangdong (centralized office area)

Patentee before: Zhongxing Technology Co., Ltd.