CN106228151B - Digital palmar veins fusion feature recognition methods - Google Patents
Digital palmar veins fusion feature recognition methods Download PDFInfo
- Publication number
- CN106228151B CN106228151B CN201610652925.3A CN201610652925A CN106228151B CN 106228151 B CN106228151 B CN 106228151B CN 201610652925 A CN201610652925 A CN 201610652925A CN 106228151 B CN106228151 B CN 106228151B
- Authority
- CN
- China
- Prior art keywords
- vein
- finger
- feature
- region
- regions
- 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.)
- Expired - Fee Related
Links
- 210000003462 vein Anatomy 0.000 title claims abstract description 87
- 238000000034 method Methods 0.000 title claims abstract description 39
- 230000004927 fusion Effects 0.000 title claims abstract description 14
- 238000000605 extraction Methods 0.000 claims description 13
- 230000011218 segmentation Effects 0.000 claims description 13
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000001186 cumulative effect Effects 0.000 claims description 2
- 101100356020 Haemophilus influenzae (strain ATCC 51907 / DSM 11121 / KW20 / Rd) recA gene Proteins 0.000 claims 4
- 101100042680 Mus musculus Slc7a1 gene Proteins 0.000 claims 4
- 101100412102 Haemophilus influenzae (strain ATCC 51907 / DSM 11121 / KW20 / Rd) rec2 gene Proteins 0.000 claims 2
- 238000004422 calculation algorithm Methods 0.000 abstract description 3
- 230000004069 differentiation Effects 0.000 abstract 1
- 230000000694 effects Effects 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000005299 abrasion Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
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
-
- 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)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention relates to digital palmar veins fusion feature recognition methods.A kind of characteristic recognition method of digital palmar veins fusion is provided, the veinprint feature for extracting four finger areas and a palm area is matched, and the matching result for merging five regions identifies user's identity, and reliable authentication may be implemented.The vena metacarpea feature of the finger vein pattern of four fingers and a palm area is blended, characteristic differentiation ability is enhanced, improves the safety of feature identification；Meanwhile being merged using vein pattern matching result of the Gauss subordinating degree function to five regions, enhance the robustness of Feature Correspondence Algorithm.This method can disposably acquire related data using same set of venous collection equipment, and under conditions of equipment cost and acquisition convenience are basically unchanged, the distinguishing ability of Enhanced feature promotes the security performance of authentication, can be widely applied to intelligent access control system.
Description
Technical Field
The invention relates to a finger and palm vein fusion feature identification method, and belongs to the technical field of security and protection biological feature identification.
Background
With the rapid development of computer network information technology, the protection of personal information becomes more and more important, and how to select a reasonable authentication technology is a necessary factor for ensuring information security. Compared with traditional authentication means such as keys, passwords and intelligent IC cards, the biometric identification technology takes the inherent physiological or behavior characteristics of human bodies as the authentication means, has the advantages of difficulty in forgetting and losing, counterfeiting and theft, portability, use anytime and anywhere and the like, and is applied to various fields such as identity authentication, access management, security monitoring and the like. Vein recognition is a new generation of biometric technology, and has the main advantages that: the vein is hidden in the body, is not easy to be copied, stolen or interfered, belongs to the living body characteristic, and has high safety performance. At present, vein recognition mainly comprises three types of finger vein recognition, palm vein recognition and hand back vein recognition, and the most widely applied method is finger vein recognition.
At present, many research results are available in the aspect of Finger vein recognition, patent ZL201110122162.9 provides a low-quality Finger vein image enhancement method, patent ZL201110158717.5 provides a Finger vein image quality detection method, patent ZL200610001324.2 proposes a Finger vein image recognition method, document "FeatureExtraction of Finger-vehicle Patterns Based on Repeated Line Tracking and Italication to Personal Identification (Machine Vision and Applications, 2004)" proposes a Repeated Line Tracking method for Finger vein Line extraction, document "Finger vein recognition method Based on relative distance and angle (the university of China's reputational science version)," proposes a point matching method for combining distance and angle features, document "Finger vein recognition Based on Fisher Identification analysis (the university of Chongqing's electronic mail (the natural mail version)", and document "proposes a vein image matching method Based on subspace analysis", and a university of vein analysis. However, the amount of finger vein feature information of a single finger is small, and it is difficult to secure high security in the case where the number of users is large. Therefore, there is a need to fuse finger vein features with other vein features to improve the discrimination of the features. For example, the document "Personal authentication using Finger vessel Pattern and Finger-Dorsa Texture Fusion (MM2009, 2009)" combines Finger Vein and Finger surface Texture for authentication, and the document "Feature-level Fusion of Finger print and Finger-vehicle for Personal authentication (Pattern Recognition Letters, 2012)" combines Finger Vein and fingerprint for authentication. However, the vein pattern inside the finger and the pattern on the surface of the finger are collected in different manners, so that the cost of equipment needs to be increased by combining the two techniques, and meanwhile, the collection needs to be performed twice, so that the convenience is poor. Moreover, the surface lines of the fingers are greatly influenced by external factors such as abrasion and the like, and the safety is not high.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a finger-palm vein fusion feature identification method, which is used for extracting vein grain features of four finger regions and a palm region for matching, fusing matching results of the five regions to identify the identity of a user, and realizing reliable identity authentication. Firstly, roughly dividing a palm vein image by adopting an OTSU method, and extracting three finger slit areas; automatically positioning five interested areas of the palm and the four fingers according to the circumscribed rectangle frame of the finger slit area and the priori knowledge; then, performing image fine segmentation on the five regions of interest by adopting an optimized repeated line tracking method, and extracting vein lines; then extracting respective fuzzy characteristics of vein lines of the five regions of interest; and finally, calculating the similarity of each region feature and the corresponding region feature in the database by adopting a template matching method, normalizing by adopting a membership function, and judging the similarity according to the weighted accumulation sum of the five region membership.
In order to achieve the above purpose, the present invention adopts the following technical scheme, and a flow chart is shown in fig. 1.
1. Image rough segmentation
Figure 2 shows an image acquired by a metacarpal vein acquisition structure. The vein images of the four finger regions and the vein image of the palm region can be used for identity authentication. The above regions (such as regions R1 to R5 selected by black boxes in fig. 2) are used as regions of interest, and these regions are extracted from the image, and then feature extraction and matching are performed. In order to extract the region of interest, the image needs to be roughly segmented, and the position of the region of interest is located.
The invention adopts Otsu method (OTSU) to obtain the optimal segmentation threshold value of the image, and carries out rough segmentation on the image. Specifically, let
Wherein ξ is the sum of gray values of all pixel points on the image, niThe number of pixels with the gray value i is represented, t is taken as a segmentation threshold,
the between-class variance after the image is divided into two classes is
V(t)＝wB(t)wO(t)(μB(t)-μO(t))2
The goal of OTSU is to choose the threshold that maximizes the between-class variance as the optimal threshold for the image, i.e., the threshold
The coarse segmentation effect obtained by this method is shown in fig. 3.
2. Region of interest extraction
In fig. 3, the positions of the finger gaps of the three fingers are very clear, and the area of the finger gap communication domain is far larger than that of the interference target area. Therefore, the invention identifies the binary image by using an 8-adjacency connection method, reserves the first three connected regions with the largest areas, and calculates the external rectangular regions thereof, where the external rectangles marking the three slit regions in the order from top to bottom are Rect1 ═ x1, { y1, w1, h1}, Rect2 ═ x2, y2, w2, h2} and Rect3 ═ x3, y3, w3, h3}, where (x1, y1) represent the coordinates of the top left vertex of the first slit region Rect1, and w1, h1 represent the width and height of Rect1, respectively. Rect2 and Rect3 are defined the same as Rect 1. Let the minimum value of x1, x2, and x3 be xmin, and yc be y2+0.5h2, so that the circumscribed rectangles of the five vein regions ROI as shown in fig. 2, which are located according to the a priori knowledge, are:
R1＝{xmin-W1,yc-0.5H1,W1,H1}
R2＝{x1,y1-H2,W2,H2}
R3＝{x2,y2-H2,W2,H2}
R4＝{x3,y3-H2,W2,H2}
R5＝{x3,y3+h3+H2,W2,H2}
where W1, H1 are the width and height, respectively, set for the palm region of interest, W2, H2 are the width and height, respectively, set for the finger region of interest, the exemplary image size used in the present invention is 640 x 480, and W1, H1, W2, and H2 take empirical values, 256, 200, and 88, respectively.
3. Vein line extraction
The invention adopts An optimized repeated line tracking method described in a document ' An algorithm for finger-vein segmentation based on modified lined tracking ' (Imaging science journal, 2013) ' to finely segment the image and extract vein lines. The vein line extraction effects of the five regions of interest R1-R5 are shown in FIGS. 4-8, respectively.
4. Vein feature extraction
The invention extracts the fuzzy characteristic of each region of interest as the vein characteristic. Here, R1 is taken as an example, and the feature extraction method of R2 to R5 is the same.
For silence of R1Two-valued vein image f1Extracting the fuzzy characteristic f of each pixel point1*The fuzzy characteristics of the pixel point (x, y) can be expressed as
Wherein, the value 2 represents the vein line target, 0 represents the background, 1 represents the fuzzy value, and the vein line target and the background may be possible.
5. Vein feature matching
The similarity between each interested area and the fuzzy characteristics of the corresponding area in the database is calculated by adopting a membership function, and then the weighted accumulated sum of the membership is used as a judgment basis for judging whether the finger palm vein images are matched or not. Here again, the membership calculation method is described by taking R1 as an example, and the membership calculation methods of R2 to R5 are the same.
Taking the fuzzy characteristic of the R1 area in the database as f10If the similarity between the R1 region to be verified and the R1 region in the database is equal to
Wherein,is a binary function of the number of bits, expressed as,
similarly, the similarities R2 to R5 of the four regions R2 to R5 are found. The invention adopts a membership function constructed by double Gaussian functions to carry out normalization processing on the similarity, and the similarity is expressed as
Wherein, i is 1,2, …, 5. c. Ci1、ci2Respectively representing the mean, σ, of two Gaussian functions corresponding to the ith regioni1、σi2The mean square deviations of two Gaussian functions corresponding to the ith area are respectively represented, the parameters are obtained through experimental statistics, and the parameter values used in the method are shown in table 1.
TABLE 1 Gaussian function parameter values
Then, a weighted cumulative sum of five degrees of membership is calculated, expressed as
Wherein, wiFor weighting, the invention takes w according to the different contribution degrees of the five regions1Is 0.4, w2～w5Are all 0.15.
And finally, verifying whether the two palm veins are similar according to psi, specifically, judging that the two palm vein images are matched when psi is larger than a threshold value T (the empirical value T of the invention is 2.2), and otherwise, judging that the two images are not matched.
The invention has the advantages that: the finger vein features of the four fingers and the palm vein feature of one palm area are fused, so that the feature identification capability is enhanced, and the safety of feature identification is improved; meanwhile, the Gaussian membership function is adopted to fuse the vein feature matching results of the five regions, so that the robustness of the feature matching algorithm is enhanced. The method can acquire related data at one time by adopting the same set of vein acquisition equipment, enhances the identification capability of characteristics and improves the safety performance of identity authentication under the condition that the equipment cost and the acquisition convenience are basically unchanged, and can be widely applied to an intelligent access control system.
Drawings
Figure 1 is a flow chart of the palm vein recognition,
figure 2 is a diagram of a palm vein image and a region of interest,
figure 3 is a diagram of the effect of rough segmentation of the finger palm vein image,
figure 4 is a graph of the extraction effect of vein lines in the R1 region,
figure 5 is a graph of the extraction effect of vein lines in the R2 region,
figure 6 is a graph of the extraction effect of vein lines in the R3 region,
figure 7 is a graph of the extraction effect of vein lines in the R4 region,
fig. 8 is a graph of the extraction effect of vein lines in the R5 region.
Detailed Description
The invention provides a finger and palm vein fusion feature identification method by combining finger veins and palm veins. Firstly, roughly dividing a palm vein image by adopting an OTSU method, and extracting three finger slit areas; automatically positioning five interested areas of the palm and the four fingers according to the circumscribed rectangle frame of the finger slit area and the priori knowledge; then, performing image fine segmentation on the five regions of interest by adopting an optimized repeated line tracking method, and extracting vein lines; then extracting respective fuzzy characteristics of vein lines of the five regions of interest; and finally, calculating the similarity of each region feature and the corresponding region feature in the database by adopting a template matching method, normalizing by adopting a membership function, and judging the similarity according to the weighted accumulation sum of the five region membership. The method can acquire related data at one time by adopting the same set of vein acquisition equipment, enhances the identification capability of characteristics and improves the safety performance of identity authentication under the condition that the equipment cost and the acquisition convenience are basically unchanged, and can be widely applied to an intelligent access control system.
Claims (5)
1. The finger and palm vein fusion feature identification method comprises the steps of extracting vein grain features of four finger areas and a palm area for matching, fusing matching results of the five areas to identify the identity of a user, and realizing reliable identity authentication, and is characterized in that in the first step, an OTSU method is adopted to roughly divide a finger and palm vein image, and three finger gap areas are extracted; secondly, automatically positioning five interested areas of the palm and the four fingers according to the circumscribed rectangle frame of the finger slit area and the priori knowledge; thirdly, performing image fine segmentation on the five regions of interest by adopting an optimized repeated line tracking method, and extracting vein grains; fourthly, extracting respective fuzzy characteristics of vein grains of the five regions of interest; and fifthly, calculating the similarity of each region feature and the corresponding region feature in the database by adopting a template matching method, normalizing by adopting a membership function, and judging the similarity according to the weighted accumulation sum of the five region membership.
2. The method for identifying a finger and palm vein fusion feature according to claim 1, wherein the first step specifically comprises:
calculating optimal segmentation threshold of the image by Otsu method, and performing rough segmentation to locate five interested regions including four finger regions and one palm region, specifically, enabling
Wherein ξ is the sum of gray values of all pixel points on the image, niThe number of pixels with the gray value i is represented, t is taken as a segmentation threshold,
the between-class variance after the image is divided into two classes is
V(t)＝wB(t)wO(t)(μB(t)-μO(t))2
The goal of OTSU is to choose the threshold that maximizes the between-class variance as the optimal threshold for the image, i.e., the threshold
3. The method for identifying a finger-palm vein fusion feature according to claim 1, wherein the second step specifically comprises:
identifying the roughly segmented binary image by using an 8-adjacency connection method, reserving the first three connected regions with the largest areas, and calculating external rectangular regions thereof, wherein the external rectangles marking the three slit regions in the order from top to bottom are rec 1 { (x1, y1, w1, h1}, rec 2 { (x 2, y2, w2, h2} and rec 3 { (x 3, y3, w3, h3}, wherein x1, y1 represent the coordinates of the top left corner of the first slit region rec 1, w1, h1 represent the width and height of rec 1, the definitions of rec 2 and rec 3 are the same as those of rec 1, and the minimum value of x1, x2, and x3 is xmin, yc 2+0.5h2, so that the prior three external rectangular regions are located according to the knowledge of the external vein:
R1＝{xmin-W1,yc-0.5H1,W1,H1}
R2＝{x1,y1-H2,W2,H2}
R3＝{x2,y2-H2,W2,H2}
R4＝{x3,y3-H2,W2,H2}
R5＝{x3,y3+h3+H2,W2,H2}
where W1, H1 are the width and height, respectively, set for the palm region of interest, W2, H2 are the width and height, respectively, set for the finger region of interest, the exemplary image size used is 640 × 480, and W1, H1, W2, and H2 take empirical values of 256, 200, and 88, respectively.
4. The method for identifying a finger and palm vein fusion feature according to claim 3, wherein the fourth step is specifically:
the fuzzy feature of each region of interest is extracted as the vein feature, taking R1 as an example for explanation, the feature extraction method of R2-R5 is the same,
vein binary image f for R11Extracting each pixelFuzzy feature f1*The fuzzy characteristics of the pixel points x, y can be expressed as
Wherein, the value 2 represents the vein line target, 0 represents the background, and 1 represents the fuzzy value, which is the vein line target or the background.
5. The method for identifying a finger and palm vein fusion feature according to claim 4, wherein the fifth step is specifically:
calculating the similarity between each interested region and the fuzzy feature of the corresponding region in the database by adopting a membership function, then taking the weighted accumulated sum of the membership as the judgment basis for judging whether the finger and palm vein images are matched or not, taking R1 as an example to introduce a membership calculation method, wherein the membership calculation method of R2-R5 is the same as that of the fuzzy feature of the corresponding region in the database,
taking the fuzzy characteristic of the R1 area in the database as f10If the similarity between the R1 region to be verified and the R1 region in the database is equal to
Wherein,is a binary function of the number of bits, expressed as,
similarly, the similarity R2-R5 of four regions R2-R5 is obtained, a membership function constructed by double Gaussian functions is adopted, and the similarity is normalized and expressed as
Wherein k is 1,2, …,5, ci1、ci2Respectively representing the mean, σ, of two Gaussian functions corresponding to the kth regionk1、σk2Respectively representing the mean square deviations of two Gaussian functions corresponding to the kth region, which are obtained through experimental statistics,
then, a weighted cumulative sum of five degrees of membership is calculated, expressed as
Wherein, wkTaking w as weight according to different contribution degrees of five regions1Is 0.4, w2～w5Are all set to be 0.15, and,
and finally, verifying whether the two palm veins are similar according to psi, specifically, when psi is greater than a threshold value T and T is 2.2, judging that the two palm vein images are matched, and otherwise, judging that the two palm vein images are not matched.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2016102854034 | 2016-05-04 | ||
| CN201610285403 | 2016-05-04 |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106228151A CN106228151A (en) | 2016-12-14 |
| CN106228151B true CN106228151B (en) | 2019-03-26 |
Family
ID=57548107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610652925.3A Expired - Fee Related CN106228151B (en) | 2016-05-04 | 2016-08-11 | Digital palmar veins fusion feature recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106228151B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107909532B (en) * | 2017-11-30 | 2021-07-09 | 公安部物证鉴定中心 | Fingerprint feature evaluation method based on combination of fuzzy mathematics and probability theory |
| CN108805034B (en) * | 2018-05-22 | 2021-09-28 | 公安部物证鉴定中心 | Fingerprint feature similarity evaluation method based on probability geometric features |
| CN110008892A (en) * | 2019-03-29 | 2019-07-12 | 北京海鑫科金高科技股份有限公司 | A kind of fingerprint verification method and device even referring to fingerprint image acquisition based on four |
| CN110033005A (en) * | 2019-04-08 | 2019-07-19 | 北京市商汤科技开发有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN111866573B (en) * | 2020-07-29 | 2022-03-11 | 腾讯科技（深圳）有限公司 | Video playing method and device, electronic equipment and storage medium |
| CN113642489B (en) * | 2021-08-19 | 2024-02-23 | 青岛奥美克生物信息科技有限公司 | Non-contact biological identification method and system |
| CN118552989A (en) * | 2024-07-26 | 2024-08-27 | 盛视科技股份有限公司 | Palm vein recognition method and vein recognition terminal based on feature calibration |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901336A (en) * | 2010-06-11 | 2010-12-01 | 哈尔滨工程大学 | Fingerprint and finger vein bimodal recognition decision level fusion method |
| CN104463120A (en) * | 2014-12-08 | 2015-03-25 | 中国人民解放军国防科学技术大学 | Finger vein recognition method based on binary tree |
| CN104951774A (en) * | 2015-07-10 | 2015-09-30 | 浙江工业大学 | Palm vein feature extracting and matching method based on integration of two sub-spaces |
| CN105426821A (en) * | 2015-11-04 | 2016-03-23 | 浙江工业大学 | Palm vein feature extracting and matching method based on eight neighborhood and secondary matching |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US9659205B2 (en) * | 2014-06-09 | 2017-05-23 | Lawrence Livermore National Security, Llc | Multimodal imaging system and method for non-contact identification of multiple biometric traits |
-
2016
- 2016-08-11 CN CN201610652925.3A patent/CN106228151B/en not_active Expired - Fee Related
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101901336A (en) * | 2010-06-11 | 2010-12-01 | 哈尔滨工程大学 | Fingerprint and finger vein bimodal recognition decision level fusion method |
| CN104463120A (en) * | 2014-12-08 | 2015-03-25 | 中国人民解放军国防科学技术大学 | Finger vein recognition method based on binary tree |
| CN104951774A (en) * | 2015-07-10 | 2015-09-30 | 浙江工业大学 | Palm vein feature extracting and matching method based on integration of two sub-spaces |
| CN105426821A (en) * | 2015-11-04 | 2016-03-23 | 浙江工业大学 | Palm vein feature extracting and matching method based on eight neighborhood and secondary matching |
Non-Patent Citations (5)
| Title |
|---|
| Finger-vein pattern restoration with Direction-Variance-Boundary Constraint Search;TongLiu;《Engineering ApplicationsofArtificial Intelligence》;20150929;第131-139页 |
| Integrated biometrics template protection technique based on fingerprint and palmprint feature-level fusion;Y.J. Chin;《Information Fusion》;20130917;第161-174页 |
| 一种基于优化区域OTSU的静脉图像分割算法;谢剑斌 等;《信号处理》;20090131;第25卷(第1期);第87-89页 |
| 一种基于先验信息和多模板匹配的票据水印检测算法;谢剑斌 等;《光子学报》;20100930;第39卷(第9期);第1706-1710页 |
| 手指静脉结构的B样条描述方法;刘通 等;《国防科技大学学报》;20141031;第36卷(第5期);第93-97页 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106228151A (en) | 2016-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106228151B (en) | Digital palmar veins fusion feature recognition methods | |
| Okawa | Synergy of foreground–background images for feature extraction: Offline signature verification using Fisher vector with fused KAZE features | |
| Kang et al. | From noise to feature: Exploiting intensity distribution as a novel soft biometric trait for finger vein recognition | |
| Zhang et al. | Fingerprint classification based on extraction and analysis of singularities and pseudo ridges | |
| Nigam et al. | Multiple texture information fusion for finger-knuckle-print authentication system | |
| Jin et al. | Face detection using template matching and skin-color information | |
| Li et al. | Principal line-based alignment refinement for palmprint recognition | |
| CN105956579A (en) | Rapid finger vein identification method integrating fuzzy template and point characteristics | |
| CN107169479A (en) | Intelligent mobile equipment sensitive data means of defence based on fingerprint authentication | |
| Fei et al. | Complete binary representation for 3-D palmprint recognition | |
| Yasuda et al. | Visual-based online signature verification using features extracted from video | |
| Ali et al. | Multimodal biometrics enhancement recognition system based on fusion of fingerprint and palmprint: a review | |
| Krishneswari et al. | A review on palm print verification system | |
| Impedovo et al. | Recent advances in offline signature identification | |
| Soh et al. | A review: Personal identification based on palm vein infrared pattern | |
| CN104361339B (en) | Slap shape Graph Extraction and recognition methods | |
| Boles et al. | Personal identification using images of the human palm | |
| Alrahawe et al. | A Contactless Palm Veins Biometric System Based on Convolutional Neural Network | |
| Mohamed et al. | Automated face recogntion system: Multi-input databases | |
| Jaswal et al. | Finger knuckle image based personal authentication using DeepMatching | |
| Ahmed et al. | Intelligent techniques for matching palm vein images | |
| Alsubari et al. | Facial expression recognition using wavelet transform and local binary pattern | |
| Shen et al. | A pornographic image filtering model based on erotic part | |
| Dubey et al. | Optimal local direction binary pattern based palmprint recognition | |
| Said et al. | Ear segmentation in color facial images using mathematical morphology |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190326 |