CN115631515A - Efficient finger vein image feature extraction method and system - Google Patents
Efficient finger vein image feature extraction method and system Download PDFInfo
- Publication number
- CN115631515A CN115631515A CN202210903447.4A CN202210903447A CN115631515A CN 115631515 A CN115631515 A CN 115631515A CN 202210903447 A CN202210903447 A CN 202210903447A CN 115631515 A CN115631515 A CN 115631515A
- Authority
- CN
- China
- Prior art keywords
- pixel
- dispersion
- feature extraction
- finger vein
- binary sequence
- 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
- G06V40/14—Vascular patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/54—Extraction of image or video features relating to texture
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention provides a high-efficiency finger vein image feature extraction method and a system, which comprises the following steps: step 1, obtaining a pixel dispersion distribution map containing main grain information by using a pixel dispersion algorithm described by a local average value and a standard deviation; step 2, performing multiple feature extraction on the obtained pixel dispersion distribution map by using a pixel dispersion extraction algorithm fused with main texture information and using a Kirsch filtering kernel to obtain a pixel block combination; wherein, the moving mode of the Kirsch is from left to right and from top to bottom; step 3, traversing all pixel blocks in the pixel block combination to obtain a global weight and a binary sequence; and 4, calculating the GLDP codes according to the obtained binary sequence and the global weight, and combining the obtained GLDP codes as pixel values of corresponding positions to finally obtain the characteristic image. The characteristic image with good main grain information description effect can be obtained through the method and the device.
Description
Technical Field
The invention belongs to the technical field of image processing and biological recognition, and particularly relates to a high-efficiency finger vein image feature extraction method and system.
Background
Finger vein recognition is a recognition technology based on biological physiological characteristics, and veins in fingers are captured by near infrared light (700 nm-1000 nm) to generate shadows, so that vein images are formed. Compared with other biological physiological characteristics, the method has obvious advantages in that the vein characteristics are as follows: (1) living body identification: finger vein images can only be obtained on a living human body; (2) uniqueness: the vein lines of the finger of each person are unique; (3) stability: the distribution characteristics of the finger veins of each individual are not changed throughout life after adulthood; (4) safety: the finger veins are distributed under the skin, and the complex degree of the lines is high, so that the finger veins are difficult to forge. Therefore, in recent years, finger vein recognition has important application values in the fields of identity authentication, entrance and exit management, security monitoring, e-commerce, e-government affairs and the like by virtue of a series of advantages thereof, and has become one of important research fields in the technology of biometric identification.
The general finger vein recognition is divided into four parts: image acquisition, preprocessing, feature extraction and matching authentication. In the process of collecting the finger vein image, the characteristic information of the finger vein image is composed of local texture information and is finally displayed through the main texture information, but at present, no matter which algorithm is adopted, the characteristic information of the finger vein image focuses on the extraction of the local texture information and ignores the importance of the main texture information, and the matching performance is reduced. Therefore, the main texture information in the feature extraction becomes particularly important.
In the existing finger vein image feature extraction method, one part of the method can not well describe main texture information, and the other part of the method does not consider filtering noise when extracting the feature information, so that the robustness of the noise is poor, for example, feature extraction algorithms such as a local orientation mode and the like can not be robustly adapted to images obtained by different image acquisition equipment, and only local textures are emphasized in the process of extracting the features of the images, but the main texture information is ignored, even the image noise can be extracted for some images with poor quality, and the local orientation mode needs to perform eight-direction Kirsch kernel function operation, so that the efficiency is low; the unified local binary pattern algorithm screens out sequences with more hops in the binary sequences, so that the influence of noise on feature extraction is filtered out, although the influence of the noise is solved to a certain extent, the effect of a feature picture is also influenced, and the extracted feature information is poor in performance in a matching authentication stage.
When observing a finger vein image, it is found that there are usually many noises in a general image, and the noises are not easily perceived by human eyes, and when feature extraction is performed by using a feature extraction algorithm based on pixel gradient information, such as a local binary operator, the noises are amplified infinitely. Meanwhile, because the local texture information and the noise information are not easy to distinguish, the noise information is difficult to screen in the feature extraction algorithm.
Disclosure of Invention
In order to solve the above problems, it is necessary to provide an efficient finger vein image feature extraction method and system.
The invention provides a high-efficiency finger vein picture feature extraction method, which comprises the following steps:
step 2, performing multiple feature extraction on the obtained pixel dispersion distribution map by using a pixel dispersion extraction algorithm fused with main grain information and using a Kirsch filtering kernel to obtain a pixel block combination; wherein, the moving mode of the Kirsch is from left to right and from top to bottom;
and 4, calculating the GLDP codes according to the obtained binary sequence and the global weight, and combining the obtained GLDP codes as pixel values of corresponding positions to finally obtain the characteristic image.
The second aspect of the present invention provides an efficient finger vein image feature extraction system, including:
the first acquisition module is used for acquiring a pixel dispersion distribution map containing main grain information by using a pixel dispersion algorithm described by a local average value and a standard deviation;
the second acquisition module is connected with the first acquisition module and used for performing feature extraction on the obtained pixel dispersion distribution map by using a Kirsch filtering kernel by using a pixel dispersion extraction algorithm fused with main line information to obtain a 3 x 3 pixel block; wherein, the moving mode of Kirsch is from left to right and from top to bottom;
the third acquisition module is connected with the second acquisition module and used for traversing all the pixel blocks to obtain a global weight and a binary sequence;
and the fourth acquisition module is connected with the third acquisition module and used for calculating the GLDP according to the acquired binary sequence and the global weight, and combining the acquired GLDP as the pixel value of the corresponding position to finally acquire the characteristic image.
The third aspect of the present invention provides a terminal, which includes a processor, a memory, and a finger vein image feature extraction algorithm program stored in the memory, where when the finger vein image feature extraction algorithm program is executed by the processor, the steps of the efficient finger vein image feature extraction method are implemented.
The invention has the beneficial effects that: in order to better extract the main grain information, the invention firstly adopts the provided extraction method of the local pixel dispersion distribution map to extract the pixel dispersion distribution map of the finger vein picture so as to remove the picture noise and extract the main grain information of the picture; then, a filtering frame is defined, the filtering frame is moved from top to bottom and from left to right on the pixel dispersion distribution diagram, the binary sequence and the weight of the sequence element in the filtering frame are extracted in sequence, and finally the obtained binary sequence is subjected to weighting operation to finally obtain the feature picture.
The invention can efficiently and accurately obtain the characteristic images for the images acquired by different devices and different application scenes, can obtain the pixel dispersion distribution diagram for the finger vein images acquired by different acquisition devices based on the essential characteristics of the images, further acquires the main grain information, and has stronger robustness.
Additional aspects and advantages of the invention will be set forth in part in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a flow chart of the overall algorithm of the present invention.
Fig. 2 is a Kirsch filter kernel to which the present invention is applied.
Fig. 3 is a diagram of the effect of feature extraction applied to different images acquired by different acquisition devices.
Detailed Description
In order that the above objects, features and advantages of the present invention can be more clearly understood, a more particular description of the invention will be rendered by reference to the appended drawings. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as specifically described herein and, therefore, the scope of the present invention is not limited by the specific embodiments disclosed below.
Example 1
As shown in fig. 1 and fig. 2, the present embodiment provides an efficient finger vein image feature extraction method, including the following steps:
the pixel dispersion algorithm described by the local mean and the standard deviation comprises the following steps:
step 1.1, at size m r ×m l The finger vein image area uses a pixel dispersion algorithm;
step 1.2, calculating the average value m of all pixels in the region operated by the current algorithm j And standard deviation s j ；
Where j is the area number operated by the current algorithm, i c Is (x) c ，y c ) The discrete value of the pixel is processed, v is the number of each pixel in the operation area, n is the number of the pixels in the operation area, (x) c ，y c ) Is the position of the pixel in the operating region;
step 1.3, combine mean values m j And standard deviation s j Obtaining the pixel dispersion T (x) of the jth domain space j ，y j )；
T(x j ，y j )＝m j +k×s j
Wherein k is the standard deviation s j An added bias value;
step 1.4, combining to obtain pixel dispersion T (x) j ，y j ) Sequentially moving from left to right and from top to bottom in the vein image, respectively calculating the pixel dispersion of all regions, and finally obtaining a pixel dispersion distribution diagram T Guided ＝{T(x 1 ，y 1 )，T(x 2 ，y 2 )，...，T(x n ，y n )}。
Step 2, performing multiple feature extraction on the obtained pixel dispersion distribution map by using a pixel dispersion extraction algorithm fused with main texture information and using a Kirsch filtering kernel to obtain a pixel block combination; wherein, the moving mode of Kirsch is from left to right and from top to bottom;
specifically, a method for performing feature extraction on the obtained pixel dispersion distribution map by using a Kirsch filtering kernel includes:
step 2.1, obtaining the pixel dispersion distribution diagram T Guided And performing feature extraction by using a Kirsch filtering kernel to obtain a pixel block P i (ii) a Defining blocks Pi of pixels except for the dispersion of the centers (x) i ，y i ) The dispersion of (b) is p;
step 2.2, using subscripts after p is sequentially sequenced as weight values of the binary pattern;
step 2.3, using the pixel blocks P defined in step 2.1 i Extracting a binary sequence, performing weighted calculation by taking the weight value defined in the step 2.2 as an index of 2 in the binary sequence, performing convolution operation on a space region by using a Kirsch filter kernel, and finally obtaining an extracted pixel block P i 。
the specific method for obtaining the global weight and the binary sequence comprises the following steps:
step 3.1, the extracted pixel block P i The central pixel in (2) is marked as p c With its neighbor pixels labeled p k ；
Step 3.2, passing the neighborhood pixel p k Assigning a value to the binary sequence s; obtaining a binary sequence by using the following formula:
wherein, s (p) k ) For the extracted pixel block P i Center pixel p c The value of the binary sequence at the position;
for the extracted pixel block P i Neighborhood pixel p corresponding to pixel region of pixel dispersion map k Carrying out sequential arrangement, and endowing the binary sequence at the corresponding position with a weight w according to the ordered subscript k Wherein k = 0.., 7;
step 3.3, sequentially traversing all the extracted pixel blocks P from left to right and from top to bottom i And 3.2, traversing and executing the step each time to obtain the binary sequences and the weights of all the regions.
wherein, GLDP (x) c ，y c ) Is (x) c ，y c ) Corresponding GLDP code.
Fig. 3 shows a feature extraction effect graph of different images obtained by different acquisition devices, and it can be seen that the algorithm of the embodiment can well represent texture information, and simultaneously well filter noise information, and has a better effect than most of local binary pattern derivation algorithms.
Example 2
The embodiment provides an efficient finger vein picture feature extraction system, including:
the first acquisition module is used for acquiring a pixel dispersion distribution map containing main grain information by using a pixel dispersion algorithm described by a local average value and a standard deviation;
the second acquisition module is connected with the first acquisition module and used for performing feature extraction on the obtained pixel dispersion distribution map by using a Kirsch filtering kernel by using a pixel dispersion extraction algorithm fused with main grain information to obtain a 3 multiplied by 3 pixel block; wherein, the moving mode of the Kirsch is from left to right and from top to bottom;
the third acquisition module is connected with the second acquisition module and used for traversing all the pixel blocks to obtain a global weight and a binary sequence;
and the fourth acquisition module is connected with the third acquisition module and used for calculating the GLDP according to the acquired binary sequence and the global weight, and combining the acquired GLDP as the pixel value of the corresponding position to finally acquire the characteristic image.
The specific implementation process of the system of this embodiment is as described in embodiment 1, and is not described herein again.
Example 3
The embodiment provides a terminal, which includes a processor, a memory, and a finger vein image feature extraction algorithm program stored in the memory, where when the finger vein image feature extraction algorithm program is executed by the processor, the steps of the efficient finger vein image feature extraction method according to embodiment 1 are implemented.
Example 4
The present embodiment provides a computer-readable storage medium, on which computer instructions are stored, and when the computer instructions are executed by a processor, the computer instructions implement the steps of the efficient finger vein image feature extraction method according to embodiment 1.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
Each functional unit in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated module may be stored in a computer-readable storage medium if it is implemented in the form of a software functional unit and sold or used as a separate product. Based on such understanding, all or part of the flow in the method of the embodiments described above may be implemented by a computer program, which may be stored in a computer-readable storage medium and can implement the steps of the embodiments of the methods described above when the computer program is executed by a processor. The computer program includes computer program code, and the computer program code may be in a source code form, an object code form, an executable file or some intermediate form.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (11)
1. An efficient finger vein picture feature extraction method is characterized by comprising the following steps:
step 1, obtaining a pixel dispersion distribution map containing main grain information by using a pixel dispersion algorithm described by a local average value and a standard deviation;
step 2, performing multiple feature extraction on the obtained pixel dispersion distribution map by using a pixel dispersion extraction algorithm fused with main texture information and using a Kirsch filtering kernel to obtain a pixel block combination; wherein, the moving mode of the Kirsch is from left to right and from top to bottom;
step 3, traversing all pixel blocks in the pixel block combination to obtain a global weight and a binary sequence;
and 4, calculating the GLDP codes according to the obtained binary sequence and the global weight, and combining the obtained GLDP codes as pixel values of corresponding positions to finally obtain the characteristic image.
2. The method for extracting characteristics of a finger vein picture with high efficiency as claimed in claim 1, wherein the pixel dispersion algorithm described by the local mean and the standard deviation comprises:
step 1.1, at size m r ×m l The finger vein image area uses a pixel dispersion algorithm;
step 1.2, calculating the average value m of all pixels in the region operated by the current algorithm j And standard deviation s j ；
Where j is the region number operated by the current algorithm, i c Is (x) c ,y c ) The discrete value of the pixel, C is the number of each pixel in the operation area, n is the number of the pixels in the operation area, (x) c ,y c ) Is the position of the pixel in the operating region;
step 1.3, combine mean values m j And standard deviation s j Obtaining the pixel dispersion T (x) of the jth domain space j ,y j )；
T(x j ,y j )＝m j +k×s j
Wherein k is the standard deviation s j An added bias value;
step 1.4, combining to obtain the pixel dispersion T (x) j ,y j ) Sequentially moving from left to right and from top to bottom in the vein image, respectively calculating the pixel dispersion of all regions, and finally obtaining a pixel dispersion distribution diagram T Guided ＝{T(x 1 ,y 1 ),T(x 2 ,y 2 ),…,T(x n ,y n )}。
3. The method for efficiently extracting the features of the finger vein picture according to claim 2, wherein the method for extracting the features of the obtained pixel dispersion distribution map by using a Kirsch filter kernel comprises the following steps:
step 2.1, obtaining the pixel dispersion distribution diagram T Guided And performing feature extraction by using a Kirsch filtering kernel to obtain a pixel block P i (ii) a Defining a block of pixels P i (x) other than central dispersion i ,y i ) The dispersion of (b) is p;
step 2.2, using subscripts after p is sequentially sequenced as weight values of the binary pattern;
step 2.3, using the pixel block P defined in step 2.1 i Extracting a binary sequence, performing weighted calculation by taking the weight value defined in the step 2.2 as an index of 2 in the binary sequence, performing convolution operation on a spatial region through a Kirsch filter core, and finally obtaining an extracted pixel block P i 。
4. The robust finger vein image feature extraction method according to claim 2, wherein the method for obtaining the global weight and the binary sequence comprises:
step 3.1, the extracted pixel block P i The central pixel in (1) is marked as p c With its neighbor pixels labeled p k ；
Step 3.2, passing the neighborhood pixel p k Assigning a value to the binary sequence s; obtaining a binary sequence by using the following formula:
wherein, s (p) k ) For the extracted pixel block P i Center pixel p c The value of the binary sequence at the position;
for the extracted pixel block P i Neighborhood pixel p corresponding to pixel region of pixel dispersion map k Carrying out sequential arrangement, and endowing the binary sequence at the corresponding position with a weight w according to the ordered subscript k Wherein k = 0.., 7;
step 3.3, sequentially traversing all the extracted pixel blocks P from left to right and from top to bottom i And 3.2, traversing and executing the step each time to obtain the binary sequences and the weights of all the regions.
5. The robust finger vein image feature extraction method according to claim 3, wherein the GLDP code calculation method is implemented by the following formula:
wherein, GLDP (x) c ，y c ) Is (x) c ，y c ) Corresponding GLDP code.
6. An efficient finger vein picture feature extraction system is characterized by comprising:
the first acquisition module is used for acquiring a pixel dispersion distribution map containing main grain information by using a pixel dispersion algorithm described by a local average value and a standard deviation;
the second acquisition module is connected with the first acquisition module and used for performing feature extraction on the obtained pixel dispersion distribution map by using a Kirsch filtering kernel by using a pixel dispersion extraction algorithm fused with main line information to obtain a 3 x 3 pixel block; wherein, the moving mode of the Kirsch is from left to right and from top to bottom;
the third acquisition module is connected with the second acquisition module and used for traversing all the pixel blocks to obtain a global weight and a binary sequence;
and the fourth acquisition module is connected with the third acquisition module and used for calculating the GLDP codes according to the acquired binary sequence and the global weight, and combining the acquired GLDP codes as pixel values of corresponding positions to finally acquire the characteristic image.
7. The efficient finger vein picture feature extraction system according to claim 5, wherein the pixel dispersion algorithm described by the local mean and standard deviation comprises:
step 1.1, at size m r ×m l The finger vein image area uses a pixel dispersion algorithm;
step 1.2, calculating the average value m of all pixels in the region operated by the current algorithm j And standard deviation s j ；
Where j is the area number operated by the current algorithm, i c Is (x) c ,y c ) The discrete value of the pixel, C is the number of each pixel in the operation area, n is the number of the pixels in the operation area, (x) c ,y c ) Is the position of the pixel in the operating region;
step 1.3, average value m of binding j And standard deviation s j Obtaining the pixel dispersion T (x) of the jth domain space j ,y j )；
T(x j ,y j )＝m j +k×s j
Wherein k is the standard deviation s j An added bias value;
step 1.4, combining to obtain pixel dispersion T (x) j ,y j ) Sequentially moving from left to right and from top to bottom in the vein image, respectively calculating the pixel dispersion of all regions, and finally obtaining a pixel dispersion distribution diagram T Guides ＝{T(x 1 ,y 1 ),T(x 2 ,y 2 ),…,T(x n ,y n )}。
8. The efficient finger vein picture feature extraction system according to claim 6, wherein the method for feature extraction using Kirsch filter kernel for the obtained pixel dispersion distribution map comprises:
step 2.1, obtaining the pixel dispersion distribution diagram T Guided And performing feature extraction by using a Kirsch filtering kernel to obtain a pixel block P i (ii) a Defining a block P of pixels i (x) other than central dispersion i ,y i ) The dispersion of (b) is p;
step 2.2, using subscripts after p is sequentially sequenced as weight values of the binary pattern;
step 2.3, using the pixel blocks P defined in step 2.1 i Extracting a binary sequence, and then taking the weight value defined in the step 2.2 as an index of 2 in the binary sequenceLine weighting calculation, convolution operation is carried out on the space region through a Kirsch filtering core, and finally the extracted pixel block P is obtained i 。
9. The efficient finger vein picture feature extraction system according to claim 7, wherein the method for obtaining the global weight and the binary sequence comprises:
step 3.1, extracting the pixel block P i The central pixel in (1) is marked as p c With its neighboring pixels labeled p k ；
Step 3.2, passing the neighborhood pixel p k Assigning a value to the binary sequence s; obtaining a binary sequence by using the following formula:
wherein, s (p) k ) For the extracted pixel block P i Center pixel p c The value of the binary sequence at the position;
for the extracted pixel block P i Neighborhood pixel p corresponding to pixel region of pixel dispersion map k Carrying out sequential arrangement, and endowing the binary sequence at the corresponding position with a weight w according to the ordered subscript k Wherein k = 0.., 7;
step 3.3, sequentially traversing all the extracted pixel blocks P from left to right and from top to bottom i And 3.2, traversing and executing the step each time to obtain the binary sequences and the weights of all the regions.
10. The efficient finger vein image feature extraction system according to claim 8, wherein the GLDP code calculation method is implemented by the following formula:
wherein, GLDP (x) c ，y c ) Is (x) c ，y c ) Corresponding GLDP code.
11. A terminal, characterized by: the finger vein image feature extraction method comprises a processor, a memory and a finger vein image feature extraction algorithm program stored in the memory, wherein when the finger vein image feature extraction algorithm program is executed by the processor, the steps of the efficient finger vein image feature extraction method according to any one of claims 1-4 are realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210903447.4A CN115631515A (en) | 2022-07-28 | 2022-07-28 | Efficient finger vein image feature extraction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210903447.4A CN115631515A (en) | 2022-07-28 | 2022-07-28 | Efficient finger vein image feature extraction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115631515A true CN115631515A (en) | 2023-01-20 |
Family
ID=84902966
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210903447.4A Pending CN115631515A (en) | 2022-07-28 | 2022-07-28 | Efficient finger vein image feature extraction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115631515A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117437665A (en) * | 2023-11-27 | 2024-01-23 | 江苏芯灵智能科技有限公司 | Finger vein feature extraction method |
-
2022
- 2022-07-28 CN CN202210903447.4A patent/CN115631515A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117437665A (en) * | 2023-11-27 | 2024-01-23 | 江苏芯灵智能科技有限公司 | Finger vein feature extraction method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Choi et al. | Finger vein extraction using gradient normalization and principal curvature | |
| Qiu et al. | Finger vein presentation attack detection using total variation decomposition | |
| CN111225611B (en) | Systems and methods for facilitating analysis of wounds in a target object | |
| CN107862249B (en) | Method and device for identifying split palm prints | |
| CN107135664B (en) | Face recognition method and face recognition device | |
| Hartung et al. | Spectral minutiae for vein pattern recognition | |
| KR20090087895A (en) | Method and apparatus for extraction and matching of biometric detail | |
| Ambeth Kumar et al. | Exploration of an innovative geometric parameter based on performance enhancement for foot print recognition | |
| CN110188614A (en) | It is a kind of based on skin crack segmentation NLM filtering refer to vein denoising method | |
| Bruno et al. | Palmprint principal lines extraction | |
| Ahamed et al. | Low complexity iris recognition using curvelet transform | |
| CN108182399B (en) | Finger vein feature comparison method and device, storage medium and processor | |
| Raghavendra et al. | Exploring dorsal finger vein pattern for robust person recognition | |
| CN111814682A (en) | Face living body detection method and device | |
| CN115631515A (en) | Efficient finger vein image feature extraction method and system | |
| Khan et al. | A new method to extract dorsal hand vein pattern using quadratic inference function | |
| JP2011044101A (en) | Threshold update device, threshold determination device, threshold update method, threshold determination method and program | |
| JP2010277315A (en) | Information processing apparatus, authentication data selection method, and program | |
| Krichen et al. | Specific texture analysis for iris recognition | |
| Wang et al. | Building palm vein capturing system for extraction | |
| Meraoumia et al. | Do multispectral palmprint images be reliable for person identification? | |
| KR101767051B1 (en) | Method and apparatus for extracting finger vein image based on fuzzy inference | |
| Das et al. | Person identification through IRIS recognition | |
| Boubchir et al. | Competitive coding scheme based on 2D log-gabor filter for palm vein recognition | |
| Cheng et al. | Multiple training stage image enhancement enrolled with ccrgan pseudo templates for large area dry fingerprint recognition |
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 |