CN112329518B - Fingerprint activity detection method based on edge texture reinforcement and symmetrical differential statistics - Google Patents
Fingerprint activity detection method based on edge texture reinforcement and symmetrical differential statistics Download PDFInfo
- Publication number
- CN112329518B CN112329518B CN202010989868.4A CN202010989868A CN112329518B CN 112329518 B CN112329518 B CN 112329518B CN 202010989868 A CN202010989868 A CN 202010989868A CN 112329518 B CN112329518 B CN 112329518B
- Authority
- CN
- China
- Prior art keywords
- fingerprint
- edge
- image
- pixel
- value
- 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
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 39
- 230000000694 effects Effects 0.000 title claims abstract description 23
- 230000002787 reinforcement Effects 0.000 title claims abstract description 7
- 238000000034 method Methods 0.000 claims abstract description 22
- 238000000605 extraction Methods 0.000 claims abstract description 10
- 239000013598 vector Substances 0.000 claims abstract description 8
- 238000012706 support-vector machine Methods 0.000 claims abstract description 5
- 238000012360 testing method Methods 0.000 claims abstract description 5
- 238000012549 training Methods 0.000 claims abstract description 5
- 238000005728 strengthening Methods 0.000 claims abstract description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 9
- 230000014509 gene expression Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000013461 design Methods 0.000 abstract description 2
- 238000005516 engineering process Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 210000004243 sweat Anatomy 0.000 description 2
- 238000010146 3D printing Methods 0.000 description 1
- 108010010803 Gelatin Proteins 0.000 description 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- QVGXLLKOCUKJST-UHFFFAOYSA-N atomic oxygen Chemical compound [O] QVGXLLKOCUKJST-UHFFFAOYSA-N 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000005284 excitation Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000008273 gelatin Substances 0.000 description 1
- 229920000159 gelatin Polymers 0.000 description 1
- 235000019322 gelatine Nutrition 0.000 description 1
- 235000011852 gelatine desserts Nutrition 0.000 description 1
- 229910052760 oxygen Inorganic materials 0.000 description 1
- 239000001301 oxygen Substances 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 239000011148 porous material Substances 0.000 description 1
- 239000000741 silica gel Substances 0.000 description 1
- 229910002027 silica gel Inorganic materials 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 230000037394 skin elasticity Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000000844 transformation 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
- G06V40/12—Fingerprints or palmprints
- G06V40/1382—Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger
- G06V40/1388—Detecting the live character of the finger, i.e. distinguishing from a fake or cadaver finger using image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration using histogram techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- 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
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- 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
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- 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
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention relates to a fingerprint activity detection method based on edge texture reinforcement and symmetrical differential statistics, which belongs to the field of information security, and mainly designs two feature descriptor extraction features: the edge strengthening texture feature descriptor and the symmetrical difference method feature descriptor are converted into one-dimensional vectors through counting two-dimensional histograms of the two types of features, and the one-dimensional vectors are used as feature descriptors for distinguishing true and false fingerprint images and are input into a support vector machine classifier for training and testing. By utilizing the two feature descriptors designed by the patent, the feature extraction of the fingerprint image is more accurate, so that the classification accuracy of the true and false fingerprint image is improved.
Description
Technical Field
The invention relates to a fingerprint activity detection method based on edge texture reinforcement and symmetric differential statistics, and belongs to the field of information security.
Background
With the rapid development of information technology and science, how to perform personal identity authentication becomes a major focus in the field of information security, and is attracting attention of countries and individuals. In the identity authentication method, the application is that a password is used for authentication of identity. However, the problems of forgetting, leakage or theft of the password also occur, which will cause a lot of security problems. In order to solve these problems, biometric-based authentication techniques such as fingerprint recognition, iris recognition, face recognition, etc. have been proposed successively, and by using biometric features specific to each person, accurate identification is achieved more safely and conveniently. Because the fingerprint has the characteristics of uniqueness, stability and convenience, the problem that a password is forgotten, leaked or stolen can be effectively solved, and the fingerprint-based identity authentication technology is widely applied to the fields of identity authentication and the like in our daily life, such as mobile phone fingerprint unlocking, an access control system, an attendance system, smart phone rapid payment and the like. However, fingerprint-based identity authentication methods also have certain security risks. In recent years, with the advent of various high-resolution simulation, 3D printing, generation of an emerging technology against a network, etc., an illegal user imitates a real fingerprint by acquiring or stealing the fingerprint of the real user, using the emerging technology or special materials. For example, an illegal user can forge a fingerprint film of a real user by using materials such as silica gel, gelatin, plasticine and the like to deceive the identity authentication equipment to perform illegal authentication. In order to prevent counterfeit fingerprint films from fraudulently attacking the identity authentication device, fingerprint activity detection techniques have been proposed which aim at distinguishing whether a fingerprint image originates from a genuine fingerprint.
Existing fingerprint activity detection algorithms are mainly divided into two categories: one is a hardware-based fingerprint activity detection algorithm, and one is a software-based fingerprint activity detection algorithm. The fingerprint activity detection method based on hardware mainly utilizes some sensing devices to detect physiological characteristics of fingerprints, such as temperature, pulse, blood oxygen content, conductivity of living fingerprints and the like, so as to judge whether the fingerprints to be detected are true or false. Although this method can discriminate between true and false fingerprints with a high detection rate, this type of method requires the cooperation of additional hardware devices. The fingerprint activity detection method based on software can be directly embedded into a fingerprint authentication system, and is more convenient and practical. The method is mainly used for distinguishing the true fingerprint from the false fingerprint by analyzing the differences of fingerprint images, such as the texture structure and the image quality of the fingerprint images, and directly realizing the identification of the true fingerprint and the false fingerprint by an image processing technology.
At present, three types of fingerprint activity detection methods based on software mainly comprise a heuristic detection method, a detection method based on deep learning and a fingerprint activity detection method based on texture features. The heuristic detection method is to detect according to some fine features of fingerprints, such as sweat pores, sweat, skin elasticity, etc. The fingerprint activity detection method based on deep learning and texture features extracts features from the true and false fingerprint images, and classifies the true and false fingerprint images according to different feature descriptions.
The existing fingerprint activity detection method based on software only considers the ratio of the absolute value difference value between the current center pixel and the adjacent pixels to the current center pixel, the ratio is positive, and the obtained binarization code is 0 or 1 through comparison with a threshold k. And when calculating the gradient direction, although the WLD method is improved and the diagonal direction is considered, only four values of the vertical, horizontal and diagonal directions are calculated, so that the accuracy of the description of the fingerprint features is not high.
Disclosure of Invention
The invention provides a fingerprint activity detection method based on edge texture reinforcement and symmetric differential statistics, which aims to solve the problems in the prior art and improves the accuracy of fingerprint feature description and the classification accuracy of true and false fingerprint images.
In order to achieve the above purpose, the technical scheme provided by the invention is as follows: a fingerprint activity detection method based on edge texture reinforcement and symmetric difference statistics comprises the following steps:
firstly, preprocessing an original fingerprint image by using an interested region extraction algorithm, and eliminating interference of a background region in the fingerprint image;
two feature descriptors are then designed: edge-enhanced texture features; symmetrical differential direction characteristics; extracting features through two feature descriptors, and then counting the two types of features into a two-dimensional histogram;
and finally, converting the statistical two-dimensional histogram into a one-dimensional vector, taking the one-dimensional vector as a characteristic descriptor for distinguishing the true fingerprint image from the false fingerprint image, and inputting the characteristic descriptor into a support vector machine classifier for training and testing, so that the true fingerprint image and the false fingerprint image are distinguished.
The technical scheme is further designed as follows: the specific steps of preprocessing the original fingerprint image by using the region of interest extraction algorithm are as follows:
loading an original fingerprint image, and carrying out graying treatment on the image;
calculating gradients in the horizontal direction and the vertical direction of the image, and performing difference value operation on the gradients in the two directions;
removing high-frequency noise in the image by using a low-pass filter, and replacing the current pixel value by using an average value;
performing binarization operation on the image, setting a threshold T, setting a pixel of the gradient image to 255 when the pixel is larger than the threshold T, otherwise, setting the pixel to 0;
filling a black region in the fingerprint with white;
searching the most edge contour in the fingerprint image to be used as a detection area;
and cutting the found detection area to obtain the region of interest.
The process of extracting features by edge-enhanced texture feature descriptors is as follows:
x for the center pixel point c Containing n edge pixels x i I=0,..n-1, when n=8, the 3×3 pixel block is represented by the following formula:
the value of the edge-enhanced texture feature is calculated from the following equation:
wherein ,k is a threshold;
in performing binarization, when positive values are considered:when negative values are considered: />Thus obtaining two groups of edge enhancement texture feature values.
The process of extracting the features through the symmetrical differential direction feature descriptors is as follows:
calculating the value of the symmetrical differential direction characteristic by the following formula;
wherein ,xi and xi+(n/2) For a central symmetrical pair of gray pixel values, passing through x i -x i+(n/2) Obtaining the difference value to obtain x 0 ，x 1 ，x 2 ，x 3 Is a value of (2);i.e. average the sum of adjacent pixel values, gradient the average value of adjacent pixels with the central pixel, as expression of the fifth direction information, i.e. x 4 ；
When (when)And calculating the binary code of the symmetrical differential direction characteristic, thereby obtaining the value of the symmetrical differential direction characteristic.
The beneficial effects of the invention are as follows:
the invention considers the difference value between the current center pixel and the adjacent pixels, and both positive and negative values can express certain texture information, so that negative values of the difference value are also considered, minus 1 is introduced, the condition of 0/1 is changed into 0/1/-1, and the fingerprint image characteristic expression is increased. Meanwhile, the invention considers that the difference between the average value of the summation of the central point and the surrounding pixels, namely global information, can also be used as the expression of the direction, thereby designing a feature descriptor of the fifth gradient direction.
According to the invention, an original fingerprint image is screened through a region of interest extraction algorithm, an effective region of the fingerprint image is extracted, feature information expressed by negative values is amplified when differential excitation is calculated respectively, so that edge-enhanced texture features are obtained, the gradient directions of neighborhood information and a central pixel point are increased, and the gradient directions of symmetric pixel pairs of the central point are used together as direction expressions, so that the texture features describing the fingerprint image are more complete, and the classification accuracy of true and false fingerprint images is effectively improved. The method provided by the invention can further promote the field of fingerprint activity detection, has higher detection accuracy and has higher practical value.
Drawings
FIG. 1 is a block diagram of a fingerprint activity detection method based on edge texture enhancement and symmetric difference statistics;
FIG. 2 is a flow chart of edge texture enhancement features and symmetric differential direction feature expression;
FIG. 3 is a graph of fingerprint image detection accuracy (LiveDet 2011 dataset) at different k values;
fig. 4 is a graph of fingerprint image detection accuracy (LiveDet 2013 dataset) at different k values.
Detailed Description
The invention will now be described in detail with reference to the accompanying drawings and specific examples.
Examples
As shown in fig. 1, a frame diagram of a fingerprint activity detection method based on edge texture enhancement and symmetric difference statistics in this embodiment is provided, first, an original fingerprint image is selected by a region of interest extraction algorithm, and effective information of the fingerprint image is selected. The method comprises the following specific steps: 1. loading an original fingerprint image, and carrying out graying treatment on the image; 2. calculating gradients in the horizontal direction and the vertical direction of the image, and performing difference value operation on the gradients in the two directions; 3. removing high-frequency noise in the image by using a low-pass filter, and replacing the current pixel value by using an average value; 4. performing binarization operation on the image, setting a threshold T, setting a pixel of the gradient image to 255 when the pixel is larger than the threshold T, otherwise, setting the pixel to 0; 5. filling a black region in the fingerprint with white; 6. searching the most edge contour in the fingerprint image to be used as a detection area; 7. and cutting the found detection area to obtain the region of interest.
As shown in fig. 2, after obtaining a fingerprint image of a region of interest, the fingerprint image is represented by two feature descriptors: and carrying out feature description on the fingerprint image by the edge enhanced texture features and the symmetrical differential direction features.
The characteristic extraction process of the edge strengthening texture characteristic comprises the following steps:
in the pixel block covered by the feature descriptors, the ratio of the difference between the middle pixel and the edge pixel to the middle pixel actually has a positive value and a negative value, and the negative value can also express the feature information of the image when the threshold value is set to encode the pixel block, so that the negative value is also taken into consideration when calculating the edge enhancement texture feature.
X for the center pixel point c Containing n edge pixels x i I=0,..n-1, when n=8, the 3×3 pixel block is as shown in formula 1:
the value of edge enhanced texture feature (ERTF) can be calculated from equation 2:
wherein ,k is a threshold value, and the adjacent points are classified into three types of 0, 1 and 1.
If the point x is near i ，[(x i -x c )/x c ]> k or [ (x) i -x c )/x c ]< k, then consider the nearest point x i Is a high perception point, otherwise, the point x is adjacent to i Is a low perceived point.
Since three values of 0, 1, -1 occur, in binarizing them, when positive values are considered:when negative values are considered: />Thus obtaining two groups of edge enhancement texture feature values.
The characteristic extraction process of the symmetrical differential direction characteristic comprises the following steps:
the edge enhancement texture features describe the amplitude variation of the pixels of the neighboring points, and the symmetrical differential direction features of the present embodiment are used to describe the direction information. When extracting the gradient direction of the center point and the symmetric pixel pair, the center point does not participate in the direction calculation, but the embodiment considers that the neighborhood direction information should be considered, so that the mean value difference between the center point and the neighborhood pixels is designed as the information of the expansion direction, and a feature descriptor of the fifth gradient direction is designed.
wherein ,xi and xi+(n/2) For a central symmetrical pair of gray pixel values, passing through x i -x i+(n/2) The difference is taken to obtain x in the formula 1 0 ，x 1 ，x 2 ，x 3 Is a value of (2).I.e. the sum of the values of the adjacent pixels is averaged, and the gradient is found between the average value of the adjacent pixels and the center pixel as the expression of the fifth direction information, i.e. x in formula (1) 4 。
When (when)And calculating the binary code of the symmetrical differential direction characteristic, thereby obtaining the value of the symmetrical differential direction characteristic.
In a specific experimental process, when calculating the edge enhancement texture feature, the embodiment sets six values, namely 0.1, 0.2, 0.3, 0.4, 0.5 and 0.6, for the k value, and compares the classification accuracy of the fingerprint image. Meanwhile, in a specific implementation process, in order to obtain more concentrated descriptors, the present patent performs unified mode processing on edge-enhanced texture features, as shown in formula 4.
Where U (ERTF) represents the number of spatial transformations (0.fwdarw.1, 1.fwdarw.0) in the calculated binary code.
And then, counting histograms of the two types of features, converting the counted two-dimensional histograms into one-dimensional vectors, and inputting the one-dimensional vectors into a classifier of a support vector machine for training and testing, so that the authenticity of the fingerprint image is distinguished. In the classifier training and testing process of the support vector machine, four kernel functions are selected for classification comparison in the embodiment, wherein the four kernel functions are obtained through experimental result analysis of Linear, rbf, polynomial, mlp, higher classification accuracy can be obtained by using the rbf kernel function, and the data of fig. 3-4 and tables 1-2 are fingerprint image classification accuracy obtained by using the rbf kernel function.
Table 1 fingerprint image detection accuracy contrast (LiveDet 2011 dataset)
| Method | Biometrika | Dig.Pers | Italdata | Sagem |
| LBP | 87.00 | 89.20 | 75.90 | 88.50 |
| LPQ | 85.30 | 93.30 | 85.60 | 92.00 |
| WLD | 86.75 | 86.25 | 72.33 | 93.34 |
| Ours | 88.50 | 85.85 | 85.95 | 95.40 |
Table 2 fingerprint image detection accuracy contrast (LiveDet 2013 dataset)
During the experiment, the present embodiment used the LiveDet2013 dataset and the LiveDet2011 dataset, respectively. Different sensors are used in different data sets, and the sensors used in the LiveDet2013 data set are: biometrika, italdata, swipe, crossmatch, the sensors used in the LiveDet2011 dataset are: biomerika, dig. Pers, italdata, sagem. Meanwhile, the patent is compared with various fingerprint activity detection methods, such as: LBP, WLD, LPQ, HIG, deep representation with AO, the effectiveness of the method proposed by this patent can be analyzed by experimental comparison.
Fig. 3-4 are the accuracy of classifying true and false fingerprint images by using the feature descriptors of the present patent design. Table 1-2 shows a comparison experiment with other fingerprint image recognition methods, and it is obvious that the feature descriptors designed in this embodiment make the final classification accuracy higher than that of other methods. The method provided by the embodiment can further promote the field of fingerprint activity detection, has higher detection accuracy and has higher practical value.
The technical scheme of the invention is not limited to the embodiments, and all technical schemes obtained by adopting equivalent substitution modes fall within the scope of the invention.
Claims (2)
1. The fingerprint activity detection method based on edge texture reinforcement and symmetrical differential statistics is characterized by comprising the following steps of: firstly, preprocessing an original fingerprint image by using an interested region extraction algorithm;
then extracting features through two feature descriptors, namely edge enhanced texture features and symmetrical differential direction features; the two extracted features are summed into a two-dimensional histogram;
finally, converting the statistical two-dimensional histogram into a one-dimensional vector, taking the one-dimensional vector as a feature descriptor for distinguishing true and false fingerprint images, and inputting the feature descriptor into a support vector machine classifier for training and testing, so that the true and false fingerprint images are distinguished;
the process of extracting features by edge-enhanced texture feature descriptors is as follows:
x for the center pixel point c Containing n edge pixels x i I=0,..n-1, when n=8, the 3×3 pixel block is represented by the following formula:
the value of the edge-enhanced texture feature is calculated from the following equation:
wherein ,k is a threshold;
in performing binarization, when positive values are considered:when negative values are considered: />Thus obtaining two groups of edge strengthening texture characteristic values;
the process of extracting the features through the symmetrical differential direction feature descriptors is as follows:
calculating the value of the symmetrical differential direction characteristic by the following formula; wherein ,xi and xi+(n/2) For a central symmetrical pair of gray pixel values, passing through x i -x i+(n/2) Obtaining the difference value to obtain x 0 ，x 1 ，x 2 ，x 3 Is a value of (2);i.e. average the sum of adjacent pixel values, gradient the average value of adjacent pixels with the central pixel, as expression of the fifth direction information, i.e. x 4 ；
When (when)And calculating the binary code of the symmetrical differential direction characteristic, thereby obtaining the value of the symmetrical differential direction characteristic.
2. The fingerprint activity detection method based on edge texture enhancement and symmetric difference statistics according to claim 1, wherein the specific steps of preprocessing the original fingerprint image by using the region of interest extraction algorithm are as follows:
loading an original fingerprint image, and carrying out graying treatment on the image;
calculating gradients in the horizontal direction and the vertical direction of the image, and performing difference value operation on the gradients in the two directions;
removing high-frequency noise in the image by using a low-pass filter, and replacing the current pixel value by using an average value;
performing binarization operation on the image, setting a threshold T, setting a pixel of the gradient image to 255 when the pixel is larger than the threshold T, otherwise, setting the pixel to 0;
filling a black region in the fingerprint with white;
searching the most edge contour in the fingerprint image to be used as a detection area;
and cutting the found detection area to obtain the region of interest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010989868.4A CN112329518B (en) | 2020-09-18 | 2020-09-18 | Fingerprint activity detection method based on edge texture reinforcement and symmetrical differential statistics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010989868.4A CN112329518B (en) | 2020-09-18 | 2020-09-18 | Fingerprint activity detection method based on edge texture reinforcement and symmetrical differential statistics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112329518A CN112329518A (en) | 2021-02-05 |
| CN112329518B true CN112329518B (en) | 2023-10-13 |
Family
ID=74304508
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010989868.4A Active CN112329518B (en) | 2020-09-18 | 2020-09-18 | Fingerprint activity detection method based on edge texture reinforcement and symmetrical differential statistics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112329518B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113688775A (en) * | 2021-09-06 | 2021-11-23 | 南京信息工程大学 | Fingerprint activity detection method based on local difference polarization |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794440A (en) * | 2015-04-15 | 2015-07-22 | 杭州景联文科技有限公司 | False fingerprint detection method based on multi-block multi-scale LBP |
| CN106295555A (en) * | 2016-08-08 | 2017-01-04 | 深圳芯启航科技有限公司 | A kind of detection method of vital fingerprint image |
| CN106372647A (en) * | 2016-10-13 | 2017-02-01 | 河南科技大学 | Image texture classification method based on Weber local binary counting |
| CN107862267A (en) * | 2017-10-31 | 2018-03-30 | 天津科技大学 | Face recognition features' extraction algorithm based on full symmetric local weber description |
| WO2018082011A1 (en) * | 2016-11-04 | 2018-05-11 | 深圳市汇顶科技股份有限公司 | Living fingerprint recognition method and device |
| CN111353472A (en) * | 2020-03-30 | 2020-06-30 | 蚌埠学院 | Finger vein identification method based on LBP and Gabor direction Weber local descriptor |
-
2020
- 2020-09-18 CN CN202010989868.4A patent/CN112329518B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104794440A (en) * | 2015-04-15 | 2015-07-22 | 杭州景联文科技有限公司 | False fingerprint detection method based on multi-block multi-scale LBP |
| CN106295555A (en) * | 2016-08-08 | 2017-01-04 | 深圳芯启航科技有限公司 | A kind of detection method of vital fingerprint image |
| CN106372647A (en) * | 2016-10-13 | 2017-02-01 | 河南科技大学 | Image texture classification method based on Weber local binary counting |
| WO2018082011A1 (en) * | 2016-11-04 | 2018-05-11 | 深圳市汇顶科技股份有限公司 | Living fingerprint recognition method and device |
| CN107862267A (en) * | 2017-10-31 | 2018-03-30 | 天津科技大学 | Face recognition features' extraction algorithm based on full symmetric local weber description |
| CN111353472A (en) * | 2020-03-30 | 2020-06-30 | 蚌埠学院 | Finger vein identification method based on LBP and Gabor direction Weber local descriptor |
Non-Patent Citations (5)
| Title |
|---|
| A Novel Weber Local Binary Descriptor for Fingerprint Liveness Detection;Zhihua Xia 等;《IEEE Transactions on Systems,Man,and Cybernetics:Systems》;第50卷(第4期);1-11 * |
| Deepshika Tiwari 等.Improved Weber's law based local binary pattern for dynamic texture recognition.《Multimedia Tools and Applications》.2016,6623-6640. * |
| Wood defect classification based on two-dimensional histogram constituted by LBP and local binary differential excitation pattern;Shaoli Li 等;《IEEE Access》;145829-145842 * |
| 基于LBP和Gabor方向的韦伯局部描述子的指静脉识别;姜雪;张自军;杜梦丽;;《兰州文理学院学报(自然科学版)》(第05期);49-56+67 * |
| 基于韦伯二值感知特征的指纹活性检测;吕锐;夏志华;陈先意;孙星明;;《应用科学学报》(第05期);146-154 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112329518A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Zaeri | Minutiae-based fingerprint extraction and recognition | |
| Palma et al. | Biometric palmprint verification: A dynamical system approach | |
| Raghavendra et al. | Presentation attack detection algorithms for finger vein biometrics: A comprehensive study | |
| Alshdadi et al. | Exploiting Level 1 and Level 3 features of fingerprints for liveness detection | |
| CN111783629A (en) | Human face in-vivo detection method and device for resisting sample attack | |
| Appati et al. | Implementation of a Transform‐Minutiae Fusion‐Based Model for Fingerprint Recognition | |
| Li et al. | Comprehensive edge direction descriptor for fingerprint liveness detection | |
| US11068693B1 (en) | Liveness detection in fingerprint-based biometric systems | |
| CN112329518B (en) | Fingerprint activity detection method based on edge texture reinforcement and symmetrical differential statistics | |
| Mehboob et al. | Dehff–a hybrid approach based on distinctively encoded fingerprint features for live fingerprint detection | |
| Harb et al. | Palm print recognition | |
| Mehboob et al. | An encoded histogram of ridge bifurcations and contours for fingerprint presentation attack detection | |
| Fernandes et al. | Directed adversarial attacks on fingerprints using attributions | |
| Berriche | Comparative study of fingerprint-based gender identification | |
| Yuan et al. | Fingerprint liveness detection adapted to different fingerprint sensors based on multiscale wavelet transform and rotation-invarient local binary pattern | |
| CN114913607A (en) | Finger vein counterfeit detection method based on multi-feature fusion | |
| Silpamol et al. | Detection and rectification of distorted fingerprints | |
| Poosarala | Uniform classifier for biometric ear and retina authentication using smartphone application | |
| Aydoğdu et al. | A study on liveness analysis for palmprint recognition system | |
| Sehgal | Palm recognition using LBP and SVM | |
| Shaju et al. | Haar wavelet transform based histogram concatenation model for finger print spoofing detection | |
| Shobha et al. | Development of palmprint verification system using biometrics. | |
| CN108491802A (en) | Palmmprint cross-matched recognition methods based on the excitation of joint weighted difference and double directions Gabor | |
| Mohan et al. | Fingerprint spoofing detection using HOG and local binary pattern | |
| Chaivong et al. | Information Fusion for Enhancing Presentation Attack Detection in Iris 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |