CN111639555B - Finger vein image noise accurate extraction and adaptive filtering denoising method and device - Google Patents
Finger vein image noise accurate extraction and adaptive filtering denoising method and device Download PDFInfo
- Publication number
- CN111639555B CN111639555B CN202010414619.2A CN202010414619A CN111639555B CN 111639555 B CN111639555 B CN 111639555B CN 202010414619 A CN202010414619 A CN 202010414619A CN 111639555 B CN111639555 B CN 111639555B
- Authority
- CN
- China
- Prior art keywords
- noise
- response value
- finger vein
- filtering
- curvature
- 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
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
- G06V40/12—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
- 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
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T90/00—Enabling technologies or technologies with a potential or indirect contribution to GHG emissions mitigation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Collating Specific Patterns (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a finger vein image noise accurate extraction and self-adaptive filtering denoising method and device, wherein the method comprises the following steps: 1) Calculating a multidirectional curvature response value of the finger vein image based on the two-dimensional Gaussian template; 2) Setting a maximum curvature response value threshold T 1 A curvature response value threshold S and a number threshold T exceeding the curvature response value threshold 2 Determining a noise area according to the curvature response value distribution condition and extracting a noise area image; 3) And filtering the noise area by a circle-by-circle self-adaptive median filtering method to obtain a denoised finger vein image. The device comprises a calculation module, a noise area extraction module and a noise area filtering module. The method can realize accurate and effective detection of the noise of the finger vein image, realize accurate and rapid filtering processing on the detected noise area, effectively improve the recognition performance of the finger vein image containing the noise, and improve the actual use experience of the finger vein recognition system.
Description
Technical Field
The invention belongs to the technical field of biological feature recognition in information security, and particularly relates to a finger vein image noise accurate extraction and adaptive filtering denoising method and device.
Background
The finger vein recognition technology belongs to the biological characteristic recognition technology and is a typical technology in the second generation biological characteristic recognition technology. The outstanding technical characteristics are that the collected biological characteristics are in the body, and compared with traditional biological characteristics such as fingerprints, faces and the like, the biological characteristics have higher safety and irreproducibility. The characteristic acquisition relies on the absorption of hemoglobin in blood to near infrared light, so that living body identification is fundamentally ensured, and meanwhile, the finger vein lines have uniqueness and long-term invariance, so that the method is a biological characteristic with high safety and great research value.
It is found that cracks on the finger, peeling areas or dust on the acquisition window are all reflected in the finger vein image, and the gray value of the dust is generally lower than that of the finger vein line area, and the dust belongs to a noise area in the finger vein image. When noise exists in the finger vein image, instability of the noise can cause great problems for the practical use experience of the finger vein recognition system: when the noise of the image is excessive, the verification passing rate may be reduced, and even verification success may not be possible. Therefore, when noise exists in the finger vein image, detection and filtering denoising are needed to be carried out on the noise area, so that the success rate of verification of the image containing the noise is improved.
The finger vein recognition method disclosed in patent number CN110119724A comprises the following steps: performing ROI positioning on an image acquired by a high-definition camera; carrying out gray scale normalization processing on different parts of the image; carrying out mean filtering and Gaussian filtering on the image to eliminate noise; judging the center position of the grain by using curvature detection; enhancing the contrast of the gray scale map through gamma transformation; judging edge pixel points by using a refinement method based on an index table; fusing, expanding and smoothing the extracted finger vein skeleton; finger vein recognition was performed by template matching, hu invariant moment, improved Zernike moment.
In the prior art, the method for eliminating noise by carrying out mean filtering and Gaussian filtering on the image has the following defects: the noise area is not positioned accurately enough, and the filtering processing speed is not fast enough.
Disclosure of Invention
The invention aims to solve the defects of inaccurate positioning of a noise region of a finger vein image and insufficient filtering processing speed in the finger vein recognition process in the prior art, and provides a finger vein image noise accurate extraction and self-adaptive filtering denoising method and device.
In order to achieve the purpose, the technical scheme provided by the invention is as follows:
the invention relates to a finger vein image noise accurate extraction and self-adaptive filtering denoising method, which comprises the following steps:
1) Calculating a multidirectional curvature response value of the finger vein image based on the two-dimensional Gaussian template;
2) Setting a maximum curvature response value threshold T 1 A curvature response value threshold S and a number threshold T exceeding the curvature response value threshold 2 Determining a noise area according to the curvature response value distribution condition and a threshold value, and extracting a noise area image;
3) And filtering the noise area by a circle-by-circle self-adaptive median filtering method to obtain a denoised finger vein image.
Preferably, the specific step of step 1) includes:
1.1 Constructing a curvature calculation operator in the 8 direction according to a two-dimensional Gaussian function, wherein the two-dimensional Gaussian function is as follows:
wherein x and y represent the length and width of the template, respectively;
1.2 Calculating a multidirectional curvature, the calculation of curvature involving the calculation of a first partial derivative, the calculation of a second partial derivative and the calculation of a gaussian function in a straight line L θ First and second directional derivatives in the direction, wherein,
the calculation formula of the first partial derivative is as follows:
the calculation formula of the second partial derivative is as follows:
calculating the Gaussian function in the straight line L θ The calculation formulas of the first-order and second-order directional derivatives in the direction are as follows:
wherein θ represents an included angle introduced, which is a certain straight line L θ An included angle with the positive direction of the x-axis;
1.3 Calculating a multidirectional curvature response value, wherein the calculation formula is as follows:
preferably, the step 2) specifically includes:
2.1 Setting a maximum curvature response value threshold T 1 According to the maximum curvature response value threshold T 1 Screening suspected noise points;
2.2 A curvature response value threshold S and a number threshold T exceeding the curvature response value threshold are set 2 According to the rate response value threshold S and the number threshold T exceeding the curvature response value threshold 2 Determining a noise area;
2.3 A noise area image is extracted.
Preferably, the rate response value threshold S is smaller than the maximum curvature response value threshold T 1 。
Preferably, the magnitude of the rate response value threshold S is: s=t 1 /2。
Preferably, the step 3) specifically includes:
3.1 Setting a proportion value eta of the noise point, and calculating the maximum median filtering template size according to the proportion value eta;
3.2 According to the maximum median filtering template size, performing circle-by-circle median filtering from outside to inside to obtain a denoised finger vein image.
Preferably, the specific step of calculating the maximum median filtering template size in the step 3.1) includes:
3.1.1 Setting the template as a square template, wherein the initial side length of the template is 1;
3.1.2 Calculating the proportion of noise points in all points in the current template size;
3.1.3 If the proportion of noise points in all points in the current template size is smaller than eta, the current template size is determined to be the best matched median filtering template size, if the proportion of noise points in all points in the current template size is larger than or equal to eta, the side length is increased on the basis of the side length of the current template, and the step 3.1.2 is returned.
Preferably, in the step 3.1.3), the increase of the side length is 1 each time.
Preferably, the specific way of the circle-by-circle median filtering from outside to inside in the step 3.2) is as follows: the median filtering is defined as one pass in four directions, namely from top to bottom, from bottom to top, from left to right, and from right to left, wherein only one noise point is processed each time, after the first pass is executed, the outermost noise point of the noise area in the image is filtered, the noise point is marked as a normal point at the moment, the next pass is performed, and the size of the maximum median filtering template needs to be recalculated every time the next pass is performed.
The invention also relates to a finger vein image noise accurate extraction and self-adaptive filtering denoising device, which comprises:
1) The calculating module is used for calculating a multidirectional curvature response value of the finger vein image based on the two-dimensional Gaussian template;
2) A noise region extraction module for setting a maximum curvature response value threshold T 1 A curvature response value threshold S and a number threshold T exceeding the curvature response value threshold 2 Determining a noise area according to the curvature response value distribution condition and extracting a noise area image;
3) And the noise region filtering module is used for filtering the noise region through a circle-by-circle self-adaptive median filtering method to obtain a denoised finger vein image.
Compared with the prior art, the technical scheme provided by the invention has the following beneficial effects:
the invention provides a finger vein image noise accurate extraction and self-adaptive filtering denoising method, which comprises the steps of firstly calculating a multidirectional curvature value of a finger vein image based on a two-dimensional Gaussian template, then extracting a noise area according to the curvature value, filtering noise points through median filtering of a circle-by-circle self-adaptive size, and realizing noise area detection and noise filtering of the finger vein image.
Drawings
FIG. 1 is a flow chart of a method for accurately extracting vein image noise and adaptively filtering and denoising;
FIG. 2 is a gray scale image of a finger vein containing noise;
FIG. 3 is a threshold T 2 Judging a suspected noise area image;
FIG. 4 is an image after adaptive turn-by-turn median filtering;
FIG. 5 is an illustration of gray scale images of the finger veins in different noise patterns;
FIG. 6 is a denoised image of a library of differently noisy images;
fig. 7 is a block diagram showing accurate extraction of vein image noise and adaptive filtering denoising.
Detailed Description
The invention will be further understood by reference to the following examples which are given to illustrate the invention but are not intended to limit the scope of the invention.
Example 1
Referring to fig. 1, the accurate extraction and adaptive filtering denoising method of finger vein image noise comprises the following steps:
1) For a finger vein gray scale image, as shown in fig. 2, the image size is 320×140, it is obvious that noise points with low gray scale value and more dispersed distribution exist in the image, and the multidirectional curvature response value of the finger vein image is calculated based on a two-dimensional gaussian template, and the specific steps include:
1.1 Constructing a curvature calculation operator in the 8 direction according to a two-dimensional Gaussian function, wherein the two-dimensional Gaussian function is as follows:
wherein x and y represent the length and width of the template, respectively, the two-dimensional gaussian template selected in this embodiment is a 9×9 square template, and x=y=9;
1.2 Calculating a multidirectional curvature, the calculation of curvature involving the calculation of a first partial derivative, the calculation of a second partial derivative and the calculation of a gaussian function in a straight line L θ First and second directional derivatives in the direction, wherein,
the calculation formula of the first partial derivative is as follows:
the calculation formula of the second partial derivative is as follows:
calculating the Gaussian function in the straight line L θ The calculation formulas of the first-order and second-order directional derivatives in the direction are as follows:
wherein θ represents an included angle introduced, which is a certain straight line L θ The included angle with the positive direction of the x-axis, the angle parameter θ in this embodiment takes the value of 0 °,22.5 °,45 °,67.5 °,90 °,112.5 °,135 °,157.5 °;
1.3 Calculating a multidirectional curvature response value K θ The calculation formula is as follows:
2) Setting a maximum curvature response value threshold T 1 Curvature responseA value threshold S and a number threshold T exceeding a curvature response value threshold 2 Determining a noise area and extracting a noise area image according to the curvature response value distribution condition and a threshold value, wherein the specific steps are as follows:
2.1 Since the curvature value of the noise region is generally large and since the continuity thereof is poor, there are large values above a plurality of direction angles, the maximum curvature response value threshold T is set first 1 T in the present embodiment 1 280, according to the maximum curvature response value threshold T 1 Screening suspected noise points, i.e. when the maximum curvature value of a point is greater than T 1 When the noise points are suspected noise points;
2.2 A rate response value threshold S and a number threshold T exceeding the curvature response value threshold 2 Wherein the magnitude of the rate response value threshold S is smaller than the maximum curvature response value threshold T 1 In the present embodiment, s=t 1 Number threshold T exceeding curvature response value threshold 2 Is 5, according to the rate response value threshold S and the quantity threshold T exceeding the curvature response value threshold 2 The noise area is determined, namely, the condition that the curvature response value exceeds 140 and the maximum curvature response value exceeds 280 is required to be satisfied at least in 5 directions, the current point is considered to be the determined noise area, the noise area image shown in fig. 4 is extracted, and compared with fig. 2 and 3, the extracted noise area image can accurately reflect the noise distribution condition in the image, so that accurate detection is realized.
3) After obtaining an accurate noise area image, filtering the noise area by a circle-by-circle self-adaptive median filtering method to obtain a denoised finger vein image, wherein the specific steps comprise:
3.1 Because the size of the median filtering template has direct influence on the filtering effect and efficiency, the noise area in the finger vein image has different sizes, and if the whole image uses a larger median filtering template, the filtering time is longer; if smaller templates are used, the filtering effect is not good for some large noisy areas. It is therefore necessary to determine its optimal median filtering template size for a certain noise point. The median filtering principle is to select the intermediate value after sorting all the values in the template to replace the current value, if a certain point is a noise point, the gray value of the point is an edge area of all the value sorting in the template size, the median is to be ensured to be close to the normal gray range, the proportion of the noise point number in the point in the current template is required to be ensured not to be too high, therefore, when the template size of median filtering is determined, the proportion value eta of the noise point is required to be set, in the embodiment, the proportion value eta is 30%, namely, the proportion of the noise point in the template participating in median filtering at present is ensured to be not to exceed 30%, the filtering effect at the moment is better, and the maximum median filtering template size is calculated according to the proportion value eta, namely
3.1.1 Setting the template as a square template, wherein the initial side length of the template is 1;
3.1.2 Calculating the proportion of noise points in all points in the current template size;
3.1.3 If the proportion of noise points in all points in the current template size is smaller than eta, the current template size is determined to be the best matched median filtering template size, if the proportion of noise points in all points in the current template size is larger than or equal to eta, the side length is increased on the basis of the side length of the current template, the increment of the side length each time is 1, and the step 3.1.2) is returned, and the maximum median filtering template side length of the embodiment is 6 is obtained through the method;
3.2 According to the maximum median filtering template size, carrying out circle-by-circle median filtering from outside to inside to obtain a denoised finger vein image, wherein the specific mode is as follows: the median filtering is defined as one time in four directions, namely one time from top to bottom, from bottom to top, and from left to right, and from right to left, wherein only one noise point is processed each time, after the first time is executed, the outermost noise point of a noise area in an image is filtered, and is marked as a normal point at the moment, and then the next time of filtering is carried out; it should be noted that: for each filtering, the size of the maximum median filtering template needs to be recalculated, the filtered image is shown in fig. 4, and compared with fig. 2, the noise area in the image is basically filtered out, the vein lines become the main areas with low gray values in the image, and the vein features are obvious.
In order to analyze the denoising effectiveness of the method, a plurality of noise image libraries of different types are selected, and as shown in fig. 5, a total of 3 noise type images are used as comparison images, and 1 group of normal acquisition image libraries which do not contain noise are saved and used as template images. The situation after denoising of the 3 kinds of noise image libraries is shown in fig. 6, and the method has good filtering effects on noise with different distribution forms at different degrees. The comparison test was based on the 4 image libraries described above, each image library containing 100 fingers, 5 images per finger. And taking the normal image input system as a template, directly inputting 3 groups of noise image libraries into the system as verification images to obtain verification results without denoising, and inputting the 3 groups of noise image libraries into the system as verification images after denoising by the method to obtain the verification results after denoising, wherein the verification passing rate and the false recognition rate are respectively counted, and when the false recognition rate is counted, the finger templates are shielded and only the rest 99 finger templates are compared. For each noise image library, the number of results of statistical verification success rate is 1500, and the number of results of statistical false verification rate is 1500. The success rate before and after denoising and the false recognition rate are compared as shown in table 1.
Table 1: comparison of success rate before and after denoising and false recognition rate
As is clear from the results in table 1, the recognition rate was reduced to different degrees when the finger vein image included noise, and the more serious the noise was, the more the recognition rate was reduced. After the noise image is denoised, the recognition rate of the noise image can be obviously improved, for 3 noise image libraries with different degrees, the recognition rate is respectively improved by 12.40 percent, 15.53 percent and 15.60 percent, and for images with more serious noise, the recognition rate is improved more, and no new false recognition is performed after the noise is removed in the aspect of false recognition rate, so that the overall recognition performance of the noise image library can be improved by the denoising method.
Example two
Referring to fig. 7, the present embodiment relates to a finger vein image noise accurate extraction and adaptive filtering denoising apparatus, including:
1) The calculating module is used for calculating a multidirectional curvature response value of the finger vein image based on the two-dimensional Gaussian template; the computing module is a module for realizing the function of the step 1) in the embodiment.
2) A noise region extraction module for setting a maximum curvature response value threshold T 1 A curvature response value threshold S and a number threshold T exceeding the curvature response value threshold 2 Determining a noise area according to the curvature response value distribution condition and extracting a noise area image; the noise region extraction module is a module for realizing the function of step 2) of the embodiment.
3) And the noise region filtering module is used for filtering the noise region through a circle-by-circle self-adaptive median filtering method to obtain a denoised finger vein image. The noise region filtering module is a module for realizing the function of the step 3) in the embodiment.
The present invention has been described in detail with reference to the embodiments, but the description is only the preferred embodiments of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention should be considered as falling within the scope of the present invention.
Claims (9)
1. A finger vein image noise accurate extraction and self-adaptive filtering denoising method is characterized in that: which comprises the following steps:
1) Calculating a multidirectional curvature response value of a finger vein image based on a two-dimensional Gaussian template, wherein the method specifically comprises the following steps of:
1.1 Constructing a curvature calculation operator in the 8 direction according to a two-dimensional Gaussian function, wherein the two-dimensional Gaussian function is as follows:
in the method, in the process of the invention,xandyrespectively representing the length and the width of the template;
1.2 Calculating a multidirectional curvature, the calculation of curvature involving the calculation of a first partial derivative, a second partial derivativeCalculation of the order partial derivative and calculation of the Gaussian function in a straight lineL θ First and second directional derivatives in the direction, wherein,
the calculation formula of the first partial derivative is as follows:
the calculation formula of the second partial derivative is as follows:
calculating the Gaussian function in straight lineL θ The calculation formulas of the first-order and second-order directional derivatives in the direction are as follows:
in the method, in the process of the invention,θindicating the included angle of introduction, which is a straight lineL θ And (3) withxAn included angle in the axial direction;
1.3 Calculating a multidirectional curvature response value, wherein the calculation formula is as follows:
2) Setting a maximum curvature response value threshold T 1 A curvature response value threshold S and a number threshold T exceeding the curvature response value threshold 2 Determining a noise area according to the curvature response value distribution condition and a threshold value, and extracting a noise area image;
3) And filtering the noise area by a circle-by-circle self-adaptive median filtering method to obtain a denoised finger vein image.
2. The method for accurately extracting and adaptively filtering and denoising finger vein image noise according to claim 1, wherein the method comprises the following steps of: the step 2) specifically comprises the following steps:
2.1 Setting a maximum curvature response value threshold T 1 According to the maximum curvature response value threshold T 1 Screening suspected noise points;
2.2 A curvature response value threshold S and a number threshold T exceeding the curvature response value threshold are set 2 According to the curvature response value threshold S and the number threshold T exceeding the curvature response value threshold 2 Determining a noise area;
2.3 A noise area image is extracted.
3. The finger vein image noise accurate extraction and adaptive filtering denoising method according to claim 2, wherein: the curvature response value threshold S is smaller than the maximum curvature response value threshold T 1 。
4. The method for accurately extracting and adaptively filtering and denoising finger vein image noise according to claim 3, wherein the method comprises the following steps of: the curvature response value threshold S is as follows: s=t 1 /2。
5. The method for accurately extracting and adaptively filtering and denoising finger vein image noise according to claim 1, wherein the method comprises the following steps of: the step 3) specifically comprises the following steps:
3.1 Setting the proportion value of noise pointsηAccording to the ratio valueηCalculating the size of a maximum median filtering template;
3.2 According to the maximum median filtering template size, performing circle-by-circle median filtering from outside to inside to obtain a denoised finger vein image.
6. The method for accurately extracting and adaptively filtering and denoising finger vein image noise according to claim 5, wherein the method comprises the following steps of: the specific step of calculating the maximum median filtering template size in the step 3.1) comprises the following steps:
3.1.1 Setting the template as a square template, wherein the initial side length of the template is 1;
3.1.2 Calculating the proportion of noise points in all points in the current template size;
3.1.3 If the proportion of noise points in all points in the current template size is smaller thanηThe current template size is determined to be the best matched median filtering template size, if the proportion of noise points in all points in the current template size is greater than or equal toηAnd (3) increasing the side length on the basis of the side length of the current template, and returning to the step 3.1.2).
7. The method for accurately extracting and adaptively filtering and denoising finger vein image noise according to claim 6, wherein the method comprises the following steps of: the increase of the side length in the step 3.1.3) is 1 each time.
8. The method for accurately extracting and adaptively filtering and denoising finger vein image noise according to claim 5, wherein the method comprises the following steps of: the specific mode of the circle-by-circle median filtering from outside to inside in the step 3.2) is as follows: the median filtering is defined as one pass in four directions, namely from top to bottom, from bottom to top, from left to right, and from right to left, wherein only one noise point is processed each time, after the first pass is executed, the outermost noise point of the noise area in the image is filtered, the noise point is marked as a normal point at the moment, the next pass is performed, and the size of the maximum median filtering template needs to be recalculated every time the next pass is performed.
9. The utility model provides a finger vein image noise accurate extraction and self-adaptation filtering denoising device which characterized in that: it comprises the following steps:
1) The calculation module calculates a multidirectional curvature response value of the finger vein image based on a two-dimensional Gaussian template, and specifically comprises the following steps:
1.1 Constructing a curvature calculation operator in the 8 direction according to a two-dimensional Gaussian function, wherein the two-dimensional Gaussian function is as follows:
in the method, in the process of the invention,xandyrespectively representing the length and the width of the template;
1.2 Calculating a multidirectional curvature, the calculation of the curvature involving the calculation of a first partial derivative, the calculation of a second partial derivative, and the calculation of a gaussian function in a straight lineL θ First and second directional derivatives in the direction, wherein,
the calculation formula of the first partial derivative is as follows:
the calculation formula of the second partial derivative is as follows:
calculating the Gaussian function in straight lineL θ The calculation formulas of the first-order and second-order directional derivatives in the direction are as follows:
in the method, in the process of the invention,θindicating the included angle of introduction, which is a straight lineL θ And (3) withxAn included angle in the axial direction;
1.3 Calculating a multidirectional curvature response value, wherein the calculation formula is as follows:
2) A noise region extraction module for setting a maximum curvature response value threshold T 1 A curvature response value threshold S and a number threshold T exceeding the curvature response value threshold 2 Determining a noise area according to the curvature response value distribution condition and extracting a noise area image;
3) And the noise region filtering module is used for filtering the noise region through a circle-by-circle self-adaptive median filtering method to obtain a denoised finger vein image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010414619.2A CN111639555B (en) | 2020-05-15 | 2020-05-15 | Finger vein image noise accurate extraction and adaptive filtering denoising method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010414619.2A CN111639555B (en) | 2020-05-15 | 2020-05-15 | Finger vein image noise accurate extraction and adaptive filtering denoising method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111639555A CN111639555A (en) | 2020-09-08 |
| CN111639555B true CN111639555B (en) | 2023-06-20 |
Family
ID=72330834
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010414619.2A Active CN111639555B (en) | 2020-05-15 | 2020-05-15 | Finger vein image noise accurate extraction and adaptive filtering denoising method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111639555B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113790818B (en) * | 2021-08-10 | 2023-09-26 | 中国电子科技集团公司第十三研究所 | Visible light heat reflection temperature measurement method and temperature measurement equipment |
| CN115272684B (en) * | 2022-09-29 | 2022-12-27 | 山东圣点世纪科技有限公司 | Method for processing pseudo noise in vein image enhancement process |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188614A (en) * | 2019-04-30 | 2019-08-30 | 杭州电子科技大学 | It is a kind of based on skin crack segmentation NLM filtering refer to vein denoising method |
Family Cites Families (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101017798B1 (en) * | 2008-11-03 | 2011-03-02 | 서울대학교산학협력단 | Method and apparatus for finger vein identification using mean curvature |
| EP2385494A1 (en) * | 2010-05-07 | 2011-11-09 | IBBT vzw | A method and device for estimating noise in a reconstructed image |
| CN103020958B (en) * | 2012-11-22 | 2015-11-18 | 北京理工大学 | A kind of blood vessel automatic matching method based on curvature scale space |
| JP5951817B1 (en) * | 2015-02-09 | 2016-07-13 | コリセン カンパニー リミテッドＫｏｒｅｃｅｎ Ｃｏ．，Ｌｔｄ． | Finger vein authentication system |
| EP3057034B1 (en) * | 2015-02-10 | 2019-08-28 | Korecen Co., Ltd. | Finger vein authentication system |
| CN106096569B (en) * | 2016-06-20 | 2019-07-09 | 广州中国科学院先进技术研究所 | A kind of finger vein identification method |
| CN106127151B (en) * | 2016-06-23 | 2019-04-19 | 北京海鑫科金高科技股份有限公司 | Based on the finger vein identification method and device for improving local binary model |
| CN108256456B (en) * | 2018-01-08 | 2020-04-07 | 杭州电子科技大学 | Finger vein identification method based on multi-feature threshold fusion |
| CN108520214A (en) * | 2018-03-28 | 2018-09-11 | 五邑大学 | A kind of finger vein identification method based on multiple dimensioned HOG and SVM |
| CN109145792A (en) * | 2018-08-09 | 2019-01-04 | 钧安科技（深圳）有限公司 | Two fingers setting refers to vein identification device and method |
| CN110119724A (en) * | 2019-05-16 | 2019-08-13 | 天津科技大学 | A kind of finger vein identification method |
| CN110751029B (en) * | 2019-09-12 | 2022-08-02 | 南京邮电大学 | Maximum curvature-based adaptive finger vein line extraction method |
| CN110852280B (en) * | 2019-11-13 | 2022-04-15 | 圣点世纪科技股份有限公司 | Detection algorithm for mirror foreign matter of finger vein equipment |
-
2020
- 2020-05-15 CN CN202010414619.2A patent/CN111639555B/en active Active
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110188614A (en) * | 2019-04-30 | 2019-08-30 | 杭州电子科技大学 | It is a kind of based on skin crack segmentation NLM filtering refer to vein denoising method |
Non-Patent Citations (1)
| Title |
|---|
| 基于L-曲率流滤波器的图像降噪算法;周昌雄;于盛林;祖克举;;《光学精密工程》(第06期);第759-765页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111639555A (en) | 2020-09-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107767387B (en) | Contour detection method based on variable receptive field scale global modulation | |
| CN110443128B (en) | Finger vein identification method based on SURF feature point accurate matching | |
| CN107368792A (en) | A kind of finger vein identification method and system based on wave filter and Bone Edge | |
| CN110837768B (en) | Online detection and identification method for rare animal protection | |
| CN106778668B (en) | A kind of method for detecting lane lines of robust that combining RANSAC and CNN | |
| CN104408707B (en) | Rapid digital imaging fuzzy identification and restored image quality assessment method | |
| CN106682678B (en) | Image corner detection and classification method based on support domain | |
| CN107729820A (en) | A kind of finger vein identification method based on multiple dimensioned HOG | |
| CN108520214A (en) | A kind of finger vein identification method based on multiple dimensioned HOG and SVM | |
| CN111639555B (en) | Finger vein image noise accurate extraction and adaptive filtering denoising method and device | |
| CN110070090A (en) | A kind of logistic label information detecting method and system based on handwriting identification | |
| CN104268515A (en) | Sperm morphology anomaly detection method | |
| CN107886539B (en) | High-precision gear visual detection method in industrial scene | |
| US11475707B2 (en) | Method for extracting image of face detection and device thereof | |
| CN112597812A (en) | Finger vein identification method and system based on convolutional neural network and SIFT algorithm | |
| CN107742302B (en) | Contour detection method based on primary visual cortex multi-scale contour fusion | |
| CN108090492B (en) | Contour detection method based on scale clue suppression | |
| CN117689655A (en) | Metal button surface defect detection method based on computer vision | |
| CN113781413A (en) | Electrolytic capacitor positioning method based on Hough gradient method | |
| CN113673396A (en) | Spore germination rate calculation method and device and storage medium | |
| CN115994870B (en) | Image processing method for enhancing denoising | |
| CN112101058A (en) | Method and device for automatically identifying test paper bar code | |
| CN111127407A (en) | Fourier transform-based style migration counterfeit image detection device and method | |
| CN114913607A (en) | Finger vein counterfeit detection method based on multi-feature fusion | |
| CN115438698A (en) | Power equipment voice recognition method and system based on image processing |
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 |