CN115272684B - Method for processing pseudo noise in vein image enhancement process - Google Patents
Method for processing pseudo noise in vein image enhancement process Download PDFInfo
- Publication number
- CN115272684B CN115272684B CN202211194944.8A CN202211194944A CN115272684B CN 115272684 B CN115272684 B CN 115272684B CN 202211194944 A CN202211194944 A CN 202211194944A CN 115272684 B CN115272684 B CN 115272684B
- Authority
- CN
- China
- Prior art keywords
- noise
- variable
- pixel point
- value
- pixel
- 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
- 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
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground 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
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method for processing pseudo noise in a vein image enhancement process, which belongs to the technical field of biological feature recognition and comprises the following steps: carrying out filtering processing in a cross symmetrical direction on each pixel point in the vein image to obtain a filtering array of each pixel point; subdividing the small neighborhood through the large neighborhood and then judging the suspected noise point; further judging whether the pixel points of suspected noise are noise points by adopting a local processing method to obtain a noise point binary image; and taking the enhanced vein image as an input image to be filtered, taking the noise point binary image as a guide image, and outputting the filtered effect image by adopting a rapid guide filtering method. The method for processing the pseudo noise in the vein image enhancement process is a rapid local denoising method, can well solve local texture noise, avoids the formation of the pseudo noise, and avoids the formation of recognition and false recognition.
Description
Technical Field
The invention belongs to the technical field of biological feature recognition, and particularly relates to a method for processing pseudo noise in a vein image enhancement process.
Background
The image enhancement technology is one of key technologies in the field of image processing, can improve and enhance the quality of an original image, and can effectively improve the identification rate and reduce the false identification rate by enhancing a near-infrared vein image particularly in the neighborhood of biological feature identification-vein identification.
A conventional enhancement processing method for vein images, for example, an image enhancement processing method for palm vein images, disclosed in CN112308044B, which includes: processing the collected palm vein image into a binary black-and-white image; determining a first finger seam point and a second finger seam point in the palm according to the binary black-and-white image; performing extension processing on the first finger seam point and the second finger seam point to obtain a third finger seam point and a fourth finger seam point, and obtaining position information of the region of interest according to the third finger seam point and the fourth finger seam point; obtaining an interested area image from the palm vein image according to the interested area position information; and performing enhancement processing on the image of the region of interest to obtain the enhanced image of the region of interest.
However, since the enhancement of the vein image and the simultaneous enhancement of the peripheral fine texture form the pseudo noise, it is an urgent problem to avoid the formation of the pseudo noise by weakening the edge texture noise while enhancing the vein feature.
Disclosure of Invention
The invention provides a method for processing pseudo noise in a vein image enhancement process, which aims to solve the problems that pseudo noise is easy to generate and identification and recognition are increased in the conventional image enhancement process.
In order to solve the technical problems, the technical scheme provided by the invention is as follows:
the invention relates to a method for processing pseudo noise in a vein image enhancement process, which comprises the following steps:
s1, filtering each pixel point in the vein image in a cross symmetrical direction to obtain a filtering array of each pixel point;
s2, setting a threshold value of the minimum value of the vein image gray level;
s3, solving 5*5 neighborhood gray scale average value and 3*3 neighborhood gray scale minimum value of a certain pixel point of the vein image;
s4, counting the number of the pixel points in the filter array with the numerical value larger than 3*3 neighborhood gray minimum, comparing 3*3 neighborhood gray minimum with a threshold value, and further judging whether the pixel points are suspected noise pixel points or not;
s5, repeating the steps S3 to S4 to obtain all the pixels of the suspected noise, further judging whether the pixels of the suspected noise are noise points by adopting a local processing method, assigning the gray value of the judged noise points as 1, and assigning the gray values of the other pixels as 0 to obtain a noise point binary image;
and S6, taking the enhanced vein image as an input image to be filtered, taking the noise point binary image as a guide image, and outputting the filtered effect image by adopting a rapid guide filtering method.
Preferably, the filter array of the pixel point (i, j) in step S1 is z (k), k =0,1,2 …, and the expression of each array is:
wherein I and j are respectively row coordinates and column coordinates of the pixel points, I is a gray value of the pixel points, k is an index of the filter array, c, b and a respectively represent filter direction coefficients, c belongs to [ -5, -1], b belongs to [ -3,0 ] and c belongs to (0,2).
Preferably, the threshold value of 3*3 neighborhood gray minimum set in step S2 is mx, mx belongs to [85,125], the average value of 5*5 neighborhood gray of the pixel point obtained in step S3 is Mean _ I (I, j), and the minimum value of 3*3 neighborhood gray is MinI (I, j); a variable ks is also set in the step S3, and the initial value of the variable ks is 0;
the step S4 of determining whether the pixel is a suspected-noise pixel includes the specific steps of:
s4.1, judging whether the numerical value in the pixel point filter array is larger than the minimum value Mini (i, j) of the 3*3 neighborhood gray scale, if so, adding 1 to a variable ks, and otherwise, keeping the variable ks unchanged;
and S4.2, if the final variable ks is not less than 6 and the minimum value Mini (i, j) of the 3*3 neighborhood gray levels of the pixel point is greater than a threshold value mx, determining that the pixel point is a suspected-noise pixel point.
Preferably, the step S5 of further determining whether the pixel point of the suspected noise is a noise point by using a local processing method includes the specific steps of:
s5.1, setting a variable km1 and a variable km2, wherein the initial values of the variable km1 and the variable km2 are both 0;
s5.2, subdividing 7*7 neighborhoods of the suspected-noise pixel points into six sub-areas of 3*3, and calculating accumulated gray values of the pixel points in each sub-area;
s5.3, judging whether the average Mean _ I (I, j) of 5*5 neighborhoods of the suspected-noise pixel points is smaller than the accumulated gray value of the pixel points in the sub-area corresponding to the pixel points or not for each suspected-noise pixel point, if yes, adding 1 to a variable km1, and if not, keeping the variable km1 unchanged;
s5.4, judging whether the gray value of each suspected noise pixel point is the maximum gray value of the sub-area corresponding to the suspected noise pixel point, if so, adding 1 to a variable km2, and if not, keeping the variable km2 unchanged;
and S5.5, when the final value of the variable km1 is not less than the threshold km1 'of the variable km1, and the final value of the variable km2 is not less than the threshold km2' of the variable km2, the km1 'is in an element of 0,6, and the km2' is in an element of 0,6, determining the pixel point of the suspected noise as a noise point, assigning the gray value of the noise point to be 1, and otherwise, assigning the gray value to be 0, thereby obtaining a noise point binary image.
Preferably, the threshold km1 'of the variable km1 is 4, and the threshold km2' of the variable km2 is 2.
Preferably, the vein image enhanced in step S6 is a vein image enhanced by Gabor filtering; the kernel function of the Gabor filter is as follows:
in the kernel function of the Gabor filter,xis the pixel point row coordinate and is,yis the pixel point column coordinate and is,λgamma, which is the wavelength of the Gabor filter, is the spatial aspect ratio, representing the ellipticity of the Gabor filter,ψ a in order to be the direction of the filtering,σthe standard deviation is used as the standard deviation,x’for rotating pixel pointsψ a The row coordinate of the angle is set to,y’for rotating pixel pointsψ a Seat row with angleMarking;
wherein the content of the first and second substances,
afor the purpose of filtering at different scales of the image,a=0,1,2…7；
rotation of pixelψ a Line coordinate of angle
And pixel point rotationψ a Column coordinate of angle
Satisfy formula (11)
Preferably, the method for enhancing the vein image in step S6 includes the following steps:
(1) Traversing each pixel point of the vein image I, and carrying out Gabor filtering processing of 8 different scales on each pixel point, wherein the filtering formula is as follows:
in the formula, the content of the active carbon is shown in the specification,I a is a pixel point (x，y) In thatψ a The gray value of the filtering direction after Gabor filtering processing;
(2) And obtaining the image I' after the Gabor filtering enhancement by taking the minimum gray values in 8 directions.
Compared with the prior art, the technical scheme provided by the invention has the following beneficial effects:
the method for processing the pseudo noise in the vein image enhancement process searches suspected noise points from cross-symmetric multidirectional filtering, subdivides a large neighborhood into small neighborhoods, further judges whether pixel points of the suspected noise are noise points by adopting a local processing method, outputs an accurate noise binary image, and filters the noise by quickly guiding a filtering method, so that the method is a quick local denoising method, can well solve local texture noise, avoids the formation of pseudo noise, and avoids the formation of recognition and false recognition.
Drawings
FIG. 1 is an original vein image;
FIG. 2 is a Gabor filtered enhanced image I';
fig. 3 is a diagram of the filtered results output by the fast-guided filtering method.
Detailed Description
For further understanding of the present invention, the present invention will be described in detail with reference to examples, which are provided for illustration of the present invention but are not intended to limit the scope of the present invention.
The invention relates to a method for processing pseudo noise in a vein image enhancement process, which comprises the following steps:
s1, carrying out filtering processing in a cross symmetry direction on each pixel point in the vein image to obtain a filtering array of each pixel point, wherein the specific mode is as follows:
for each pixel point (i, j) in the image, designing a filter direction in a cross symmetry direction, assuming that a filter array in the cross symmetry direction is z (k), k =0,1,2 …, and the expression of each array is:
wherein I and j are respectively row coordinates and column coordinates of the pixel points, I is a gray value of the pixel points, k is an index of the filter array, c, b and a respectively represent filter direction coefficients, c belongs to [ -5, -1], b belongs to [ -3,0 ] and c belongs to (0,2).
S2, setting a threshold value of the minimum value of the vein image gray level: and setting a threshold value of 3*3 neighborhood gray minimum value as mx, wherein mx belongs to 85,125.
S3, solving 5*5 neighborhood gray scale average value and 3*3 neighborhood gray scale minimum value of a certain pixel point of the vein image, wherein 5*5 neighborhood gray scale average value is Mean _ I (I, j), and 3*3 neighborhood gray scale minimum value is Mini (I, j); a variable ks is set, and the initial value of the variable ks is 0.
S4, counting the number of the pixel points in the filter array with the numerical value larger than 3*3 neighborhood gray minimum, comparing the 3*3 neighborhood gray minimum with a threshold, and further judging whether the pixel points are suspected noise pixel points or not, wherein the specific steps of judging whether the pixel points are the suspected noise pixel points or not comprise:
s4.1, judging whether the numerical value in the pixel point filter array is larger than the minimum value Mini (i, j) of the 3*3 neighborhood gray scale, if so, adding 1 to a variable ks, and otherwise, keeping the variable ks unchanged;
and S4.2, if the final variable ks is not less than 6 and the minimum value Mini (i, j) of the 3*3 neighborhood gray levels of the pixel point is greater than a threshold value mx, determining that the pixel point is a suspected-noise pixel point.
S5, repeating the steps S3-S4 to obtain all the pixels of the suspected noise, further judging whether the pixels of the suspected noise are noise points by adopting a local processing method, assigning the gray value of the judged noise points as 1, assigning the gray values of the other pixels as 0, and obtaining a noise point binary image, wherein the specific steps are as follows:
s5.1, setting a variable km1 and a variable km2, wherein the initial values of the variable km1 and the variable km2 are both 0;
s5.2, subdividing 7*7 neighborhoods of the suspected-noise pixel points into six sub-areas of 3*3, and calculating accumulated gray values of the pixel points in each sub-area;
s5.3, judging whether the average Mean value Mean _ I (I, j) of 5*5 neighborhoods of the suspected-noise pixel points is smaller than the accumulated gray value of the pixel points in the sub-areas corresponding to the pixel points or not for each suspected-noise pixel point, if so, adding 1 to a variable km1, and if not, keeping the variable km1 unchanged;
s5.4, judging whether the gray value of each suspected noise pixel point is the maximum gray value of the sub area corresponding to the suspected noise pixel point, if so, adding 1 to a variable km2, and if not, keeping the variable km2 unchanged;
and S5.5, when the final value of the variable km1 is not less than the threshold km1 'of the variable km1, and the final value of the variable km2 is not less than the threshold km2' of the variable km2, the km1 'is in an E [0,6], and the km2' is in an E [0,6], determining that the pixel point of the suspected noise is a noise point, assigning the gray value of the noise point to be 1, and otherwise, assigning the gray value to be 0, and further obtaining a noise point binary image, wherein in the embodiment, the threshold km1 'is 4, and the threshold km2' is 2.
S6, taking the enhanced vein image as an input image to be filtered, taking the noise point binary image as a guide image, and outputting a filtered effect image by adopting a rapid guide filtering method;
in this embodiment, a Gabor filter is used to enhance an original vein image, and a kernel function of the Gabor filter is:
in the kernel function of the Gabor filter,xis the pixel point line coordinate and is the pixel point line coordinate,yis the pixel point column coordinate and is,λgamma, which is the wavelength of the Gabor filter, is the spatial aspect ratio, representing the ellipticity of the Gabor filter,ψ a to be the direction of the filtering,σis the standard deviation of the measured data to be measured,x’for rotating pixel pointsψ a The row coordinate of the angle is set to,y’for rotating pixel pointsψ a Column coordinates of the angle;
wherein, the first and the second end of the pipe are connected with each other,
afor the purpose of filtering at different scales of the image,a=0,1,2…7；
pixel rotationψ a Line coordinate of angle
And the pixel point rotatesψ a Column coordinates of angles
Satisfy formula (11)
The specific steps of adopting Gabor filtering to enhance the original vein image are as follows:
(1) Inputting an original vein image as shown in figure 1; traversing each pixel point of the vein image I, and carrying out Gabor filtering processing of 8 different scales on each pixel point, wherein the filtering formula is as follows:
in the formula, the first step is that,I a is a pixel point (x，y) In thatψ a The gray value of the filtering direction after Gabor filtering processing;
(2) The minimum gray values in 8 directions are taken to obtain the image I' after the enhancement by Gabor filtering as shown in fig. 2.
The filtered result output by the fast-guided filtering method is shown in fig. 3.
The present invention has been described in detail with reference to the embodiments, but the description is only for the preferred embodiments of the present invention and should not be construed as limiting the scope of the present invention. All equivalent changes and modifications made within the scope of the present invention shall fall within the scope of the present invention.
Claims (5)
1. A method for processing pseudo noise in a vein image enhancement process is characterized in that: which comprises the following steps:
s1, filtering each pixel point in the vein image in a cross symmetrical direction to obtain a filtering array of each pixel point;
s2, setting a threshold value mx of the minimum value of the vein image gray level, wherein mx belongs to the field of 85,125;
s3, solving 5*5 neighborhood gray level average Mean value Mean _ I (I, j) and 3*3 neighborhood gray level minimum value Mini (I, j) of a certain pixel point of the vein image, and setting a variable ks, wherein the initial value of the variable ks is 0;
s4, counting the number of the pixel points in the filter array with the value larger than 3*3 neighborhood gray minimum, comparing 3*3 neighborhood gray minimum with a threshold value, and judging whether the pixel points are suspected noise pixel points or not, wherein the method specifically comprises the following steps:
s4.1, judging whether the numerical value in the pixel point filter array is larger than the minimum value Mini (i, j) of the 3*3 neighborhood gray scale, if so, adding 1 to a variable ks, and if not, keeping the variable ks unchanged;
s4.2, if the final variable ks is not less than 6 and the minimum value Mini (i, j) of the 3*3 neighborhood gray levels of the pixel point is greater than a threshold value mx, determining that the pixel point is a suspected-noise pixel point;
s5, repeating the steps S3-S4 to obtain all the suspected noise pixel points, further judging whether the suspected noise pixel points are noise points or not by adopting a local processing method, assigning the gray values of the judged noise points as 1, assigning the gray values of the other pixel points as 0, and obtaining a noise point binary image, wherein the specific steps are as follows:
s5.1, setting a variable km1 and a variable km2, wherein the initial values of the variable km1 and the variable km2 are both 0;
s5.2, subdividing 7*7 neighborhoods of the suspected-noise pixel points into six sub-areas of 3*3, and calculating accumulated gray values of the pixel points in each sub-area;
s5.3, judging whether the average Mean _ I (I, j) of 5*5 neighborhoods of the suspected-noise pixel points is smaller than the accumulated gray value of the pixel points in the sub-area corresponding to the pixel points or not for each suspected-noise pixel point, if yes, adding 1 to a variable km1, and if not, keeping the variable km1 unchanged;
s5.4, judging whether the gray value of each suspected noise pixel point is the maximum gray value of the sub area corresponding to the suspected noise pixel point, if so, adding 1 to a variable km2, and if not, keeping the variable km2 unchanged;
s5.5, when the final value of the variable km1 is not less than the threshold km1 'of the variable km1 and the final value of the variable km2 is not less than the threshold km2' of the variable km2, the km1 'belongs to [0,6], the km2' belongs to [0,6], determining the pixel point of the suspected noise as a noise point, assigning the gray value of the noise point to be 1, and otherwise, assigning the gray value to be 0, thereby obtaining a noise point binary image;
and S6, taking the enhanced vein image as an input image to be filtered, taking the noise point binary image as a guide image, and outputting the filtered effect image by adopting a rapid guide filtering method.
2. The method for processing pseudo noise in the process of enhancing the vein image according to claim 1, wherein: in step S1, the filter array of the pixel point (i, j) is z (k), k =0,1,2 …, and the expression of each array is:
wherein I and j are respectively row coordinates and column coordinates of the pixel points, I is a gray value of the pixel points, k is an index of the filter array, c, b and a respectively represent filter direction coefficients, c belongs to [ -5, -1], b belongs to [ -3,0 ] and c belongs to (0,2).
3. The method for processing pseudo noise in the process of enhancing the vein image according to claim 1, wherein: the threshold value km1 'of the variable km1 is 4, and the threshold value km2' of the variable km2 is 2.
4. The method for processing pseudo noise in the process of enhancing the vein image according to claim 1, wherein: the vein image enhanced in step S6 is a vein image enhanced by Gabor filtering, and a kernel function of a Gabor filter used in the Gabor filtering enhancement is:
in the kernel function of the Gabor filter,xis the pixel point line coordinate and is the pixel point line coordinate,yis the pixel point column coordinate and is,λgamma, which is the wavelength of the Gabor filter, is the spatial aspect ratio, representing the ellipticity of the Gabor filter,ψ a to be the direction of the filtering,σthe standard deviation is used as the standard deviation,x’for rotating pixel pointsψ a The row coordinate of the angle is set to,y’for rotating pixel pointsψ a Column coordinates of the angle;
wherein the content of the first and second substances,
afor the purpose of filtering at different scales of the image,a=0,1,2…7；
rotation of pixelψ a Line coordinate of angle
And the pixel point rotatesψ a Column coordinates of angles
Satisfy formula (11)
5. The method for processing pseudo noise in the process of enhancing the vein image according to claim 4, wherein: the method for enhancing the vein image in the step S6 comprises the following steps:
(1) Traversing each pixel point of the vein image I, and carrying out Gabor filtering processing of 8 different scales on each pixel point, wherein the filtering formula is as follows:
in the formula, the first step is that,I a is a pixel point (x，y) In thatψ a The gray value of the filtering direction after Gabor filtering processing;
(2) And obtaining the image I' after the Gabor filtering enhancement by taking the minimum gray values in 8 directions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211194944.8A CN115272684B (en) | 2022-09-29 | 2022-09-29 | Method for processing pseudo noise in vein image enhancement process |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211194944.8A CN115272684B (en) | 2022-09-29 | 2022-09-29 | Method for processing pseudo noise in vein image enhancement process |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115272684A CN115272684A (en) | 2022-11-01 |
| CN115272684B true CN115272684B (en) | 2022-12-27 |
Family
ID=83756764
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211194944.8A Active CN115272684B (en) | 2022-09-29 | 2022-09-29 | Method for processing pseudo noise in vein image enhancement process |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115272684B (en) |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020911A (en) * | 2012-12-12 | 2013-04-03 | 中国航空工业集团公司洛阳电光设备研究所 | Image processing method for filtering mixed noise |
| CN105243649A (en) * | 2015-11-09 | 2016-01-13 | 天津大学 | Image denoising method based on secondary noise point detection |
| CN106548176A (en) * | 2016-11-18 | 2017-03-29 | 安徽大学 | Finger vein image enhancement method based on self adaptation guiding filtering |
| CN108256456A (en) * | 2018-01-08 | 2018-07-06 | 杭州电子科技大学 | A kind of finger vein identification method based on multiple features Threshold Fusion |
| CN109872289A (en) * | 2019-02-19 | 2019-06-11 | 重庆邮电大学 | Image enchancing method based on improved non-downsampling Contourlet conversion |
| CN111199527A (en) * | 2020-01-04 | 2020-05-26 | 圣点世纪科技股份有限公司 | Finger vein image noise detection method based on multi-direction self-adaptive threshold |
| CN111291709A (en) * | 2020-02-25 | 2020-06-16 | 华南理工大学 | Finger vein image quality evaluation method based on image processing |
| CN111368661A (en) * | 2020-02-25 | 2020-07-03 | 华南理工大学 | Finger vein image enhancement method based on image processing |
| CN111639555A (en) * | 2020-05-15 | 2020-09-08 | 圣点世纪科技股份有限公司 | Finger vein image noise accurate extraction and self-adaptive filtering denoising method and device |
| CN112529800A (en) * | 2020-12-07 | 2021-03-19 | 同济大学 | Near-infrared vein image processing method for filtering hair noise |
| CN113313641A (en) * | 2021-04-28 | 2021-08-27 | 北京理工大学 | CT image denoising method with self-adaptive median filtering |
| WO2022005336A1 (en) * | 2020-06-29 | 2022-01-06 | Autonomous Non-Profit Organization For Higher Education «Skolkovo Institute Of Science And Technology» | Noise-resilient vasculature localization method with regularized segmentation |
| WO2022110804A1 (en) * | 2020-11-24 | 2022-06-02 | 海南大学 | Image noise measurement method and device based on local statistical information |
| CN114724188A (en) * | 2022-05-23 | 2022-07-08 | 北京圣点云信息技术有限公司 | Vein identification method and device based on gray level co-occurrence matrix |
| CN114863498A (en) * | 2022-05-27 | 2022-08-05 | 武汉理工大学 | Hand vein infrared image enhancement and segmentation method based on AGC and Frangi |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080037044A1 (en) * | 2006-08-08 | 2008-02-14 | Xerox Corporation | Methods for background and noise suppression in binary to grayscale image conversion |
| CN111223063B (en) * | 2020-01-12 | 2023-05-02 | 杭州电子科技大学 | Finger vein image NLM denoising method based on texture features and binuclear functions |
| CN112288660B (en) * | 2020-12-25 | 2021-04-13 | 四川圣点世纪科技有限公司 | Vein image restoration method and device based on NMRT (NMRT) directional feature constraint |
-
2022
- 2022-09-29 CN CN202211194944.8A patent/CN115272684B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103020911A (en) * | 2012-12-12 | 2013-04-03 | 中国航空工业集团公司洛阳电光设备研究所 | Image processing method for filtering mixed noise |
| CN105243649A (en) * | 2015-11-09 | 2016-01-13 | 天津大学 | Image denoising method based on secondary noise point detection |
| CN106548176A (en) * | 2016-11-18 | 2017-03-29 | 安徽大学 | Finger vein image enhancement method based on self adaptation guiding filtering |
| CN108256456A (en) * | 2018-01-08 | 2018-07-06 | 杭州电子科技大学 | A kind of finger vein identification method based on multiple features Threshold Fusion |
| CN109872289A (en) * | 2019-02-19 | 2019-06-11 | 重庆邮电大学 | Image enchancing method based on improved non-downsampling Contourlet conversion |
| CN111199527A (en) * | 2020-01-04 | 2020-05-26 | 圣点世纪科技股份有限公司 | Finger vein image noise detection method based on multi-direction self-adaptive threshold |
| CN111291709A (en) * | 2020-02-25 | 2020-06-16 | 华南理工大学 | Finger vein image quality evaluation method based on image processing |
| CN111368661A (en) * | 2020-02-25 | 2020-07-03 | 华南理工大学 | Finger vein image enhancement method based on image processing |
| CN111639555A (en) * | 2020-05-15 | 2020-09-08 | 圣点世纪科技股份有限公司 | Finger vein image noise accurate extraction and self-adaptive filtering denoising method and device |
| WO2022005336A1 (en) * | 2020-06-29 | 2022-01-06 | Autonomous Non-Profit Organization For Higher Education «Skolkovo Institute Of Science And Technology» | Noise-resilient vasculature localization method with regularized segmentation |
| WO2022110804A1 (en) * | 2020-11-24 | 2022-06-02 | 海南大学 | Image noise measurement method and device based on local statistical information |
| CN112529800A (en) * | 2020-12-07 | 2021-03-19 | 同济大学 | Near-infrared vein image processing method for filtering hair noise |
| CN113313641A (en) * | 2021-04-28 | 2021-08-27 | 北京理工大学 | CT image denoising method with self-adaptive median filtering |
| CN114724188A (en) * | 2022-05-23 | 2022-07-08 | 北京圣点云信息技术有限公司 | Vein identification method and device based on gray level co-occurrence matrix |
| CN114863498A (en) * | 2022-05-27 | 2022-08-05 | 武汉理工大学 | Hand vein infrared image enhancement and segmentation method based on AGC and Frangi |
Non-Patent Citations (4)
| Title |
|---|
| Adaptive threshold vein enhancement method based on illuminance estimation;Hailan Kuang等;《2021 IEEE 5th Advanced Information Technology, Electronic and Automation Control Conference (IAEAC)》;20210405;2591-2595 * |
| Performance evaluation of various filters for Noise removal on near Infrared Palm Dorsal Vascular Images;Rajalakshmi.M等;《2020 3rd International Conference on Intelligent Sustainable Systems (ICISS)》;20210118;1024-1031 * |
| 基于纹理约束的手指静脉图像去噪与修复算法研究;蒋寒琼;《中国优秀硕士学位论文全文数据库 信息科技辑》;20220315;第2022年卷(第3期);I138-967 * |
| 镜面污损下的静脉图像去噪算法研究;何必锋;《中国优秀硕士学位论文全文数据库 信息科技辑》;20220315;第2022年卷(第3期);I138-1519 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115272684A (en) | 2022-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112800964B (en) | Remote sensing image target detection method and system based on multi-module fusion | |
| Sulaiman et al. | Denoising-based clustering algorithms for segmentation of low level salt-and-pepper noise-corrupted images | |
| CN114387273B (en) | Environmental dust concentration detection method and system based on computer image recognition | |
| WO2017041488A1 (en) | Fingerprint ridge point recognition method and apparatus | |
| WO2017161636A1 (en) | Fingerprint-based terminal payment method and device | |
| CN116823824B (en) | Underground belt conveyor dust fall detecting system based on machine vision | |
| WO2023116632A1 (en) | Video instance segmentation method and apparatus based on spatio-temporal memory information | |
| CN114972339B (en) | Data enhancement system for bulldozer structural member production abnormity detection | |
| Hait et al. | The Bonferroni mean-type pre-aggregation operators construction and generalization: Application to edge detection | |
| CN117689655B (en) | Metal button surface defect detection method based on computer vision | |
| CN116051382A (en) | Data enhancement method based on deep reinforcement learning generation type antagonistic neural network and super-resolution reconstruction | |
| CN115187688A (en) | Fog map reconstruction method based on atmospheric light polarization orthogonal blind separation and electronic equipment | |
| CN115272684B (en) | Method for processing pseudo noise in vein image enhancement process | |
| WO2022116492A1 (en) | Image template selection method and apparatus, device and storage medium | |
| CN112801141B (en) | Heterogeneous image matching method based on template matching and twin neural network optimization | |
| CN115619678B (en) | Correction method and device for image deformation, computer equipment and storage medium | |
| CN111461999A (en) | SAR image speckle suppression method based on super-pixel similarity measurement | |
| Li et al. | No-reference sharpness index for scanning electron microscopy images based on dark channel prior | |
| Gantenapalli et al. | Selective mean filtering for reducing impulse noise in digital color images | |
| Heras et al. | Surveying and benchmarking techniques to analyse DNA gel fingerprint images | |
| Arpacı et al. | LUPU-Net: a new improvement proposal for encoder-decoder architecture | |
| CN112435186A (en) | Fingerprint image enhancement method based on double-rule matrix direction field | |
| Shao et al. | No-Reference image quality assessment based on edge pattern feature in the spatial domain | |
| CN117115717B (en) | Internet network data analysis method and system | |
| CN113256614B (en) | Medical image processing system |
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 | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20230412 Address after: Room 2309, 23rd Floor, Qidi Building, No. 99, South Tiancheng Road, High Speed Rail New Town, Xiangcheng District, Suzhou City, Jiangsu Province, 215000 - Work Station A029 (cluster registration) Patentee after: Jiangsu Shengdian Century Technology Co.,Ltd. Address before: 266010 Room 1602, Qianshan Building, Building D2, Qingdao International Innovation Park, No. 169, Songling Road, Laoshan District, Qingdao, Shandong Patentee before: Shandong ShengDian Century Technology Co.,Ltd. |
|
| TR01 | Transfer of patent right |