CN112435186B - Fingerprint image enhancement method based on double-rule matrix direction field - Google Patents
Fingerprint image enhancement method based on double-rule matrix direction field Download PDFInfo
- Publication number
- CN112435186B CN112435186B CN202011315342.4A CN202011315342A CN112435186B CN 112435186 B CN112435186 B CN 112435186B CN 202011315342 A CN202011315342 A CN 202011315342A CN 112435186 B CN112435186 B CN 112435186B
- Authority
- CN
- China
- Prior art keywords
- matrix
- fingerprint
- double
- point
- 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
- 239000011159 matrix material Substances 0.000 title claims abstract description 76
- 238000000034 method Methods 0.000 title claims abstract description 24
- 230000000877 morphologic effect Effects 0.000 claims abstract description 6
- 230000009977 dual effect Effects 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 7
- 238000010200 validation analysis Methods 0.000 claims 1
- 238000005516 engineering process Methods 0.000 description 4
- 230000011218 segmentation Effects 0.000 description 3
- 238000005260 corrosion Methods 0.000 description 2
- 230000007797 corrosion Effects 0.000 description 2
- 230000010339 dilation Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000002708 enhancing effect Effects 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013527 convolutional neural network Methods 0.000 description 1
- 238000011840 criminal investigation Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/77—Retouching; Inpainting; Scratch removal
-
- 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
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- 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
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- 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
- G06V40/1359—Extracting features related to ridge properties; Determining the fingerprint type, e.g. whorl or loop
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20021—Dividing image into blocks, subimages or windows
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a fingerprint image enhancement method based on a double-rule matrix direction field, which comprises the following steps: firstly, calculating whether an image mean value and a variance judgment point are on a fingerprint or not to obtain a foreground and a background; the double-rule matrix is designed again, fingerprint direction field characteristics are obtained through the double-rule matrix, a direction characteristic formula is calculated to judge whether the foreground region pixel points are located on the ridge line, if so, the foreground region pixel points are set to be black, otherwise, the foreground region pixel points are set to be white; removing burrs and holes in the fingerprint graph according to the neighborhood of each pixel point; and finally, morphological operation is carried out to obtain a final fingerprint image, so that the image enhancement of the fingerprint is realized. The invention realizes the fingerprint image enhancement method based on the direction field, and the fingerprint image enhancement is realized by determining the direction field characteristic region and the direction characteristic formula by providing a double square method.
Description
Technical Field
The invention belongs to the field of image processing, and particularly relates to a fingerprint image enhancement method based on a double-rule matrix direction field in the field of images.
Background
The fingerprint identification technology is one of the technologies with the highest occupancy rate in the biological identification technology, and is widely applied to the fields of access control technology, criminal investigation, fingerprint payment and the like. In criminal events, criminal suspects often leave fingerprints at criminal sites, and the suspects can be determined by comparing the fingerprints at the sites with fingerprints in a database, however, the fingerprints at the sites are often vague, so that difficulties are increased for subsequent fingerprint comparison, and the fingerprints are required to be enhanced.
The current fingerprint image enhancement algorithm mainly comprises histogram equalization, principal component analysis, gabor filtering, median filtering, sobel filtering and the like, but the method can enhance noise and cause fingerprint ridge contour blurring at the same time of enhancing; the deep learning algorithm is used for enhancing fingerprints, such as a convolutional neural network and an countermeasure generation network, so that the fingerprint processing algorithm has high time complexity and high requirements on hardware, and the fingerprints are difficult to process on a common computer; in addition, if water, oil and the like are present on the finger, the fingerprint image is blurred and broken, and the fingerprint image is distinguished from the actual fingerprint texture.
Disclosure of Invention
The invention aims to provide a fingerprint image enhancement method based on a double-rule matrix direction field, which improves the details of enhanced fingerprint characteristics and removes redundant noise.
In order to achieve the purpose of the invention, the technical scheme adopted by the invention is that the fingerprint image enhancement method based on the double-rule matrix direction field comprises the following steps:
step 1: acquiring a fingerprint image, and determining an area where the fingerprint is located as a foreground area;
step 2: designing a double-rule matrix, and acquiring fingerprint direction field characteristics through the double-rule matrix;
Step 3: judging whether the foreground region pixel point is positioned on the ridge line or not through a direction field characteristic formula;
step 4: deleting flaws in the image output in the step 3;
step 5: and (3) morphological filtering is carried out on the image processed in the step (4), and the enhanced fingerprint image is output.
Preferably, the step 1 includes the steps of:
step 1.1: acquiring a fingerprint image, converting the fingerprint image into a gray image, establishing a coordinate system for the gray image, and calculating a pixel MEAN value MEAN and a variance VAR of the gray image;
Step 1.2: normalizing pixel points of coordinates (x, y) of the gray level image;
step 1.3: dividing the processed gray image into preset image blocks, judging the pixel MEAN value of each image block, and if the pixel MEAN value is smaller than MEAN, the current image block is a fingerprint area and is a foreground, otherwise, the current image block is a background;
step 1.4: and (3) repeating the step (1.3) until all the image blocks are traversed, wherein all the foreground is used as a foreground area of the fingerprint image, and the rest is used as a background area.
Preferably, in the step 1.1, the pixel mean valueVariance ofWherein M and N are the number of pixels of the gray image in the length and width directions, and G (x, y) represents the pixel value of the pixel point of the coordinate (x, y);
in the step 1.2, to Pixel normalization processing is performed on coordinates (x, y) of the gray image, wherein M 0 and VAR 0 are a desired mean and a desired variance, respectively.
Preferably, the dual rule matrix in the step 2 includes an outer matrix and an inner matrix.
Preferably, the external matrix is a sparse interval matrix a, a is the number of pixels on the edge of the external matrix; the internal matrix is a continuous connected non-interval matrix b, and b is the number of pixels on the edge of the internal matrix.
Preferably, b is an odd number and a= 2*b-1.
Specifically, the step 2 includes the following steps:
step 2.1: confirming a double-rule matrix a and b, wherein the periphery is a sparse interval matrix a, and a is the number of pixels on the periphery matrix side; the internal matrix is a continuous connected non-interval matrix b x b, wherein b is the number of pixel points on the edge of the internal matrix; requiring b to be odd and a = 2*b-1; in this specification, b= 7,a =13 is taken as an example;
step 2.2: the process of confirming the direction field area by the double-rule matrix is as follows, and a square matrix of 13 x 13 is made for each pixel point C in the foreground area by taking C as a center; calibrating 1A to 12A, 1B to 12B, 1A 'to 12A', 1B 'to 12B' in the matrix according to preset rules;
Preferably, in step 2.2, 1A to 12A, 1A 'to 12A' are sequentially marked on sides of a rectangle with C as a center point, the side length of the internal rectangle is 7 pixel points, and 1A 'to 12A' and 1A to 12A are center-symmetrical with C.
Preferably, in step 2.2, 1B to 12B, 1B 'to 12B' are sequentially marked on sides of a rectangle with C as a center point at 1 pixel interval, the sides of the external rectangle are 13 pixel points, and 1B 'to 12B' and 1B to 12B are symmetrical with C as a center.
Preferably, in the step 3, the center point C of the bi-regular matrix is connected with the pixel points of the bi-regular matrix, and the sum of the pixel values of the lines in all the directions n is calculated, wherein the maximum value is assigned as S max, the minimum value is assigned as S min, and the average value in all the directions is assigned as S ave; if the direction field characteristic formula S max+Smin+4*c>3*Save is satisfied, the point C is located on the valley line, and the point C is assigned 255, that is, white, otherwise, the point C is located on the ridge line.
Specifically, the step3 includes the following steps:
step 3.1: taking lines passing through nA, nB, nA ', nB' as directions n, respectively calculating the sum of pixel values of the lines in all directions n, and assigning a maximum value S max, a minimum value S min and an average value S ave in all directions;
Step 3.2: the direction field characteristic formula judges the pixel point position, namely if S max+Smin+4*c>3*Save is met, the point C is located on the valley line, the point C is assigned to 255, namely white, otherwise, the point C is located on the ridge line.
Preferably, in the step 4, the flaws include burrs and voids.
Preferably, if any pixel is black and there are three or more white pixels in the four-adjacent area of the pixel, the pixel is the endpoint of the burr or ridge, and the current pixel is assigned 255, that is, white.
Preferably, if any pixel is white and there are three or more black pixels in the four neighboring areas of the pixel, the pixel is a hole, and the current pixel is assigned 0, i.e. black.
Preferably, the step 5 includes the steps of:
Step 5.1: scanning each pixel in the image output in the step 3 by using a structural element of 3x3 by using a corrosion operation in morphology, performing AND operation by using the structural element and the area of the image covered by the structural element, and if the result is 1, setting the pixel value to be 1;
Step 5.2: using dilation operation in morphology, scanning each pixel of the image processed in step 4.1 with a 3x3 structuring element, and performing an and operation with the structuring element and the region of the image it covers, if the result is 0, the pixel value is 0.
The invention provides an optimized fingerprint image enhancement method based on a double-rule matrix direction field, which has the beneficial effects that:
(1) Judging whether the point is positioned on a ridge line or not according to the average gray values of 12 directions of each pixel point to enhance the fingerprint image, and removing the influence of burrs and holes on the fingerprint image;
(2) For sparse fingerprint images, the ridge line distance is larger due to the factors such as pressing force, and the method predicts whether pixel points are positioned on ridge lines or not according to 12 directions, so that partial sparse fingerprints are connected;
(3) For a compact fingerprint image, the segmentation details of the fingerprint detail parts are not reserved by other algorithms, so that the ridge lines are aggregated and ambiguous, and the fingerprint features can be extracted well by the method.
Drawings
FIG. 1 is a flow chart of the present invention;
fig. 2 is a schematic diagram of the dual rule matrix of the present invention, in which b= 7,a =13 is taken as an example, solid dots are used to identify 1A to 12A, 1B to 12B, 1A 'to 12A', 1B 'to 12B', and arrows show direction 1 to direction 12;
Fig. 3 shows the effect patterns of the present invention, wherein the effect patterns are 3 groups in total, and in any one group, (a) is an original pattern, (b) is a normalized pattern, (c) is a fingerprint region pattern, (d) is a directional field ridge line segmentation pattern, (e) is a fingerprint pattern with holes and burrs removed, and (f) is a morphological filtered result pattern.
Detailed Description
The present invention will be described in further detail with reference to examples, but the scope of the present invention is not limited thereto.
The invention provides a fingerprint image enhancement method based on a double-rule matrix direction field, which judges whether the point is positioned on a ridge line or not by estimating the values of 12 directions of a fingerprint, thereby realizing the segmentation of the fingerprint.
To achieve the above object, the method of the present invention comprises the following steps.
Step 1: and acquiring a fingerprint image, and determining the area where the fingerprint is located as a foreground area.
The step 1 comprises the following steps:
step 1.1: acquiring a fingerprint image, converting the fingerprint image into a gray image, establishing a coordinate system for the gray image, and calculating a pixel MEAN value MEAN and a variance VAR of the gray image;
In the step 1.1, the pixel mean value Variance ofWherein M and N are the number of pixels of the gray image in the length and width directions, and G (x, y) represents the pixel value of the pixel point of the coordinate (x, y);
Step 1.2: normalizing pixel points of coordinates (x, y) of the gray level image;
in the step 1.2, to Pixel point normalization processing is carried out on coordinates (x, y) of the gray level image, wherein M 0 and VAR 0 are respectively a desired mean value and a desired variance, and are respectively assigned to 150 and 120;
Step 1.3: dividing the processed gray image into preset image blocks, namely 5*5 image blocks, judging the pixel MEAN value of each image block, and if the pixel MEAN value is smaller than MEAN, the current image block is a fingerprint area and is a foreground, otherwise, the current image block is a background;
step 1.4: and (3) repeating the step (1.3) until all the image blocks are traversed, wherein all the foreground is used as a foreground area of the fingerprint image, and the rest is used as a background area.
Step 2: and designing a double-rule matrix, and acquiring the fingerprint direction field characteristics through the double-rule matrix.
The dual rule matrix in step 2 includes an outer matrix and an inner matrix.
The external matrix is a sparse interval matrix a, and a is the number of pixels on the edge of the external matrix; the internal matrix is a continuous connected non-interval matrix b, and b is the number of pixels on the edge of the internal matrix.
B is an odd number and a= 2*b-1.
The step 2 comprises the following steps:
step 2.1: confirming a double-rule matrix a and b, wherein the periphery is a sparse interval matrix a, and a is the number of pixels on the periphery matrix side; the internal matrix is a continuous connected non-interval matrix b x b, wherein b is the number of pixel points on the edge of the internal matrix; requiring b to be odd and a = 2*b-1; in this specification, b= 7,a =13 is taken as an example;
step 2.2: the process of confirming the direction field area by the double-rule matrix is as follows, and a square matrix of 13 x 13 is made for each pixel point C in the foreground area by taking C as a center; calibrating 1A to 12A, 1B to 12B, 1A 'to 12A', 1B 'to 12B' in the matrix according to preset rules;
in the step 2.2, 1A to 12A, 1A 'to 12A' are sequentially marked on the sides of a rectangle taking C as a center point, the side length of the internal rectangle is 7 pixel points, and 1A 'to 12A' and 1A to 12A are symmetrical with C center.
In the step 2.2, 1B to 12B, 1B 'to 12B' are sequentially marked on the sides of a rectangle with C as a center point at 1 pixel interval, the side length of the external rectangle is 13 pixel points, and 1B 'to 12B' and 1B to 12B are symmetrical with C as a center.
In the present invention, 1A to 12A, 1B to 12B, 1A 'to 12A', 1B 'to 12B' are all calibrated clockwise or counterclockwise simultaneously.
In the invention, C is taken as a center, and a square matrix of 13 x 13 is taken as a preferable scheme for comprehensive operation amount and precision, and a person skilled in the art can set the size, the number of directions and the corresponding calibration rules of the square matrix according to the requirements.
Step 3: judging whether the foreground region pixel point is positioned on the ridge line or not through a direction field characteristic formula.
In the step 3, the center point C of the dual rule matrix is respectively connected with the pixel points of the dual rule matrix, and the sum of the pixel values of the lines in all directions n is respectively calculated, wherein the maximum value is assigned as S max, the minimum value is assigned as S min, and the average value in all directions is assigned as S ave; if the direction field characteristic formula is satisfied
S max+Smin+4*c>3*Save, the point C is located on the valley line, and the point C is assigned a value of 255, i.e. white, otherwise, the point C is located on the ridge line.
The step3 comprises the following steps:
step 3.1: taking lines passing through nA, nB, nA ', nB' as directions n, respectively calculating the sum of pixel values of the lines in all directions n, and assigning a maximum value S max, a minimum value S min and an average value S ave in all directions;
Step 3.2: the direction field characteristic formula judges the pixel point position, namely if S max+Smin+4*c>3*Save is met, the point C is located on the valley line, the point C is assigned to 255, namely white, otherwise, the point C is located on the ridge line.
In the present invention, it is apparent that C is the pixel value of the center point C in the direction field characteristic formula.
Step 4: and (3) deleting flaws in the image output in the step (3).
In the step 4, the flaws include burrs and voids.
If any pixel point is black and three or more white pixel points exist in the four adjacent domains of the pixel point, the pixel point is the endpoint of the burr or the ridge line, and the current pixel point is assigned 255, namely white.
If any pixel point is white and three or more black pixel points exist in the four adjacent domains of the pixel point, the pixel point is a cavity, and the current pixel point is assigned to be 0, namely black.
In the present invention, when processing burrs, there is a case where three white pixels are present in the four neighborhoods of the end points of the ridge line of the fingerprint in addition to the burrs, but in general, setting one black pixel of the end points of the ridge line of the fingerprint to white does not affect the overall appearance of the fingerprint.
Step 5: and (3) morphological filtering is carried out on the image processed in the step (4), and the enhanced fingerprint image is output.
Said step 5 comprises the steps of:
Step 5.1: scanning each pixel in the image output in the step 3 by using a structural element of 3x3 by using a corrosion operation in morphology, performing AND operation by using the structural element and the area of the image covered by the structural element, and if the result is 1, setting the pixel value to be 1;
Step 5.2: using dilation operation in morphology, scanning each pixel of the image processed in step 4.1 with a 3x3 structuring element, and performing an and operation with the structuring element and the region of the image it covers, if the result is 0, the pixel value is 0.
In the invention, in the morphological filtering process, the 3x3 structural elements are not unique, and a person skilled in the art can set different structural elements according to requirements to process the output image.
Claims (3)
1. A fingerprint image enhancement method based on a double-rule matrix direction field is characterized by comprising the following steps of: the method comprises the following steps:
step 1: acquiring a fingerprint image, and determining an area where the fingerprint is located as a foreground area;
step 2: designing a double-rule matrix, and acquiring fingerprint direction field characteristics through the double-rule matrix;
The dual rule matrix comprises an external matrix and an internal matrix;
The procedure of the dual rule matrix validation direction field area is as follows:
for each pixel point C in the foreground area, taking C as a center, and making a square matrix; calibrating the sides of the rectangle taking C as the center point in the matrix according to a preset rule, wherein the side length of the inner rectangle is continuous and continuous without interval, and the side length of the outer rectangle is sparse interval;
Step 3: judging whether the foreground region pixel point is positioned on the ridge line or not through a direction field characteristic formula; respectively connecting the central point C of the double-rule matrix with the pixel points of the double-rule matrix, and respectively calculating the pixel value sum of the lines in all directions n, wherein the maximum value is assigned as S max, the minimum value is assigned as S min, and the average value in all directions is assigned as S ave; if the direction field characteristic formula S max+Smin+4*c>3*Save is satisfied, the point C is positioned on the valley line, the point C is assigned to 255, namely white, otherwise, the point C is positioned on the ridge line;
step 4: deleting flaws in the image output in the step 3;
step 5: and (3) morphological filtering is carried out on the image processed in the step (4), and the enhanced fingerprint image is output.
2. The fingerprint image enhancement method based on a bi-regular matrix directional field according to claim 1, wherein: the external matrix is a sparse interval matrix a, and a is the number of pixels on the edge of the external matrix; the internal matrix is a continuous connected non-interval matrix b, and b is the number of pixels on the edge of the internal matrix.
3. A method of fingerprint image enhancement based on a bi-regular matrix directional field as claimed in claim 2, wherein: b is an odd number and a= 2*b-1.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011315342.4A CN112435186B (en) | 2020-11-20 | 2020-11-20 | Fingerprint image enhancement method based on double-rule matrix direction field |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202011315342.4A CN112435186B (en) | 2020-11-20 | 2020-11-20 | Fingerprint image enhancement method based on double-rule matrix direction field |
Publications (2)
Publication Number | Publication Date |
---|---|
CN112435186A CN112435186A (en) | 2021-03-02 |
CN112435186B true CN112435186B (en) | 2024-04-26 |
Family
ID=74693408
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202011315342.4A Active CN112435186B (en) | 2020-11-20 | 2020-11-20 | Fingerprint image enhancement method based on double-rule matrix direction field |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112435186B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN116823679B (en) * | 2023-08-30 | 2023-12-05 | 山东龙腾控股有限公司 | Full-automatic fingerprint lock fingerprint image enhancement method based on artificial intelligence |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1421815A (en) * | 2001-11-29 | 2003-06-04 | 田捷 | Fingerprint image enhancement method based on knowledge |
CN101079102A (en) * | 2007-06-28 | 2007-11-28 | 中南大学 | Fingerprint identification method based on statistic method |
CN102103692A (en) * | 2011-03-17 | 2011-06-22 | 电子科技大学 | Fingerprint image enhancing method |
-
2020
- 2020-11-20 CN CN202011315342.4A patent/CN112435186B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1421815A (en) * | 2001-11-29 | 2003-06-04 | 田捷 | Fingerprint image enhancement method based on knowledge |
CN101079102A (en) * | 2007-06-28 | 2007-11-28 | 中南大学 | Fingerprint identification method based on statistic method |
CN102103692A (en) * | 2011-03-17 | 2011-06-22 | 电子科技大学 | Fingerprint image enhancing method |
Also Published As
Publication number | Publication date |
---|---|
CN112435186A (en) | 2021-03-02 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108520225B (en) | Fingerprint detection classification method based on spatial transformation convolutional neural network | |
US7072523B2 (en) | System and method for fingerprint image enhancement using partitioned least-squared filters | |
CN109461163B (en) | Edge detection method for magnetic resonance standard water model | |
Yang et al. | -Means Based Fingerprint Segmentation with Sensor Interoperability | |
CN108509886B (en) | Palm vein identification method based on vein pixel point judgment | |
CN113781406B (en) | Scratch detection method and device for electronic component and computer equipment | |
CN113592923A (en) | Batch image registration method based on depth local feature matching | |
CN111914755A (en) | Eight-direction gradient-solving fingerprint identification model | |
CN112883941A (en) | Facial expression recognition method based on parallel neural network | |
CN114820625A (en) | Automobile top block defect detection method | |
CN112435186B (en) | Fingerprint image enhancement method based on double-rule matrix direction field | |
CN111079626B (en) | Living body fingerprint identification method, electronic equipment and computer readable storage medium | |
CN112330561A (en) | Medical image segmentation method based on interactive foreground extraction and information entropy watershed | |
CN117541983A (en) | Model data quality analysis method and system based on machine vision | |
CN110349119B (en) | Pavement disease detection method and device based on edge detection neural network | |
Zheng et al. | Research on offline palmprint image enhancement | |
Aly et al. | Efficient implementation of image fusion and interpolation for brain tumor diagnosis | |
CN112070689A (en) | Data enhancement method based on depth image | |
Prakram et al. | EVALUATION OF IMPROVED FUZZY INFERENCE SYSTEM TO PRESERVE IMAGE EDGE FOR IMAGE ANALYSIS. | |
Motwakel et al. | Fingerprint Image Enhancement and Quality Analysis–A Survey | |
CN110674681A (en) | Identity verification method and device based on attention mechanism | |
CN117557785B (en) | Image processing-based long-distance fishing boat plate recognition method | |
CN116245770B (en) | Endoscope image edge sharpness enhancement method and device, electronic equipment and storage medium | |
CN114332108B (en) | Method for extracting virtual-real line local area in picture | |
Jayadevan et al. | A new ridge orientation based method of computation for feature extraction from fingerprint images |
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 |