CN108280448B - Finger vein pressing graph distinguishing method and device and finger vein identification method - Google Patents
Finger vein pressing graph distinguishing method and device and finger vein identification method Download PDFInfo
- Publication number
- CN108280448B CN108280448B CN201711468210.3A CN201711468210A CN108280448B CN 108280448 B CN108280448 B CN 108280448B CN 201711468210 A CN201711468210 A CN 201711468210A CN 108280448 B CN108280448 B CN 108280448B
- Authority
- CN
- China
- Prior art keywords
- image
- finger
- vein
- horizontal
- vertical
- 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
- 210000003462 vein Anatomy 0.000 title claims abstract description 90
- 238000000034 method Methods 0.000 title claims abstract description 44
- 238000003825 pressing Methods 0.000 title abstract description 4
- 238000012545 processing Methods 0.000 claims abstract description 30
- 238000009826 distribution Methods 0.000 claims abstract description 24
- 230000002708 enhancing effect Effects 0.000 claims abstract description 8
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 206010070995 Vascular compression Diseases 0.000 claims description 22
- 238000013139 quantization Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000013507 mapping Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000012850 discrimination method Methods 0.000 claims 1
- 230000007246 mechanism Effects 0.000 abstract description 3
- 230000000694 effects Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 230000000873 masking effect Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 102000001554 Hemoglobins Human genes 0.000 description 1
- 108010054147 Hemoglobins Proteins 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000012805 post-processing Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
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
- G06V10/98—Detection or correction of errors, e.g. by rescanning the pattern or by human intervention; Evaluation of the quality of the acquired patterns
- G06V10/993—Evaluation of the quality of the acquired pattern
-
- 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
- G06V10/255—Detecting or recognising potential candidate objects based on visual cues, e.g. shapes
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (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)
Abstract
The invention discloses a method and a device for judging a finger vein pressing graph and a finger vein identification method, wherein the method comprises the following steps: preprocessing an image; positioning a finger boundary; obtaining an effective area; enhancing the effective area; SOBEL edge enhancement, namely performing convolution on the SOBEL operator and the vein distribution image to obtain a SOBEL enhancement image containing a fingerprint information area; calculating an image judgment coefficient, calculating horizontal gradient energy and vertical gradient energy on the SOBEL enhancement map, and adopting the ratio of the vertical gradient energy to the horizontal gradient energy or the ratio of the horizontal gradient energy to the vertical gradient energy as the judgment coefficient; and (5) judging the fingerprint-containing vein map. According to the method, the fingerprint information content in the collected finger image is quantized and then compared with the threshold, unreasonable images are blocked at the current processing stage through a preset shielding mechanism, the rationality, the authenticity and the effectiveness of processing data in the system are maintained, and effective guarantee is provided for the comparison result of the system.
Description
Technical Field
The present invention relates to the field of finger vein recognition, and in particular, to a method and an apparatus for determining a finger vein compression map, and a finger vein recognition method.
Background
Finger vein recognition is a new biometric technology that has been developed in recent years. The technical principle is based on that: hemoglobin in human veins can absorb near infrared rays, so that the images of the veins can be acquired through a sensor; further, modern medicine has demonstrated that the images of each individual's finger vein vessels are different, and thus, this uniqueness of the veins can be exploited to generate a biometric that identifies the individual's identity.
Compared with identification technologies such as fingerprint identification, iris and voice print identification, finger vein identification is gaining more and more attention in the field of biological identification due to the safety brought by the natural living characteristics of the finger vein identification.
The source of the finger vein recognition processing is a finger vein image acquired by equipment, and a vein image without interference and with clear vein texture is an ideal processing object of the recognition system. But due to equipment, operation, etc., it is impossible to obtain a satisfactory vein image in all applications. For example, the finger vein image is pressed intentionally or unintentionally to add fingerprint interference information to the image, and if the image is sent to the system as the finger vein image, because the fingerprint and finger vein information in the image are indistinguishable, the misleading information will pass through each subsequent processing stage of the system smoothly, and finally the comparison result of the system will become unreliable, and the identification performance of the system will be seriously reduced.
Disclosure of Invention
The invention provides a method and a device for judging a finger vein pressing image and a finger vein identification method, which aim to solve the technical problem that fingerprint interference information is additionally added in vein collection to influence the identification performance of a system.
The technical scheme adopted by the invention is as follows:
in one aspect, the present invention provides a method for determining a finger vein compression chart, including:
the method comprises the steps of image preprocessing, wherein the acquired finger images are subjected to filtering processing to suppress noise, and the acquired finger images are horizontal acquisition images or vertical acquisition images;
positioning a finger boundary, and fitting a boundary line of an effective finger area on the preprocessed image;
obtaining an effective area, searching a maximum inscribed rectangle in an effective finger area positioned by the fitted boundary line, and cutting pixels of the rectangular area to obtain a real vein processing subgraph;
enhancing the effective area, namely enhancing the real vein processing subgraph to obtain a vein distribution image;
performing SOBEL edge enhancement, namely performing convolution on the vein distribution image by adopting a Sobel SOBEL operator to obtain a SOBEL enhancement image containing a fingerprint information area;
calculating an image judgment coefficient, calculating horizontal gradient energy and vertical gradient energy on the SOBEL enhancement map, and adopting the ratio of the vertical gradient energy to the horizontal gradient energy or the ratio of the horizontal gradient energy to the vertical gradient energy as the judgment coefficient;
and judging the fingerprint-containing vein image, comparing the judgment coefficient with a preset classification threshold, and judging the unreasonable image containing the fingerprint if the judgment coefficient is smaller than the preset classification threshold.
Further, the step of finger boundary positioning comprises:
dividing the preprocessed image into a plurality of sections in a first direction perpendicular to the extending direction of the fingers;
searching an extreme value of each segment pixel gray level and a first direction position coordinate of the extreme value in the corresponding segment;
carrying out arithmetic average on the coordinate values of the first direction position in the segment to obtain a mean value of the coordinates in the segment;
and calculating a continuous best fit line in the region as a boundary line of the effective finger region based on the mean value of the segmented boundary coordinates by using a linear fitting function under the constraint of a distance condition.
As one embodiment of the above scheme, the acquired finger image is a horizontal acquisition image, and the step of positioning the finger boundary includes:
dividing the preprocessed image into uniform and discontinuous multiple sections in the vertical direction;
each segment adopts a horizontal projection method to search the extreme value of the gray level of each segment pixel and the vertical position coordinate of the extreme value in the corresponding segment;
carrying out arithmetic average on the coordinate values of the vertical positions in the segments to obtain a mean value of the coordinates in the segments;
and calculating continuous best fit lines in the region as upper and lower boundary lines of the effective finger region based on the mean value of the segmented boundary coordinates by using a linear fitting function under the constraint of a distance condition.
Further, the step of active area enhancement comprises:
expanding the gray value of pixels in the real vein processing subgraph to be within the range of 0-255 through gray distribution expansion;
mapping and converting the image pixels by using a preset step quantization table;
and replacing the pixel values of the image by adopting corresponding values of the step quantization table according to the mapping relation with the step interval to generate a new enhancement image as the vein distribution image.
Further, the step of SOBEL edge enhancement includes: and (3) performing convolution on the vein distribution image by adopting a vertical SOBEL operator, and performing edge enhancement on the image in the vertical direction to obtain an SOBEL enhancement image.
Further, the step of calculating the image determination coefficient includes:
defining the calculation range of the gradient of each pixel point in the SOBEL enhancement graph as a preset pixel;
calculating gradient information point by point to respectively generate a horizontal gradient map and a vertical gradient map;
calculating the gradient sums of all pixels in the horizontal gradient map and the vertical gradient map respectively to obtain horizontal gradient energy and vertical gradient energy;
and dividing the vertical gradient energy by the horizontal gradient energy to obtain a vertical coefficient of the vein image as a judgment coefficient.
As another embodiment of the above solution, the acquired finger image is a vertically acquired image, and the step of positioning the finger boundary includes:
dividing the preprocessed image into a plurality of uniform and discontinuous sections in the horizontal direction;
each segment adopts a vertical projection method to search the extreme value of the gray level of each segment pixel and the horizontal position coordinate of the extreme value in the corresponding segment;
carrying out arithmetic average on the horizontal position coordinate values in the segments to obtain the mean value of the coordinates in the segments;
and calculating continuous best fit lines in the region as the left and right boundary lines of the effective finger region based on the mean value of the coordinates of each segment boundary by using a linear fitting function under the constraint of a distance condition.
Further, in the step of SOBEL edge enhancement, performing convolution on the vein distribution image by adopting a horizontal SOBEL operator, and performing edge enhancement on the image in the horizontal direction to obtain a SOBEL enhancement image; in the step of calculating the image determination coefficient, the horizontal gradient energy is divided by the vertical gradient energy to obtain a vein image horizontal coefficient as the determination coefficient.
According to another aspect of the present invention, there is also provided a device for determining a finger vein compression chart, including a processor, where the processor is configured to execute a program, and the processor executes the method for determining a finger vein compression chart.
According to another aspect of the present invention, before performing recognition judgment on the received finger vein image, the above method for judging the finger vein compression map is performed, and finger vein images corresponding to the finger vein compression map with the masking judgment coefficient smaller than the preset classification threshold value are provided.
The method is applied to the early stage of processing of the finger vein recognition system, specifically quantifies the fingerprint information content in the acquired finger image by evaluating the content of the acquired finger image, then compares the quantified value with the threshold value, blocks the unreasonable image in the current processing stage through a preset shielding mechanism, maintains the rationality of processing data in the system, ensures that the finger vein data source processed by the system is real and effective, and finally provides effective guarantee for the correctness of the comparison result of the system.
In addition to the objects, features and advantages described above, other objects, features and advantages of the present invention are also provided. The present invention will be described in further detail below with reference to the accompanying drawings.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this application, illustrate embodiments of the invention and, together with the description, serve to explain the invention and not to limit the invention. In the drawings:
FIG. 1 is a flow chart of a method for discriminating a finger vein compression chart according to a preferred embodiment of the present invention;
FIG. 2 is an artwork of a captured finger image;
FIG. 3 is a diagram of the effects of FIG. 2 after image pre-processing and finger border location;
FIG. 4 is a graph of the effect of FIG. 3 after gray scale expansion;
FIG. 5 is a diagram of the effect of FIG. 4 after being enhanced by the step quantization;
FIG. 6 is a diagram of the effect of a finger image after finger boundary positioning, active area acquisition and enhancement, and vertical SOBEL edge enhancement of the present invention.
Detailed Description
It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict. The present invention will be described in detail below with reference to the embodiments with reference to the attached drawings.
Referring to fig. 1, a preferred embodiment of the present invention provides a method for determining a finger vein compression diagram, including:
step S100, image preprocessing, namely filtering an acquired finger image to suppress noise, wherein the acquired finger image is a horizontal acquisition image or a vertical acquisition image;
step S200, positioning the finger boundary, and fitting a boundary line of an effective finger area on the preprocessed image;
step S300, obtaining an effective area, searching a maximum inscribed rectangle in an effective finger area positioned by the fitted boundary line, and cutting pixels of the rectangular area to obtain a real vein processing subgraph;
s400, enhancing an effective area, and enhancing a real vein processing subgraph to obtain a vein distribution image;
s500, carrying out SOBEL edge enhancement, and carrying out convolution on the SoBEL edge enhancement and the vein distribution image by adopting a Sobel SOBEL operator to obtain a SOBEL enhancement image containing a fingerprint information area;
step S600, calculating an image judgment coefficient, calculating horizontal gradient energy and vertical gradient energy on the SOBEL enhancement map, and taking the ratio of the vertical gradient energy to the horizontal gradient energy or the ratio of the horizontal gradient energy to the vertical gradient energy as the judgment coefficient;
and step S700, judging the fingerprint-containing vein image, comparing the judgment coefficient with a preset classification threshold value, and judging the unreasonable image containing the fingerprint if the judgment coefficient is smaller than the preset classification threshold value.
The method is applied to the early stage of processing of the finger vein recognition system, specifically, the content of fingerprint information in the image is quantized by evaluating the content of the input image, then the quantized value is compared with a threshold value, an unreasonable image is blocked at the current processing stage through a preset shielding mechanism, the rationality of the processing data in the system is maintained, the fact that a finger vein data source processed by the system is real and effective is guaranteed, and finally, effective guarantee is provided for the correctness of the comparison result of the system.
In the preferred embodiment, the original image of the finger image captured by the device is a horizontally captured image in which the finger area extends in the horizontal direction, as shown in fig. 2. In the step S100 of image preprocessing, filtering methods such as median or mean may be used to suppress noise, and the noise of the smoothed image is reduced, while the concerned vein information is maintained, and it is important that the vein edge is also enhanced to a certain extent.
As shown in fig. 2, in the imaging diagram, the effective finger area is distributed only in the image decentered area in the horizontal direction. In addition, the background area is meaningless for subsequent processing on one hand, and secondly, the random gray distribution of background pixels, the huge contrast of background and foreground gray values, and the like can form a significant interference on the statistics of the parameter values of the effective area, so that the background area needs to be masked or cut off on the basis of positioning the finger boundary in step S200.
Further, in the preferred embodiment, the step S200 of positioning the finger boundary is as follows:
firstly, dividing a preprocessed two-dimensional image into uniform and discontinuous multiple sections in the vertical direction; each segment adopts a horizontal projection method to search the extreme value of the gray level of each segment pixel and the vertical position coordinate of the extreme value in the corresponding segment; then, in order to obtain a stable boundary value in the segment, the coordinate values of the vertical positions in the segment are calculated and averaged to obtain a mean value of the coordinates in the segment; and then, under the constraint of a distance condition, calculating continuous best fit lines in the region based on the mean value of the coordinates of each segment boundary by using a linear fitting function to serve as the upper boundary line and the lower boundary line of the effective finger region. Through the calculation, the lines of the upper area and the lower area are respectively fitted in the horizontal direction of the image, and the lines are the boundaries of the fingers in the image. Effect diagram of finger boundary positioning as shown in fig. 3, the region enclosed by line A, B in the diagram is the finger effective region, that is, the vein information region of interest to be processed subsequently; A. the part from the B line to the image edge is a background area.
Step S300, obtaining an effective area:
because the fingers are roughly distributed in a trapezoid shape in the imaging graph, in order to further reduce the influence of background pixels and also facilitate quick calculation, the invention reduces the image processing range again and tries to position the processing data in the optimal rectangular area. And searching the maximum inscribed rectangle in the finger effective area positioned by the fitting line in the previous step, and cutting pixels in the rectangular area to obtain a real vein processing subgraph.
Step S400, effective area enhancement:
in order to highlight the vein part in the real vein processing subgraph, the invention enhances the vein part, tries to obtain a clearer vein distribution image through gray scale expansion and step quantization enhancement, and comprises the following specific steps:
firstly, expanding the gray value of a pixel to be within the range of 0-255 through gray distribution expansion, wherein an effect graph after gray expansion is shown in FIG. 4;
then, mapping conversion is performed on image pixels by using a preset step quantization table, for example, a gray scale region from 0 to 255 is divided into 30 step intervals, each step interval takes only a median value of the interval as a step quantization table value, and then image pixel values are replaced by corresponding values of the step quantization table according to a mapping relation with the step intervals to generate a new enhancement map as a vein distribution image. As shown in fig. 5, the enhancement map significantly increases the gray scale difference between adjacent pixels at the vein edge, highlighting the effect of the presence of the vein.
The original image has a small dynamic range of the gray value of the effective area, the vein information is very fuzzy, and the distribution of the veins can be seen clearly through gray expansion and step quantization enhancement.
Further, in the preferred embodiment, the step S500 of SOBEL edge enhancement includes:
and (3) performing convolution on the image by adopting a vertical SOBEL operator, and performing edge enhancement on the image in the vertical direction to obtain an SOBEL enhancement image. This step further enhances information on the region of the image where the change in gray scale is severe in the vertical direction (longitudinal texture edge region). Because vein collection is mostly concentrated near the second and third joints of the finger, the fingerprints in the region are normally vertically distributed (horizontal texture on the finger), and the SOBEL convolution is adopted by the invention, namely, the distribution characteristics of the fingerprints in the region are utilized and strengthened, so that the subsequent calculation is convenient. The vertical SOBEL enhancement effect graph is shown in fig. 6. After the transformation of the vertical SOBEL operator, the vertical distribution texture (the area containing the fingerprint information) in the image is enhanced, and a more obvious vertical distribution state is presented.
Further, in the present preferred embodiment, the step S600 of calculating the image determination coefficient includes:
on the SOBEL map, horizontal gradient energy and vertical gradient energy are calculated. Specifically, firstly, a gradient map is generated, in order to make the statistics more effective, the calculation range of the gradient of each pixel point is defined as 4 pixels, namely the difference between the adjacent first 2 pixels and the next 2 pixels is taken as the gradient of the pixel at the current point; and calculating gradient information point by point to respectively generate a horizontal gradient map and a vertical gradient map.
Then, gradient energy is calculated on the gradient map, that is, the gradient of all pixels is calculated in the horizontal and vertical gradient maps respectively and the horizontal and vertical gradient energy is obtained.
And finally, dividing the vertical gradient energy by the horizontal gradient energy to obtain a vertical coefficient of the vein image, and taking the vertical coefficient as a judgment coefficient.
And calculating the vertical coefficients of all samples of the vein test set by adopting the 6 steps, and then obtaining the optimal classification threshold value related to the vertical coefficients by comprehensively analyzing according to the comparison scores, the recognition passing rate, the false recognition rate and other statistical conditions of the set. Through statistical analysis of the test set, when the vertical coefficient threshold is set to be 0.6, the method can reliably judge whether the vein image contains excessive fingerprint information.
Finally, the fingerprint-containing vein map is determined in step S700. In the application stage of the system, the vertical coefficient of the identification image is obtained by adopting the method, then the coefficient is compared with a preset classification threshold value, if the coefficient is smaller than the threshold value, the image is judged to contain the fingerprint image, and the fingerprint information content of the image is judged to seriously interfere the finger vein information, so that the image is discarded and does not participate in the subsequent processing of the system.
When the captured finger image is a vertically captured image, i.e., the finger region in the image extends in the vertical direction, the processing and determination process for the image is substantially similar to that for the horizontally captured image, except that it varies only in direction. For vertically acquired maps, the step of finger boundary positioning comprises: dividing the preprocessed image into a plurality of uniform and discontinuous sections in the horizontal direction; each segment adopts a vertical projection method to search the extreme value of the gray level of each segment pixel and the horizontal position coordinate of the extreme value in the corresponding segment; carrying out arithmetic average on the horizontal position coordinate values in the segments to obtain the mean value of the coordinates in the segments; and calculating continuous best fit lines in the region as the left and right boundary lines of the effective finger region based on the mean value of the coordinates of each segment boundary by using a linear fitting function under the constraint of a distance condition. In addition, in the step of SOBEL edge enhancement, a horizontal SOBEL operator is adopted to be convoluted with the vein distribution image, and the edge enhancement is carried out on the image in the horizontal direction to obtain a SOBEL enhancement image. In the step of calculating the image determination coefficient, the horizontal gradient energy is divided by the vertical gradient energy to obtain a vein image horizontal coefficient as the determination coefficient.
According to another aspect of the present invention, there is also provided a device for determining a finger vein compression chart, including a processor, where the processor is configured to execute a program, and the processor executes the method for determining a finger vein compression chart.
According to another aspect of the present invention, there is also provided a storage medium, which includes a stored program, and when the program is executed, the program controls a device in which the storage medium is located to execute the above method for discriminating a finger vein compression chart.
According to another aspect of the present invention, before performing recognition judgment on the received finger vein image, the above method for judging the finger vein compression map is performed, and finger vein images corresponding to the finger vein compression map with the masking judgment coefficient smaller than the preset classification threshold value are provided.
The method can intercept unreasonable images containing fingerprints at the early stage of system processing, saves a large amount of subsequent meaningless calculation time, enables the system to enter a new target identification processing stage in as short a time as possible, and improves the response speed of a finger vein comparison system; meanwhile, unreasonable images containing fingerprints are prevented from entering post-processing, so that the identification features extracted by the system are pure vein features, and the identification performance of the finger vein comparison system is improved.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. A method for judging a finger vein compression chart is characterized by comprising the following steps:
the method comprises the steps of image preprocessing, wherein the acquired finger images are subjected to filtering processing to suppress noise, and the acquired finger images are horizontal acquisition images or vertical acquisition images;
positioning a finger boundary, and fitting a boundary line of an effective finger area on the preprocessed image;
obtaining an effective area, searching a maximum inscribed rectangle in an effective finger area positioned by the fitted boundary line, and cutting pixels of the rectangular area to obtain a real vein processing subgraph;
enhancing the effective area, namely enhancing the real vein processing subgraph to obtain a vein distribution image;
performing edge enhancement, namely performing convolution on the vein distribution image by adopting a Sobel SOBEL operator to obtain a SOBEL enhancement image containing a fingerprint information area;
calculating an image judgment coefficient, calculating horizontal gradient energy and vertical gradient energy on the SOBEL enhancement map, and adopting the ratio of the vertical gradient energy to the horizontal gradient energy or the ratio of the horizontal gradient energy to the vertical gradient energy as the judgment coefficient;
judging the fingerprint-containing vein image, comparing the judgment coefficient with a preset classification threshold value, and judging the unreasonable image containing the fingerprint if the judgment coefficient is smaller than the preset classification threshold value;
the step of finger boundary positioning comprises:
dividing the preprocessed image into a plurality of sections in a first direction perpendicular to the extending direction of the fingers;
searching an extreme value of each segment pixel gray level and a first direction position coordinate of the extreme value in the corresponding segment;
carrying out arithmetic average on the coordinate values of the first direction position in the segment to obtain a mean value of the coordinates in the segment;
and calculating a continuous best fit line in the region as a boundary line of the effective finger region based on the mean value of the segmented boundary coordinates by using a linear fitting function under the constraint of a distance condition.
2. The method for discriminating a finger vein compression map according to claim 1, wherein the acquired finger image is a horizontal acquisition map, and the step of positioning the finger boundary includes:
dividing the preprocessed image into uniform and discontinuous multiple sections in the vertical direction;
each segment adopts a horizontal projection method to search the extreme value of the gray level of each segment pixel and the vertical position coordinate of the extreme value in the corresponding segment;
carrying out arithmetic average on the coordinate values of the vertical positions in the segments to obtain a mean value of the coordinates in the segments;
and calculating continuous best fit lines in the region as upper and lower boundary lines of the effective finger region based on the mean value of the segmented boundary coordinates by using a linear fitting function under the constraint of a distance condition.
3. The method for discriminating a finger vein compression map according to claim 1, wherein the step of enhancing the effective region includes:
expanding the pixel gray value in the real vein processing sub-image to be within the range of 0-255 through gray distribution expansion;
mapping and converting the image pixels by using a preset step quantization table;
and replacing the pixel values of the image by adopting corresponding values of a step quantization table according to the mapping relation with the step interval to generate a new enhancement image as the vein distribution image.
4. The method for discriminating a finger vein compression map according to claim 2, wherein the step of SOBEL edge enhancement comprises:
and performing convolution on the vein distribution image by adopting a vertical SOBEL operator, and performing edge enhancement on the image in the vertical direction to obtain the SOBEL enhancement image.
5. The method according to claim 4, wherein the step of calculating the image determination coefficient includes:
defining the calculation range of the gradient of each pixel point in the SOBEL enhancement graph as a preset pixel;
calculating gradient information point by point to respectively generate a horizontal gradient map and a vertical gradient map;
calculating the gradient sums of all pixels in the horizontal gradient map and the vertical gradient map respectively to obtain horizontal gradient energy and vertical gradient energy;
and dividing the vertical gradient energy by the horizontal gradient energy to obtain a vein image vertical coefficient as the judgment coefficient.
6. The method for discriminating a finger vein compression map according to claim 1, wherein the acquired finger image is a vertically acquired map, and the step of positioning the finger boundary includes:
dividing the preprocessed image into a plurality of uniform and discontinuous sections in the horizontal direction;
each segment adopts a vertical projection method to search the extreme value of the gray level of each segment pixel and the horizontal position coordinate of the extreme value in the corresponding segment;
carrying out arithmetic average on the horizontal position coordinate values in the segments to obtain the mean value of the coordinates in the segments;
and calculating continuous best fit lines in the region as the left and right boundary lines of the effective finger region based on the mean value of the coordinates of each segment boundary by using a linear fitting function under the constraint of a distance condition.
7. The method for discriminating a finger vein compression chart according to claim 6,
in the step of SOBEL edge enhancement, a horizontal SOBEL operator is adopted to carry out convolution with the vein distribution image, and the edge enhancement is carried out on the image in the horizontal direction to obtain the SOBEL enhancement image;
in the step of calculating the image determination coefficient, the horizontal gradient energy is divided by the vertical gradient energy to obtain a vein image horizontal coefficient as the determination coefficient.
8. A finger vein compression chart discrimination apparatus comprising a processor for executing a program, wherein the processor executes a finger vein compression chart discrimination method according to any one of claims 1 to 7.
9. A finger vein recognition method, characterized in that before the recognition judgment of the received finger vein image, the method for judging the finger vein compression map according to any one of claims 1 to 7 is executed, and the finger vein image with the judgment coefficient smaller than the preset classification threshold value is shielded.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711468210.3A CN108280448B (en) | 2017-12-29 | 2017-12-29 | Finger vein pressing graph distinguishing method and device and finger vein identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711468210.3A CN108280448B (en) | 2017-12-29 | 2017-12-29 | Finger vein pressing graph distinguishing method and device and finger vein identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108280448A CN108280448A (en) | 2018-07-13 |
| CN108280448B true CN108280448B (en) | 2020-04-21 |
Family
ID=62802495
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711468210.3A Active CN108280448B (en) | 2017-12-29 | 2017-12-29 | Finger vein pressing graph distinguishing method and device and finger vein identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108280448B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111223082B (en) * | 2020-01-03 | 2023-06-20 | 圣点世纪科技股份有限公司 | Quantitative evaluation method for finger vein image quality |
| CN111797828B (en) * | 2020-06-19 | 2023-04-07 | 智慧眼科技股份有限公司 | Method and device for acquiring ROI (region of interest) of finger vein image and related equipment |
| CN112714232B (en) * | 2020-12-31 | 2023-04-07 | 中国工商银行股份有限公司 | Finger vein image data transmission method and device |
| CN116030264B (en) * | 2023-02-01 | 2024-03-29 | 安徽信息工程学院 | Method and device for assisting visually impaired people in understanding pictures |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1990005345A1 (en) * | 1988-10-31 | 1990-05-17 | Nathaniel Gould Diagnostics, Inc. | Pedotopography apparatus and method using moire fringe analysis to measure foot shapes |
| EP0881596A2 (en) * | 1997-05-28 | 1998-12-02 | Xerox Corporation | Image enhancement and thresholding of images |
| CN1980321A (en) * | 2005-12-09 | 2007-06-13 | 逐点半导体（上海）有限公司 | Picture reinforcing treatment system and treatment method |
| CN102222229A (en) * | 2011-07-28 | 2011-10-19 | 陈庆武 | Method for preprocessing finger vein images |
| CN103279733A (en) * | 2013-03-19 | 2013-09-04 | 陈威霖 | Finger vein identification device capable of improving identification success rate |
| CN106059753A (en) * | 2016-03-10 | 2016-10-26 | 西京学院 | Novel fingerprint key generation method for digital signature |
| CN107368792A (en) * | 2017-06-29 | 2017-11-21 | 广州智慧城市发展研究院 | A kind of finger vein identification method and system based on wave filter and Bone Edge |
-
2017
- 2017-12-29 CN CN201711468210.3A patent/CN108280448B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1990005345A1 (en) * | 1988-10-31 | 1990-05-17 | Nathaniel Gould Diagnostics, Inc. | Pedotopography apparatus and method using moire fringe analysis to measure foot shapes |
| EP0881596A2 (en) * | 1997-05-28 | 1998-12-02 | Xerox Corporation | Image enhancement and thresholding of images |
| CN1980321A (en) * | 2005-12-09 | 2007-06-13 | 逐点半导体（上海）有限公司 | Picture reinforcing treatment system and treatment method |
| CN102222229A (en) * | 2011-07-28 | 2011-10-19 | 陈庆武 | Method for preprocessing finger vein images |
| CN103279733A (en) * | 2013-03-19 | 2013-09-04 | 陈威霖 | Finger vein identification device capable of improving identification success rate |
| CN106059753A (en) * | 2016-03-10 | 2016-10-26 | 西京学院 | Novel fingerprint key generation method for digital signature |
| CN107368792A (en) * | 2017-06-29 | 2017-11-21 | 广州智慧城市发展研究院 | A kind of finger vein identification method and system based on wave filter and Bone Edge |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108280448A (en) | 2018-07-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108280448B (en) | Finger vein pressing graph distinguishing method and device and finger vein identification method | |
| US7965874B2 (en) | Biological information detecting device | |
| US8606012B2 (en) | Image processing method and image processor | |
| US10558841B2 (en) | Method and apparatus for recognizing fingerprint ridge point | |
| EP3807839B1 (en) | Deformity edge detection | |
| CN106548176B (en) | Finger vein image enhancement method based on self-adaptive guide filtering | |
| CN110009653A (en) | Increase limb recognition point sharp picture based on gray level threshold segmentation method and knows method for distinguishing | |
| CN108876795A (en) | A kind of dividing method and system of objects in images | |
| CN108960185A (en) | Vehicle target detection method and system based on YOLOv2 | |
| CN111105427B (en) | Lung image segmentation method and system based on connected region analysis | |
| KR101654287B1 (en) | A Navel Area Detection Method Based on Body Structure | |
| KR20030066512A (en) | Iris Recognition System Robust to noises | |
| US20040247183A1 (en) | Method for image analysis | |
| CN117392404A (en) | Method and system for improving image detection speed | |
| KR100374695B1 (en) | Automatic Fingerprint Identification System using Direct Ridge Extraction | |
| CN106682627B (en) | Palm print data identification method and device | |
| Makrushin et al. | Visibility enhancement and validation of segmented latent fingerprints in crime scene forensics | |
| CN112541471B (en) | Multi-feature fusion-based shielding target identification method | |
| KR102223263B1 (en) | Method and Apparatus for Interpretation of Magnifying Endoscopy Images of Esophageal Cancer using Computer Aided Diagnostic System | |
| CN112801034A (en) | Finger vein recognition device | |
| CN107977604B (en) | Hand detection method based on improved aggregation channel characteristics | |
| CN117275130B (en) | Intelligent access control verification system based on face recognition | |
| KR101750897B1 (en) | A Biometric Method using Thumb feature | |
| KR20130036511A (en) | Method for validation of object boundaries and system of thereof, method for detection of object | |
| KR20100094045A (en) | Lewd image detection method using papilla and breast line |
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 | ||
| CB02 | Change of applicant information |
Address after: 100097 Beijing Haidian District Kunming Hunan Road 51 C block two floor 207. Applicant after: BEIJING ATHENA EYES SCIENCE & TECHNOLOGY CO.,LTD. Address before: 100193 4, 403, block A, 14 building, 10 East North Road, Haidian District, Beijing. Applicant before: BEIJING ATHENA EYES SCIENCE & TECHNOLOGY CO.,LTD. |
|
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 410205 14 Changsha Zhongdian Software Park Phase I, 39 Jianshan Road, Changsha High-tech Development Zone, Yuelu District, Changsha City, Hunan Province Applicant after: Wisdom Eye Technology Co.,Ltd. Address before: 100097 2nd Floor 207, Block C, 51 Hunan Road, Kunming, Haidian District, Beijing Applicant before: BEIJING ATHENA EYES SCIENCE & TECHNOLOGY CO.,LTD. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| PE01 | Entry into force of the registration of the contract for pledge of patent right |
Denomination of invention: Discriminant method and device of finger vein compression diagram, and finger vein recognition method Effective date of registration: 20221205 Granted publication date: 20200421 Pledgee: Agricultural Bank of China Limited Hunan Xiangjiang New Area Branch Pledgor: Wisdom Eye Technology Co.,Ltd. Registration number: Y2022430000107 |
|
| PE01 | Entry into force of the registration of the contract for pledge of patent right | ||
| PC01 | Cancellation of the registration of the contract for pledge of patent right |
Date of cancellation: 20231220 Granted publication date: 20200421 Pledgee: Agricultural Bank of China Limited Hunan Xiangjiang New Area Branch Pledgor: Wisdom Eye Technology Co.,Ltd. Registration number: Y2022430000107 |
|
| PC01 | Cancellation of the registration of the contract for pledge of patent right | ||
| CP03 | Change of name, title or address |
Address after: No. 205, Building B1, Huigu Science and Technology Industrial Park, No. 336 Bachelor Road, Bachelor Street, Yuelu District, Changsha City, Hunan Province, 410000 Patentee after: Wisdom Eye Technology Co.,Ltd. Address before: 410205 building 14, phase I, Changsha Zhongdian Software Park, No. 39, Jianshan Road, Changsha high tech Development Zone, Yuelu District, Changsha City, Hunan Province Patentee before: Wisdom Eye Technology Co.,Ltd. |
|
| CP03 | Change of name, title or address |