CN108280448A - The method of discrimination and device of finger intravenous pressing figure refer to vein identification method - Google Patents
The method of discrimination and device of finger intravenous pressing figure refer to vein identification method Download PDFInfo
- Publication number
- CN108280448A CN108280448A CN201711468210.3A CN201711468210A CN108280448A CN 108280448 A CN108280448 A CN 108280448A CN 201711468210 A CN201711468210 A CN 201711468210A CN 108280448 A CN108280448 A CN 108280448A
- Authority
- CN
- China
- Prior art keywords
- image
- finger
- vein
- vertical
- sobel
- 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.)
- Granted
Links
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 kind of method of discrimination referring to intravenous pressing figure and device, refer to vein identification method, this method includes：Image preprocessing；Finger boundary alignment；Effective coverage obtains；Effective coverage enhances；The edges SOBEL enhance, and make convolution using SOBEL operators and vein distributed image, obtain the SOBEL enhancing figures comprising finger print information region；Spectral discrimination coefficient is calculated, in the upper calculated level gradient energy of SOBEL enhancing figures and vertical gradient energy, and using the ratio or the ratio of horizontal gradient energy divided by vertical gradient energy of vertical gradient energy divided by horizontal gradient energy as coefficient of determination；The judgement of the figure of vein containing fingerprint.The present invention quantified by the finger print information content in the finger-image to acquisition after with threshold value comparison, pass through preset shielding mechanism, unreasonable image was blocked in the currently processed stage, reasonability, authenticity and the validity that data are handled in maintenance system, effective guarantee is provided for system comparison result.
Description
Technical field
The present invention relates to hand vein recognition field is referred to, particularly, be related to a kind of method of discrimination referring to intravenous pressing figure and device,
Refer to vein identification method.
Background technology
It is a kind of new biological identification technology that developed recently gets up to refer to hand vein recognition.The technical principle is according to being：Human body
Hemoglobin meeting absorption near infrared ray in vein then can obtain the image of vein by sensor；Further, modern
Medicine confirms that everyone finger vena blood vessel image is different, thus, it is possible to which this uniqueness using vein goes to generate
Identify the biological characteristic of personal identification.
Compared to identification technologies such as fingerprint recognition, iris and Application on Voiceprint Recognition, refer to hand vein recognition because of its natural live body characteristic institute band
The safety come, more and more concerns are just being obtained in field of biological recognition.
The source object for referring to hand vein recognition processing is the finger vein image of equipment acquisition, noiseless, vein clean mark quiet
Arteries and veins image is the ideal process object of identifying system.But due to equipment, operation etc., what is obtained in can not possibly all be to the greatest extent
Such as the vein image of people's will.Such as the intentional or unintentional pressing operation of venous collection, make in acquisition figure additional fingerprint dry
Information is disturbed, if this kind of image, which is taken as, refers to vein figure feeding system, due to fingerprint in image and refers to what venous information showed
Indistinguishability, then this kind of misleading information will will finally make system smoothly by system subsequent each processing stage
Comparison result becomes unreliable, the serious recognition performance for reducing system.
Invention content
The present invention provides a kind of method of discrimination referring to intravenous pressing figure and device, refer to vein identification method, it is quiet to solve
The technical issues of arteries and veins acquisition influences system identification performance due to pressing operation additional fingerprint interference information.
The technical solution adopted by the present invention is as follows：
On the one hand, the present invention provides a kind of method of discrimination referring to intravenous pressing figure, including：
Image preprocessing is filtered to inhibit noise the finger-image of acquisition, wherein the finger-image of acquisition
For level acquisition figure or vertical collection figure；
Finger boundary alignment fits the boundary lines of effective finger areas on image after the pre-treatment；
Effective coverage obtains, and maximum inscribed rectangle is searched in effective finger areas of the boundary line orientation fitted simultaneously
Rectangular area pixel is cut, obtains true vein treatments subgraph；
Effective coverage enhances, and enhances true vein treatments subgraph, obtains vein distributed image；
The edges SOBEL enhance, and make convolution using Sobel SOBEL operators and vein distributed image, obtain and believe comprising fingerprint
Cease the SOBEL enhancing figures in region；
Spectral discrimination coefficient is calculated, in the upper calculated level gradient energy of SOBEL enhancing figures and vertical gradient energy, and is used
The ratio conduct of the ratio or horizontal gradient energy divided by vertical gradient energy of vertical gradient energy divided by horizontal gradient energy
Coefficient of determination；
The judgement of the figure of vein containing fingerprint, by coefficient of determination compared with default classification thresholds, if it is determined that coefficient is less than default point
Class threshold value is then determined as the unreasonable image containing fingerprint.
Further, the step of finger boundary alignment includes：
Pretreated image is divided into multistage on the first direction vertical with finger extending direction；
Search the first direction position coordinates where extreme value in the extreme value and corresponding section of each segmented pixels gray scale；
Arithmetic average is made to first direction position coordinate value in section and obtains section internal coordinate mean value；
With linear fit function under distance condition constraint, go out in the region to connect based on each section boundaries coordinate mean value computation
Boundary lines of the continuous best fit lines as effective finger areas.
As the one of which embodiment of said program, the finger-image of acquisition is level acquisition figure, and finger boundary is fixed
Position the step of include：
Pretreated image is divided into uniform and discontinuous multistage in vertical direction；
Every section uses horizontal projection method, searches the vertical position where extreme value in the extreme value and corresponding section of each segmented pixels gray scale
Set coordinate；
Arithmetic average is made to vertical position coordinate value in section and obtains section internal coordinate mean value；
With linear fit function under distance condition constraint, go out in the region to connect based on each section boundaries coordinate mean value computation
Upper and lower boundary lines of the continuous best fit lines as effective finger areas.
Further, effective coverage enhance the step of include：
It is extended by intensity profile, grey scale pixel value in true vein treatments subgraph is extended in 0~255 range；
Mapping and Converting is carried out to image pixel with default scalar quantization table；
By image pixel value according to the mapping relations with ladder section, is replaced, generated using the respective value of scalar quantization table
New enhancing figure is as vein distributed image.
Further, the edges SOBEL enhance the step of include：Using vertical direction SOBEL operators and vein distributed image
Make convolution, edge enhancing is carried out to image in vertical direction, obtains SOBEL enhancing figures.
Further, the step of calculating spectral discrimination coefficient includes：
The computer capacity of each pixel gradient in SOBEL enhancing figures is defined as intended pixel；
Node-by-node algorithm gradient information generates horizontal gradient figure and vertical gradient map respectively；
The gradient of all pixels is calculated in horizontal gradient figure and in vertical gradient map respectively and to obtain horizontal gradient energy
Amount and vertical gradient energy；
By vertical gradient energy divided by horizontal gradient energy, vein image Vertical factor is obtained as coefficient of determination.
As the another embodiment of said program, the finger-image of acquisition is vertical collection figure, finger boundary alignment
The step of include：
Pretreated image is divided into uniform and discontinuous multistage in the horizontal direction；
Every section uses vertical projection method, searches the horizontal position where extreme value in the extreme value and corresponding section of each segmented pixels gray scale
Set coordinate；
Arithmetic average is made to horizontal position coordinate value in section and obtains section internal coordinate mean value；
With linear fit function under distance condition constraint, go out in the region to connect based on each section boundaries coordinate mean value computation
Left and right boundary lines of the continuous best fit lines as effective finger areas.
Further, in the step of edges SOBEL enhance, made using horizontal direction SOBEL operators and vein distributed image
Convolution carries out edge enhancing to image in the horizontal direction, obtains SOBEL enhancing figures；It, will in the step of calculating spectral discrimination coefficient
Horizontal gradient energy divided by vertical gradient energy obtain vein image horizontal coefficients as coefficient of determination.
According to another aspect of the present invention, a kind of discriminating gear referring to intravenous pressing figure, including processor, place are additionally provided
Reason device executes the method for discrimination of above-mentioned finger intravenous pressing figure for running program, processor when running.
According to another aspect of the present invention, a kind of finger vein identification method is additionally provided, in the finger vein image to reception
It is identified before judgement, executes the method for discrimination of above-mentioned finger intravenous pressing figure, shielding coefficient of determination is less than default classification thresholds
Corresponding finger vein image.
The present invention is applied in the preliminary stage for referring to vein recognition system processing, passes through the finger-image content progress to acquisition
Assessment, specifically quantifies the finger print information content in the finger-image of acquisition, then by this quantized value and threshold value comparison, leads to
Preset shielding mechanism is crossed, unreasonable image is blocked to the reasonability for handling data in the currently processed stage, maintenance system,
The handled intravenous data source that refers to of guarantee system is true, effective, and final is that the correct of system comparison result provides effective guarantee.
Other than objects, features and advantages described above, the present invention also has other objects, features and advantages.
Below with reference to accompanying drawings, the present invention is described in further detail.
Description of the drawings
The attached drawing constituted part of this application is used to provide further understanding of the present invention, schematic reality of the invention
Example and its explanation are applied for explaining the present invention, is not constituted improper limitations of the present invention.In the accompanying drawings：
Fig. 1 is the flow chart of the method for discrimination of the finger intravenous pressing figure of the preferred embodiment of the present invention；
Fig. 2 is the artwork of the finger-image of acquisition；
Fig. 3 is design sketch of the Fig. 2 after image preprocessing and finger boundary alignment；
Fig. 4 is design sketch of the Fig. 3 after expansion of gradation；
Fig. 5 is Fig. 4 through the enhanced design sketch of scalar quantization；
Fig. 6 is finger boundary alignment, effective coverage acquisition and enhancing and vertical SOBEL of the finger-image by the present invention
The enhanced design sketch in edge.
Specific implementation mode
It should be noted that in the absence of conflict, the features in the embodiments and the embodiments of the present application can phase
Mutually combination.The present invention will be described in detail below with reference to the accompanying drawings and embodiments.
Referring to Fig.1, the preferred embodiment of the present invention provides a kind of method of discrimination referring to intravenous pressing figure, including：
Step S100, image preprocessing are filtered to inhibit noise the finger-image of acquisition, wherein acquisition
Finger-image be level acquisition figure or vertical collection figure；
Step S200, finger boundary alignment fit the boundary lines of effective finger areas on image after the pre-treatment；
Step S300, effective coverage obtain, and are searched in effective finger areas of the boundary line orientation fitted maximum
Rectangular area pixel simultaneously is cut by inscribed rectangle, obtains true vein treatments subgraph；
Step S400, effective coverage enhancing, enhances true vein treatments subgraph, obtains vein distributed image；
The edges step S500, SOBEL enhance, and make convolution using Sobel SOBEL operators and vein distributed image, are wrapped
The SOBEL enhancing figures in the region containing finger print information；
Step S600 calculates spectral discrimination coefficient, in the upper calculated level gradient energy of SOBEL enhancing figures and vertical gradient energy
Amount, and using the ratio or horizontal gradient energy divided by vertical gradient energy of vertical gradient energy divided by horizontal gradient energy
Ratio is as coefficient of determination；
Step S700, the judgement of the figure of vein containing fingerprint, by coefficient of determination compared with default classification thresholds, if it is determined that coefficient is small
Then it is determined as the unreasonable image containing fingerprint in default classification thresholds.
The present invention is applied in the preliminary stage for referring to vein recognition system processing, by assessing Input Image Content,
It refers specifically to quantify the finger print information content in image, then by this quantized value and threshold value comparison, passes through preset shielding
Unreasonable image, is blocked the reasonability that data are handled in the currently processed stage, maintenance system by mechanism, residing for guarantee system
It is true, effective that reason, which refers to intravenous data source, and final is that the correct of system comparison result provides effective guarantee.
In this preferred embodiment, the artwork of the finger-image of equipment acquisition is as shown in Fig. 2, be level acquisition figure, wherein hand
Refer to region in the horizontal direction to extend.Inevitably because the factors such as electronic device, environment make image when equipment acquires
Including certain noise, in the step S100 of image preprocessing of the present invention, the filtering methods such as intermediate value or mean value may be used to making an uproar
Sound is inhibited, and the image after smooth, noise is cut in, and the venous information that we are concerned about is kept, it is important that quiet
The edge of arteries and veins also obtains certain enhancing.
As shown in Fig. 2, in image, effective finger areas is only distributed in the inclined middle section of image in the horizontal direction.This
On the one hand outer background area is meaningless to subsequent processing, secondly, the random intensity profile of background pixel, background is with before
Huge contrast of scape gray value etc. all can form great interference to the statistics of effective coverage parameter value, so needing carrying out step
S200 on the basis of finger boundary alignment to by background area mask or cropping.
Further, in this preferred embodiment, the step S200 of finger boundary alignment is as follows：
Pretreated two dimensional image is divided into uniform, discontinuous multistage in vertical direction first；Every section of use
The vertical position coordinate where extreme value in the extreme value and corresponding section of each segmented pixels gray scale is searched by horizontal projection method；Then in order to
The boundary value stablized in section is obtained, making arithmetic average to vertical position coordinate value in section obtains section internal coordinate mean value；Then line is used
Property fitting function distance condition constraint under, continuous best fit in the region is gone out based on each section boundaries coordinate mean value computation
Upper and lower boundary lines of the lines as effective finger areas.By above-mentioned calculating, the present invention intends respectively on image level direction
The lines in upper and lower two region are closed out, they are exactly the place on finger boundary in image.The design sketch of finger boundary alignment such as Fig. 3
Shown in, the region that A, B lines surround in figure is exactly finger effective district, that is, subsequently by the venous information interested of processing
Area；A, B lines are then background area to image border part.
Step S300, effective coverage obtain：
Because of finger substantially trapezoidal distribution in image, in order to further decrease the influence of background pixel, also for
Convenient for quickly calculating, the present invention will downscaled images process range again, it is intended to which processing data are located in best rectangular area.
Maximum inscribed rectangle is searched in the finger effective coverage that upper step is fitted line orientation, and rectangular area pixel is cut, is obtained
Obtain true vein treatments subgraph.
Step S400, effective coverage enhancing：
In order to highlight the vein segment in true vein treatments subgraph, the present invention enhances it, passes through ash
Degree extension and scalar quantization enhancing, it is intended to obtain clearer vein distributed image, be as follows：
Intensity profile extension is first passed through, grey scale pixel value is extended in 0~255 range, the effect after expansion of gradation
Figure is as shown in Figure 4；
Then, Mapping and Converting is carried out to image pixel with default scalar quantization table, for example 0 to 255 gray areas is drawn
It is divided into 30 ladder sections, each ladder section only takes the section intermediate value as scalar quantization tabular value, and then image pixel value is pressed
According to the mapping relations with ladder section, is replaced by the respective value of scalar quantization table, generate new enhancing figure as vein distribution map
Picture.As shown in Figure 5, enhancing figure obviously increases the gray scale difference between the neighborhood pixels of vein edge, has highlighted existing for vein
Effect.
For artwork since effective coverage gray value dynamic range is small, venous information has been very fuzzy, by expansion of gradation and
Scalar quantization enhances, it is already possible to compare the distribution for being clearly seen that vein.
Further, in this preferred embodiment, the step S500 of the edges SOBEL enhancing includes：
Convolution is made using vertical direction SOBEL operators and image, edge enhancing is carried out to image in vertical direction, is obtained
SOBEL enhancing figures.This step further enhances in image grey scale change intense regions (longitudinal texture edge in vertical direction
Region) information.Because venous collection has focused largely on second and third juxtra-articular of finger, under normal conditions the finger in this region
Line is in vertical distribution (cross grain on finger), and the present invention is exactly that the distribution of this section fingerprint is utilized using SOBEL convolution
Characteristic, and it is strengthened, it is calculated convenient for follow-up.Vertical SOBEL enhancing effect figures are as shown in Figure 6.Become by vertical SOBEL operators
After changing, vertical distribution texture (region containing finger print information) is enhanced in image, and more obvious vertical distribution state is presented.
Further, in this preferred embodiment, the step S600 for calculating spectral discrimination coefficient includes：
On SOBEL figures, calculated level gradient energy, vertical gradient energy.Specifically, gradient map is firstly generated, in order to
Keep statistic more effective, the computer capacity of each pixel gradient is defined as 4 pixels by the present invention, exactly takes adjacent preceding 2 pictures
Element and with rear 2 pixels and difference as current point pixel gradient；Node-by-node algorithm gradient information generates horizontal gradient figure, hangs down respectively
Straight gradient map.
Then gradient energy is calculated in gradient map, that is, in horizontal, vertical gradient map calculate all pixels respectively
Gradient and obtain horizontal, vertical gradient energy.
Finally by vertical gradient energy divided by horizontal direction gradient energy, vein image Vertical factor is obtained, this is vertical
Coefficient is as coefficient of determination.
Using above-mentioned 6 steps, its Vertical factor is calculated to all samples of vein test set, in conjunction with the set
It compares score and is identified by the statistical conditions such as rate, misclassification rate, by comprehensive analysis, obtain the relevant optimal classification of Vertical factor
Threshold value.The present invention passes through the statistical analysis to test set, it is found that when Vertical factor threshold value is set as 0.6, this method can compare can
Whether contain excessive finger print information in the judgement vein figure leaned on.
Finally, the judgement of the step S700 figures of vein containing fingerprint is carried out.In the system application stage, first the above method is used to obtain
The Vertical factor for identifying image, then the coefficient and default classification thresholds are compared, then judged if it is less than the threshold value
To contain fingerprint image, and assert the finger print information content of the figure severe jamming finger venous information, then, which will be thrown
It abandons, is no longer participate in system subsequent processing.
When the finger-image of acquisition is vertical collection figure, that is, finger areas extends in vertical direction in image, right
The processing of image and decision process with it is substantially similar to the processing and decision process of level acquisition figure above, difference is only in side
It is varied from upwards.For vertical collection figure, the step of finger boundary alignment, includes：In the horizontal direction by pretreated image
On be divided into uniform and discontinuous multistage；Every section uses vertical projection method, searches the extreme value of each segmented pixels gray scale and corresponding section
Horizontal position coordinate where interior extreme value；Arithmetic average is made to horizontal position coordinate value in section and obtains section internal coordinate mean value；Use line
Property fitting function distance condition constraint under, continuous best fit in the region is gone out based on each section boundaries coordinate mean value computation
Left and right boundary lines of the lines as effective finger areas.In addition, in the step of edges SOBEL enhance, using horizontal direction
SOBEL operators make convolution with vein distributed image, carry out edge enhancing to image in the horizontal direction, obtain SOBEL enhancing figures.Separately
Outside, in the step of calculating spectral discrimination coefficient, by horizontal gradient energy divided by vertical gradient energy, it is horizontal to obtain vein image
Coefficient is as coefficient of determination.
According to another aspect of the present invention, a kind of discriminating gear referring to intravenous pressing figure, including processor, place are additionally provided
Reason device executes the method for discrimination of above-mentioned finger intravenous pressing figure for running program, processor when running.
According to another aspect of the present invention, a kind of storage medium is additionally provided, storage medium includes the program of storage, program
Equipment where controlling storage medium when operation executes the method for discrimination of above-mentioned finger intravenous pressing figure.
According to another aspect of the present invention, a kind of finger vein identification method is additionally provided, in the finger vein image to reception
It is identified before judgement, executes the method for discrimination of above-mentioned finger intravenous pressing figure, shielding coefficient of determination is less than default classification thresholds
Corresponding finger vein image.
The present invention can be just intercepted in system processing early stage by the unreasonable image containing fingerprint, saves a large amount of follow-up nothings
The calculating time of meaning, system is allow to enter the identifying processing stage of fresh target in the shortest possible time, raising refers to quiet
Arteries and veins Compare System response speed；Meanwhile the unreasonable image containing fingerprint being avoided to enter post-processing so that the knowledge that system is extracted
It is not characterized in that pure vein pattern, raising refer to vein Compare System recognition performance.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.All within the spirits and principles of the present invention, any made by repair
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
1. a kind of method of discrimination referring to intravenous pressing figure, which is characterized in that including：
Image preprocessing is filtered to inhibit noise the finger-image of acquisition, wherein the finger-image of acquisition is water
Flat acquisition figure or vertical collection figure；
Finger boundary alignment fits the boundary lines of effective finger areas on image after the pre-treatment；
Effective coverage obtains, and maximum inscribed rectangle is searched in effective finger areas of the boundary line orientation fitted and by square
Shape area pixel cuts, and obtains true vein treatments subgraph；
Effective coverage enhances, and enhances the true vein treatments subgraph, obtains vein distributed image；
Edge enhances, and makees convolution using Sobel SOBEL operators and the vein distributed image, and it includes finger print information region to obtain
SOBEL enhancing figure；
Spectral discrimination coefficient is calculated, in the upper calculated level gradient energy of SOBEL enhancing figures and vertical gradient energy, and is used
The ratio conduct of the ratio or horizontal gradient energy divided by vertical gradient energy of vertical gradient energy divided by horizontal gradient energy
Coefficient of determination；
The judgement of the figure of vein containing fingerprint, by the coefficient of determination compared with default classification thresholds, if the coefficient of determination is less than institute
It states default classification thresholds and is then determined as the unreasonable image containing fingerprint.
2. the method for discrimination according to claim 1 for referring to intravenous pressing figure, which is characterized in that the finger boundary alignment
Step includes：
Pretreated image is divided into multistage on the first direction vertical with finger extending direction；
Search the first direction position coordinates where extreme value in the extreme value and corresponding section of each segmented pixels gray scale；
Arithmetic average is made to first direction position coordinate value in section and obtains section internal coordinate mean value；
With linear fit function under distance condition constraint, gone out based on each section boundaries coordinate mean value computation continuous in the region
Boundary lines of the best fit lines as effective finger areas.
3. the method for discrimination according to claim 2 for referring to intravenous pressing figure, which is characterized in that the finger-image of the acquisition
For level acquisition figure, the step of finger boundary alignment, includes：
Pretreated image is divided into uniform and discontinuous multistage in vertical direction；
Every section uses horizontal projection method, searches the upright position in the extreme value and corresponding section of each segmented pixels gray scale where extreme value and sits
Mark；
Arithmetic average is made to vertical position coordinate value in section and obtains section internal coordinate mean value；
With linear fit function under distance condition constraint, gone out based on each section boundaries coordinate mean value computation continuous in the region
Upper and lower boundary lines of the best fit lines as effective finger areas.
4. the method for discrimination according to claim 2 for referring to intravenous pressing figure, which is characterized in that the effective coverage enhancing
Step includes：
It is extended by intensity profile, grey scale pixel value in the true vein treatments subgraph is extended in 0~255 range；
Mapping and Converting is carried out to image pixel with default scalar quantization table；
By image pixel value according to the mapping relations with ladder section, is replaced, generated new using the respective value of scalar quantization table
Enhancing figure is used as the vein distributed image.
5. the method for discrimination according to claim 3 for referring to intravenous pressing figure, which is characterized in that the edges the SOBEL enhancing
The step of include：
Convolution is made using vertical direction SOBEL operators and the vein distributed image, edge increasing is carried out to image in vertical direction
By force, the SOBEL enhancings figure is obtained.
6. the method for discrimination according to claim 5 for referring to intravenous pressing figure, which is characterized in that the calculating spectral discrimination system
Several steps include：
The computer capacity of each pixel gradient in the SOBEL enhancings figure is defined as intended pixel；
Node-by-node algorithm gradient information generates horizontal gradient figure and vertical gradient map respectively；
Respectively in horizontal gradient figure and vertical gradient map in calculate all pixels gradient and with obtain horizontal gradient energy and
Vertical gradient energy；
By vertical gradient energy divided by horizontal gradient energy, vein image Vertical factor is obtained as the coefficient of determination.
7. the method for discrimination according to claim 2 for referring to intravenous pressing figure, which is characterized in that the finger-image of the acquisition
For vertical collection figure, the step of finger boundary alignment, includes：
Pretreated image is divided into uniform and discontinuous multistage in the horizontal direction；
Every section uses vertical projection method, searches the horizontal position in the extreme value and corresponding section of each segmented pixels gray scale where extreme value and sits
Mark；
Arithmetic average is made to horizontal position coordinate value in section and obtains section internal coordinate mean value；
With linear fit function under distance condition constraint, gone out based on each section boundaries coordinate mean value computation continuous in the region
Left and right boundary lines of the best fit lines as effective finger areas.
8. the method for discrimination according to claim 7 for referring to intravenous pressing figure, which is characterized in that
In the step of edges SOBEL enhancing, convolution is made using horizontal direction SOBEL operators and the vein distributed image,
Edge enhancing is carried out to image in the horizontal direction, obtains the SOBEL enhancings figure；
In the step of calculating spectral discrimination coefficient, by horizontal gradient energy divided by vertical gradient energy, vein image is obtained
Horizontal coefficients are as the coefficient of determination.
9. a kind of discriminating gear referring to intravenous pressing figure, including processor, for running program, feature exists the processor
In the processor executes the method for discrimination as described in any of the claims 1 to 8 for referring to intravenous pressing figure when running.
10. a kind of finger vein identification method, which is characterized in that before judgement is identified in the finger vein image to reception, hold
Row refers to the method for discrimination of intravenous pressing figure as described in claim 1 to 8 is any, shields the coefficient of determination and is less than described default point
The corresponding finger vein image of class threshold value.
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 true CN108280448A (en) | 2018-07-13 |
| CN108280448B 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) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111223082A (en) * | 2020-01-03 | 2020-06-02 | 圣点世纪科技股份有限公司 | Quantitative evaluation method for finger vein image quality |
| CN111797828A (en) * | 2020-06-19 | 2020-10-20 | 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 |
| CN112714232A (en) * | 2020-12-31 | 2021-04-27 | 中国工商银行股份有限公司 | Finger vein image data transmission method and device |
| CN116030264A (en) * | 2023-02-01 | 2023-04-28 | 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 |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111223082A (en) * | 2020-01-03 | 2020-06-02 | 圣点世纪科技股份有限公司 | Quantitative evaluation method for finger vein image quality |
| 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 |
| CN111797828A (en) * | 2020-06-19 | 2020-10-20 | 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 |
| CN112714232A (en) * | 2020-12-31 | 2021-04-27 | 中国工商银行股份有限公司 | Finger vein image data transmission method and device |
| 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 |
| CN116030264A (en) * | 2023-02-01 | 2023-04-28 | 安徽信息工程学院 | Method and device for assisting visually impaired people in understanding pictures |
| CN116030264B (en) * | 2023-02-01 | 2024-03-29 | 安徽信息工程学院 | A method and device for assisting visually impaired people to understand pictures |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108280448B (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN117078672B (en) | Intelligent detection method for mobile phone screen defects based on computer vision | |
| CN108280448A (en) | The method of discrimination and device of finger intravenous pressing figure refer to vein identification method | |
| CN107871322B (en) | Iris image segmentation method and device | |
| Zhang et al. | Finger vein image enhancement based on guided tri-Gaussian filters | |
| CN101266645B (en) | A method of iris localization based on multi-resolution analysis | |
| CN105654501B (en) | Adaptive Image Segmentation Method Based on Fuzzy Threshold | |
| Versaci et al. | Adaptive image contrast enhancement by computing distances into a 4-dimensional fuzzy unit hypercube | |
| CN105261015B (en) | Eye fundus image blood vessel automatic division method based on Gabor filter | |
| CN106548463A (en) | Based on dark and the sea fog image automatic defogging method and system of Retinex | |
| WO2011151821A1 (en) | Inspection of region of interest | |
| CN106548176B (en) | Finger vein image enhancement method based on adaptive guided filtering | |
| CN106447634B (en) | A kind of privacy places positioning and guard method based on active mm-wave imaging | |
| CN1885314A (en) | Pre-processing method for iris image | |
| CN105869174B (en) | A kind of Sky Scene image partition method | |
| CN107273812B (en) | A living iris anti-counterfeiting method for identity authentication | |
| CN108960185A (en) | Vehicle target detection method and system based on YOLOv2 | |
| CN109377450A (en) | An edge-preserving denoising method | |
| He et al. | Retinal image denoising via bilateral filter with a spatial kernel of optimally oriented line spread function | |
| CN108647693A (en) | A kind of sea infrared target detection method based on binary significant characteristics | |
| CN110909631B (en) | Finger vein image ROI extraction and enhancement method | |
| CN101866420B (en) | Image preprocessing method for optical volume holographic iris recognition | |
| CN107977973A (en) | The method and device on beam-defining clipper irradiation field border in a kind of acquisition medical diagnostic images | |
| CN105046230A (en) | Image based human canthus detection method and system | |
| Fazli et al. | A novel retinal vessel segmentation based on local adaptive histogram equalization | |
| CN114863498A (en) | Hand vein infrared image enhancement and segmentation method based on AGC and Frangi |
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 |