CN108182399A - Refer to vein characteristic comparison method, apparatus, storage medium and processor - Google Patents
Refer to vein characteristic comparison method, apparatus, storage medium and processor Download PDFInfo
- Publication number
- CN108182399A CN108182399A CN201711443496.XA CN201711443496A CN108182399A CN 108182399 A CN108182399 A CN 108182399A CN 201711443496 A CN201711443496 A CN 201711443496A CN 108182399 A CN108182399 A CN 108182399A
- Authority
- CN
- China
- Prior art keywords
- gabor
- characteristic
- parameter
- value
- finger vein
- 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
- 210000003462 vein Anatomy 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 41
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 239000013598 vector Substances 0.000 claims abstract description 72
- 238000000605 extraction Methods 0.000 claims abstract description 17
- 230000009467 reduction Effects 0.000 claims abstract description 16
- 230000002708 enhancing effect Effects 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 6
- 238000005520 cutting process Methods 0.000 claims description 5
- 238000009826 distribution Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 241000208340 Araliaceae Species 0.000 claims description 3
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 claims description 3
- 235000003140 Panax quinquefolius Nutrition 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 3
- 235000008434 ginseng Nutrition 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims description 3
- 235000013399 edible fruits Nutrition 0.000 claims description 2
- 239000013604 expression vector Substances 0.000 claims 1
- 230000008901 benefit Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000001755 vocal effect Effects 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 102000001554 Hemoglobins Human genes 0.000 description 1
- 108010054147 Hemoglobins Proteins 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000008280 blood Substances 0.000 description 1
- 210000004369 blood Anatomy 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000036651 mood Effects 0.000 description 1
- 238000011946 reduction process Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000000638 stimulation Effects 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of finger vein characteristic comparison method, apparatus, storage medium and processor, this method to include：The finger vein image of input is pre-processed；Processing is carried out using the pretreated image of Gabor function pairs and obtains Gabor vector characteristics；Dimension-reduction treatment is carried out to the Gabor vector characteristics of acquisition；The extraction of binaryzation Gabor Gradient Features is carried out to the Gabor vector characteristics after dimensionality reduction：By the gradient for calculating Gabor coefficients at corresponding direction under different frequency parameter, and Grad two-value is turned to " 0 ", " 1 " value by the sign symbol according to Grad, then corresponding value is placed in the corresponding completely new vector of component positions indexed by block coordinate, frequency, directioin parameter, generates the completely new vector characteristic of binary expression；Aspect ratio pair is carried out to the completely new vector characteristic of binary expression and exports comparison result.The present invention obtains stable expressing feature, improves the performance for referring to hand vein recognition algorithm.
Description
Technical field
The present invention relates to hand vein recognition field is referred to, particularly, it is related to a kind of finger vein characteristic comparison method, apparatus, storage
Medium and processor.
Background technology
It is the one kind understood the characteristic of absorption near infrared ray according to the hemoglobin in blood and grown up to refer to hand vein recognition
New biological identification technology.
In current biological identification technology：Although fingerprint technique is very ripe, fingerprint characteristic is easy to be imitated, and face is also deposited
In easy the problem of being imitated, rely on and have much room for improvement, and face recognition technology is also so they lack in performance for security
There are the insecure risks of result under big posture, big expression shape change；Iris recognition technology performance is stablized, but the operation of its contact
Method is not received by extensive crowd, is not suitable for large-scale promotion；Application on Voiceprint Recognition although have acquisition, application aspect advantage, it is but first
First individual vocal print feature can with the age, mood, physical condition and change, it is close with collecting device that next acquires vocal print signal quality
Cut phase is closed, and notably, the noise signals such as background environment can form vocal print signal serious interference；Above-mentioned biological identification technology, though
So respectively there is its advantage, but can not also despise using upper limitation.
Refer to hand vein recognition to be then easy to acquire, smaller by such environmental effects, more crucial it is that a kind of natural live body is special
It levies, it is secure in safety, so, vein identification technology obtains more and more close in bio-identification application field in recent years
Note.
Refer to the ripe of vein identification technology and rely on both sides progress：Collecting device and alignment algorithm；Collecting device needs to have
The standby ability for getting clear venous information, alignment algorithm then can will rationally distinguish comparison target, provide correct target identification
As a result.It is clear that effective vein Expressive Features can provide reliable support for the accuracy of alignment algorithm.And how to obtain
Effectively stable vein pattern is then the research key for referring to vein identification technology at present.
Invention content
It is more stable to obtain the present invention provides a kind of finger vein characteristic comparison method, apparatus, storage medium and processor
Expressive Features, for refer to hand vein recognition provide safeguard.
The technical solution adopted by the present invention is as follows：
One aspect of the present invention provides a kind of finger vein characteristic comparison method, includes the following steps：
The finger vein image of input is pre-processed；
Processing is carried out using the pretreated image of Gabor function pairs and obtains Gabor vector characteristics；
Dimension-reduction treatment is carried out to the Gabor vector characteristics of acquisition；
The extraction of binaryzation Gabor Gradient Features is carried out to the Gabor vector characteristics after dimensionality reduction：Joined by calculating different frequency
The gradient of Gabor coefficients at several lower corresponding directions, and Grad two-value is turned to " 0 ", " 1 " by the sign symbol according to Grad
Then corresponding value is placed in the corresponding completely new vector of component positions indexed by block coordinate, frequency, directioin parameter by value,
Generate the completely new vector characteristic of binary expression；
Aspect ratio pair is carried out to the completely new vector characteristic of binary expression and exports comparison result.
Further, the step of being pre-processed to the finger vein image of input includes：
The finger vein image of input is filtered and finger edge positions；
Region cutting is carried out to input picture according to finger edge location information to obtain the son of effective vein texture region
Figure；
Enhancing is done to the subgraph after cutting and obtains curvature enhancing figure.
Further, the step of processing acquisition Gabor vector characteristics is carried out using Gabor filter to pretreated image
Suddenly include：
Curvature enhancing figure is normalized into master pattern size；
The frequency parameter and directioin parameter of Gabor functions are defined, this group of parameter is substituted into Gabor function formulas, acquisition pair
Answer the Gabor convolutional filtering coefficients under parameter；
The stepped parameter of defined feature extraction block both horizontally and vertically；
Each block in traversal curvature enhancing figure under stepped parameter guiding, and use what is be obtained ahead of time in each block
Gabor convolutional filterings coefficient carries out the Gabor characteristic under convolutional calculation respective frequencies, directioin parameter；
Each block is calculated to the Gabor characteristic obtained and is connected in series generation Gabor vector characteristics.
Preferably, frequency parameter is set as 7；Directioin parameter is set as 16.
Further, the step of carrying out dimension-reduction treatment to the Gabor vector characteristics of acquisition includes：
Each block in curvature enhancing figure by even distribution pattern is selected, filters out Partial Block feature；
Down-sampling is carried out according to direction initialization parameter to remaining Block Characteristic, forms the spy of the Gabor vectors after new dimensionality reduction
Sign.
Further, the step of binaryzation Gabor Gradient Features extract is carried out to the Gabor vector characteristics after dimensionality reduction to wrap
It includes：
Calculate the gradient of two neighboring coefficient under same frequency parameter, and binaryzation；
Calculate the complex gradient value that two coefficient sums of neighbour are corresponded under different frequency parameter, and binaryzation；
By sequentially calculating the binaryzation Gabor Grad of adjacent coefficient under single frequency in each frequency parameter, recombinant
In each frequency parameter under neighbour's frequency parameter adjacent coefficient sum complex gradient binary value, obtain by block coordinate, frequency ginseng
The completely new vector characteristic of binary expression that number, directioin parameter index.
Aspect ratio pair is carried out to the completely new vector characteristic of binary expression and is included the step of exporting comparison result：
" 0 ", " 1 " occur in corresponding position in the completely new vector characteristic after two width recognition target images progress binaryzation
Same number is counted, and is changed into the similarity value of two width recognition target images under normalization operation；
Judge and export comparison result, similarity value is converted to the score value between 0 to the 1 of real number expression, formed final
Comparison result score, then by score value compared with predetermined threshold value, same target is then considered more than predetermined threshold value, is otherwise different
Class target.
According to another aspect of the present invention, a kind of finger vein characteristic comparison system is additionally provided, including：
Preprocessing module pre-processes for the finger vein image to input；
Gabor characteristic extraction module obtains Gabor for carrying out processing using Gabor functions to pretreated image
Vector characteristic；
Gabor characteristic dimensionality reduction module, for carrying out dimension-reduction treatment to the Gabor vector characteristics of acquisition；
Binaryzation Gabor Gradient Features extraction modules, for carrying out binaryzation to the Gabor vector characteristics after dimensionality reduction
Gabor Gradient Features extract：By calculating the gradient of Gabor coefficients at corresponding direction under different frequency parameter, and according to gradient
Grad two-value is turned to " 0 ", " 1 " value by the sign symbol of value, and then corresponding value is placed in by block coordinate, frequency, direction
In the corresponding completely new vector of component positions of parameter reference, the completely new vector characteristic of binary expression is generated；
Output module is compared, for carrying out aspect ratio pair to the completely new vector characteristic of binary expression and exporting comparison knot
Fruit.
The present invention also provides a kind of storage medium, storage medium includes the program of storage, control storage when program is run
Equipment where medium performs above-mentioned finger vein characteristic comparison method.
The present invention also provides a kind of processor, for processor for running program, processor performs above-mentioned finger when running
Vein characteristic comparison method.
The present invention is extracted by binaryzation Gabor Gradient Features, and embryonic character vector is extracted again, in low order spy
Higher Order Abstract is done on the basis of sign, computing cost relative increase is less, without adjusting system flow on a large scale, and can obtain more stable
Expressing feature, further improve refer to hand vein recognition algorithm performance.
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 for forming the part of the 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 finger vein characteristic comparison method of the preferred embodiment of the present invention；
Fig. 2 is the schematic diagram of adjacent coefficient gradient binaryzation under same frequency；
Fig. 3 is the schematic diagram of adjacent coefficient complex gradient binaryzation under different frequency；
Fig. 4 is the structure diagram of the finger vein characteristic comparison system of the preferred embodiment of the present invention.
Specific embodiment
It should be noted that in the absence of conflict, the feature in embodiment and embodiment in the application can phase
Mutually combination.The present invention will be described in detail below with reference to the accompanying drawings and in conjunction with the embodiments.
With reference to Fig. 1, the preferred embodiment of the present invention provides a kind of finger vein characteristic comparison method, includes the following steps：
Step S100 pre-processes the finger vein image of input；
Step S200 carries out processing using the pretreated image of Gabor function pairs and obtains Gabor vector characteristics；
Step S300 carries out dimension-reduction treatment to the Gabor vector characteristics of acquisition；
Step S400 carries out the Gabor vector characteristics after dimensionality reduction the extraction of binaryzation Gabor Gradient Features：Pass through calculating
Under different frequency parameter at corresponding direction Gabor coefficients gradient, and the sign symbol according to Grad is by Grad binaryzation
For " 0 ", " 1 " value, then corresponding value is placed in corresponding complete by the component positions of block coordinate, frequency, directioin parameter index
In new vector, the completely new vector characteristic of binary expression is generated；
Step S500 carries out aspect ratio pair to the completely new vector characteristic of binary expression and exports comparison result.
Gabor functions are a linear filters, and in the spatial domain, a two-dimensional Gabor filter is one by sine
The gaussian kernel function of plane wave modulation.The frequency of Gabor filter and direction expression are similar with human visual system, it can be very
Approximate single celled receptive field function (transmission function under light intensity stimulation) well.
Vein recognition system is compared in operation, even same target finger, because of time, individual play's custom, acquisition
Environmental change, device parameter adjustment etc. reasons necessarily result in acquisition figure there is difference, nevertheless, the target finger is quiet
Vein reason is substantially determining certainly.The preferred first Gabor characteristic of the present invention is as vein low order feature is referred to, then in its base
Do the extraction of high-order feature on plinth, smooth this species diversity caused by above-mentioned reason at character pair of new feature, it is easier to catch
The inherent characteristic of vein texture is grasped, thus to obtain a kind of more stable Expressive Features, makes finger vein comparison result robustness more
By force.
The concrete processing procedure of the finger vein comparison method of the preferred embodiment of the present invention is described below.
The step S100 pre-processed to the finger vein image of input is specifically included：First to the finger vein image of input
It is filtered and is positioned with finger edge.Region is carried out to input picture according to finger edge location information to cut to be had
Imitate the subgraph of vein texture region.Then enhancing is done to the subgraph after cutting and obtains curvature enhancing figure.
The step S200 packets of processing acquisition Gabor vector characteristics are carried out using Gabor filter to pretreated image
It includes：
Curvature enhancing figure is normalized into master pattern size.
The frequency parameter and directioin parameter of Gabor functions are defined, this group of parameter is substituted into Gabor function formulas, acquisition pair
Answer the Gabor convolutional filtering coefficients under parameter.In this preferred embodiment, it is contemplated that the present invention is finally using based on Gabor
On high-order feature, the present invention directioin parameter has been done to finer setting, by common 8 Directional Extension of people be 16 sides
To.In addition, in this preferred embodiment, frequency parameter is set as 7.
The stepped parameter of defined feature extraction block both horizontally and vertically.
Each block in traversal curvature enhancing figure under stepped parameter guiding, and use what is be obtained ahead of time in each block
Gabor convolutional filterings coefficient (filtering core) carries out the Gabor characteristic under convolutional calculation respective frequencies, directioin parameter；
Each block is calculated to the Gabor characteristic obtained and is connected in series generation Gabor vector characteristics.
In above-mentioned steps, 7 frequencies and 16 direction Gabor parameters are defined, are calculated in this way, original Gabor systems
Array into the dimension of vector characteristic be considerable.The present invention considers that the gray scale of image neighbor pixel is slowly excessively divided
Cloth, their features of (frequency neighbour or direction neighbour) under neighbour's parameter are bound to comprising considerable redundancy, we
Down-sampling can be done to them completely, the sampled data under certain sparse density can be to save the characteristic of former target from damage.
Specifically, the step S300 that dimension-reduction treatment is carried out to the Gabor vector characteristics of acquisition includes：
Each block in curvature enhancing figure by even distribution pattern is selected first, filters out Partial Block feature.
Then down-sampling is carried out according to direction initialization parameter to remaining Block Characteristic, filters out even number direction coefficient, retained strange
Number direction coefficient, the Gabor vector characteristics after new dimensionality reduction is formed by such intercept operation.
For the stability of Enhanced feature expression, binaryzation is carried out to the Gabor vector characteristics after dimensionality reduction in the present invention
The step S400 of Gabor Gradient Features extraction includes：
Calculate the gradient of two neighboring coefficient under same frequency parameter, and binaryzation.With reference to Fig. 2, specific calculating process is such as
Under：Under frequency parameter 1, gradient of the directioin parameter 1 with 2 corresponding Gabor coefficients of directioin parameter is calculated, calculates directioin parameter 2 and side
The gradient of Gabor coefficients is corresponded to parameter 3, and so on, it calculates the reversion of 16 coefficient of directioin parameter and returns and 1 coefficient of directioin parameter
Gradient, traverse 16 directions and obtain 16 Grad, then according to each value sign symbol distribution, positive gradient value is replaced with " 1 ",
Negative gradient value is replaced with " 0 ", and 16 Grad are converted to 16 binary values.
Calculate the complex gradient value that two coefficient sums of neighbour are corresponded under different frequency parameter, and binaryzation.With reference to Fig. 3, tool
Body calculating process is as follows：Under first calculated rate parameter 1,1 coefficient of correspondence of directioin parameter and 2 coefficient of proximal direction parameter and, then
First ask under frequency parameter 2,1 coefficient of correspondence of directioin parameter and 2 coefficient of proximal direction parameter and, then calculate front two and value phase
Subtract and obtain complex gradient value, and so on, it traverses 16 directions and obtains 8 complex gradient values, similary low, the symbol according to Grad
Number by Grad be converted to " 0 ", " 1 " expression 8 binary values.
By sequentially calculating the binaryzation Gabor Grad of adjacent coefficient under single frequency in 7 frequency parameters, recombinant
In 7 frequency parameters under neighbour's frequency parameter adjacent coefficient sum complex gradient binary value, obtain by block coordinate, frequency ginseng
The completely new vector characteristic of binary expression that number, directioin parameter index.
The step S500 for carrying out aspect ratio pair to the completely new vector characteristic of binary expression and exporting comparison result includes：
" 0 ", " 1 " occur in corresponding position in the completely new vector characteristic after two width recognition target images progress binaryzation
Same number is counted, and is changed into the similarity value of two width recognition target images under normalization operation；
Judge and export comparison result, similarity value is converted to the score value between 0 to the 1 of real number expression, formed final
Comparison result score, then by score value compared with predetermined threshold value, same target is then considered more than predetermined threshold value, is otherwise different
Class target.
With reference to Fig. 4, refer to vein characteristic comparison device the present invention also provides a kind of, including：
Preprocessing module 100 pre-processes for the finger vein image to input；Specific preprocessing process is with reference to upper
Description in literary middle finger vein characteristic comparison method.
Gabor characteristic extraction module 200, for carrying out processing acquisition using Gabor functions to pretreated image
Gabor vector characteristics；Specific characteristic extraction procedure is with reference to the description in middle finger vein characteristic comparison method above.
Gabor characteristic dimensionality reduction module 300, for carrying out dimension-reduction treatment to the Gabor vector characteristics of acquisition；Specific dimensionality reduction
Process is with reference to the description in middle finger vein characteristic comparison method above.
Binaryzation Gabor Gradient Features extraction module 400, for carrying out binaryzation to the Gabor vector characteristics after dimensionality reduction
Gabor Gradient Features extract：By calculating the gradient of Gabor coefficients at corresponding direction under different frequency parameter, and according to gradient
Grad two-value is turned to " 0 ", " 1 " value by the sign symbol of value, and then corresponding value is placed in by block coordinate, frequency, direction
In the corresponding completely new vector of component positions of parameter reference, the completely new vector characteristic of binary expression is generated；Specifically calculated
Journey is with reference to the description in middle finger vein characteristic comparison method above.
Output module 500 is compared, for carrying out aspect ratio pair to the completely new vector characteristic of binary expression and exporting comparison
As a result.Specific comparison process is with reference to the description in middle finger vein characteristic comparison method above.
The embodiment of the present invention additionally provides a kind of storage medium, and storage medium includes the program of storage, program operation time control
Equipment where storage medium processed performs above-mentioned finger vein characteristic comparison method.
The embodiment of the present invention additionally provides a kind of processor, and processor performs for running program, when processor is run
The finger vein characteristic comparison method stated.
The present invention obtains the piecemeal Gabor characteristic of vein texture first with functional transformation, then sequentially by piecemeal Gabor characteristic
The corresponding identification feature vector for referring to vein image is combined into, direct target is carried out using Gabor vector characteristics compare point with common
Class is different, and the present invention processes Gabor vector characteristics again, to the Gabor values in different parameters section, by frequency and scale
Component value under (direction) is corresponding asks for gradient, and be converted to " 0 ", " 1 " binaryzation data (such as according to the positive negative test of Grad：A
Component is more than B component, then puts result as " 1 ", otherwise reset), and should " 0/1 " value be placed on and the component index position pair
In the completely new vector answered, what is finally obtained is the completely new characteristic vector of binary expression；Because completely new characteristic vector record is not
Simple Gabor characteristic, but the gradient information between Gabor characteristic component, so, the present invention will refer in vein imaging due to
Interference greatly reduces caused by the uncontrollable factors such as equipment, environment, acquisition operations are lack of standardization, and the feature of presentation can more capture
The genuine property of target also necessarily greatly promotes the stability of feature representation.
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, that is made any repaiies
Change, equivalent replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (10)
- A kind of 1. finger vein characteristic comparison method, which is characterized in that include the following steps：The finger vein image of input is pre-processed；Processing is carried out using the pretreated image of Gabor function pairs and obtains Gabor vector characteristics；Dimension-reduction treatment is carried out to the Gabor vector characteristics of acquisition；The extraction of binaryzation Gabor Gradient Features is carried out to the Gabor vector characteristics after dimensionality reduction：By calculating under different frequency parameter The gradient of Gabor coefficients at corresponding direction, and Grad two-value is turned to " 0 ", " 1 " value by the sign symbol according to Grad, so Corresponding value is placed in afterwards in the corresponding completely new vector of component positions indexed by block coordinate, frequency, directioin parameter, generation two The completely new vector characteristic of system expression；Aspect ratio pair is carried out to the completely new vector characteristic of binary expression and exports comparison result.
- 2. finger vein characteristic comparison method according to claim 1, which is characterized in that the finger vein image of described pair of input The step of being pre-processed includes：The finger vein image of input is filtered and finger edge positions；Region cutting is carried out to input picture according to finger edge location information to obtain the subgraph of effective vein texture region；Enhancing is done to the subgraph after cutting and obtains curvature enhancing figure.
- 3. finger vein characteristic comparison method according to claim 2, which is characterized in that described to be adopted to pretreated image The step of processing obtains Gabor vector characteristics is carried out with Gabor filter to include：Curvature enhancing figure is normalized into master pattern size；The frequency parameter and directioin parameter of Gabor functions are defined, this group of parameter is substituted into Gabor function formulas, obtains corresponding ginseng Gabor convolutional filtering coefficients under several；The stepped parameter of defined feature extraction block both horizontally and vertically；Each block in traversal curvature enhancing figure under stepped parameter guiding, and using Gabor volumes be obtained ahead of time in each block Product filter factor carries out the Gabor characteristic under convolutional calculation respective frequencies, directioin parameter；Each block is calculated to the Gabor characteristic obtained and is connected in series generation Gabor vector characteristics.
- 4. finger vein characteristic comparison method according to claim 3, which is characterized in thatThe frequency parameter is set as 7；The directioin parameter is set as 16.
- 5. finger vein characteristic comparison method according to claim 3, which is characterized in that the Gabor vectors of described pair of acquisition The step of feature progress dimension-reduction treatment, includes：Each block in curvature enhancing figure by even distribution pattern is selected, filters out Partial Block feature；Down-sampling is carried out according to direction initialization parameter to remaining Block Characteristic, forms the Gabor vector characteristics after new dimensionality reduction.
- 6. finger vein characteristic comparison method according to claim 5, which is characterized in that the Gabor to after dimensionality reduction is sweared The step of measure feature progress binaryzation Gabor Gradient Features extractions, includes：Calculate the gradient of two neighboring coefficient under same frequency parameter, and binaryzation；Calculate the complex gradient value that two coefficient sums of neighbour are corresponded under different frequency parameter, and binaryzation；By sequentially calculating the binaryzation Gabor Grad of adjacent coefficient under single frequency in each frequency parameter, each frequency of recombinant In rate parameter under neighbour's frequency parameter adjacent coefficient sum complex gradient binary value, obtain by block coordinate, frequency parameter, side To the completely new vector characteristic of the binary expression of parameter reference.
- 7. finger vein characteristic comparison method according to claim 1, which is characterized in that described to the completely new of binary expression Vector characteristic carries out aspect ratio pair and includes the step of exporting comparison result：Two width recognition target images are carried out in the completely new vector characteristic after binaryzation with " 0 " in corresponding position, " 1 " occur it is identical Number is counted, and is changed into the similarity value of two width recognition target images under normalization operation；Judge and export comparison result, similarity value is converted to the score value between 0 to the 1 of real number expression, forms final ratio To result score, then by score value compared with predetermined threshold value, same target is then considered more than predetermined threshold value, is otherwise foreign peoples's mesh Mark.
- 8. a kind of finger vein characteristic comparison device, which is characterized in that including：Preprocessing module (100) pre-processes for the finger vein image to input；Gabor characteristic extraction module (200) obtains Gabor for carrying out processing using Gabor functions to pretreated image Vector characteristic；Gabor characteristic dimensionality reduction module (300), for carrying out dimension-reduction treatment to the Gabor vector characteristics of acquisition；Binaryzation Gabor Gradient Features extraction module (400), for carrying out binaryzation to the Gabor vector characteristics after dimensionality reduction Gabor Gradient Features extract：By calculating the gradient of Gabor coefficients at corresponding direction under different frequency parameter, and according to gradient Grad two-value is turned to " 0 ", " 1 " value by the sign symbol of value, and then corresponding value is placed in by block coordinate, frequency, direction In the corresponding completely new vector of component positions of parameter reference, the completely new vector characteristic of binary expression is generated；Output module (500) is compared, for carrying out aspect ratio pair to the completely new vector characteristic of binary expression and exporting comparison knot Fruit.
- 9. a kind of storage medium, the storage medium includes the program of storage, which is characterized in that described program controls institute when running Equipment where stating storage medium performs the finger vein characteristic comparison method as described in claim 1 to 7 is any.
- 10. a kind of processor, the processor is used to run program, which is characterized in that is performed during the processor operation as weighed Profit requires 1 to 7 any finger vein characteristic comparison method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711443496.XA CN108182399B (en) | 2017-12-27 | 2017-12-27 | Finger vein feature comparison method and device, storage medium and processor |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711443496.XA CN108182399B (en) | 2017-12-27 | 2017-12-27 | Finger vein feature comparison method and device, storage medium and processor |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108182399A true CN108182399A (en) | 2018-06-19 |
| CN108182399B CN108182399B (en) | 2020-04-21 |
Family
ID=62547631
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711443496.XA Active CN108182399B (en) | 2017-12-27 | 2017-12-27 | Finger vein feature comparison method and device, storage medium and processor |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108182399B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543580A (en) * | 2018-11-15 | 2019-03-29 | 北京智慧眼科技股份有限公司 | Refer to vena characteristic extracting method, comparison method, storage medium and processor |
| CN109800702A (en) * | 2019-01-16 | 2019-05-24 | 北京智慧眼科技股份有限公司 | Refer to the rapid comparison method and computer-readable storage medium of hand vein recognition |
| CN109903444A (en) * | 2019-03-29 | 2019-06-18 | 深圳市威富视界有限公司 | Refer to vein lock and its control method |
| CN110348289A (en) * | 2019-05-27 | 2019-10-18 | 广州中国科学院先进技术研究所 | A kind of finger vein identification method based on binary map |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090161967A1 (en) * | 2007-12-20 | 2009-06-25 | Jianguo Li | Method and apparatus for obtaining and processing image features |
| US20100260424A1 (en) * | 2009-04-08 | 2010-10-14 | Sony Corporation | Gabor filter, image recognition apparatus and method, program, and recording medium |
| CN104268535A (en) * | 2014-10-10 | 2015-01-07 | 上海海事大学 | Method for extracting features of two-dimensional image |
| CN104504370A (en) * | 2014-12-15 | 2015-04-08 | 广东智冠信息技术股份有限公司 | Finger vein recognition method combining bionic texture feature and linear texture feature |
| CN106022391A (en) * | 2016-05-31 | 2016-10-12 | 哈尔滨工业大学深圳研究生院 | Hyperspectral image characteristic parallel extraction and classification method |
| CN106326827A (en) * | 2015-11-08 | 2017-01-11 | 北京巴塔科技有限公司 | Palm vein recognition system |
-
2017
- 2017-12-27 CN CN201711443496.XA patent/CN108182399B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20090161967A1 (en) * | 2007-12-20 | 2009-06-25 | Jianguo Li | Method and apparatus for obtaining and processing image features |
| US20100260424A1 (en) * | 2009-04-08 | 2010-10-14 | Sony Corporation | Gabor filter, image recognition apparatus and method, program, and recording medium |
| CN104268535A (en) * | 2014-10-10 | 2015-01-07 | 上海海事大学 | Method for extracting features of two-dimensional image |
| CN104504370A (en) * | 2014-12-15 | 2015-04-08 | 广东智冠信息技术股份有限公司 | Finger vein recognition method combining bionic texture feature and linear texture feature |
| CN106326827A (en) * | 2015-11-08 | 2017-01-11 | 北京巴塔科技有限公司 | Palm vein recognition system |
| CN106022391A (en) * | 2016-05-31 | 2016-10-12 | 哈尔滨工业大学深圳研究生院 | Hyperspectral image characteristic parallel extraction and classification method |
Non-Patent Citations (4)
| Title |
|---|
| 刘娟 等: "Gabor多方向特征融合与分块统计的表情识别", 《电子测量与仪器学报》 * |
| 张文超 等: "基于局部Gabor变化直方图序列的人脸描述与识别", 《软件学报》 * |
| 胡敏 等: "基于梯度Gabor直方图特征的表情识别方法", 《计算机辅助设计与图形学学报》 * |
| 邵虹 等: "基于集成Gabor特征的步态识别方法", 《电子测量与仪器学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543580A (en) * | 2018-11-15 | 2019-03-29 | 北京智慧眼科技股份有限公司 | Refer to vena characteristic extracting method, comparison method, storage medium and processor |
| CN109800702A (en) * | 2019-01-16 | 2019-05-24 | 北京智慧眼科技股份有限公司 | Refer to the rapid comparison method and computer-readable storage medium of hand vein recognition |
| CN109800702B (en) * | 2019-01-16 | 2021-01-26 | 智慧眼科技股份有限公司 | Quick comparison method for finger vein identification and computer readable storage medium |
| CN109903444A (en) * | 2019-03-29 | 2019-06-18 | 深圳市威富视界有限公司 | Refer to vein lock and its control method |
| CN110348289A (en) * | 2019-05-27 | 2019-10-18 | 广州中国科学院先进技术研究所 | A kind of finger vein identification method based on binary map |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108182399B (en) | 2020-04-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Yuan et al. | Fingerprint liveness detection using an improved CNN with image scale equalization | |
| Wong et al. | Multi-task CNN for restoring corrupted fingerprint images | |
| CN108182399A (en) | Refer to vein characteristic comparison method, apparatus, storage medium and processor | |
| Zhang et al. | Finger vein image enhancement based on guided tri-Gaussian filters | |
| CN110390282A (en) | A kind of finger vein identification method and system based on the loss of cosine center | |
| CN110163180A (en) | Mental imagery eeg data classification method and system | |
| Farokhian et al. | Automatic parameters selection of Gabor filters with the imperialism competitive algorithm with application to retinal vessel segmentation | |
| CN105869166B (en) | A kind of human motion recognition method and system based on binocular vision | |
| CN107292250A (en) | A kind of gait recognition method based on deep neural network | |
| CN106022218A (en) | Palm print palm vein image layer fusion method based on wavelet transformation and Gabor filter | |
| Khan et al. | A spatial domain scar removal strategy for fingerprint image enhancement | |
| SG190730A1 (en) | Method and an apparatus for determining vein patterns from a colour image | |
| CN111000555B (en) | Training data generation method, automatic recognition model modeling method and automatic recognition method for epileptic electroencephalogram signals | |
| Salazar-Jurado et al. | Towards the generation of synthetic images of palm vein patterns: A review | |
| Meng et al. | A framework for retinal vasculature segmentation based on matched filters | |
| Elalfi et al. | Artificial neural networks in medical images for diagnosis heart valve diseases | |
| Guo et al. | Multifeature extracting CNN with concatenation for image denoising | |
| Albadarneh et al. | Iris recognition system for secure authentication based on texture and shape features | |
| CN110334597A (en) | Finger vein identification method and system based on Gabor neural network | |
| CN104200201B (en) | A kind of coding method and system applied to iris recognition | |
| Gaikwad et al. | Multi-modal biometric system using palm print and palm vein features | |
| CN115953822B (en) | Human face video fake identification method and device based on rPPG physiological signals | |
| CN111968087A (en) | Plant disease area detection method | |
| Tallapragada et al. | Iris recognition based on combined feature of GLCM and wavelet transform | |
| Choras | Ocular biometrics-automatic feature extraction from eye images |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| 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: Finger vein feature comparison method, device, storage medium and processor 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 |