CN110427826A - A kind of hand identification method, apparatus, electronic equipment and storage medium - Google Patents
A kind of hand identification method, apparatus, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN110427826A CN110427826A CN201910598360.9A CN201910598360A CN110427826A CN 110427826 A CN110427826 A CN 110427826A CN 201910598360 A CN201910598360 A CN 201910598360A CN 110427826 A CN110427826 A CN 110427826A
- Authority
- CN
- China
- Prior art keywords
- palm
- point
- finger
- feature
- finger web
- 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
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1347—Preprocessing; Feature extraction
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/12—Fingerprints or palmprints
- G06V40/1365—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a kind of hand identification method, apparatus, electronic equipment and storage mediums, which comprises obtains the infrared palm image of palm to be identified, identifies the centre of the palm point in the infrared palm image;According to the offset of setting, at least one neighborhood point of the centre of the palm point is determined;And feature identification region is determined centered on the centre of the palm point and each neighborhood point respectively;According to the corresponding palm feature of each palm saved in the palm feature of each feature identification region and palm library, each feature identification region matched candidate's palm in palm library is determined;According to the matching degree and frequency of occurrence of each candidate palm and character pair identification region, the matched target palm of the palm to be identified is determined.To improve the accuracy of hand identification.
Description
Technical field
The present invention relates to technical field of image processing more particularly to a kind of hand identification method, apparatus, electronic equipment and deposit
Storage media.
Background technique
Biometrics identification technology is the intrinsic physiological characteristic or behavioural characteristic using people, carries out person identification
Technology.Biometrics identification technology is easy to use, everyone is to identify body using intrinsic self and unique biological characteristic
Part information, compared with the mode of traditional identification, it does not need setting password, is not required to carry key, safety card yet
And other items, it is capable of providing that safer, reliable and efficiently identity identifies and authentication result.Currently, biometrics identification technology
It has obtained people more and more to pay attention to, the field of application is also more and more, such as gate inhibition, payment field.Biological characteristic is known
The other common feature of technology includes fingerprint, face, iris etc..
Along with the continuous development of biometrics identification technology, the identifying schemes such as fingerprint, face are no longer satisfied user
Demand, and palm with it includes the far super fingerprint of biological characteristic it is receive more and more attention, however, existing hand identification
Scheme, the palm feature for being usually based only upon a certain feature identification region of palm identified, but palm when due to palm acquisition
Position it is uncertain, lead to the feature identification region inaccuracy determined when hand identification, the precision of hand identification is not high.
Summary of the invention
The present invention provides a kind of hand identification method, apparatus, electronic equipment and storage medium, to solve in the prior art
There is a problem of that hand identification precision is not high.
In a first aspect, the invention discloses a kind of hand identification methods, which comprises
The infrared palm image of palm to be identified is obtained, identifies the centre of the palm point in the infrared palm image;
According to the offset of setting, at least one neighborhood point of the centre of the palm point is determined;And respectively with the centre of the palm point and
Centered on each neighborhood point, feature identification region is determined;
According to the corresponding palm feature of each palm saved in the palm feature of each feature identification region and palm library,
Determine each feature identification region matched candidate's palm in palm library;
According to the matching degree and frequency of occurrence of each candidate palm and character pair identification region, the hand to be identified is determined
Slap matched target palm.
In an optional design, before the centre of the palm point in the identification infrared palm image, the method is also
Include:
The first coordinate of the first the finger web and the second coordinate of the second the finger web in the infrared palm image are identified, wherein described
The finger web of first the finger web between little finger and the third finger, the finger web of second the finger web between index finger and middle finger;
Straight line is determined according to first coordinate and the second coordinate, and the horizontal axis for obtaining the straight line and image coordinate system is constituted
The target power of angle;
By target power described in the infrared palm image rotation, keep the horizontal axis of the straight line and described image coordinate system flat
Row.
In an optional design, the centre of the palm point in the identification infrared palm image includes:
According to x=(x1+x2The He of)/2Determine the centre of the palm point in the infrared palm image, wherein x is
The abscissa of centre of the palm point, ordinate, the x that y is centre of the palm point1Abscissa, x for the first the finger web2Abscissa, y for the second the finger webn
For the ordinate of the first the finger web or the ordinate of the second the finger web.
In an optional design, determine that the offset of the setting includes:
Product by the distance between first the finger web and second the finger web with the deviation ratio of setting, as setting
Offset.
It is described respectively centered on the centre of the palm point and each neighborhood point in an optional design, determine that feature is known
Other region includes:
For side length centered on the centre of the palm point, with the distance between first the finger web and second the finger web, determine
Fisrt feature identification region;
Respectively centered on each neighborhood point, with the weight coefficient of setting and first the finger web and second the finger web it
Between distance product be side length, determine second feature identification region.
In an optional design, the first coordinate and second of the first the finger web in the identification infrared palm image
Second coordinate of the finger web includes:
The binary image for determining the infrared palm image extracts palm to be identified described in the binary image
Each profile point;
For each profile point, the profile point two profile points adjacent with the profile point respectively constitute two are judged
Whether the product of the slope of straight line is less than zero;If so, by the profile point two profile points adjacent with the profile point point
The sum of the absolute value of the slope for two straight lines not constituted, as the score value of the profile point, and using the profile point as time
Reconnaissance is added in Candidate Set;
The highest candidate point of score value is successively chosen in the Candidate Set in remaining candidate point as characteristic point and is added to spy
In collection, and the highest candidate point of score value described in the Candidate Set and being less than with the score value highest candidate point distance is set
Determine the candidate point deletion of threshold value;
The smallest characteristic point of ordinate in the feature set is deleted, and chooses in the feature set distance in residue character point
As the first the finger web and the second the finger web, the first coordinate and described second for identifying first the finger web refer to maximum two characteristic points
Second coordinate of web.
It is described according to being saved in the palm feature of each feature identification region and palm library in the optional design
The corresponding palm feature of each palm determines that each feature identification region matched candidate's palm in palm library includes:
Real Gabor wavelet transformation is done for each feature identification region, extracts the Gabor characteristic of the feature identification region
Figure, and the local binary patterns LBP feature vector of the Gabor characteristic figure is extracted, according to the LBP feature vector and palm library
The corresponding LBP feature vector of each palm of middle preservation determines the feature identification region matched candidate's hand in palm library
The palm.
Second aspect, the invention discloses a kind of hand identification device, described device includes:
Identification module is obtained, for obtaining the infrared palm image of palm to be identified, is identified in the infrared palm image
Centre of the palm point;
First determining module determines at least one neighborhood point of the centre of the palm point for the offset according to setting;And point
Not centered on the centre of the palm point and each neighborhood point, feature identification region is determined;
Second determining module, for according to each hand saved in the palm feature of each feature identification region and palm library
Corresponding palm feature is slapped, determines each feature identification region matched candidate's palm in palm library;
Third determining module, for according to the matching degree of each candidate palm and character pair identification region and occurrence out
Number, determines the matched target palm of the palm to be identified.
In an optional design, described device further include:
Correction module, for identification in the infrared palm image the first coordinate of the first the finger web and the second the finger web second
Coordinate, wherein the finger web of first the finger web between little finger and the third finger, second the finger web is between index finger and middle finger
The finger web;Straight line is determined according to first coordinate and the second coordinate, and the horizontal axis for obtaining the straight line and image coordinate system is constituted
The target power of angle;By target power described in the infrared palm image rotation, make the straight line and described image coordinate system
Horizontal axis it is parallel.
In an optional design, the acquisition identification module is specifically used for according to x=(x1+x2The He of)/2Determine the centre of the palm point in the infrared palm image, wherein x is the abscissa of centre of the palm point, y is centre of the palm point
Ordinate, x1Abscissa, x for the first the finger web2Abscissa, y for the second the finger webnRefer to for the ordinate of the first the finger web or second
The ordinate of web.
In an optional design, first determining module is also used to refer to first the finger web and described second
The product of the distance between web and the deviation ratio of setting, the offset as setting.
In an optional design, first determining module is specifically used for centered on the centre of the palm point, with described
The distance between first the finger web and second the finger web are side length, determine fisrt feature identification region;Respectively with each neighborhood point
Centered on, using the product of the weight coefficient and the distance between first the finger web and second the finger web that set as side length, determine
Second feature identification region.
In an optional design, the correction module, specifically for the binaryzation of the determination infrared palm image
Image extracts each profile point of palm to be identified described in the binary image;For each profile point, the wheel is judged
Whether exterior feature puts the product of the slope for two straight lines that two profile points adjacent with the profile point respectively constitute less than zero;If
It is, the absolute value of the slope for two straight lines that the profile point two profile points adjacent with the profile point are respectively constituted
Be added in Candidate Set as the score value of the profile point, and using the profile point as candidate point;Successively choose the time
The highest candidate point of score value is added in feature set as characteristic point in remaining candidate point in selected works, and will be in the Candidate Set
The highest candidate point of the score value and the candidate point deletion for being less than given threshold with the highest candidate point distance of the score value;It deletes
The smallest characteristic point of ordinate in the feature set, and choose in the feature set maximum two spies of distance in residue character point
Sign point is used as the first the finger web and the second the finger web, identifies that the first coordinate of first the finger web and the second of second the finger web are sat
Mark.
In an optional design, second determining module is small specifically for doing for each feature identification region
Wave Gabor transformation, extracts the Gabor characteristic figure of the feature identification region, and extracts the local binary of the Gabor characteristic figure
Mode LBP feature vector, according to the corresponding LBP feature vector of each palm saved in the LBP feature vector and palm library,
Determine the feature identification region matched candidate's palm in palm library.
The third aspect, the invention discloses a kind of electronic equipment, comprising: memory and processor;
The processor executes any of above-mentioned first aspect or first aspect for reading the program in memory
Method described in optional design.
Fourth aspect, the invention discloses a kind of computer readable storage medium, being stored with can be executed by electronic equipment
Computer program, when described program is run on the electronic equipment, so that the electronic equipment executes above-mentioned first party
Method described in any optional design of face or first aspect.
The present invention has the beneficial effect that:
Due in embodiments of the present invention, according to the offset of setting, determine centre of the palm point in infrared palm image extremely
A few neighborhood point;And respectively centered on centre of the palm point and each neighborhood point, feature identification region and the identification of each feature are determined
Region matched candidate's palm in palm library, and according to the matching degree of each candidate palm and character pair identification region and go out
Occurrence number determines the matched target palm of the palm to be identified, and the position for avoiding palm when due to palm acquisition is uncertain,
The problem of leading to the feature identification region inaccuracy determined when hand identification, influencing the recognition result of palm, improve palm
Accuracy of identification.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
It obtains other drawings based on these drawings.
Fig. 1 is a kind of hand identification method schematic diagram provided in an embodiment of the present invention;
Fig. 2 is a kind of image capture device schematic diagram provided in an embodiment of the present invention;
Fig. 3 is a kind of one of infrared palm image provided in an embodiment of the present invention;
Fig. 4 is a kind of binary image schematic diagram provided in an embodiment of the present invention;
Fig. 5 is a kind of 4 neighborhood point schematic diagram provided in an embodiment of the present invention;
Fig. 6 is a kind of 8 neighborhood point schematic diagram provided in an embodiment of the present invention;
Fig. 7 A provides the two of a kind of infrared palm image for the embodiment of the present invention;
Fig. 7 B provides the three of a kind of infrared palm image for the embodiment of the present invention;
Fig. 8 A provides candidate point schematic diagram in a kind of infrared palm image for the embodiment of the present invention;
Fig. 8 B provides characteristic point schematic diagram in a kind of infrared palm image for the embodiment of the present invention;
Fig. 9 provides a kind of hand identification apparatus structure schematic diagram for the embodiment of the present invention;
Figure 10 is a kind of electronic equipment structural schematic diagram provided in an embodiment of the present invention.
Specific embodiment
To make the objectives, technical solutions, and advantages of the present invention clearer, make below in conjunction with the attached drawing present invention into one
Step ground detailed description, it is clear that described embodiment is only a part of the embodiments of the present invention, rather than whole implementation
Example.Based on the embodiments of the present invention, obtained by those of ordinary skill in the art without making creative efforts
Every other embodiment, shall fall within the protection scope of the present invention.
Embodiment 1:
Fig. 1 is a kind of hand identification method schematic diagram provided in an embodiment of the present invention, this method comprises:
S101: obtaining the infrared palm image of palm to be identified, identifies the centre of the palm point in the infrared palm image.
The vein and palmmprint of palm all have uniqueness and stability, may be used for the biological characteristic of identification.And
And the vein of palm is hidden under epidermis, is in net distribution, structure is complicated is difficult to be replicated, and needs to clap under near infrared light
It takes the photograph, these features make the vein of palm become a kind of biological characteristic that safety is high, and whether can become is living body
Foundation, the present invention is directed to based on palm vein and palmmprint realize hand identification.
Hand identification method provided in an embodiment of the present invention be applied to electronic equipment, the electronic equipment can be vending machine,
The equipment such as gate, PC (PC).Electronic equipment can be obtained by the image capture device being arranged in electronic equipment wait know
The infrared palm image of other palm, can also be by the way that there are image capture device acquisitions that is wired or being wirelessly connected with electronic equipment
The infrared palm image of palm to be identified.In addition, sufficiently obtaining has hand to be identified in order to guarantee in the infrared palm image obtained
The vein and palm print characteristics of the palm, personnel to be identified are when image capture device obtains infrared palm image, by palm to be identified
Facies palmaris face image capture device, stretchs out the five fingers naturally, sufficiently obtains in the infrared palm image obtained so as to image capture device
Take the vein and palm print characteristics of palm to be identified.
Preferably, can also be set by shown in Fig. 2, being provided with the Image Acquisition of raised A and protrusion B for separation finger
The standby infrared palm image for obtaining palm to be identified has palm to be identified to guarantee sufficiently to obtain in the infrared palm image obtained
Vein and palm print characteristics.
In embodiments of the present invention, electronic equipment can identify infrared hand according to the binary image of infrared palm image
Slap the centre of the palm point in image.Such as: the infrared palm image that electronic equipment obtains is as shown in figure 3, electronic equipment can be by most
The methods of big Ostu method (otsu), determines the binary image of infrared palm image, as shown in figure 4, in binary image
Palm area is white, other regions are black.Electronic equipment can be chosen in binary image and can determine in palm area
Maximum circle central point be infrared palm image in centre of the palm point.
It of courses, can also be sat according to the second of the first coordinate of the first the finger web in infrared palm image and the second the finger web
Mark, identifies the centre of the palm point in infrared palm image, in embodiments of the present invention, can be by the finger web between little finger and the third finger
It, can also be by the finger between little finger and the third finger as the finger web between the first the finger web, index finger and middle finger as the second the finger web
Web is as the finger web between the second the finger web, index finger and middle finger as the first the finger web.Below using the first the finger web as little finger and unknown
The finger web between finger, the second the finger web are illustrated for the finger web between index finger and middle finger, and electronic equipment identifies infrared palm
Second coordinate of the first coordinate of the first the finger web and the second the finger web in image, and according to following recognition methods, identify infrared palm
Centre of the palm point in image.
It is described to identify that the centre of the palm point in the infrared palm image includes:
According to x=(x1+x2The He of)/2Determine the centre of the palm point in the infrared palm image, wherein x is
The abscissa of centre of the palm point, ordinate, the x that y is centre of the palm point1Abscissa, x for the first the finger web2Abscissa, y for the second the finger webn
For the ordinate of the first the finger web or the ordinate of the second the finger web.
S102: according to the offset of setting, at least one neighborhood point of the centre of the palm point is determined;And respectively with the centre of the palm
Centered on point and each neighborhood point, feature identification region is determined.
In embodiments of the present invention, it is set with offset, the offset of the setting can be fixed value such as 1mm, 2mm
Deng, it can also be determining according to the size of the infrared palm image of acquisition, the size of the infrared palm image such as obtained is 152mm*
102mm, wherein vertical (Y) axis of height " 152mm " correspondence image coordinate system, the cross (X) of width " 102mm " correspondence image coordinate system
Axis, 1% offset as setting of the width for the infrared palm image that can be will acquire.In addition, feature identification region can also
To be known as the area-of-interest (region of interest, ROI) handled by electronic equipment.
Because the hand size of different personnel to be identified has differences, in order to guarantee the accuracy of offset setting, in this hair
In bright embodiment, determine that the offset of the setting includes:
Product by the distance between first the finger web and second the finger web with the deviation ratio of setting, as setting
Offset.
Preferably, in embodiments of the present invention, for the deviation ratio set as 0.01,0.02 etc., electronic equipment can basis
First coordinate of the first the finger web and the second coordinate of the second the finger web determine the distance between the first the finger web and the second the finger web, and will
The product of the distance between first the finger web and the second the finger web and the deviation ratio of setting, the offset as setting.
Specifically, electronic equipment, centered on the point of the centre of the palm, determination is put centered on the point of the centre of the palm in infrared palm image
At least one neighborhood point, preferably, can determine 4 neighborhoods as shown in Figure 5 according to the coordinate of centre of the palm point and the offset of setting
Point, wherein o is centre of the palm point, 4 neighborhood points that o1, o2, o3, o4 are centre of the palm point;It can also determine 8 neighborhood point as shown in FIG. 6,
Wherein o is centre of the palm point, 8 neighborhood points that o1, o2, o3, o4, o5, o6, o7, o8 are centre of the palm point.
In addition, in embodiments of the present invention, feature identification region can be square, or it is round, it is set in electronics
The side length or radius that feature identification region is preserved in standby, the side length for such as preserving feature identification region is 40mm, electronic equipment
Feature cog region can be determined with the side length of the feature identification region of preservation respectively centered on centre of the palm point and each neighborhood point
Domain.
Preferably, because the hand size of different personnel to be identified has differences, in order to guarantee what feature identification region determined
Accuracy, and then hand identification precision is improved, it is described respectively centered on the centre of the palm point and each neighborhood point, determine that feature is known
Other region includes:
For side length centered on the centre of the palm point, with the distance between first the finger web and second the finger web, determine
Fisrt feature identification region;
Respectively centered on each neighborhood point, with the weight coefficient of setting and first the finger web and second the finger web it
Between distance product be side length, determine second feature identification region.
In embodiments of the present invention, it can be set with a weight coefficient, multiple weight coefficients can be set, also with o
For centre of the palm point, o1, o2, o3, o4, o5, o6, o7, o8 be centre of the palm point 8 neighborhood points, the first the finger web and second the finger web it
Between distance be (size), the weight coefficient set is for 0.9,1.1, electronic equipment, the point centered on o, size is side length
Determination has feature identification region 1, and respectively centered on o1, o2, o3, o4, o5, o6, o7, o8,0.9size is that side length determination has spy
Levy identification region 2, feature identification region 3 ... feature identification region 9 is respectively with o1, o2, o3, o4, o5, o6, o7, o8
The heart, 1.1size be side length determine have feature identification region 10, feature identification region 11 ... feature identification region 17, altogether determination have
17 feature identification regions.
S103: according to the corresponding palm of each palm saved in the palm feature of each feature identification region and palm library
Feature determines each feature identification region matched candidate's palm in palm library.
In embodiments of the present invention, it is also previously provided with palm library, typing has the hand of the palm of a large amount of personnel in palm library
Feature is slapped, wherein the palm feature of the palm to be identified of personnel to be identified is entered into palm library in advance.
Specifically, electronic equipment is according to the hand saved in the palm feature of each feature identification region and palm library
Corresponding palm feature is slapped, each feature identification region matched candidate's palm in palm library is determined, preferably, in the present invention
In embodiment, determining feature identification region in palm library it is matched candidate palm, be palm library in this feature cog region
The highest palm of palm characteristic matching degree in domain.
By electronic equipment determine have features described above identification region 1, feature identification region 2 ... for feature identification region 17,
Electronic equipment is according to the corresponding palm feature of each palm saved in the palm feature of feature identification region 1 and palm library, really
Determine the matched candidate's palm in palm library of feature identification region 1;According in the palm feature and palm library of feature identification region 2
The corresponding palm feature of each palm saved determines the matched candidate's palm in palm library of feature identification region 2;... according to
The corresponding palm feature of each palm saved in the palm feature of feature identification region 17 and palm library, determines feature cog region
The matched candidate's palm in palm library of domain 17.
S104: according to the matching degree and frequency of occurrence of each candidate palm and character pair identification region, determine described in
Identify the matched target palm of palm.
Specifically, electronic equipment can in determining candidate palm, according to corresponding identification region matching degree by height to
Low sequence chooses the matched candidate palm of feature identification region of setting quantity, and the candidate hand of the setting quantity in selection
In the palm, the highest candidate palm of frequency of occurrence is chosen as the matched target palm of palm to be identified.And then it can be according to target
The identity of the corresponding personnel of palm determines the identity of the corresponding personnel to be identified of palm to be identified.
Such as: the matched candidate's palm in palm library of feature identification region 1 is palm 5, matching degree 83.5%;Feature
The matched candidate's palm in palm library of identification region 2 is palm 6, matching degree 69.3%;Feature identification region 3 is in palm library
In matched candidate palm be palm 5, matching degree 76.2%;... the matched candidate's hand in palm library of feature identification region 17
The palm is palm 8, matching degree 66%;Quantity is set as 3, electronic equipment according to corresponding identification region matching degree from high to low
Sequentially, the matched palm 5 of selected characteristic identification region 1, the matched palm 5 of feature identification region 3, feature identification region 11 match
Palm 6, palm 5 occur number highest, by palm 5 be used as the matched target palm of palm to be identified.
It of courses, electronic equipment can also choose the Mean match degree highest in candidate palm with character pair identification region
Candidate palm as the matched target palm of palm to be identified, can also choose in candidate palm and be matched with feature identification region
The most candidate palm of frequency of occurrence is as the matched target palm of palm to be identified.
Due in embodiments of the present invention, according to the offset of setting, determine centre of the palm point in infrared palm image extremely
A few neighborhood point;And respectively centered on centre of the palm point and each neighborhood point, feature identification region and the identification of each feature are determined
Region matched candidate's palm in palm library, and according to the matching degree of each candidate palm and character pair identification region and go out
Occurrence number determines the matched target palm of the palm to be identified, and the position for avoiding palm when due to palm acquisition is uncertain,
The problem of leading to the feature identification region inaccuracy determined when hand identification, influencing the recognition result of palm, improve palm
Accuracy of identification.
Embodiment 2:
Direction in order to guarantee the feature identification region extracted is consistent, further increases the accuracy of hand identification, In
On the basis of above-described embodiment, in embodiments of the present invention, before the centre of the palm point in the identification infrared palm image, institute
State method further include:
The first coordinate of the first the finger web and the second coordinate of the second the finger web in the infrared palm image are identified, wherein described
The finger web of first the finger web between little finger and the third finger, the finger web of second the finger web between index finger and middle finger;
Straight line is determined according to first coordinate and the second coordinate, and the horizontal axis for obtaining the straight line and image coordinate system is constituted
The target power of angle;
By target power described in the infrared palm image rotation, keep the horizontal axis of the straight line and described image coordinate system flat
Row.
As shown in Figure 7 A, it after electronic equipment obtains the infrared palm image of palm to be identified, identifies in infrared palm image
First coordinate of the first the finger web (A) and the second coordinate of the second the finger web (B), and first is determined according to the first coordinate and the second coordinate
The horizontal axis of straight line and image coordinate system that the finger web (A) and the second the finger web (B) are constituted constitutes the target power of angle (θ), will be infrared
Target power described in palm image rotation, the straight line and image for constituting postrotational first the finger web (A) and the second the finger web (B) are sat
The horizontal axis for marking system is parallel, as shown in Figure 7 B to the infrared palm image after infrared palm image rotation as shown in Figure 7 A.At this
It is that infrared palm image is subjected to center rotation, i.e., with red described in Fig. 7 A by infrared palm image rotation in inventive embodiments
The central point (O) of outer palm image is that rotation center is rotated.
Preferably, formula can be passed through in embodiments of the present inventionWith θ=
arccos(cosθ) * 180/ π determines that the horizontal axis of straight line and image coordinate system that the first the finger web and the second the finger web are constituted constitutes angle
Target power, θ be angle target power, xaAbscissa, x for the first the finger webbAbscissa, y for the second the finger webaIt is
Ordinate, the y of one the finger webbFor the ordinate of the second the finger web.
Embodiment 3:
In order to guarantee the accuracy of the first coordinate of the first determining the finger web and the second coordinate of the second the finger web, above-mentioned each
On the basis of embodiment, in embodiments of the present invention, the first coordinate of the first the finger web in the identification infrared palm image
The second coordinate with the second the finger web includes:
The binary image for determining the infrared palm image extracts palm to be identified described in the binary image
Each profile point;
For each profile point, the profile point two profile points adjacent with the profile point respectively constitute two are judged
Whether the product of the slope of straight line is less than zero;If so, by the profile point two profile points adjacent with the profile point point
The sum of the absolute value of the slope for two straight lines not constituted, as the score value of the profile point, and using the profile point as time
Reconnaissance is added in Candidate Set;
The highest candidate point of score value is successively chosen in the Candidate Set in remaining candidate point as characteristic point and is added to spy
In collection, and the highest candidate point of score value described in the Candidate Set and being less than with the score value highest candidate point distance is set
Determine the candidate point deletion of threshold value;
The smallest characteristic point of ordinate in the feature set is deleted, and chooses in the feature set distance in residue character point
As the first the finger web and the second the finger web, the first coordinate and described second for identifying first the finger web refer to maximum two characteristic points
Second coordinate of web.
Specifically, electronic equipment can determine infrared palm image by the methods of maximum variance between clusters (otsu)
Binary image is illustrated in figure 4 the binary image for the infrared palm image as shown in Figure 3 that electronic equipment determines, two-value
Palm area is white in change image, other regions are black.Wherein the value of palm area is 1 or 255, and the value in other regions is
0, electronic equipment identify binary image in palm profile point, and be directed to each profile point, judge the profile point with it is described
Whether the product of the slope for two straight lines that two adjacent profile points of profile point respectively constitute is less than zero;If so, illustrating palm
Profile the profile point out in the presence of turnover, the profile point may be the first the finger web or the second the finger web, by the profile point
The absolute value of the slope for two straight lines that two profile points adjacent with the profile point respectively constitute and, as the profile
The score value of point, and be added in Candidate Set using the profile point as candidate point, in embodiments of the present invention, according to infrared palm
The profile point of the binary image identification palm of image is the prior art, is no longer repeated.
As shown in Figure 8 A, the position of a certain the finger web is it is possible that multiple candidate points, electronic equipment can be using non-very big
Value inhibits (Non-maximum suppression, NMS) algorithm, removes the candidate point of non-the finger web in Candidate Set, specifically, step
Rapid 1: electronic equipment chooses in Candidate Set in remaining candidate point the highest candidate point of score value as characteristic point and is added to feature set
In, and it is less than setting threshold by the highest candidate point of score value described in the Candidate Set and with the highest candidate point distance of the score value
The candidate point deletion of value;Step 2: electronic equipment judge in Candidate Set whether be it is empty, i.e., whether there is also candidate points, if not,
Return step 1, if it is terminates.In embodiments of the present invention, given threshold is less than the distance between palm any two the finger web.
The distribution of characteristic point is as shown in Figure 8 B in the feature set obtained based on Fig. 8 A, specifically, ordinate is most in feature set
Small characteristic point is the characteristic point of the finger web between corresponding thumb and index finger, and electronic equipment deletes feature and middle ordinate is minimum
Characteristic point, delete the smallest characteristic point of ordinate after, maximum two characteristic points of distance are little finger and nothing in feature set
Name refer between the finger web (the first the finger web) and index finger and middle finger between the finger web (the second the finger web), electronic equipment chooses the feature
Maximum two characteristic points of distance are as the first the finger web and the second the finger web in concentration residue character point, and identify first the finger web
The first coordinate and second the finger web the second coordinate.Preferably, electronic equipment can be maximum according to the distance of the selection
Two characteristic points respectively at a distance from the smallest characteristic point of the ordinate of deletion, choose in described two characteristic points with deletion
The finger web (second the finger web) of the small characteristic point of the distance of the smallest characteristic point of ordinate between index finger and middle finger, it is vertical with deletion
The finger web (first the finger web) of the big characteristic point of the distance of the smallest characteristic point of coordinate between little finger and the third finger.
Embodiment 4:
It is in embodiments of the present invention, described on the basis of the various embodiments described above in order to improve the accuracy of hand identification
According to the corresponding palm feature of each palm saved in the palm feature of each feature identification region and palm library, determine each
Feature identification region in palm library it is matched candidate palm include:
Small echo (Gabor) transformation is done for each feature identification region, extracts the Gabor characteristic of the feature identification region
Figure, and local binary patterns (Local Binary Pattern, LBP) feature vector of the Gabor characteristic figure is extracted, according to
The corresponding LBP feature vector of each palm saved in the LBP feature vector and palm library, determines each feature identification region
Matched candidate's palm in palm library.
Gabor transformation can extract relevant feature on different scale, different directions, and simple in human visual system
The visual stimulus response of cell is closely similar.There is good spy in terms of the local space and frequency-domain information for extracting target
Property.Gabor transformation is capable of providing good direction selection and scale selection characteristic for the edge sensitive of image, and for
Illumination variation is insensitive, can be good at the transformation for adapting to illumination.LBP is a kind of calculation for describing image local textural characteristics
Son;It has the advantages that rotational invariance and gray scale invariance etc. are significant.
Specifically, electronic equipment does Gabor transformation for each feature identification region, the feature identification region is extracted
Gabor characteristic figure, and extract the LBP feature vector of the Gabor characteristic figure.Such as electronic equipment is to each feature cog region
Domain uses the core of Gabor transformation for 5*5, carries out the Gabor transformation in 10 directions, determines by the feature identification region 10
The Gabor characteristic figure that the Gabor transformation characteristic spectrum in direction is spliced into.And it is special according to the LBP that the Gabor characteristic figure extracts
The corresponding LBP feature vector of each palm saved in sign vector sum palm library, determines in the LBP feature vector and palm library
The matching degree of the corresponding LBP feature vector of each palm saved, selection and the highest palm of matching degree in palm library, as institute
State feature identification region matched candidate's palm in palm library.In embodiments of the present invention, Gabor is done to feature identification region
Transformation, extract feature identification region Gabor characteristic figure be the prior art, calculate feature identification region LBP feature vector and
The matching degree of the corresponding LBP feature vector of each palm saved in palm library can use the methods of cosine similarity to realize,
No longer repeated.
Embodiment 5:
Fig. 9 is a kind of hand identification apparatus structure schematic diagram provided in an embodiment of the present invention, which includes:
Identification module 91 is obtained, for obtaining the infrared palm image of palm to be identified, identifies the infrared palm image
In centre of the palm point;
First determining module 92 determines at least one neighborhood point of the centre of the palm point for the offset according to setting;And
Respectively centered on the centre of the palm point and each neighborhood point, feature identification region is determined;
Second determining module 93, for according to each of being saved in the palm feature of each feature identification region and palm library
The corresponding palm feature of palm determines each feature identification region matched candidate's palm in palm library;
Third determining module 94, for according to the matching degree of each candidate palm and character pair identification region and occurrence out
Number, determines the matched target palm of the palm to be identified.
Preferably, described device further include:
Correction module 95, for identification in the infrared palm image the first coordinate of the first the finger web and the second the finger web
Two coordinates, wherein the finger web of first the finger web between little finger and the third finger, second the finger web be index finger and middle finger it
Between the finger web;Straight line is determined according to first coordinate and the second coordinate, obtains the horizontal axis structure of the straight line and image coordinate system
At the target power of angle;By target power described in the infrared palm image rotation, make the straight line and described image coordinate
The horizontal axis of system is parallel.
Preferably, the acquisition identification module 91 is specifically used for according to x=(x1+x2The He of)/2It determines
Centre of the palm point in the infrared palm image, wherein x is the abscissa of centre of the palm point, y is the ordinate of centre of the palm point, x1Refer to for first
Abscissa, the x of web2Abscissa, y for the second the finger webnFor the ordinate of the first the finger web or the ordinate of the second the finger web.
Preferably, first determining module 92, be also used to by between first the finger web and second the finger web away from
Product from the deviation ratio with setting, the offset as setting.
Preferably, first determining module 92, be specifically used for centered on the centre of the palm point, with first the finger web and
The distance between described second the finger web is side length, determines fisrt feature identification region;Respectively centered on each neighborhood point, to set
The product of fixed weight coefficient and the distance between first the finger web and second the finger web is side length, determines that second feature identifies
Region.
Preferably, the correction module 95 extracts institute specifically for the binary image of the determination infrared palm image
State each profile point of palm to be identified described in binary image;For each profile point, judge the profile point with it is described
Whether the product of the slope for two straight lines that two adjacent profile points of profile point respectively constitute is less than zero;If so, by the wheel
Exterior feature put the absolute value of the slope for two straight lines that two profile points adjacent with the profile point respectively constitute and, as described
The score value of profile point, and be added in Candidate Set using the profile point as candidate point;It successively chooses remaining in the Candidate Set
Candidate point in the highest candidate point of score value be added in feature set as characteristic point, and most by score value described in the Candidate Set
High candidate point and the candidate point deletion with the highest candidate point distance of the score value less than given threshold;Delete the feature set
The middle the smallest characteristic point of ordinate, and maximum two characteristic points of distance are chosen in the feature set in residue character point as
One the finger web and the second the finger web identify the first coordinate of first the finger web and the second coordinate of second the finger web.
Preferably, second determining module 93, specifically for doing real Gabor wavelet change for each feature identification region
It changes, extracts the Gabor characteristic figure of the feature identification region, and the local binary patterns LBP for extracting the Gabor characteristic figure is special
Levy vector, according to the corresponding LBP feature vector of each palm saved in the LBP feature vector and palm library, determine described in
Feature identification region matched candidate's palm in palm library.
Embodiment 6:
Based on the same inventive concept, a kind of electronic equipment is additionally provided in the embodiment of the present invention, due to above-mentioned electronic equipment
The principle solved the problems, such as is similar to hand identification method, therefore the implementation of above-mentioned electronic equipment may refer to the implementation of method, weight
Multiple place repeats no more.
It as shown in Figure 10, is the structural schematic diagram of electronic equipment provided in an embodiment of the present invention, wherein in Figure 10, always
Line architecture may include the bus and bridge of any number of interconnection, specifically have processor 11 represent one or more processors and
The various circuits for the memory that memory 12 represents link together.Bus architecture can also will such as peripheral equipment, voltage-stablizer
It is linked together with various other circuits of management circuit or the like, these are all it is known in the art, therefore, herein
No longer it is described further.Bus interface provides interface.Memory 12 can store processor 11 when executing operation
Used data.
In electronic equipment provided in an embodiment of the present invention:
The processor 11 executes following process: obtaining the red of palm to be identified for reading the program in memory 12
Outer palm image identifies the centre of the palm point in the infrared palm image;According to the offset of setting, the centre of the palm point is determined extremely
A few neighborhood point;And feature identification region is determined centered on the centre of the palm point and each neighborhood point respectively;According to each spy
The corresponding palm feature of each palm saved in the palm feature and palm library of identification region is levied, determines each feature cog region
Domain matched candidate's palm in palm library;According to the matching degree of each candidate palm and character pair identification region and occurrence out
Number, determines the matched target palm of the palm to be identified.
Preferably, the processor 11, be also used to identify in the infrared palm image the first coordinate of the first the finger web and
Second coordinate of the second the finger web, wherein the finger web of first the finger web between little finger and the third finger, second the finger web are
The finger web between index finger and middle finger;Straight line is determined according to first coordinate and the second coordinate, obtains the straight line and image is sat
The horizontal axis of mark system constitutes the target power of angle;By target power described in the infrared palm image rotation, make the straight line with
The horizontal axis of described image coordinate system is parallel.
Preferably, the processor 11 is specifically used for according to x=(x1+x2The He of)/2It determines described red
Centre of the palm point in outer palm image, wherein x is the abscissa of centre of the palm point, y is the ordinate of centre of the palm point, x1For the cross of the first the finger web
Coordinate, x2Abscissa, y for the second the finger webnFor the ordinate of the first the finger web or the ordinate of the second the finger web.
Preferably, the processor 11, be also used to by the distance between first the finger web and second the finger web with set
The product of fixed deviation ratio, the offset as setting.
Preferably, the processor 11 is specifically used for centered on the centre of the palm point, with first the finger web and described the
The distance between two the finger webs are side length, determine fisrt feature identification region;Respectively centered on each neighborhood point, with the power of setting
The product of the distance between weight coefficient and first the finger web and second the finger web is side length, determines second feature identification region.
Preferably, the processor 11, specifically for the binary image of the determination infrared palm image, described in extraction
Each profile point of palm to be identified described in binary image;For each profile point, the profile point and the wheel are judged
Whether exterior feature puts the product of the slope for two straight lines that two adjacent profile points respectively constitute less than zero;If so, by the profile
The absolute value of the slope for two straight lines that point two profile points adjacent with the profile point respectively constitute and, as the wheel
The score value of exterior feature point, and be added in Candidate Set using the profile point as candidate point;It successively chooses remaining in the Candidate Set
The highest candidate point of score value is added in feature set as characteristic point in candidate point, and by score value highest described in the Candidate Set
Candidate point and be less than the candidate point deletion of given threshold with the score value highest candidate point distance;It deletes in the feature set
The smallest characteristic point of ordinate, and maximum two characteristic points of distance are chosen in the feature set in residue character point as first
The finger web and the second the finger web identify the first coordinate of first the finger web and the second coordinate of second the finger web.
Preferably, the processor 11 is extracted specifically for doing real Gabor wavelet transformation for each feature identification region
The Gabor characteristic figure of the feature identification region, and the local binary patterns LBP feature vector of the Gabor characteristic figure is extracted,
According to the corresponding LBP feature vector of each palm saved in the LBP feature vector and palm library, the feature identification is determined
Region matched candidate's palm in palm library.
On the basis of the various embodiments described above, the embodiment of the invention also provides a kind of computers to store readable storage medium
Matter is stored with the computer program that can be executed by electronic equipment in the computer readable storage medium, when described program is in institute
It states when being run on electronic equipment, so that the electronic equipment executes the hand identification method of above-described embodiment description.
For systems/devices embodiment, since it is substantially similar to the method embodiment, so the comparison of description is simple
Single, the relevent part can refer to the partial explaination of embodiments of method.
It should be understood by those skilled in the art that, embodiments herein can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the application
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the application, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The application is referring to method, the process of equipment (system) and computer program product according to the embodiment of the present application
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
Although the preferred embodiment of the application has been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications can be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the application range.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
Claims (16)
1. a kind of hand identification method, which is characterized in that the described method includes:
The infrared palm image of palm to be identified is obtained, identifies the centre of the palm point in the infrared palm image;
According to the offset of setting, at least one neighborhood point of the centre of the palm point is determined;And respectively with the centre of the palm point and each
Centered on neighborhood point, feature identification region is determined;
According to the corresponding palm feature of each palm saved in the palm feature of each feature identification region and palm library, determine
Each feature identification region matched candidate's palm in palm library;
According to the matching degree and frequency of occurrence of each candidate palm and character pair identification region, the palm to be identified is determined
The target palm matched.
2. the method as described in claim 1, which is characterized in that centre of the palm point in the identification infrared palm image it
Before, the method also includes:
The first coordinate of the first the finger web and the second coordinate of the second the finger web in the infrared palm image are identified, wherein described first
The finger web of the finger web between little finger and the third finger, the finger web of second the finger web between index finger and middle finger;
Straight line is determined according to first coordinate and the second coordinate, and the horizontal axis for obtaining the straight line and image coordinate system constitutes angle
Target power;
By target power described in the infrared palm image rotation, keep the straight line parallel with the horizontal axis of described image coordinate system.
3. method according to claim 2, which is characterized in that the centre of the palm Dian Bao in the identification infrared palm image
It includes:
According to x=(x1+x2The He of)/2Determine the centre of the palm point in the infrared palm image, wherein x is the centre of the palm
The abscissa of point, ordinate, the x that y is centre of the palm point1Abscissa, x for the first the finger web2Abscissa, y for the second the finger webnIt is
The ordinate of the ordinate of one the finger web or the second the finger web.
4. method according to claim 2, which is characterized in that the offset for determining the setting includes:
Product by the distance between first the finger web and second the finger web with the deviation ratio of setting, the offset as setting
Amount.
5. method according to claim 2, which is characterized in that described to be respectively with the centre of the palm point and each neighborhood point
The heart determines that feature identification region includes:
For side length centered on the centre of the palm point, with the distance between first the finger web and second the finger web, first is determined
Feature identification region;
Respectively centered on each neighborhood point, between the weight coefficient of setting and first the finger web and second the finger web
The product of distance is side length, determines second feature identification region.
6. method according to claim 2, which is characterized in that the of the first the finger web in the identification infrared palm image
One coordinate and the second coordinate of the second the finger web include:
The binary image for determining the infrared palm image extracts each of palm to be identified described in the binary image
Profile point;
For each profile point, judge two that the profile point two profile points adjacent with the profile point respectively constitute it is straight
Whether the product of the slope of line is less than zero;If so, the profile point two profile points adjacent with the profile point are distinguished structure
At two straight lines slope absolute value sum, as the score value of the profile point, and using the profile point as candidate point
It is added in Candidate Set;
The highest candidate point of score value is successively chosen in the Candidate Set in remaining candidate point as characteristic point and is added to feature set
In, and it is less than setting threshold by the highest candidate point of score value described in the Candidate Set and with the highest candidate point distance of the score value
The candidate point deletion of value;
The smallest characteristic point of ordinate in the feature set is deleted, and it is maximum to choose in the feature set distance in residue character point
Two characteristic points as the first the finger web and the second the finger web, identify first the finger web the first coordinate and second the finger web
Second coordinate.
7. the method as described in claim 1, which is characterized in that the palm feature and hand according to each feature identification region
The corresponding palm feature of each palm saved in palm library determines each feature identification region matched candidate's hand in palm library
The palm includes:
Real Gabor wavelet transformation is done for each feature identification region, extracts the Gabor characteristic figure of the feature identification region, and
The local binary patterns LBP feature vector for extracting the Gabor characteristic figure, is protected according in the LBP feature vector and palm library
The corresponding LBP feature vector of each palm deposited determines the feature identification region matched candidate's palm in palm library.
8. a kind of hand identification device, which is characterized in that described device includes:
Identification module is obtained, for obtaining the infrared palm image of palm to be identified, identifies the palm in the infrared palm image
Heart point;
First determining module determines at least one neighborhood point of the centre of the palm point for the offset according to setting;And respectively with
Centered on the centre of the palm point and each neighborhood point, feature identification region is determined;
Second determining module, for according to each palm pair saved in the palm feature of each feature identification region and palm library
The palm feature answered determines each feature identification region matched candidate's palm in palm library;
Third determining module, for the matching degree and frequency of occurrence according to each candidate palm and character pair identification region, really
The fixed matched target palm of palm to be identified.
9. device as claimed in claim 8, which is characterized in that described device further include:
Correction module the second of the first coordinate of the first the finger web and the second the finger web is sat in the infrared palm image for identification
Mark, wherein the finger web of first the finger web between little finger and the third finger, second the finger web is between index finger and middle finger
The finger web;Straight line is determined according to first coordinate and the second coordinate, and the horizontal axis for obtaining the straight line and image coordinate system constitutes folder
The target power at angle;By target power described in the infrared palm image rotation, make the straight line and described image coordinate system
Horizontal axis is parallel.
10. device as claimed in claim 9, which is characterized in that the acquisition identification module is specifically used for according to x=(x1+
x2The He of)/2Determine the centre of the palm point in the infrared palm image, wherein x is the abscissa of centre of the palm point, y is
Ordinate, the x of centre of the palm point1Abscissa, x for the first the finger web2Abscissa, y for the second the finger webnFor the ordinate of the first the finger web
Or second the finger web ordinate.
11. device as claimed in claim 9, which is characterized in that first determining module is also used to first the finger web
Product of the distance between described second the finger web with the deviation ratio of setting, the offset as setting.
12. device as claimed in claim 9, which is characterized in that first determining module is specifically used for the centre of the palm point
Centered on, with the distance between first the finger web and second the finger web for side length, determine fisrt feature identification region;Respectively
Centered on each neighborhood point, with the product of the distance between the weight coefficient of setting and first the finger web and second the finger web
For side length, second feature identification region is determined.
13. device as claimed in claim 9, which is characterized in that the correction module is specifically used for determining the infrared palm
The binary image of image extracts each profile point of palm to be identified described in the binary image;For each profile
Point, judge the slope for two straight lines that the profile point two profile points adjacent with the profile point respectively constitute product whether
Less than zero;If so, two straight lines that the profile point two profile points adjacent with the profile point are respectively constituted is oblique
The sum of the absolute value of rate is added in Candidate Set as the score value of the profile point, and using the profile point as candidate point;According to
The highest candidate point of score value is added in feature set as characteristic point in remaining candidate point in the secondary selection Candidate Set, and will
The highest candidate point of score value described in the Candidate Set and the time for being less than given threshold with the highest candidate point distance of the score value
Reconnaissance is deleted;Delete the smallest characteristic point of ordinate in the feature set, and choose in the feature set in residue character point away from
From maximum two characteristic points as the first the finger web and the second the finger web, the first coordinate and described second of first the finger web is identified
Second coordinate of the finger web.
14. device as claimed in claim 8, which is characterized in that second determining module is specifically used for being directed to each feature
Identification region does real Gabor wavelet transformation, extracts the Gabor characteristic figure of the feature identification region, and extracts the Gabor characteristic
The local binary patterns LBP feature vector of figure, it is corresponding according to each palm saved in the LBP feature vector and palm library
LBP feature vector determines the feature identification region matched candidate's palm in palm library.
15. a kind of electronic equipment characterized by comprising memory and processor;
The processor, for reading the program in memory, the step of perform claim requires any one of 1-7 the method.
16. a kind of computer readable storage medium, which is characterized in that it is stored with the computer journey that can be executed by electronic equipment
Sequence, when described program is run on the electronic equipment, so that the electronic equipment perform claim requires described in any one of 1-7
The step of method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910598360.9A CN110427826B (en) | 2019-07-04 | 2019-07-04 | Palm recognition method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910598360.9A CN110427826B (en) | 2019-07-04 | 2019-07-04 | Palm recognition method and device, electronic equipment and storage medium |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110427826A true CN110427826A (en) | 2019-11-08 |
CN110427826B CN110427826B (en) | 2022-03-15 |
Family
ID=68408926
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910598360.9A Active CN110427826B (en) | 2019-07-04 | 2019-07-04 | Palm recognition method and device, electronic equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110427826B (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114220142A (en) * | 2021-11-24 | 2022-03-22 | 慧之安信息技术股份有限公司 | Face feature recognition method of deep learning algorithm |
EP4216082A1 (en) * | 2022-01-21 | 2023-07-26 | IDEMIA Identity & Security France | Method for matching an image of a palm of an individual with at least one image of a plurality of reference palm images |
CN117831082A (en) * | 2023-12-29 | 2024-04-05 | 广电运通集团股份有限公司 | Palm area detection method and device |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101236599A (en) * | 2007-12-29 | 2008-08-06 | 浙江工业大学 | Human face recognition detection device based on multi- video camera information integration |
CN101295361A (en) * | 2007-04-25 | 2008-10-29 | 中国科学院自动化研究所 | Multi-biological characteristic authentication amalgamation method based on rejection region |
CN101350063A (en) * | 2008-09-03 | 2009-01-21 | 北京中星微电子有限公司 | Method and apparatus for locating human face characteristic point |
CN100458822C (en) * | 2005-11-30 | 2009-02-04 | 中国科学院自动化研究所 | Smart identification terminal system and method based radio-frequency identification and biological characteristic |
CN101819629A (en) * | 2010-04-08 | 2010-09-01 | 西京学院 | Supervising tensor manifold learning-based palmprint identification system and method |
CN101833647A (en) * | 2009-03-11 | 2010-09-15 | 中国科学院自动化研究所 | Acquisition device and processing method of palm print image |
CN102591451A (en) * | 2010-12-27 | 2012-07-18 | 日立民用电子株式会社 | Image processing device and image display device |
CN102629295A (en) * | 2011-02-07 | 2012-08-08 | 富士胶片株式会社 | Image processing apparatus, method and program |
CN104951940A (en) * | 2015-06-05 | 2015-09-30 | 西安理工大学 | Mobile payment verification method based on palmprint recognition |
CN105701473A (en) * | 2016-01-15 | 2016-06-22 | 深圳市未来媒体技术研究院 | Method for matching palm print image detail point characteristics |
CN105975833A (en) * | 2016-05-27 | 2016-09-28 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
-
2019
- 2019-07-04 CN CN201910598360.9A patent/CN110427826B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN100458822C (en) * | 2005-11-30 | 2009-02-04 | 中国科学院自动化研究所 | Smart identification terminal system and method based radio-frequency identification and biological characteristic |
CN101295361A (en) * | 2007-04-25 | 2008-10-29 | 中国科学院自动化研究所 | Multi-biological characteristic authentication amalgamation method based on rejection region |
CN101236599A (en) * | 2007-12-29 | 2008-08-06 | 浙江工业大学 | Human face recognition detection device based on multi- video camera information integration |
CN101350063A (en) * | 2008-09-03 | 2009-01-21 | 北京中星微电子有限公司 | Method and apparatus for locating human face characteristic point |
CN101833647A (en) * | 2009-03-11 | 2010-09-15 | 中国科学院自动化研究所 | Acquisition device and processing method of palm print image |
CN101819629A (en) * | 2010-04-08 | 2010-09-01 | 西京学院 | Supervising tensor manifold learning-based palmprint identification system and method |
CN102591451A (en) * | 2010-12-27 | 2012-07-18 | 日立民用电子株式会社 | Image processing device and image display device |
CN102629295A (en) * | 2011-02-07 | 2012-08-08 | 富士胶片株式会社 | Image processing apparatus, method and program |
CN104951940A (en) * | 2015-06-05 | 2015-09-30 | 西安理工大学 | Mobile payment verification method based on palmprint recognition |
CN105701473A (en) * | 2016-01-15 | 2016-06-22 | 深圳市未来媒体技术研究院 | Method for matching palm print image detail point characteristics |
CN105975833A (en) * | 2016-05-27 | 2016-09-28 | 广东欧珀移动通信有限公司 | Fingerprint unlocking method and terminal |
Non-Patent Citations (3)
Title |
---|
JIYI LI 等: "A New Point Pattern Matching Method for Palmprint", 《RESEARCHGATE》 * |
M ASIF AFZAL BUTT 等: "Palmprint Identification Using Contourlet Transform", 《 2008 IEEE SECOND INTERNATIONAL CONFERENCE ON BIOMETRICS: THEORY, APPLICATIONS AND SYSTEMS》 * |
吴凌智 等: "基于MBLBP和Gabor小波的掌纹识别", 《软件导刊》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114220142A (en) * | 2021-11-24 | 2022-03-22 | 慧之安信息技术股份有限公司 | Face feature recognition method of deep learning algorithm |
CN114220142B (en) * | 2021-11-24 | 2022-08-23 | 慧之安信息技术股份有限公司 | Face feature recognition method of deep learning algorithm |
EP4216082A1 (en) * | 2022-01-21 | 2023-07-26 | IDEMIA Identity & Security France | Method for matching an image of a palm of an individual with at least one image of a plurality of reference palm images |
FR3132153A1 (en) * | 2022-01-21 | 2023-07-28 | Idemia Identity Security France | Method for matching an image of an individual's palm with at least one of a plurality of reference palm images |
US11847856B2 (en) | 2022-01-21 | 2023-12-19 | Idemia Identity & Security France | Method for matching an image of a palm of an individual with at least one image from a plurality of reference palm images |
CN117831082A (en) * | 2023-12-29 | 2024-04-05 | 广电运通集团股份有限公司 | Palm area detection method and device |
Also Published As
Publication number | Publication date |
---|---|
CN110427826B (en) | 2022-03-15 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yuan et al. | Fingerprint liveness detection from different fingerprint materials using convolutional neural network and principal component analysis | |
Xin et al. | Multimodal feature-level fusion for biometrics identification system on IoMT platform | |
CA2817686C (en) | Image identification system | |
Kong et al. | A survey of palmprint recognition | |
Zhang et al. | Combining global and minutia deep features for partial high-resolution fingerprint matching | |
CN110427826A (en) | A kind of hand identification method, apparatus, electronic equipment and storage medium | |
CN107169479A (en) | Intelligent mobile equipment sensitive data means of defence based on fingerprint authentication | |
Zhong et al. | Towards application of dorsal hand vein recognition under uncontrolled environment based on biometric graph matching | |
Huang et al. | An evaluation of fake fingerprint databases utilizing SVM classification | |
Fei et al. | Enhanced minutiae extraction for high-resolution palmprint recognition | |
Song et al. | Fingerprint indexing based on pyramid deep convolutional feature | |
Xiao et al. | Extracting palmprint ROI from whole hand image using straight line clusters | |
Shakil et al. | An optimal method for identification of finger vein using supervised learning | |
CN116884045B (en) | Identity recognition method, identity recognition device, computer equipment and storage medium | |
Pradeep et al. | An revolutionary fingerprint authentication approach using GABOR filters for feature extraction and deep learning classification using convolutional neural networks | |
Yuan et al. | Fingerprint liveness detection using an improved CNN with the spatial pyramid pooling structure | |
CN117058723A (en) | Palmprint recognition method, palmprint recognition device and storage medium | |
Kumar et al. | An empirical evaluation of rotation invariance of LDP feature for fingerprint matching using neural networks | |
Fanchang et al. | Local image quality measurement for multi-scale forensic palmprints | |
Zhang et al. | Deep dense multi-level feature for partial high-resolution fingerprint matching | |
CN103593660A (en) | Palm print recognition method based on cross gradient encoding of image with stable characteristics | |
Soldek et al. | Image analysis and pattern recognition in biometric technologies | |
Qin et al. | Partial fingerprint matching via phase-only correlation and deep convolutional neural network | |
Yuan et al. | A realtime fingerprint liveness detection method for fingerprint authentication systems | |
JP5279007B2 (en) | Verification system, verification method, program, and recording medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |