CN110826452A - Palm print verification method and device, computer equipment and readable storage medium - Google Patents
Palm print verification method and device, computer equipment and readable storage medium Download PDFInfo
- Publication number
- CN110826452A CN110826452A CN201911045136.3A CN201911045136A CN110826452A CN 110826452 A CN110826452 A CN 110826452A CN 201911045136 A CN201911045136 A CN 201911045136A CN 110826452 A CN110826452 A CN 110826452A
- Authority
- CN
- China
- Prior art keywords
- palm
- verification
- image
- verified
- set number
- 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
- 238000012795 verification Methods 0.000 title claims abstract description 158
- 238000000034 method Methods 0.000 title claims abstract description 45
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims abstract description 20
- 230000009466 transformation Effects 0.000 claims abstract description 20
- 238000012937 correction Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 5
- 238000013507 mapping Methods 0.000 claims description 4
- 230000036544 posture Effects 0.000 description 6
- 210000003811 finger Anatomy 0.000 description 5
- 241000282376 Panthera tigris Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000002996 emotional effect Effects 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000004080 punching Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 210000000707 wrist Anatomy 0.000 description 2
- 238000013527 convolutional neural network Methods 0.000 description 1
- 235000019788 craving Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 210000003813 thumb Anatomy 0.000 description 1
Images
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
- G06V40/1365—Matching; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a palm print verification method, a palm print verification device, computer equipment and a readable storage medium, wherein the method comprises the following steps: when a palm print verification instruction is received, acquiring an image to be verified through a preset camera; the image to be verified comprises palm information of a user; recognizing a set number of reference points from the image to be verified by using a pre-trained reference point recognition model; based on the identified reference points with the set number, a plurality of verification sub-regions are divided in the image to be verified by using a Dioney Delaunay triangulation algorithm; carrying out position correction on each verification subarea by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane; splicing the corrected verification subareas to form a palm verification image; judging whether a target palm image matched with the palm verification image exists in a preset palm image library or not, if so, passing the palm print verification; the invention improves the accuracy of palm print identification.
Description
Technical Field
The invention relates to the technical field of palm print identification, in particular to a palm print verification method, a palm print verification device, computer equipment and a readable storage medium.
Background
The palm print is a relatively stable biological characteristic, the identity of a person can be effectively identified by utilizing the palm print, contact type equipment is mostly adopted in the traditional palm print identification, a user needs to press a hand on the equipment, but the palm print identification is not friendly to people with cravings, the user experience is poor, equipment pollution can be caused by long-term contact, and the identification accuracy is influenced. If the device is removed, a digital camera or a computer camera is directly used for photographing to obtain a palm image, and then palm print recognition is carried out according to the palm image, so that the problem of low palm print recognition accuracy caused by unobvious palm print characteristics and more palm postures exists.
Disclosure of Invention
The invention aims to provide a palm print verification method, a palm print verification device, computer equipment and a readable storage medium, which can realize non-contact palm print identification operation and improve the accuracy of palm print identification.
According to an aspect of the present invention, a palm print verification method is provided, which specifically includes the following steps:
when a palm print verification instruction is received, acquiring an image to be verified through a preset camera; the image to be verified comprises palm information of a user;
recognizing a set number of reference points from the image to be verified by using a pre-trained reference point recognition model;
based on the identified reference points with the set number, a plurality of verification sub-regions are divided in the image to be verified by using a Dioney Delaunay triangulation algorithm; each verification sub-region is a trilateral, and the edge of each verification sub-region is a Delaunay edge;
carrying out position correction on each verification subarea by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane;
splicing the corrected verification subareas to form a palm verification image;
and judging whether a target palm image matched with the palm verification image exists in a preset palm image library or not, and if so, passing the palm print verification.
Optionally, before the set number of fiducial points are identified from the image to be verified by using the pre-trained fiducial point identification model, the method further includes:
acquiring a set number of original sample palm images; wherein the set number of fiducial points are marked in each original sample palm image;
zooming, translating and/or rotating an original sample palm image according to a preset image processing mode aiming at the original sample palm image to obtain at least one new sample palm image;
forming a training sample set by all original sample palm images and new sample palm images;
and training and learning a deep alignment network DAN model according to the training sample set to obtain the reference point identification model.
Optionally, the dividing, by using a dironi Delaunay triangulation algorithm, a plurality of verification sub-regions in the image to be verified based on the identified reference points with the set number specifically includes:
setting the set number of reference points as a point set, setting a line segment formed by taking any two points in the point set as end points as a reference line, and setting all the reference lines as a line set;
for a datum line in the line set, if the datum line is satisfied that no other datum point in the point set is included in a circle formed by two end points of the datum line, the datum line is a Delaunay edge;
and setting a triangular area formed by any three Delaunay sides as a verification sub-area.
Optionally, before the performing position correction on each verification sub-region by using the affine transformation algorithm to correct each verification sub-region into the preset reference plane, the method further includes:
acquiring a standard palm image; the palm information in the standard palm image is located in a preset reference plane;
identifying a set number of reference points from the standard palm image using the reference point identification model;
and dividing a plurality of standard palm sub-regions in the standard palm image by utilizing a Delaunay triangulation algorithm based on the set number of reference points.
Optionally, the performing, by using an affine transformation algorithm, position correction on each verification sub-region to correct each verification sub-region into a preset reference plane specifically includes:
aiming at one verification subarea, finding a standard palm subarea corresponding to the verification subarea in the standard palm image;
and mapping the three end points of the verification sub-region to the three end points of the found standard palm sub-region by using an affine transformation algorithm so as to enable the verification sub-region to be corrected into a preset reference plane.
According to another aspect of the present invention, there is also provided a palm print verification apparatus, specifically including the following components:
the acquisition module is used for acquiring an image to be verified through a preset camera when a palm print verification instruction is received; the image to be verified comprises palm information of a user;
the identification module is used for identifying a set number of reference points from the image to be verified by utilizing a pre-trained reference point identification model;
the dividing module is used for dividing a plurality of verification sub-regions in the image to be verified by utilizing a Dironey Delaunay triangulation algorithm based on the identified reference points with the set number; each verification sub-region is a trilateral, and the edge of each verification sub-region is a Delaunay edge;
the correction module is used for correcting the position of each verification subarea by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane;
the splicing module is used for splicing the corrected verification sub-areas to form a palm verification image;
and the verification module is used for judging whether a target palm image matched with the palm verification image exists in a preset palm image library or not, and if so, the palm print verification is passed.
Optionally, the apparatus further comprises:
the training module is used for acquiring a set number of original sample palm images before a set number of reference points are identified from the image to be verified by using a pre-trained reference point identification model; wherein the set number of fiducial points are marked in each original sample palm image; zooming, translating and/or rotating an original sample palm image according to a preset image processing mode aiming at the original sample palm image to obtain at least one new sample palm image; forming a training sample set by all original sample palm images and new sample palm images; and training and learning a deep alignment network DAN model according to the training sample set to obtain the reference point identification model.
Optionally, the dividing module is specifically configured to:
setting the set number of reference points as a point set, setting a line segment formed by taking any two points in the point set as end points as a reference line, and setting all the reference lines as a line set; for a datum line in the line set, if the datum line is satisfied that no other datum point in the point set is included in a circle formed by two end points of the datum line, the datum line is a Delaunay edge; and setting a triangular area formed by any three Delaunay sides as a verification sub-area.
According to another aspect of the present invention, there is also provided a computer device, specifically including: the palm print verification method comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor realizes the steps of the palm print verification method when executing the program.
According to another aspect of the present invention, there is also provided a computer-readable storage medium, on which a computer program is stored, which when executed by a processor, performs the steps of the above-described palm print verification method.
According to the palmprint verification method, the palmprint verification device, the computer equipment and the readable storage medium, the palms of the users are photographed through the digital camera or the computer camera to obtain the images to be verified, the palms of the users do not need to be contacted with the equipment, and a non-contact palmprint recognition mode is adopted; in the process of acquiring the image to be verified through the preset camera, the palm of the user moves in a three-dimensional space, the placing postures of all the palms are more diversified, and in order to improve the accuracy of palm print recognition, the palm in different postures is corrected into a preset reference plane by utilizing the existing mature affine transformation algorithm, so that the accuracy of palm print recognition is improved.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the invention. Also, like reference numerals are used to refer to like parts throughout the drawings. In the drawings:
fig. 1 is a schematic flow chart of an alternative palm print verification method according to an embodiment;
fig. 2 is a schematic diagram of an optional program module of the palm print verification apparatus according to the second embodiment;
fig. 3 is a schematic diagram of an alternative hardware architecture of the computer device according to the third embodiment.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example one
The embodiment of the invention provides a palm print verification method, which specifically comprises the following steps as shown in figure 1:
step S101: when a palm print verification instruction is received, acquiring an image to be verified through a preset camera; wherein the image to be verified comprises palm information of the user.
In this embodiment, the palm of the user may be photographed by a digital camera or a computer camera to obtain an image to be verified.
Step S102: and recognizing a set number of reference points from the image to be verified by using a pre-trained reference point recognition model.
Specifically, the set number of reference points includes the following nine points: the center point of the forefinger-palm connecting line, the center point of the middle finger-palm connecting line, the center point of the ring finger-palm connecting line, the center point of the little finger-palm connecting line, the two end points of the emotional line in the palm, the tail end point of the intelligent line in the palm and the two end points of the lifeline in the palm.
Wherein, the life line is a palm print line which naturally runs from the central starting point of the tiger's mouth to the wrist; the intelligent line is a palm print line from the starting point of the life line to the centre of the palm to the middle perpendicular line of the ring finger; the feeling line is a palm line from the arc line below the outer side of the female position to the perpendicular bisector of the middle finger.
In a face recognition scene, the reference points are usually five points of two eyes, two ends of a mouth corner and a nose tip of a face; the five reference points are relatively obvious feature points and are relatively easy to determine from the face image; in contrast, the stable feature points on the palm are difficult to select, and the four middle points at the joint roots of the other four fingers except the thumb are found to be stable through repeated tests, and the end points of the three palm lines are also stable. In addition to the reason that the nine reference points are relatively obvious feature points, the nine reference points are distributed on various parts of the palm, which is necessary for subsequent palm print recognition, and if the reference points are distributed only on the upper part or the lower part of the palm, the subsequent palm print recognition has a large error.
Further, before step S102, the method further includes:
step A1: acquiring a set number of original sample palm images; wherein the set number of fiducial points are marked in each original sample palm image;
step A2: zooming, translating and/or rotating an original sample palm image according to a preset image processing mode aiming at the original sample palm image to obtain at least one new sample palm image;
step A3: forming a training sample set by all original sample palm images and new sample palm images;
step A4: and training and learning a deep alignment network DAN model according to the training sample set to obtain the reference point identification model.
In this embodiment, the reference points in each sample palm image in the training sample set are labeled in a manual labeling manner, the labeled training sample set is used to train the DAN model, and the trained reference point recognition model is used to predict the reference points; because the number of the acquired original sample palm images is limited, in order to increase the number of the sample palm images in the training sample set, a new sample palm image can be generated by performing image processing on the original sample palm images, so that the number of samples in the training sample set is increased and the sample diversity of the training sample set is enriched; the DAN model is called Deep Align Network, the model utilizes the thought of heat map and combines the traditional cascade structure, a regression model is constructed to predict the reference point, the experimental result display effect is good, and the position error of the predicted reference point can be controlled within 3 pixels.
Step S103: based on the identified reference points with the set number, a plurality of verification sub-regions are divided in the image to be verified by using a Dioney Delaunay triangulation algorithm; each verification sub-region is a trilateral, and the edge of each verification sub-region is a Delaunay edge.
Specifically, step S103 includes:
step A1: setting the set number of reference points as a point set, setting a line segment formed by taking any two points in the point set as end points as a reference line, and setting all the reference lines as a line set;
step A2: for a datum line in the line set, if the datum line is satisfied that no other datum point in the point set is included in a circle formed by two end points of the datum line, the datum line is a Delaunay edge;
step A3: and setting a triangular area formed by any three Delaunay sides as a verification sub-area.
Step S104: and carrying out position correction on each verification subarea by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane.
Because in the process of acquiring the image to be verified through the preset camera, the palm of the user moves in the three-dimensional space, the placing postures of all the palms are more various, and if the postures of the palms are not corrected, the difference of the same palm even exceeds the difference between different palms on the small sample data volume. Therefore, in order to improve the accuracy of palm print recognition, in the present embodiment, the existing relatively mature affine transformation algorithm is used to correct the palms in different postures into the preset reference plane.
Specifically, before step S104, the method further includes:
step B1: acquiring a standard palm image; the palm information in the standard palm image is located in a preset reference plane;
step B2: identifying the set number of reference points from the standard palm image using the reference point identification model;
step B3: and dividing a plurality of standard palm sub-regions in the standard palm image by utilizing a Delaunay triangulation algorithm based on the set number of reference points.
Further, step S104 includes:
step C1: aiming at one verification subarea, finding a standard palm subarea corresponding to the verification subarea in the standard palm image;
step C2: and mapping the three end points of the verification sub-region to the three end points of the found standard palm sub-region by using an affine transformation algorithm so as to enable the verification sub-region to be corrected into a preset reference plane.
It should be noted that the standard palm sub-regions divided according to the standard palm image and the verification sub-regions divided according to the image to be verified have a one-to-one correspondence relationship.
Step S105: and splicing the corrected verification subareas to form a palm verification image.
Step S106: and judging whether a target palm image matched with the palm verification image exists in a preset palm image library or not, and if so, passing the palm print verification.
A plurality of standard palm images of a plurality of users are stored in the palm image library, and each standard palm image can be obtained according to the methods from step S101 to step S105. For example, a standard palm image is extracted according to a palm image of each employee of an enterprise, the standard palm image of each employee is stored in a palm image library, when the enterprise performs attendance checking and card punching by using palm print recognition, the palm verification image acquired in real time can be matched with the standard palm image in the palm image library one by one so as to perform identity verification on the employee, and thus attendance checking and card punching operation is performed; preferably, the image matching can be performed using a convolutional neural network algorithm.
Example two
The embodiment of the invention provides a palm print verification device, which specifically comprises the following components as shown in fig. 2:
the acquiring module 201 is configured to acquire an image to be verified through a preset camera when a palm print verification instruction is received; wherein the image to be verified comprises palm information of the user.
In this embodiment, the palm of the user may be photographed by a digital camera or a computer camera to obtain an image to be verified.
The identification module 202 is configured to identify a set number of reference points from the image to be verified by using a pre-trained reference point identification model.
Specifically, the set number of reference points includes the following nine points: the center point of the forefinger-palm connecting line, the center point of the middle finger-palm connecting line, the center point of the ring finger-palm connecting line, the center point of the little finger-palm connecting line, the two end points of the emotional line in the palm, the tail end point of the intelligent line in the palm and the two end points of the lifeline in the palm.
Wherein, the life line is a palm print line which naturally runs from the central starting point of the tiger's mouth to the wrist; the intelligent line is a palm print line from the starting point of the life line to the centre of the palm to the middle perpendicular line of the ring finger; the feeling line is a palm line from the arc line below the outer side of the female position to the perpendicular bisector of the middle finger.
Further, the apparatus further comprises:
the training module is used for acquiring a set number of original sample palm images before a set number of reference points are identified from the image to be verified by using a pre-trained reference point identification model; wherein the set number of fiducial points are marked in each original sample palm image; zooming, translating and/or rotating an original sample palm image according to a preset image processing mode aiming at the original sample palm image to obtain at least one new sample palm image; forming a training sample set by all original sample palm images and new sample palm images; and training and learning a deep alignment network DAN model according to the training sample set to obtain the reference point identification model.
A dividing module 203, configured to divide a plurality of verification sub-regions in the image to be verified by using a dironi Delaunay triangulation algorithm based on the identified reference points in the set number; each verification sub-region is a trilateral, and the edge of each verification sub-region is a Delaunay edge.
Specifically, the dividing module 203 is configured to:
setting the set number of reference points as a point set, setting a line segment formed by taking any two points in the point set as end points as a reference line, and setting all the reference lines as a line set; for a datum line in the line set, if the datum line is satisfied that no other datum point in the point set is included in a circle formed by two end points of the datum line, the datum line is a Delaunay edge; and setting a triangular area formed by any three Delaunay sides as a verification sub-area.
And the correcting module 204 is configured to perform position correction on each verification sub-region by using an affine transformation algorithm, so as to correct each verification sub-region into a preset reference plane.
Specifically, the apparatus further comprises:
the processing module is used for acquiring a standard palm image before the position of each verification subarea is corrected by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane; the palm information in the standard palm image is located in a preset reference plane; identifying a set number of reference points from the standard palm image using the reference point identification model; and dividing a plurality of standard palm sub-regions in the standard palm image by utilizing a Delaunay triangulation algorithm based on the set number of reference points.
Further, the correction module 204 is specifically configured to:
aiming at one verification subarea, finding a standard palm subarea corresponding to the verification subarea in the standard palm image; and mapping the three end points of the verification sub-region to the three end points of the found standard palm sub-region by using an affine transformation algorithm so as to enable the verification sub-region to be corrected into a preset reference plane.
And the splicing module 205 is configured to splice the corrected verification sub-regions to form a palm verification image.
The verification module 206 is configured to determine whether a target palm image matching the palm verification image exists in a preset palm image library, and if so, pass the palm print verification.
EXAMPLE III
The embodiment also provides a computer device, such as a smart phone, a tablet computer, a notebook computer, a desktop computer, a rack server, a blade server, a tower server or a rack server (including an independent server or a server cluster composed of a plurality of servers) capable of executing programs, and the like. As shown in fig. 3, the computer device 30 of the present embodiment includes at least but is not limited to: a memory 301, a processor 302 communicatively coupled to each other via a system bus. It is noted that FIG. 3 only shows the computer device 30 having components 301 and 302, but it is understood that not all of the shown components are required and that more or fewer components may be implemented instead.
In this embodiment, the memory 301 (i.e., the readable storage medium) includes a flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a read-only memory (ROM), an electrically erasable programmable read-only memory (EEPROM), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, and the like. In some embodiments, the storage 301 may be an internal storage unit of the computer device 30, such as a hard disk or a memory of the computer device 30. In other embodiments, the memory 301 may also be an external storage device of the computer device 30, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), or the like, provided on the computer device 30. Of course, the memory 301 may also include both internal and external storage devices for the computer device 30. In this embodiment, the memory 301 is generally used for storing an operating system and various application software installed in the computer device 30, such as a program code of the palm print verification apparatus of the second embodiment. In addition, the memory 301 may also be used to temporarily store various types of data that have been output or are to be output.
Processor 302 may be a Central Processing Unit (CPU), controller, microcontroller, microprocessor, or other data Processing chip in some embodiments. The processor 302 generally serves to control the overall operation of the computer device 30.
Specifically, in this embodiment, the processor 302 is configured to execute a program of a palm print verification method stored in the processor 302, and when executed, the program of the palm print verification method implements the following steps:
when a palm print verification instruction is received, acquiring an image to be verified through a preset camera; the image to be verified comprises palm information of a user;
recognizing a set number of reference points from the image to be verified by using a pre-trained reference point recognition model;
based on the identified reference points with the set number, a plurality of verification sub-regions are divided in the image to be verified by using a Dioney Delaunay triangulation algorithm; each verification sub-region is a trilateral, and the edge of each verification sub-region is a Delaunay edge;
carrying out position correction on each verification subarea by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane;
splicing the corrected verification subareas to form a palm verification image;
and judging whether a target palm image matched with the palm verification image exists in a preset palm image library or not, and if so, passing the palm print verification.
The specific embodiment process of the above method steps can be referred to in the first embodiment, and the detailed description of this embodiment is not repeated here.
Example four
The present embodiments also provide a computer readable storage medium, such as a flash memory, a hard disk, a multimedia card, a card type memory (e.g., SD or DX memory, etc.), a Random Access Memory (RAM), a Static Random Access Memory (SRAM), a Read Only Memory (ROM), an Electrically Erasable Programmable Read Only Memory (EEPROM), a Programmable Read Only Memory (PROM), a magnetic memory, a magnetic disk, an optical disk, a server, an App application mall, etc., having stored thereon a computer program that when executed by a processor implements the method steps of:
when a palm print verification instruction is received, acquiring an image to be verified through a preset camera; the image to be verified comprises palm information of a user;
recognizing a set number of reference points from the image to be verified by using a pre-trained reference point recognition model;
based on the identified reference points with the set number, a plurality of verification sub-regions are divided in the image to be verified by using a Dioney Delaunay triangulation algorithm; each verification sub-region is a trilateral, and the edge of each verification sub-region is a Delaunay edge;
carrying out position correction on each verification subarea by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane;
splicing the corrected verification subareas to form a palm verification image;
and judging whether a target palm image matched with the palm verification image exists in a preset palm image library or not, and if so, passing the palm print verification.
The specific embodiment process of the above method steps can be referred to in the first embodiment, and the detailed description of this embodiment is not repeated here.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other like elements in a process, method, article, or apparatus that comprises the element.
The above-mentioned serial numbers of the embodiments of the present invention are merely for description and do not represent the merits of the embodiments.
Through the above description of the embodiments, those skilled in the art will clearly understand that the method of the above embodiments can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware, but in many cases, the former is a better implementation manner.
The above description is only a preferred embodiment of the present invention, and not intended to limit the scope of the present invention, and all modifications of equivalent structures and equivalent processes, which are made by using the contents of the present specification and the accompanying drawings, or directly or indirectly applied to other related technical fields, are included in the scope of the present invention.
Claims (10)
1. A palm print verification method, the method comprising:
when a palm print verification instruction is received, acquiring an image to be verified through a preset camera; the image to be verified comprises palm information of a user;
recognizing a set number of reference points from the image to be verified by using a pre-trained reference point recognition model;
based on the identified reference points with the set number, a plurality of verification sub-regions are divided in the image to be verified by using a Dioney Delaunay triangulation algorithm; each verification sub-region is a trilateral, and the edge of each verification sub-region is a Delaunay edge;
carrying out position correction on each verification subarea by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane;
splicing the corrected verification subareas to form a palm verification image;
and judging whether a target palm image matched with the palm verification image exists in a preset palm image library or not, and if so, passing the palm print verification.
2. The palm print verification method according to claim 1, wherein before the set number of fiducial points are recognized from the image to be verified by using a pre-trained fiducial point recognition model, the method further comprises:
acquiring a set number of original sample palm images; wherein the set number of fiducial points are marked in each original sample palm image;
zooming, translating and/or rotating an original sample palm image according to a preset image processing mode aiming at the original sample palm image to obtain at least one new sample palm image;
forming a training sample set by all original sample palm images and new sample palm images;
and training and learning a deep alignment network DAN model according to the training sample set to obtain the reference point identification model.
3. The palm print verification method according to claim 1, wherein the step of dividing a plurality of verification sub-regions in the image to be verified by using a dironi Delaunay triangulation algorithm based on the identified set number of reference points specifically comprises:
setting the set number of reference points as a point set, setting a line segment formed by taking any two points in the point set as end points as a reference line, and setting all the reference lines as a line set;
for a datum line in the line set, if the datum line is satisfied that no other datum point in the point set is included in a circle formed by two end points of the datum line, the datum line is a Delaunay edge;
and setting a triangular area formed by any three Delaunay sides as a verification sub-area.
4. The palm print verification method according to claim 1, wherein before the position correction of each verification sub-region by using the affine transformation algorithm to correct each verification sub-region into a preset reference plane, the method further comprises:
acquiring a standard palm image; the palm information in the standard palm image is located in a preset reference plane;
identifying a set number of reference points from the standard palm image using the reference point identification model;
and dividing a plurality of standard palm sub-regions in the standard palm image by utilizing a Delaunay triangulation algorithm based on the set number of reference points.
5. The palm print verification method according to claim 4, wherein the performing position correction on each verification sub-region by using an affine transformation algorithm to correct each verification sub-region into a preset reference plane specifically comprises:
aiming at one verification subarea, finding a standard palm subarea corresponding to the verification subarea in the standard palm image;
and mapping the three end points of the verification sub-region to the three end points of the found standard palm sub-region by using an affine transformation algorithm so as to enable the verification sub-region to be corrected into a preset reference plane.
6. A palm print verification apparatus, the apparatus comprising:
the acquisition module is used for acquiring an image to be verified through a preset camera when a palm print verification instruction is received; the image to be verified comprises palm information of a user;
the identification module is used for identifying a set number of reference points from the image to be verified by utilizing a pre-trained reference point identification model;
the dividing module is used for dividing a plurality of verification sub-regions in the image to be verified by utilizing a Dironey Delaunay triangulation algorithm based on the identified reference points with the set number; each verification sub-region is a trilateral, and the edge of each verification sub-region is a Delaunay edge;
the correction module is used for correcting the position of each verification subarea by using an affine transformation algorithm so as to correct each verification subarea into a preset reference plane;
the splicing module is used for splicing the corrected verification sub-areas to form a palm verification image;
and the verification module is used for judging whether a target palm image matched with the palm verification image exists in a preset palm image library or not, and if so, the palm print verification is passed.
7. The palm print verification device of claim 6, further comprising:
the training module is used for acquiring a set number of original sample palm images before a set number of reference points are identified from the image to be verified by using a pre-trained reference point identification model; wherein the set number of fiducial points are marked in each original sample palm image; zooming, translating and/or rotating an original sample palm image according to a preset image processing mode aiming at the original sample palm image to obtain at least one new sample palm image; forming a training sample set by all original sample palm images and new sample palm images; and training and learning a deep alignment network DAN model according to the training sample set to obtain the reference point identification model.
8. The palm print verification device according to claim 6, wherein the dividing module is specifically configured to:
setting the set number of reference points as a point set, setting a line segment formed by taking any two points in the point set as end points as a reference line, and setting all the reference lines as a line set; for a datum line in the line set, if the datum line is satisfied that no other datum point in the point set is included in a circle formed by two end points of the datum line, the datum line is a Delaunay edge; and setting a triangular area formed by any three Delaunay sides as a verification sub-area.
9. A computer device, the computer device comprising: memory, processor and computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 5 are implemented when the processor executes the program.
10. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 5.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911045136.3A CN110826452B (en) | 2019-10-30 | Palm print verification method and device, computer equipment and readable storage medium | |
| PCT/CN2020/093186 WO2021082425A1 (en) | 2019-10-30 | 2020-05-29 | Palmprint verification method and apparatus, computer device, and readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911045136.3A CN110826452B (en) | 2019-10-30 | Palm print verification method and device, computer equipment and readable storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110826452A true CN110826452A (en) | 2020-02-21 |
| CN110826452B CN110826452B (en) | 2024-07-16 |
Family
ID=
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082425A1 (en) * | 2019-10-30 | 2021-05-06 | 平安科技（深圳）有限公司 | Palmprint verification method and apparatus, computer device, and readable storage medium |
| CN113515987A (en) * | 2020-07-09 | 2021-10-19 | 腾讯科技（深圳）有限公司 | Palm print recognition method and device, computer equipment and storage medium |
| WO2023160048A1 (en) * | 2022-02-28 | 2023-08-31 | 腾讯科技（深圳）有限公司 | Palmprint sample generation method and apparatus, and device, medium and program product |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017107865A1 (en) * | 2015-12-22 | 2017-06-29 | 成都理想境界科技有限公司 | Image retrieval system, server, database, and related method |
| CN108985132A (en) * | 2017-05-31 | 2018-12-11 | 腾讯科技（深圳）有限公司 | A kind of face image processing process, calculates equipment and storage medium at device |
| CN109993129A (en) * | 2019-04-04 | 2019-07-09 | 郑州师范学院 | A kind of fingerprint identification method based on the thin node cylinder code of fingerprint |
| CN110334598A (en) * | 2019-05-31 | 2019-10-15 | 平安科技（深圳）有限公司 | A kind of palm grain identification method and device |
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017107865A1 (en) * | 2015-12-22 | 2017-06-29 | 成都理想境界科技有限公司 | Image retrieval system, server, database, and related method |
| CN108985132A (en) * | 2017-05-31 | 2018-12-11 | 腾讯科技（深圳）有限公司 | A kind of face image processing process, calculates equipment and storage medium at device |
| CN109993129A (en) * | 2019-04-04 | 2019-07-09 | 郑州师范学院 | A kind of fingerprint identification method based on the thin node cylinder code of fingerprint |
| CN110334598A (en) * | 2019-05-31 | 2019-10-15 | 平安科技（深圳）有限公司 | A kind of palm grain identification method and device |
Non-Patent Citations (2)
| Title |
|---|
| 窦慧丽: ""基于Delaunay三角剖分的指纹匹配算法"", 《中国优秀博硕士学位论文全文数据库（硕士）信息科技辑》, pages 25 - 28 * |
| 窦慧丽: ""基于Delaunay三角剖分的指纹匹配算法"", 《中国优秀硕士学位论文全文数据库信息科技辑》, pages 25 - 28 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2021082425A1 (en) * | 2019-10-30 | 2021-05-06 | 平安科技（深圳）有限公司 | Palmprint verification method and apparatus, computer device, and readable storage medium |
| CN113515987A (en) * | 2020-07-09 | 2021-10-19 | 腾讯科技（深圳）有限公司 | Palm print recognition method and device, computer equipment and storage medium |
| CN113515987B (en) * | 2020-07-09 | 2023-08-08 | 腾讯科技（深圳）有限公司 | Palmprint recognition method, palmprint recognition device, computer equipment and storage medium |
| WO2023160048A1 (en) * | 2022-02-28 | 2023-08-31 | 腾讯科技（深圳）有限公司 | Palmprint sample generation method and apparatus, and device, medium and program product |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2021082425A1 (en) | 2021-05-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109543663B (en) | Method, device and system for identifying identity of dog and storage medium | |
| CN110197146B (en) | Face image analysis method based on deep learning, electronic device and storage medium | |
| CN111914775B (en) | Living body detection method, living body detection device, electronic equipment and storage medium | |
| CN110852216A (en) | Palm print verification method and device, computer equipment and readable storage medium | |
| WO2018028546A1 (en) | Key point positioning method, terminal, and computer storage medium | |
| CN111898411B (en) | Text image labeling system, method, computer device and storage medium | |
| JP6952094B2 (en) | Image processing device and image processing method | |
| CN111310705A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN110008824B (en) | Palmprint recognition method, palmprint recognition device, palmprint recognition computer device and palmprint recognition storage medium | |
| CN110837580A (en) | Pedestrian picture marking method and device, storage medium and intelligent device | |
| CN110738219A (en) | Method and device for extracting lines in image, storage medium and electronic device | |
| CN113111880B (en) | Certificate image correction method, device, electronic equipment and storage medium | |
| US20140233854A1 (en) | Real time object scanning using a mobile phone and cloud-based visual search engine | |
| CN110033388B (en) | Social relationship establishing method and device and server | |
| CN111783882A (en) | Key point detection method and device, electronic equipment and storage medium | |
| CN113378764A (en) | Video face acquisition method, device, equipment and medium based on clustering algorithm | |
| CN112036362A (en) | Image processing method, image processing device, computer equipment and readable storage medium | |
| CN111178128A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN110135889A (en) | Method, server and the storage medium of intelligent recommendation book list | |
| CN111414914A (en) | Image recognition method and device, computer equipment and storage medium | |
| CN111858977A (en) | Bill information acquisition method and device, computer equipment and storage medium | |
| CN111178308A (en) | Gesture track recognition method and device | |
| CN114067406A (en) | Key point detection method, device, equipment and readable storage medium | |
| CN113486739A (en) | Screw detection method and device, electronic equipment and storage medium | |
| CN110766938B (en) | Road network topological structure construction method and device, computer equipment and storage 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 |