Method for scanning palm veins to carry out three-dimensional modeling and identification
Technical Field
The invention relates to the technical field of palm vein recognition, in particular to a method for scanning palm veins to perform three-dimensional modeling and recognition.
Background
The traditional identity authentication method comprises an identity identification article and identity identification knowledge, but as the identity authentication method mainly borrows foreign objects, once the identity identification article and the identity identification knowledge are stolen or forgotten, the identity of the identity authentication method is easily faked or replaced by others. Compared with the traditional identity authentication method, the biological identification technology has higher safety, confidentiality and convenience. The biological characteristic identification technology has the advantages of difficult forgetting, good anti-counterfeiting performance, difficult counterfeiting or theft, portability, availability at any time and any place and the like.
The biometric technology is a technology for recognizing a human body based on physiological or behavioral characteristics inherent to the human body. The applied biometric features include fingerprint identification, iris identification, palm geometry identification, retina identification, face identification, signature identification, voice identification and the like, the corresponding biometric features include hand shape, fingerprint, iris, face shape, retina, pulse, auricle and the like, and the behavior features include signature, voice, key pressing force and the like. The biological identification technology can be widely applied to governments, armies, banks, social welfare guarantee, electronic commerce and security defense.
Vein recognition is one type of biometric recognition. One implementation is that a personal vein distribution map is obtained, and characteristic values are extracted from the vein distribution map according to a special comparison algorithm; in another mode, images of veins of fingers, palms and palms are obtained through an infrared CCD camera, and the digital images of the veins are stored in a computer system to realize characteristic value storage. When vein is compared, a vein image is adopted in real time, advanced filtering, image binarization and thinning means are used for extracting features of the digital image, and a complex matching algorithm is adopted to compare and match the vein feature values stored in the host computer, so that identity identification is carried out on an individual, and the identity is confirmed.
The existing palm vein recognition technology is mostly based on an image processing technology, for example, a mode of extracting feature points and comparing the feature points is adopted, the gesture of a user hand is required to be in a stretching state during recognition, if other gestures are changed, the error is large, and the recognition cannot be realized easily or the recognition is wrong.
Disclosure of Invention
The invention provides a method for scanning a palm vein to perform three-dimensional modeling and identification, and solves the technical problems that the existing palm vein two-dimensional identification technology has higher requirements on the posture of a hand of a user and has more influence factors on identification accuracy.
In order to solve the technical problems, the invention provides a method for scanning a palm vein to perform three-dimensional modeling, which comprises the following steps:
s1, three-dimensionally scanning veins of a palm vein of a user;
s2, establishing a three-dimensional coordinate system by taking the metacarpophalangeal joint point of the thumb as an origin;
s3, extracting a blood vessel vein stereogram of the palm in the three-dimensional coordinate system;
s4, preprocessing the blood vessel venation stereo image to obtain a standard palm vein stereo model for comparison;
and S5, fusing the standard palm vein three-dimensional models of all users to establish a standard palm vein three-dimensional model database.
Further, the step S2 is specifically:
a three-dimensional rectangular coordinate system is established by taking a metacarpophalangeal joint point of a thumb as an origin, taking a fixed direction extending horizontally towards an index finger as an X axis, taking a horizontal direction perpendicular to the X axis as a Y axis and taking a vertical direction perpendicular to the X axis as a Z axis.
Further, the step S3 is specifically: and taking the metacarpophalangeal joint points of five fingers of the palm as base points, and cutting out a three-dimensional view of blood vessels extending from the five fingers to the wrist.
Further, the step S4 specifically includes:
s41, screening the blood vessel with the largest side section area in the blood vessel venation stereo map as a main trunk;
s42, with the main trunk as a reference, reserving a first-stage trunk extending outwards from the main trunk, and removing other trunks extending outwards from the first-stage trunk to obtain a great vessel venation stereogram;
s43, establishing a space three-dimensional model of the large vessel venation three-dimensional graph as a standard palm vein three-dimensional model.
Further, the step S1 is specifically: and carrying out three-dimensional scanning on the vein lines of the palm under the condition that the palm of the user is naturally straightened.
Further, the standard palm vein stereo model database in step S5 calculates and stores the number of first-level trunks, the number of nodes of the first-level trunks, and the distances between nodes of the large blood vessel venation stereo map in each standard palm vein stereo model.
The invention also provides a method for scanning the palm vein to carry out three-dimensional identification, and the method for carrying out three-dimensional modeling based on the palm vein scanning comprises the following steps:
x1. stereo scanning the vein lines of palm vein at any posture;
x2. executing the steps S2-S4 in the method for scanning the palm vein to carry out three-dimensional modeling to obtain the current palm vein three-dimensional model;
x3., comparing the current palm vein stereo model in the standard palm vein stereo model library, and outputting the recognition result.
Further, the step X3 specifically includes the steps of:
calculating the number of first-stage trunks, the number of nodes of the first-stage trunks and the distances between the nodes of a large blood vessel venation stereograph in the current palm vein stereomodel;
and X32, judging whether the current user passes the identification according to the number of the first-stage trunks, the number of nodes of the first-stage trunks and the number of the same large-vessel venation stereograms matched by the distances between the nodes in the standard palm vein stereomodel library.
Further, in the step X32:
if the number of the matched large vessel venation stereograms is 1, outputting basic information of a user corresponding to the matched large vessel venation stereograms and prompting that the identification is passed, if the number is 0, prompting that the identification is not passed, and if the number is more than or equal to 2, entering a re-judgment step.
Further, the step of re-judging is:
respectively integrating the large blood vessel venation stereo map in the current palm vein stereo model and the matched large blood vessel venation stereo map to obtain the corresponding current large blood vessel venation volume and other large blood vessel venation volumes;
and finding out a large vessel venation stereo map in which the large vessel venation volume in the other large vessel venation volumes is only within an error range with the current large vessel venation volume, outputting the corresponding basic information of the user and prompting that the identification is passed, and if not, prompting that the identification is not passed.
Further, after the prompt identification fails, prompting the user to put the palm again for identification, and prompting the user to register if the identification fails.
The invention provides a method for scanning a palm vein to carry out three-dimensional modeling, which comprises the steps of carrying out three-dimensional scanning on palm vein blood vessel lines of a user to obtain a blood vessel vein three-dimensional image under a three-dimensional coordinate system, then preprocessing the blood vessel vein three-dimensional image, and removing other veins except a main trunk and a first-stage trunk extending from the main trunk in the blood vessel vein, thereby obtaining a standard palm vein three-dimensional model and a standard palm vein three-dimensional model database, and completing the collection and three-dimensional modeling processes of the palm vein of the user.
The invention provides a method for scanning palm veins to carry out three-dimensional identification, which is executed after the method for three-dimensional modeling, after a standard palm vein three-dimensional model database of a user is established, based on the characteristics that the number of blood vessels and the distance points of the extension between the blood vessels are not changed after the human adults grow up, and the proportion of the trunk and the trunk of the blood vessels is never changed, the palm vein of the user identified currently is scanned in the same process to obtain a current palm vein three-dimensional model, the method comprises the steps of searching a standard palm vein three-dimensional model with the strictly identical and unique first-stage trunk number, the first-stage trunk node number and the distances between nodes in a standard palm vein three-dimensional model database to carry out first-stage comparison, and further searching a standard palm vein three-dimensional model consistent with the current palm vein three-dimensional model in a venation integration mode to carry out second-stage comparison if the comparison fails.
The method for three-dimensional modeling and identification by scanning the palm vein provided by the invention realizes three-dimensional modeling and identification of the palm vein of the user, can correctly identify no matter how the gesture of the hand of the user changes, enhances the use experience of the user and ensures the identification accuracy.
Drawings
Fig. 1 is a flowchart illustrating steps of a method for scanning a palm vein to perform three-dimensional modeling according to embodiment 1 of the present invention;
FIG. 2 is a schematic diagram of a three-dimensional coordinate system provided in embodiment 1 of the present invention;
fig. 3 is a schematic diagram of the palm posture corresponding to step S1 provided in embodiment 1 of the present invention;
fig. 4 is a flowchart illustrating steps of a method for scanning a palm vein for three-dimensional stereo recognition according to an embodiment of the present invention.
Detailed Description
The embodiments of the present invention will be described in detail below with reference to the accompanying drawings, which are given solely for the purpose of illustration and are not to be construed as limitations of the invention, including the drawings which are incorporated herein by reference and for illustration only and are not to be construed as limitations of the invention, since many variations thereof are possible without departing from the spirit and scope of the invention.
Example 1
The method for performing three-dimensional modeling by scanning the palm vein provided by the embodiment of the invention is as shown in a step flow chart shown in fig. 1, and in the embodiment, the method comprises the following steps:
s1, three-dimensionally scanning veins of a palm vein of a user;
s2, establishing a three-dimensional coordinate system by taking the metacarpophalangeal joint point of the thumb as an origin;
s3, extracting a blood vessel vein stereogram of the palm in the three-dimensional coordinate system;
s4, preprocessing the blood vessel venation stereo image to obtain a standard palm vein stereo model for comparison;
and S5, fusing the standard palm vein three-dimensional models of all users to establish a standard palm vein three-dimensional model database.
Further, the step S2 is specifically:
as shown in fig. 2, a three-dimensional rectangular coordinate system is established with the metacarpophalangeal joint point of the thumb as the origin O, the fixed direction extending horizontally toward the index finger as the X-axis, the horizontal direction perpendicular to the X-axis as the Y-axis, and the vertical direction perpendicular to the X-axis as the Z-axis. In the present embodiment, the three-dimensional rectangular coordinate system strictly takes the vertical direction as the Z-axis, and in other embodiments, the X-axis, the Y-axis, and the Z-axis of the three-dimensional rectangular coordinate system may be in other directions, and it is only necessary to keep the origin unchanged. The coordinate system of the present embodiment includes, but is not limited to, a three-dimensional rectangular coordinate system, and other three-dimensional coordinate systems are also applicable.
Further, the step S3 is specifically: taking metacarpophalangeal joint points of five fingers of a palm as base points, intercepting a palm solid view of the five fingers extending to the wrist (stopping extending at the point with the maximum radian change between the wrist and the palm), and carrying out infrared scanning on the palm solid view to obtain a corresponding blood vessel vein solid view.
Further, the step S4 specifically includes:
s41, screening the blood vessel with the largest side section area in the blood vessel venation stereo map as a main trunk;
s42, with the main trunk as a reference, reserving a first-stage trunk extending outwards from the main trunk, and removing other trunks extending outwards from the first-stage trunk to obtain a great vessel venation stereogram;
s43, establishing a space three-dimensional model of the large vessel venation three-dimensional graph as a standard palm vein three-dimensional model.
Further, the step S1 is specifically: the palm vein is scanned three-dimensionally in a palm posture of the user which is a natural straightened posture as shown in fig. 1.
Further, the standard palm vein stereo model database in step S5 calculates and stores the number of first-level trunks, the number of nodes of the first-level trunks, and the distances between nodes of the large blood vessel venation stereo map in each standard palm vein stereo model.
In the method for scanning the palm vein to perform the three-dimensional modeling provided in embodiment 1 of the present invention, the palm vein blood vessel lines of the user are three-dimensionally scanned to obtain the blood vessel venation stereo image under the three-dimensional coordinate system, and then the blood vessel venation stereo image is preprocessed to remove the main part and other venations of the first-stage trunk extending from the main part in the blood vessel venation, so as to obtain the standard palm vein stereo model and the standard palm vein stereo model database, and complete the collection and the three-dimensional modeling processes of the palm vein of the user.
Example 2
The embodiment of the invention also provides a method for scanning the palm vein to perform three-dimensional identification, which is based on the method for performing three-dimensional modeling by scanning the palm vein, and as shown in fig. 4, the method comprises the following steps:
x1. stereo scanning the vein lines of palm vein at any posture;
x2. executing the steps S2-S4 in the method for scanning the palm vein to carry out three-dimensional modeling to obtain the current palm vein three-dimensional model;
x3., comparing the current palm vein stereo model in the standard palm vein stereo model library, and outputting the recognition result.
Further, the step X3 specifically includes the steps of:
calculating the number of first-stage trunks, the number of nodes of the first-stage trunks and the distances between the nodes of a large blood vessel venation stereograph in the current palm vein stereomodel;
and X32, judging whether the current user passes the identification according to the number of the first-stage trunks, the number of nodes of the first-stage trunks and the number of the same large-vessel venation stereograms matched by the distances between the nodes in the standard palm vein stereomodel library.
Further, in the step X32:
if the number of the matched large vessel venation stereograms is 1, outputting basic information of a user corresponding to the matched large vessel venation stereograms and prompting that the identification is passed, if the number is 0, prompting that the identification is not passed, and if the number is more than or equal to 2, entering a re-judgment step.
Further, the step of re-judging is:
respectively integrating the large blood vessel venation stereo map in the current palm vein stereo model and the matched large blood vessel venation stereo map to obtain the corresponding current large blood vessel venation volume and other large blood vessel venation volumes;
and finding out a large vessel venation stereo map in which the large vessel venation volume in the other large vessel venation volumes is only within an error range with the current large vessel venation volume, outputting the corresponding basic information of the user and prompting that the identification is passed, and if not, prompting that the identification is not passed.
In the integration process, the volume of the large blood vessel venation in the large blood vessel venation stereogram is obtained in an integration mode according to the cloud data of the coordinate points of the large blood vessel venation, which can be realized in the field of mathematics, and the integration process is not repeated in this embodiment.
Further, after the prompt identification fails, prompting the user to put the palm again for identification, and prompting the user to register if the identification still fails (possibly a new user, a registration program needs to be started for entering new palm vein data).
It should be further noted that, in the standard palm vein three-dimensional model database, user basic information which is recorded and corresponds to the user standard palm vein three-dimensional model one to one is also stored in a data chain manner, so that identity recognition can be completed, and the method and the device can be used in the fields of attendance checking, palm vein payment and the like.
The method for scanning the palm vein to perform the three-dimensional identification provided by the embodiment 2 of the invention is executed after the method for the three-dimensional modeling, after a standard palm vein three-dimensional model database of a user is established, based on the characteristics that the number of blood vessels and the distance points of the extension between the blood vessels are not changed after the human adults grow up, and the proportion of the trunk and the trunk of the blood vessels is never changed, the palm vein of the user identified currently is scanned in the same process to obtain a current palm vein three-dimensional model, the method comprises the steps of searching a standard palm vein three-dimensional model with the strictly identical and unique first-stage trunk number, the first-stage trunk node number and the distances between nodes in a standard palm vein three-dimensional model database to carry out first-stage comparison, and further searching a standard palm vein three-dimensional model consistent with the current palm vein three-dimensional model in a venation integration mode to carry out second-stage comparison if the comparison fails.
The method for three-dimensional modeling and identification by scanning the palm vein provided by the embodiment of the invention realizes three-dimensional modeling and identification of the palm vein of the user, can correctly identify the palm vein no matter how the posture of the hand of the user changes, enhances the use experience of the user and ensures the identification accuracy.
The above embodiments are preferred embodiments of the present invention, but the present invention is not limited to the above embodiments, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and all such changes, modifications, substitutions, combinations, and simplifications are intended to be included in the scope of the present invention.