WO2021128433A1

WO2021128433A1 - Method for performing three-dimensional modeling by scanning palm veins and recognition method

Info

Publication number: WO2021128433A1
Application number: PCT/CN2019/130849
Authority: WO
Inventors: 卢慧莉; 詹恩毅; 聂为清; 孙恺斌; 林智惠
Original assignee: 广东智冠信息技术股份有限公司
Priority date: 2019-12-28
Filing date: 2019-12-31
Publication date: 2021-07-01
Also published as: CN111160247B; CN111160247A

Abstract

The present application relates to the technical field of palm vein recognition, and provides a method for performing three-dimensional modeling by scanning palm veins and a recognition method. The three-dimensional modeling method obtains a blood vessel vein stereogram under a three-dimensional coordinate system by performing stereoscopic scanning on palm vein blood vessel lines of a user, then preprocesses the blood vessel vein stereogram, removes other veins except the trunk and the first-stage torso extending from the trunk in the blood vessel veins, so as to obtain a standard palm vein stereoscopic model and a standard palm vein stereoscopic model database, and the acquisition and three-dimensional modeling process of the palm vein of the user is completed. The three-dimensional recognition method performs recognition through the first-stage comparison and second-stage comparison in the standard palm vein stereoscopic model database for the current palm vein stereoscopic model. The three-dimensional modeling and recognition methods realize the three-dimensional modeling and recognition of the palm vein for the user, the correct recognition can be performed no matter how the posture of the hand of the user changes.

Description

Method for scanning palm veins to perform three-dimensional modeling and recognition

Technical field

The invention relates to the technical field of palm vein recognition, in particular to a method for scanning palm veins to perform stereoscopic three-dimensional modeling and recognition.

Background technique

Traditional identification methods include identification items and identification knowledge, but because they mainly rely on external objects, once the identification items and identification knowledge that prove the identity are stolen or forgotten, their identities are easily impersonated or replaced by others. Biometrics is more secure, confidential and convenient than traditional identification methods. Biometric identification technology has the advantages of being hard to forget, having good anti-counterfeiting performance, being hard to forge or being stolen, "carrying" it with you, and being usable anytime, anywhere.

Biometrics is a technology for identification based on the inherent physiological or behavioral characteristics of human beings. It has been used including fingerprint recognition, iris recognition, palm geometry recognition, retina recognition, facial recognition, signature recognition, voice recognition, etc. The corresponding biometric biometric features include hand shape, fingerprint, iris, face shape, retina, pulse, The auricle, etc., the behavioral characteristics include signature, voice, keystroke, etc. Biometrics technology can be widely used in government, military, bank, social welfare, e-commerce, security and defense.

Vein recognition is a type of biometrics. One way to achieve this is to obtain a personal vein distribution map and extract feature values from the vein distribution map according to a special comparison algorithm; the other way uses an infrared CCD camera to obtain images of the veins of the fingers, palms, and palms, and combine the digital images of the veins. Stored in the computer system to realize feature value storage. During vein comparison, the vein map is taken in real time, the features are extracted from the digital image using advanced filtering, image binarization, and refinement methods, and the complex matching algorithm is used to compare and match the vein feature values stored in the host, so as to perform the matching on the individual Identification, confirmation of identity.

The existing palm vein recognition technology is mostly based on image processing technology, such as the method of extracting feature points and comparing feature points, requiring the user's hand posture to be in the extended state during recognition. If you change other postures, the error will be large and easy to recognize. Or identify errors.

Summary of the invention

The present invention provides a method for scanning palm veins to perform stereoscopic three-dimensional modeling and recognition. The technical problem solved is that the existing palm vein two-dimensional recognition technology has higher requirements on the posture of the user's hand, and the recognition accuracy rate has relatively high influence factors. many.

In order to solve the above technical problems, the present invention provides a method for scanning palm veins to perform stereoscopic three-dimensional modeling, which includes the following steps:

S1. Perform a stereo scan of a user's palm vein veins;

S2. Establish a three-dimensional coordinate system with the metacarpophalangeal joint point of the thumb as the origin;

S3. Extract a three-dimensional view of the vascular and collaterals of the palm in the three-dimensional coordinate system;

S4. Preprocessing the three-dimensional map of the blood vessel and collaterals to obtain a standard three-dimensional model of the palm vein for comparison;

S5. Integrating 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:

Take the metacarpophalangeal joint point of the thumb as the origin, the fixed direction extending horizontally to 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. The axis establishes a three-dimensional rectangular coordinate system.

Further, the step S3 is specifically: taking the metacarpophalangeal joint points of the five fingers of the palm as a base point, and intercepting a three-dimensional view of the blood vessels and veins extending from the five fingers to the wrist.

Further, the step S4 specifically includes:

S41. Select the blood vessel with the largest lateral cross-sectional area in the three-dimensional view of the blood vessel and collaterals as the backbone;

S42. Taking the main trunk as a reference, retaining the first-level trunk extending outward from the main trunk, and excluding other trunks extending outward from the first-level trunk, to obtain a three-dimensional view of the large blood vessels;

S43. Establish a three-dimensional model of the three-dimensional view of the large blood vessels and veins as a standard three-dimensional model of palm veins.

Further, the step S1 is specifically: performing a three-dimensional scan of the veins of the palm veins under the posture of the user's palm in a naturally straightened posture.

Further, the standard palm vein three-dimensional model database in the step S5 calculates and saves the number of first-level torso and the number of first-level torso of the large blood vessel and vein three-dimensional diagram in each of the standard palm vein three-dimensional models. The number of nodes, the distance between nodes.

The present invention also provides a method for scanning palm veins for three-dimensional recognition. Based on the above-mentioned method for scanning palm veins for three-dimensional modeling, the method includes the following steps:

X1. Carry out a stereo scan of a palm vein vein pattern of a user in any posture;

X2. Perform steps S2 to S4 in the above-mentioned method for scanning palm veins for three-dimensional modeling to obtain the current three-dimensional model of palm veins;

X3. Compare the current palm vein three-dimensional model with the standard palm vein three-dimensional model library, and output the recognition result.

Further, the step X3 specifically includes the steps:

X31. Calculate the number of first-level torsos, the number of nodes of the first-level torso, and the distance between nodes in the large blood vessel context three-dimensional map of the current palm vein three-dimensional model;

X32. The number of first-level torso, the number of nodes of the first-level torso, and the distance between nodes in the current three-dimensional model of palm veins are matched to the same in the standard palm vein three-dimensional model library. The number of three-dimensional diagrams of large blood vessels and collaterals determines whether the current user has been recognized.

Further, in the step X32:

If the number of matching stereograms of the same large blood vessel context is 1, the basic information of the user corresponding to the matching three-dimensional diagram of large blood vessels will be output and the recognition passed, if the number is 0, the recognition failed, if the number is greater than or equal to 2, Then enter the judgment step again.

Further, the re-judgment step is:

Integrate the three-dimensional diagram of the large blood vessel and the same large blood vessel in the current three-dimensional model of the palm vein and the three-dimensional diagram of the large blood vessel that is matched to obtain the corresponding volume of the current large blood vessel and other large blood vessels;

Find out the three-dimensional diagram of the macrovascular choroid whose volume is the only one within the error range of the current macrovascular choroid volume among the other macrovascular choroid volumes, and output the corresponding user's basic information and prompt the identification to pass, if not found If it is out, it prompts that the recognition has not passed.

Further, after the prompt recognition fails, the user is prompted to re-place the palm for recognition, and if the recognition still fails, the user is prompted to register.

The present invention provides a method for scanning palm veins to perform stereoscopic three-dimensional modeling. By performing three-dimensional scanning on the veins of the palm veins of a user, a three-dimensional diagram of the blood vessel and collaterals in a three-dimensional coordinate system is obtained, and then the three-dimensional diagram of the vascular and collaterals is preprocessed to remove blood vessels. In the veins, except for the main trunk and the first-level torso extending from the main trunk, the standard palm vein three-dimensional model and the standard palm vein three-dimensional model database are obtained, and the process of collecting and three-dimensional modeling of the user's palm vein is completed.

The present invention provides a method for scanning palm veins for three-dimensional three-dimensional recognition. After the three-dimensional modeling method is executed, after the user's standard palm vein three-dimensional model database is established, it is based on the number of blood vessels and blood vessels in adulthood. The elongation distance between the points will not change, and the ratio of the main vascular trunk to the trunk will never change. Perform the same scanning process on the palm veins of the currently recognized user to obtain the current palm vein three-dimensional model. In the vein three-dimensional model database, search for the number of first-level torso, the number of nodes of the first-level torso, and the only standard palm vein three-dimensional model that is strictly the same and the distance between nodes is the first level of comparison. If the comparison fails, further pass The method of integrating the veins finds the standard palm vein three-dimensional model consistent with the current three-dimensional model of palm vein for the second level comparison.

The present invention provides a method for scanning palm veins for three-dimensional modeling and recognition, which realizes the three-dimensional modeling and recognition of the palm veins of the user. No matter how the posture of the user's hand changes, the correct recognition can be performed and the user is enhanced. The user experience also ensures the accuracy of recognition.

Description of the drawings

FIG. 1 is a flow chart of the steps of a method for scanning palm veins to perform three-dimensional modeling according to Embodiment 1 of the present invention;

2 is a schematic diagram of a three-dimensional coordinate system provided by Embodiment 1 of the present invention;

FIG. 3 is a schematic diagram of the palm posture corresponding to step S1 provided by Embodiment 1 of the present invention; FIG.

Fig. 4 is a flow chart of the steps of a method for scanning palm veins for stereo three-dimensional recognition provided by an embodiment of the present invention.

Detailed ways

The following describes the implementation of the present invention in detail with reference to the accompanying drawings. The examples given are for illustrative purposes only and should not be understood as limiting the present invention. The accompanying drawings are for reference and illustrative purposes only, and do not constitute the scope of patent protection of the present invention. Limitation, because many changes can be made to the present invention without departing from the spirit and scope of the present invention.

Example 1

An embodiment of the present invention provides a method for scanning palm veins to perform three-dimensional modeling. As shown in the step flowchart of FIG. 1, in this embodiment, the method includes the following steps:

S1. Perform a stereo scan of a user's palm vein veins;

Further, the step S2 is specifically:

As shown in Figure 2, the metacarpophalangeal joint point of the thumb is taken as the origin O, the fixed direction extending horizontally to the index finger is taken as the X axis, the horizontal direction perpendicular to the X axis is taken as the Y axis, and the horizontal direction perpendicular to the X axis is taken as the Y axis. The vertical direction of the axis is the Z axis to establish a three-dimensional rectangular coordinate system. In this embodiment, the three-dimensional rectangular coordinate system strictly takes the vertical direction as the Z axis. In other embodiments, the X-axis, Y-axis and Z-axis of the three-dimensional rectangular coordinate system can be in other directions, and the only need to keep the origin unchanged . In addition, the coordinate system of this 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 the metacarpophalangeal joint points of the five fingers of the palm as the base point, intercepting the palm of the five fingers extending toward the wrist (stop extending at the point where the arc between the wrist and the palm changes the most) A three-dimensional view, performing infrared scanning on the three-dimensional view of the palm to obtain a corresponding three-dimensional view of blood vessels and veins.

Further, the step S4 specifically includes:

Further, the step S1 is specifically: performing a three-dimensional scan of the palm vein vein pattern under the posture of the user's palm in a naturally straight posture as shown in FIG. 1.

Embodiment 1 of the present invention provides a method for scanning palm veins to perform three-dimensional modeling. By performing three-dimensional scanning on the veins of the palm veins of the user, a three-dimensional view of the blood vessel and vein in a three-dimensional coordinate system is obtained, and then the three-dimensional view of the blood vessel and vein is preprocessed , Except for the main trunk and the first-level torso extending from the main trunk, the blood vessels and veins are removed, so as to obtain the standard palm vein three-dimensional model and the standard palm vein three-dimensional model database, and complete the process of collecting and three-dimensional modeling of the user's palm veins.

Example 2

The embodiment of the present invention also provides a method for scanning palm veins for three-dimensional recognition. Based on the above-mentioned method for scanning palm veins for three-dimensional modeling, as shown in FIG. 4, the method includes the steps:

Further, the step X3 specifically includes the steps:

X32. The number of first-level torso, the number of nodes of the first-level torso, and the distance between nodes in the current three-dimensional model of palm veins are matched to the same in the standard palm vein three-dimensional model library. The number of three-dimensional diagrams of large blood vessels and collaterals determines whether the current user has been recognized or not.

Further, in the step X32:

Further, the re-judgment step is:

In the process of calculating the integral, the volume is obtained by integration based on the coordinate point cloud data of the macrovascular context in the three-dimensional diagram of the macrovascular context. This can already be achieved in the field of mathematics, and this embodiment will not repeat its calculation. The process of integration.

Further, after the prompt recognition fails, the user is prompted to re-place the palm for recognition, if the recognition still fails, the user is prompted to register (may be a new user, the registration procedure needs to be started to enter new palm vein data ).

It should also be noted that in the standard palm vein three-dimensional model database, the entered basic user information corresponding to the user's standard palm vein three-dimensional model is also stored in the form of data link, so as to complete the identification and use in Fields such as attendance or palm vein payment.

Embodiment 2 of the present invention provides a method for scanning palm veins for three-dimensional three-dimensional recognition. After performing the three-dimensional three-dimensional modeling method, after the user’s standard palm vein three-dimensional model database is established, it is based on human adult blood vessels. The number and the elongation distance between the blood vessels will not change, and the ratio of the main blood vessel to the trunk will never change. Perform the same scanning process on the palm veins of the currently identified user to obtain the current palm vein three-dimensional model. Search the standard palm vein three-dimensional model database for the number of first-level torso, the number of nodes of the first-level torso, and the only standard palm vein three-dimensional model that is strictly the same and the distance between nodes is the first level of comparison. If the comparison fails Then, the standard palm vein three-dimensional model that is consistent with the current three-dimensional model of the palm vein is found for the second-level comparison by means of integrating the veins.

The embodiment of the present invention provides a method for scanning palm veins for three-dimensional modeling and recognition, which realizes the three-dimensional modeling and recognition of the palm veins of the user. No matter how the posture of the user's hand changes, it can be correctly recognized and enhanced. This improves the user experience while ensuring the recognition accuracy.

The above-mentioned embodiments are preferred embodiments of the present invention, but the embodiments of the present invention are not limited by the above-mentioned embodiments, and any other changes, modifications, substitutions, combinations, etc. made without departing from the spirit and principle of the present invention Simplified, all should be equivalent replacement methods, and they are all included in the protection scope of the present invention.

Claims

A method for scanning palm veins to perform stereoscopic three-dimensional modeling, which is characterized in that it comprises the following steps:

S1. Perform a stereo scan of a user's palm vein veins;

S2. Establish a three-dimensional coordinate system with the metacarpophalangeal joint point of the thumb as the origin;

S3. Extract a three-dimensional view of the vascular and collaterals of the palm in the three-dimensional coordinate system;

S4. Preprocessing the three-dimensional map of the blood vessel and collaterals to obtain a standard three-dimensional model of the palm vein for comparison;

S5. Integrating the standard palm vein three-dimensional models of all users to establish a standard palm vein three-dimensional model database.
The method for scanning palm veins for three-dimensional modeling according to claim 1, wherein the step S2 is specifically:

Take the metacarpophalangeal joint point of the thumb as the origin, the fixed direction extending horizontally to 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. The axis establishes a three-dimensional rectangular coordinate system.
The method for scanning palm veins to perform three-dimensional modeling according to claim 2, wherein the step S3 is specifically:

Taking the metacarpophalangeal joint points of the five fingers of the palm as the base point, a three-dimensional view of the blood vessels and veins extending from the five fingers to the wrist is intercepted.
The method for scanning palm veins for three-dimensional modeling according to claim 3, wherein said step S4 specifically comprises:

S41. Select the blood vessel with the largest lateral cross-sectional area in the three-dimensional view of the blood vessel and collaterals as the backbone;

S42. Taking the main trunk as a reference, retaining the first-level trunk extending outward from the main trunk, and excluding other trunks extending outward from the first-level trunk, to obtain a three-dimensional view of the large blood vessels and veins;

S43. Establish a three-dimensional model of the three-dimensional view of the large blood vessels and veins as a standard three-dimensional model of palm veins.
The method for scanning palm veins to perform three-dimensional modeling according to claim 4, wherein the step S1 is specifically: performing three-dimensional modeling of the veins of the palm veins in the posture of the palm of the user in a naturally straightened posture. scanning;

In the standard palm vein three-dimensional model database in the step S5, the number of first-level trunks, the number of nodes of the first-level trunk, and the number of first-level trunks of the large blood vessel chord three-dimensional diagram in each of the standard palm vein three-dimensional models are calculated and stored. The distance between nodes.
A method for scanning palm veins to perform three-dimensional three-dimensional recognition, which is characterized in that it comprises the following steps:

X1. Carry out a stereo scan of a palm vein vein pattern of a user in any posture;

X2. Perform steps S2 to S4 as described in any one of claims 1 to 5 to obtain the current palm vein three-dimensional model;

X3. Compare the current palm vein three-dimensional model with the standard palm vein three-dimensional model library, and output the recognition result.
The method for scanning palm veins to perform three-dimensional three-dimensional recognition according to claim 6, wherein said step X3 specifically includes the steps of:

X31. Calculate the number of first-level torsos, the number of nodes of the first-level torso, and the distance between nodes in the large blood vessel context three-dimensional map of the current palm vein three-dimensional model;

X32. The number of first-level torso, the number of nodes of the first-level torso, and the distance between nodes in the current three-dimensional model of palm veins are matched to the same in the standard palm vein three-dimensional model library. The number of three-dimensional diagrams of large blood vessels and collaterals determines whether the current user has been recognized or not.
The method for scanning palm veins to perform three-dimensional three-dimensional recognition according to claim 7, characterized in that, in the step X32:

If the number of matching stereograms of the same large blood vessel context is 1, the basic information of the user corresponding to the matching three-dimensional diagram of large blood vessels will be output and the recognition passed, if the number is 0, the recognition failed, if the number is greater than or equal to 2, Then enter the judgment step again.
The method for scanning palm veins for three-dimensional three-dimensional recognition according to claim 8, wherein the re-judgment step is:

Integrate the three-dimensional diagram of the large blood vessel and the same large blood vessel in the current three-dimensional model of the palm vein and the three-dimensional diagram of the large blood vessel that is matched to obtain the corresponding volume of the current large blood vessel and other large blood vessels;

Find out the three-dimensional diagram of the macrovascular choroid whose volume is the only one within the error range of the current macrovascular choroid volume among the other macrovascular choroid volumes, and output the corresponding user's basic information and prompt the identification to pass, if not found If it is out, it prompts that the recognition has not passed.
The method of scanning palm veins for three-dimensional three-dimensional recognition according to claim 9, characterized in that, after the prompt recognition fails, the user is prompted to re-place the palm for recognition, and if the recognition still fails, the user is prompted registered.