CN117152802A - Finger vein recognition and detection method and device integrating texture and living body characteristics - Google Patents
Finger vein recognition and detection method and device integrating texture and living body characteristics Download PDFInfo
- Publication number
- CN117152802A CN117152802A CN202311258660.5A CN202311258660A CN117152802A CN 117152802 A CN117152802 A CN 117152802A CN 202311258660 A CN202311258660 A CN 202311258660A CN 117152802 A CN117152802 A CN 117152802A
- Authority
- CN
- China
- Prior art keywords
- finger
- finger vein
- living body
- image
- imaging device
- 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.)
- Pending
Links
- 210000003462 vein Anatomy 0.000 title claims abstract description 187
- 238000001514 detection method Methods 0.000 title claims abstract description 36
- 238000005286 illumination Methods 0.000 claims abstract description 101
- 238000003384 imaging method Methods 0.000 claims abstract description 91
- 230000005540 biological transmission Effects 0.000 claims abstract description 69
- 238000000034 method Methods 0.000 claims abstract description 21
- 238000004364 calculation method Methods 0.000 claims abstract description 10
- 230000004044 response Effects 0.000 claims description 67
- 230000004927 fusion Effects 0.000 claims description 36
- 238000010586 diagram Methods 0.000 claims description 29
- 238000012545 processing Methods 0.000 claims description 20
- 238000001914 filtration Methods 0.000 claims description 7
- 238000010276 construction Methods 0.000 claims description 6
- 238000003672 processing method Methods 0.000 claims description 2
- 238000005316 response function Methods 0.000 abstract description 2
- 238000002601 radiography Methods 0.000 description 8
- 230000001276 controlling effect Effects 0.000 description 7
- 238000010521 absorption reaction Methods 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 230000004298 light response Effects 0.000 description 6
- 230000009286 beneficial effect Effects 0.000 description 5
- 230000000694 effects Effects 0.000 description 4
- 210000001519 tissue Anatomy 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 238000013519 translation Methods 0.000 description 3
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 description 2
- 230000009471 action Effects 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 238000002834 transmittance Methods 0.000 description 2
- 102000001554 Hemoglobins Human genes 0.000 description 1
- 108010054147 Hemoglobins Proteins 0.000 description 1
- 230000003044 adaptive effect Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 210000004204 blood vessel Anatomy 0.000 description 1
- 229910002092 carbon dioxide Inorganic materials 0.000 description 1
- 239000001569 carbon dioxide Substances 0.000 description 1
- 238000006073 displacement reaction Methods 0.000 description 1
- 210000002615 epidermis Anatomy 0.000 description 1
- 238000001727 in vivo Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000007430 reference method Methods 0.000 description 1
- 238000002310 reflectometry Methods 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/14—Vascular patterns
-
- 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
- G06V40/40—Spoof detection, e.g. liveness detection
- G06V40/45—Detection of the body part being alive
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Vascular Medicine (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The application belongs to the technical field of biological recognition, and particularly relates to a finger vein recognition and detection method and device integrating texture and living body characteristics, wherein the method comprises the steps of firstly installing an imaging device, a plurality of beam splitters, a plurality of reflectors, a filter, a light source module and a processor at a preset position; and (3) placing the finger to be detected in a preset position to obtain a plurality of near infrared vein contrast images, performing pixel-level registration, then cutting out the images of the regions of interest with different light intensities, combining the images into a multichannel image, establishing a transmission model of the finger by utilizing the known illumination intensity ratio of the multichannel vein images and a camera illumination response function, performing quantitative calculation of transmission illumination offset of each point on the finger image, and comparing the registered finger transmission illumination offset image with the transmission offset image of the finger to be detected to obtain a comparison result of whether the finger is the same finger and whether the finger is a living body. The application can solve the problem that the finger vein prosthesis attack and the video replay attack in the prior art are weak to resist.
Description
Technical Field
The application belongs to the technical field of biological recognition, and particularly relates to a finger vein recognition and detection method and device integrating textures and living body characteristics.
Background
Along with the rapid development of technologies such as the internet of things, big data, cloud computing and artificial intelligence, the biological recognition technology is also greatly developed, and key technologies for finger vein recognition are also beginning to be applied to various fields.
The finger vein recognition technology is a technology for recognizing by utilizing the internal biological characteristics which cannot be seen from the outside, specifically, infrared light with specific wavelength is utilized to irradiate hemoglobin in finger vein blood, and an image sensor is utilized to acquire clear finger vein images, so that the finger vein has the advantages of high concealment, high uniqueness, high stability, living body detection and simplicity and convenience, but the hidden danger of being attacked also exists, and when the original finger vein images are stolen, namely, finger vein videos acquired in a vein recognition terminal are acquired by other people, the finger vein images are easily manufactured into prostheses, and replay attacks are carried out.
At present, for the manufactured prosthesis, the living body detection of a single image is carried out by using texture statistics, pulse motion and other methods, but the detection effect of the methods on replay attack of video is weak, particularly when video replay is carried out through a terminal video acquisition channel, a terminal main control system is more difficult to resist the attack of the video replay, the existing method respectively carries out texture feature extraction and living body feature extraction, then vein recognition and living body detection are correspondingly carried out, and the calculated amount is large.
Disclosure of Invention
The application aims to provide a finger vein recognition and detection method and device integrating texture and living body characteristics, which are used for solving the problem of weak resistance to finger vein prosthesis attack and video replay attack in the prior art.
The basic scheme provided by the application is as follows: a method of finger vein recognition and detection incorporating texture and living body features, comprising:
s1: the imaging device, the beam splitters, the reflectors, the filter, the light source module and the processor are arranged at preset positions to form a finger vein detection device;
s2: the finger vein image processing method comprises the steps of obtaining a finger sample, controlling a light source module to emit light beams to transmit the finger sample through a processor, dividing the light beams transmitted by the finger sample into new transmitted light beams and reflected light beams by a beam splitter, reflecting the transmitted light beams and the reflected light beams to an imaging plane of an imaging device through a reflecting mirror, obtaining finger vein images with different light intensities through one-time imaging of the imaging device, cutting the finger vein images obtained through one-time imaging according to the different light intensities, performing pixel-level registration and region-of-interest cutting, and generating a plurality of finger vein images.
S3: carrying out quantitative calculation on a plurality of finger vein images through a transmission model and an illumination response curve to obtain a transmission illumination offset image of the finger sample, and putting the transmission illumination offset image serving as a fusion feature image of finger vein line distribution features and living body features into a feature library;
s4: and obtaining a finger to be detected, generating a fusion characteristic diagram and an illumination response curve of the finger vein line distribution characteristics and the living body characteristics to be detected by processing the finger to be detected through S2 and S3, and comparing the fusion characteristic diagram and the illumination response curve with the characteristic library to generate a comparison result.
The principle and the advantages of the application are as follows: when the device is used, the imaging device, the beam splitters, the filter plates, the light source modules and the processor are arranged at preset positions, wherein the imaging device is used for collecting finger vein images, the light source modules are used for emitting light sources such as near infrared light to enable finger veins to appear, the filter plates are used for filtering wave bands of the light source modules, the beam splitters are used for dividing reflected light of fingers into transmitted light beams and reflected light beams, so that the imaging device is convenient to collect, and images collected by the imaging device are collected at the same time, so that displacement phenomenon caused by batch collection can be avoided; the processor processes the finger vein image generated by the imaging device, carries out quantitative calculation through a transmission model-illumination response curve, generates a transmission illumination offset image of the finger sample, and stores the transmission illumination offset image as a feature map into a feature library, wherein the feature map comprises vein texture distribution features and living body features; and finally, collecting and quantitatively calculating the finger to be detected in the same mode, wherein the finger to be detected can be used for identifying the vein lines, and can be compared to judge whether the finger to be detected is a prosthesis or not and effectively resist replay attack.
Therefore, the application has the advantages that the imaging device synchronously collects a plurality of vein images under one-time illumination intensity, and the beam splitter can distinguish the light intensity generated by the light source module, so that the light intensity with different degrees is generated, a plurality of finger vein images with different light intensities are generated, the finger vein images are processed and calculated through the transmission model, therefore, the application provides the finger vein recognition detection method based on the transmission model, which can solve the problems that in the prior art, living body characteristics and texture distribution characteristics are required to be calculated separately, and the problem that the living body characteristics and the texture distribution characteristics are complicated is solved, and the problem that the attack of finger vein prosthesis and the replay attack of videos are weak is solved.
Further, in the step S1, the imaging device, the beam splitter, the plurality of reflectors, the filter, the light source module and the processor are installed at a preset position specifically: the imaging device and the light source module are electrically connected with the processor, the beam splitter is arranged according to a preset angle, and the reflecting mirror and the beam splitter are arranged in mirror symmetry; the imaging plane of the imaging device corresponds to the reflection path of the reflector; the filter is used for filtering the wave band emitted by the light source module.
The beneficial effects are that: the light source module and the filter plate can enable light beams transmitted and reflected on the beam splitter to keep effectiveness, then the processor controls the imaging device to collect finger vein images with different light intensities once through the beam splitting effect of the beam splitter, the user can conveniently collect the finger vein images, the user does not need to place fingers for more than 0.5 seconds in a matching way, and the accuracy of comparison and subsequent analysis is improved.
Further, the S2 includes:
s2-1: acquiring a finger sample, adjusting the light intensity of the light source module, and acquiring finger vein images of the finger sample under different light intensities through an imaging device;
s2-2: cutting the acquired finger vein images according to different light intensities to generate a plurality of finger vein images;
s2-3: and carrying out pixel level registration and region-of-interest clipping on finger areas in the plurality of finger vein images, and sequentially placing the plurality of finger vein images into the multi-channel image according to the light intensity to generate the multi-channel image.
The beneficial effects are that: the light intensity is regulated once, a plurality of finger vein images with different light intensities are acquired through the acquisition of the finger vein detection device, and then the multichannel image is generated through the multichannel image processing, so that the calculation of a transmission model-illumination response curve is facilitated.
Further, the step S3 includes:
s3-1: acquiring an illumination response curve of the imaging device;
s3-2: a transmission model is built, the light intensity ratio of the multichannel image, the illumination response curve and the plurality of finger vein images is input into the transmission model, a transmission illumination deviation image of the finger sample is output, and the image is used as a fusion characteristic image of finger vein line distribution characteristics and living body characteristics;
s3-3: constructing a feature library, storing user registration information corresponding to a finger sample and an illumination response curve of an imaging device, and storing a transmission illumination offset image of the finger sample into the feature library as a fusion feature map of finger vein line distribution features and living body features.
The beneficial effects are that: the illumination response curve of the imaging device is acquired in advance, the light intensity ratio of the multichannel image, the illumination response curve and the plurality of finger vein images is input into the transmission model for processing, and the fusion characteristic image of the finger vein line distribution characteristic and the living body characteristic is output and can be used as the characteristic image of the finger sample, so that living body detection and texture identification are facilitated.
Further, the S4 includes:
s4-1: acquiring a finger to be detected, and processing the finger to be detected through S2 and S3 to generate a characteristic diagram and an illumination response curve of the finger to be detected;
s4-2: constructing a classifier, comparing the feature map and the illumination response curve of the finger to be detected with the feature map and the illumination response curve in the feature library as inputs of the classifier, and outputting a comparison result.
The beneficial effects are that: and (3) carrying out the same processing on the finger vein image of the finger to be detected, generating a characteristic image of the finger to be detected, and comparing the characteristic image with the characteristic image in the characteristic library to identify whether the finger to be detected is a living body or not and whether the finger to be detected is matched or not.
Further, the S4-2 includes:
s4-2-1: the output comparison result is a set comprising a first scalar and a second scalar, and the labels of the first scalar and the second scalar comprise 1 and 0;
if the scalar I and the scalar II in the set are both 1, the finger to be detected is a living body, and vein line characteristics are matched; if not, S4-2-2 is carried out;
s4-2-2: if the scalar I in the set is 1 and the scalar II is 0, the finger to be detected is a living body, but the vein line characteristics are not matched;
if the scalar I in the set is 0 and the scalar II is 1, the finger to be detected is not living, but vein line characteristics are matched;
if the first scalar in the set is 0 and the second scalar is 0, the finger to be detected is non-living body, and the vein line characteristics are not matched.
The beneficial effects are that: by analyzing the scalar in the detection result, the exact identification result can be obtained.
The finger vein recognition and detection device integrating textures and living body characteristics comprises an imaging device, a plurality of beam splitters, a plurality of reflectors, a filter, a light source module and a processor, wherein the imaging device and the light source module are electrically connected with the processor, the beam splitters are arranged according to a preset angle, the reflectors are arranged in mirror symmetry with the beam splitters, and the mirror surfaces of the reflectors can reflect light beams emitted by the beam splitters into the imaging device; the filter is used for filtering wave bands emitted by the light source module, the processor is used for controlling the light source module to be turned on and turned off and controlling the light intensity of the light source module, the beam splitter splits a light beam emitted by the light source module into a transmission light beam and a reflection light beam, the reflection light beam is reflected to the imaging device by the reflection mirror, and the controller is also used for controlling the imaging device to receive the reflection light beam and the transmission light beam to generate a finger vein image.
Further, the system also comprises a model construction module, a feature library, a data processing module and a comparison module;
the model construction module is used for constructing a transmission model and a classifier;
the data processing module is used for acquiring an illumination response curve of the imaging device, and is also used for calculating a transmission illumination offset image of the finger sample according to the transmission model and the illumination response curve and taking the transmission illumination offset image as a fusion characteristic diagram of finger vein line distribution characteristics and living body characteristics;
the feature library is used for storing a fusion feature map of finger vein line distribution features and living body features, an illumination response curve and user registration information corresponding to the finger sample;
the data processing module is also used for calculating the finger to be detected and acquiring a fusion characteristic diagram of the finger vein line distribution characteristic and the living body characteristic of the finger to be detected and a corresponding illumination response curve;
the comparison module is used for comparing the fusion characteristic graph of the finger vein line distribution characteristics and the living body characteristics of the finger to be detected and the illumination response curve with the stored data in the characteristic library through the classifier to generate a comparison result.
Drawings
FIG. 1 is a block flow diagram of a first embodiment of the present application;
FIG. 2 is a schematic diagram of a device according to a first embodiment of the present application;
FIG. 3 is a view of a finger vein image acquired by an imaging device at different intensities in accordance with a first embodiment of the present application;
FIG. 4 is a label drawing in an embodiment of the present application;
FIG. 5 is a registration diagram in an embodiment of the present application;
FIG. 6 is a schematic diagram of an illumination response curve, an illumination response curve of a non-venous point, and an illumination response curve of a venous point of an imaging device according to the present application;
FIG. 7 is a schematic diagram II of the illumination response curves of the imaging device, the illumination response curves of the non-venous points and the illumination response curves of the venous points;
FIG. 8 is a schematic diagram of a device according to a second embodiment of the present application;
fig. 9 is a schematic structural diagram of a third embodiment of the present application.
Detailed Description
The following is a further detailed description of the embodiments:
the labels in the drawings of this specification include: processor 1, image device 2, camera one 201, camera two 202, camera three 203, camera four 204, camera five 205, camera six 206, beam splitter 3, beam splitter one 301, beam splitter two 302, beam splitter three 303, light source module 4, filter 5, reflector 6, baffle one 7, baffle two 8, baffle three 9, baffle four 10.
The vein is a blood vessel in a human body, is responsible for sending carbon dioxide, waste and the like back to the heart along with blood for treatment, is distributed with rich vein networks under the epidermis of the human hand, the vein grows thicker along with the development of the hand after birth, but the distribution and the shape of the vein networks are not changed, and after adult, the vein networks are stable and are not changed, so the vein of the human hand can be used as the basis of the biological characteristics of personal identification, and the vein of the finger, palm and the like of the hand is commonly used as the biological characteristic parts of personal identification at present.
The current finger vein recognition is used as in-vivo biological feature recognition, has very high precision and safety, has many applications in high-end markets, but has the hidden danger of being attacked, if an original finger vein image is stolen, the finger vein image is easy to be attacked by a fake prosthesis, and if finger vein videos acquired in a vein recognition terminal are accidentally acquired, the finger vein image can be possibly used for replay attack or prosthesis attack and the like.
For the prosthesis attack, the existing methods such as texture statistics, pulse motion and the like detect a single image, but the methods have weaker detection effect on video replay attack, and particularly when a terminal video acquisition channel is hijacked to replay video, the terminal main control system is harder to resist the attack of video replay; therefore, the application provides a finger vein recognition detection device and method based on a transmission model.
In the present application, the finger sample represents a finger of a unique feature that each user has been acquired.
Embodiment one:
embodiment one is substantially as shown in fig. 1 and 2: a method of finger vein recognition and detection incorporating texture and living body features, comprising:
s1: the imaging device 2, the beam splitters 3, the reflectors 6, the filter 5, the light source module 4 and the processor 1 are arranged at preset positions to form a finger vein detection device; in this embodiment, the imaging device 2 and the light source module 4 are electrically connected with the processor 1, the beam splitter 3 is set according to a preset angle, and the reflecting mirror 6 is set in mirror symmetry with the beam splitter 3; the imaging plane of the imaging device 2 corresponds to the reflection path of the mirror 6; the filter 5 is used for filtering the wave band emitted by the light source module 4.
S2: the finger sample is obtained, the light source module 4 is controlled by the processor 1 to emit light beams to transmit the finger sample, the beam splitter 3 divides the light beams transmitted by the finger sample into new transmitted light beams and reflected light beams, the transmitted light beams and the reflected light beams are reflected to an imaging plane of the imaging device 2 by the reflector 6, the imaging device 2 images the finger vein images with different light intensities once, the finger vein images obtained by the imaging once are cut according to the different light intensities, and pixel-level registration and region-of-interest cutting are carried out to generate a plurality of finger vein images.
The step S2 comprises the following steps:
s2-1: acquiring a finger sample, adjusting the light intensity of the light source module 4, and acquiring finger vein images of the finger sample under different light intensities through the imaging device 2;
s2-2: cutting the acquired finger vein images according to different light intensities to generate a plurality of finger vein images;
s2-3: and carrying out pixel level registration and region-of-interest clipping on finger areas in the plurality of finger vein images, and sequentially placing the plurality of finger vein images into the multi-channel image according to the light intensity to generate the multi-channel image.
Specifically, the finger vein detection device composed of the imaging device 2, the beam splitters 3, the reflectors 6, the filter 5, the light source module 4 and the processor 1 comprises a rectangular shell, a contrast opening is formed in the top of the shell at the side, the filter 5 is installed at the contrast opening, the light source module 4 is arranged above the contrast opening, in the embodiment, the light source module 4 is a near-infrared LED lamp, and the filter 5 is a near-infrared filter 5; to ensure that the light source module 4 can emit near infrared uniform illumination, a light guide plate is used to generate uniformly distributed near infrared illumination.
One end of the beam splitter 3 is fixed at one side of the contrast port, and the mirror surface of the beam splitter 3 can receive the light beam diverging from the contrast port to the inside of the housing, in this embodiment, the mirror surface of the beam splitter 3 is 45 ° with the contrast port, and the beam splitter 3 adopts a model of 60% transmission and 40% reflection, so the light beam passing through the contrast port can be split into a light beam with 60% light intensity and a light beam with 40% light intensity by the action of the beam splitter 3.
The two reflectors 6 are arranged in the application, the reflectors 6 are arranged in a mirror symmetry way with the beam splitter 3, the mirror surface of the reflectors 6 can receive the light beams with different light intensities emitted by the beam splitter 3 completely, the imaging device 2 is arranged in the shell, and when the reflectors 6 receive the light beams of the beam splitter 3, the reflected light beams can be received by the imaging device 2; because two reflectors 6 are arranged, one reflector 6 receives 60% of the light intensity of the beam splitter 3, the other reflector 6 receives 40% of the light intensity of the beam splitter 3, and the light beams reflected by the reflectors 6 can be reflected to the imaging device 2, specifically, one reflector is reflected to the left plane of the imaging device 2, and the other reflector is reflected to the right plane of the imaging device 2, therefore, when a finger sample is placed at a radiography port, through one acquisition, transmission finger vein images with the light intensity of 60% and 40% can be respectively acquired.
In the present application, the imaging device 2 adopts a CMOS sensor, and the type of the beam splitter 3 may also be selected according to the user's requirements in other embodiments of the present embodiment, for example, the types of 60% transmission and 40% reflection; the number of the reflectors 6 can influence the number of finger vein images acquired by the imaging device 2 at one time, the number of the reflectors 6 is preferably 2, and in other embodiments of the application, a larger number of reflectors 6 can be selected, and the reflectivity of the reflectors 6 is the same by default in the application; the shell of the application adopts the black box, and the filter 5 is arranged just below the finger, so that a contrast image with only the finger area can be completely formed, the rest part is black, and the non-finger area can not be excessively influenced when covered on the finger area.
In finger vein radiography technology, because the infrared light source illumination intensity distribution is uneven, the thickness and depth of the finger veins and the reflection and absorption rate of surrounding physiological tissues are different, and the dynamic range of single imaging is limited by the photosensitive dynamic range of a camera optical sensor, the dynamic range is generally lower, so that the contrast of finger vein images is lower, overexposure and underexposure are easy to occur, and therefore, the light intensity is adjusted after illumination imaging quality evaluation and calculation of a plurality of areas are carried out according to the vein images acquired on site, so that the finger vein images which are overexposed and underexposed can be prevented from being acquired as much as possible.
In the present application, according to the device structure diagram in fig. 2, the finger sample is placed at the radiography port, and the adaptive dimming of the light source module 4 is first performed, and the light intensity at this time is denoted as E 1 An image is obtained in the imaging device 2, wherein the image is a contrast image of a finger sample under the action of the beam splitter 3 and the reflecting mirror 6 and generated under two different light intensities, and the two contrast images are in mirror symmetry and are marked as F 11 And F 12 Indicated at E 1 Finger vein radiography under light intensity, wherein the former digit of the subscript represents sampling times, and the latter digit of the subscript represents weaker light intensity and stronger light intensity;
taking m finger vein contrast pairs with different light intensities for several times, calculating the lowest illumination of the contrast pairs of the finger sample, which are not underexposed, to be Emin through a light response curve of a preset imaging device 2, wherein the highest illumination of the exposure is Emax, and selecting a pair of finger vein images F with different light intensities from the m finger vein contrast pairs c1 And F c2 Firstly, respectively finding out finger outline and two finger knuckle fold regions (the partial region has weak absorption of near infrared light by finger physiological tissue), and respectively binarizing into B c1 And B c2 Using the contour, fold region and binarization result to image the finger vein F c1 And F c2 Performing pixel level registration, extracting a registered rectangular region containing fingers, placing the rectangular region into a multi-channel image, wherein the multi-channel image used in the application is a two-channel image, placing a finger vein image with strong and weak light into a first channel and placing a finger vein image with strong and weak light into a second channel, thereby generating a multi-channel image containing finger vein images with multiple light intensities, and as shown in fig. 3 and 5, fig. 3 is a view of acquisition and capture of the image device 2 at one timeFig. 5 shows a finger vein image captured under different light intensities, wherein an original image is cut into left and right parts to be changed into two pictures, and ROIs in the finger body are respectively drawn in the two pictures to be combined into a two-channel image.
S3: carrying out quantitative calculation on a plurality of finger vein images through a transmission model and an illumination response curve to obtain a transmission illumination offset image of the finger sample, and putting the transmission illumination offset image serving as a fusion feature image of finger vein line distribution features and living body features into a feature library;
s3 comprises the following steps:
s3-1: acquiring an illumination response curve of the imaging device 2;
s3-2: a transmission model is built, the light intensity ratio of the multichannel image, the illumination response curve and the plurality of finger vein images is input into the transmission model, a transmission illumination deviation image of the finger sample is output, and the image is used as a fusion characteristic image of finger vein line distribution characteristics and living body characteristics;
s3-3: constructing a feature library, storing user registration information corresponding to a finger sample and an illumination response curve of the imaging device 2, and storing a transmission illumination offset image of the finger sample as a fusion feature map of finger vein line distribution features and living body features into the feature library.
In the present application, since the light source used is near infrared light for acquiring the illumination response curve of the imaging device 2 when imaging is blocked by a finger, and each point on the image generated by imaging the finger vein using near infrared is formed by light that reaches the pixel of the imaging device 2 through absorption and attenuation, the illumination response curve is defined as:
X(x，y)＝f(E(x，y)-t)
wherein t represents the offset of illumination intensity, t is equal to or greater than 0, X is an obtained finger vein image, (X, y) is an image coordinate, f is an illumination response curve of an optical sensor in the imaging device 2, E (X, y) is the light intensity received when the position of the captured image on the optical sensor is (X, y), and X (X, y) is the gray level of an image pixel at the position.
Because of the absorption of the physiological tissues of the finger, only when E (x, y) -t is larger than the original minimum illumination, a response with gray values larger than 0 can be formed on the pixels of the imaging device 2, and radiography can be performed; meanwhile, as the absorption rate of each point on the finger is different, particularly the absorption rate difference between a vein area and a non-vein area is larger, the method is also a main method of near infrared vein radiography, T (X, y) corresponding to each point X (X, y) on a finger vein image is calculated, a transmission offset image of the finger vein is formed and is recorded as T (X, y), and a new image T is formed.
The transmission model is constructed, the mapping method of the transmission model is condition Pix2Pix in Pix2Pix, firstly, a plurality of original images and label images are required to be input into the model for training, then, a multi-channel image, an illumination ratio and an illumination response curve are received for processing, in the output process, as the illumination response curve of each point on a finger vein is a translation t result according to the acquired illumination response curve of the imaging device 2, the method comprises the following steps:
X(x，y)＝f(E-t(x，y))
t is related to the point (x, y), that is, the intensity of the near infrared light absorbed by the finger tissue of the point, and the translational value t (x, y) of each point in the finger outline area and the vein feature of the point (x, y) are recorded, and the E is evolved through the E (x, y), because the light source module 4 generates uniform light after using the light guide plate in the application, and the E can be regarded as invariable.
And outputting a fusion characteristic diagram of the finger vein line distribution characteristic and the living body characteristic.
By adopting experimental demonstration, a prosthesis sample with gradually changed thickness and uniform medium is placed into a finger vein detection device to be static, the illumination duty ratio of a light source is adjusted from 0 to 255, 256 finger sample images with different duty ratios are acquired, 256 static images with different light intensities of the same scene can be obtained (reference: development P E, malikJ.recording high dynamic range radiance maps from photographs [ J ]. Siggraph,1997, 97), the illumination response curve f0 of the camera is acquired according to the reference method, as shown by the f0 curve of fig. 5, the curve has monotonically increasing characteristic, discrete value solutions can be obtained after multi-light intensity sampling, the illumination response function f0 also has inverse function g0, and according to the prior demonstration, the illumination response curve on all pixel points is obtained by rightward translation of the f0 curve, and the translation distance is the embodiment of the transmittance.
Specifically, as shown in fig. 6, under the condition of proper light intensity ratio, the acquired vein images with two light intensities do not have the conditions of underexposure and overexposure, and a point A is arbitrarily taken in the image, so that two gray values X under the two light intensities can be found A1 And X A2 Then the response curve at point a can be expressed by the following calculation formula:
X A1 ＝f0(q 1 -t A )
X A2 ＝f0(q 2 -t A )
wherein q 1 And q 2 The light intensity is expressed, the ratio of the light intensity to the light intensity is recorded as k,1 is less than k, and the illumination response curve of the point A is that the f0 curve shifts rightwards by t A Obtaining a distance;
the deduction is carried out according to the calculation formula, namely:
g0(X A1 )＝q 1 -t A
g0(X A2 )＝q 2 -t A
q 2 ＝kq 1
t A the solution calculation formula of (2) is as follows:
t A ＝k*g0(X A1 )-g0(X A2 )/(k-1)
wherein g0 represents the inverse of f0, and g0 is also a monotonically increasing function;
therefore, the parameter t of the illumination response offset of the point A can be obtained A I.e. the reflection of the transmission illumination offset image characteristic of the finger vein image at the point A, the transmission illumination response offset parameter t A Is related to the initial value of the f0 curve, relative to other points such as B, C, e.g. t B 、t c Also regarding the initial value of f0, the points a, B, C are shown in fig. 4 for example, the corresponding light response curves are shown in fig. 7 for three light response curves f0, fA and fB, so that the deviation of the light response parameters is stable, i.e., the same living body, even if the light intensities are different, the transmittance characteristic of the obtained finger vein image is stable with respect to f0, even if the f0 is deviated, the relative transmission light response values between any two points a, B are stable, i.e., the deviation between the curves of fA and fB is stable, and the deviation between the curves of fA and fB of the prosthesis is very different from the deviation position of the living body, so that the deviation of the light response curves of a plurality of points on the prosthesis image and the living body image is impossible to be identical, and thus the transmission light deviation map reflects the distribution characteristic of vein lines and can also be used as the line identification characteristic.
Next step S4: acquiring a finger to be detected, generating a fusion characteristic diagram and an illumination response curve of vein line distribution characteristics and living body characteristics of the finger to be detected through S2 and S3 processing, and comparing the fusion characteristic diagram and the illumination response curve with those in a characteristic library to generate a comparison result; in S4, it includes:
s4-1: acquiring a finger to be detected, and processing the finger to be detected through S2 and S3 to generate a fusion characteristic diagram and an illumination response curve of vein line distribution characteristics and living body characteristics of the finger to be detected;
s4-2: constructing a classifier, wherein the classifier used in the application can output 2 bits, specifically, inputting a fusion characteristic diagram and an illumination response curve of a finger to be detected, and a fusion characteristic diagram and an illumination response curve in a characteristic library into the classifier, comparing the fusion characteristic diagram and the illumination response curve with a discriminator in the classifier, and outputting a comparison result; specifically, S4-2 includes:
s4-2-1: the output comparison result is a set comprising a first scalar and a second scalar, and the labels of the first scalar and the second scalar comprise 1 and 0;
if the scalar I and the scalar II in the set are both 1, the finger to be detected is a living body, and vein line characteristics are matched; if not, S4-2-2 is carried out;
s4-2-2: if the scalar I in the set is 1 and the scalar II is 0, the finger to be detected is a living body, but the vein line characteristics are not matched;
if the scalar I in the set is 0 and the scalar II is 1, the finger to be detected is not living, but vein line characteristics are matched;
if the first scalar in the set is 0 and the second scalar is 0, the finger to be detected is non-living body, and the vein line characteristics are not matched.
In this embodiment, the above feature matching or feature mismatch may represent the texture information of the finger, and the classifier may be the existing one, which is not described in detail in the present application.
Therefore, in the application, by actively changing the near infrared light intensity and carrying out light intensity-gray scale response analysis on the collected finger vein image by using a transmission model, replay attack, prosthesis attack and finger vein image and video of a living body can be distinguished.
In another embodiment of the present embodiment, the finger vein recognition and detection device further includes a vein recognition and detection device that fuses a texture and a living body feature, including an imaging device 2, a plurality of beam splitters 3, a plurality of reflectors 6, a filter 5, a light source module 4, and a processor 1, where the imaging device 2 and the light source module 4 are electrically connected to the processor 1, the beam splitters 3 are set according to a preset angle, the reflectors 6 are set in mirror symmetry with the beam splitters 3, and a mirror surface of the reflectors 6 can reflect a light beam emitted by the beam splitters 3 onto the imaging device 2; the filter 5 is used for filtering a wave band emitted by the light source module 4, the processor 1 is used for controlling the light source module 4 to be turned on and turned off and controlling the light intensity of the light source module 4, the beam splitter 3 splits a light beam emitted by the light source module 4 into a transmission light beam and a reflection light beam, the reflection mirror 6 reflects the transmission light beam and the reflection light beam to the imaging device 2, and the controller is also used for controlling the imaging device 2 to receive the reflection light beam and the transmission light beam to generate a finger vein image.
The system also comprises a model construction module, a feature library, a data processing module and a comparison module;
the model construction module is used for constructing a transmission model and a classifier;
the data processing module is used for acquiring an illumination response curve of the imaging device 2, and is also used for calculating a transmission illumination offset image of the finger sample according to the transmission model and the illumination response curve and taking the transmission illumination offset image as a fusion characteristic diagram of finger vein line distribution characteristics and living body characteristics;
the feature library is used for storing a fusion feature map of finger vein line distribution features and living body features, an illumination response curve and user registration information corresponding to the finger sample;
the data processing module is also used for calculating the finger to be detected and acquiring a fusion characteristic diagram of the finger vein line distribution characteristic and the living body characteristic of the finger to be detected and a corresponding illumination response curve;
the comparison module is used for comparing the fusion characteristic graph of the finger vein line distribution characteristics and the living body characteristics of the finger to be detected and the illumination response curve with the stored data in the characteristic library through the classifier to generate a comparison result.
Embodiment two:
as shown in fig. 8, the difference between the second embodiment and the first embodiment is that in the second embodiment, the beam splitter 3 in the finger vein recognition and detection device integrating the texture and the living body characteristics includes a first beam splitter 301, a second beam splitter 302 and a third beam splitter 303, the imaging device 2 includes a first camera 201 and a second camera 202, a third camera 203 and a fourth camera 204, a first baffle 7, a second baffle 8, a third baffle 9 and a fourth baffle 10 are arranged in the finger vein detection device, the first baffle 7 and the second baffle 8 are fixed at the bottom of the inner wall of the housing and are arranged in parallel with each other, the third baffle 9 and the fourth baffle 10 are fixed on the side wall in the housing, the third baffle 9 and the fourth baffle 10 are parallel with each other and are perpendicular to the first baffle 7 or the second baffle 8, and the other end of the third baffle 9 is connected to the second baffle 8; the other ends of the first baffle 7, the second baffle 8 and the fourth baffle 10 are free ends, one end of the beam splitter 301 is arranged at the free end of the second baffle 8, and the other end of the beam splitter 301 is arranged on the inner wall of the shell, so that an included angle between the beam splitter 301 and the filter 5 at the radiography port is 45 degrees, and an included angle between the beam splitter 301 and an extension line of the second baffle 8 is 45 degrees; one end of the beam splitter 302 is connected with the free end of the baffle IV 10, and the other end of the beam splitter 302 is connected with the inner wall of the shell, so that an included angle between the beam splitter 302 and the filter 5 at the imaging port is 45 degrees, and an included angle between the beam splitter 302 and an extension line of the baffle IV 10 is 45 degrees; one end of the beam splitter 303 is connected to the free end of the first baffle 7, and the other end of the beam splitter 303 is connected to the free end of the second baffle 8, so that an included angle between the beam splitter 303 and an extension line of the second baffle 8 is 135 degrees, and an included angle between the beam splitter 303 and the extension line of the first baffle 7 is 45 degrees.
The first camera 201 and the second camera 202 are installed on the inner wall of the shell and are in mirror symmetry relative to the third beam splitter 303, the third camera 203 and the fourth camera 204 are in mirror symmetry relative to the second beam splitter 302, through the arrangement, reflected light of a finger irradiated from an imaging port generates a first transmission beam and a first reflection beam through the first beam splitter 301, the first transmission beam is transmitted to the third beam splitter 303 to form a second transmission beam and a second reflection beam, the second transmission beam is collected by the first camera 201 to generate a first finger vein image, the second reflection beam is collected by the second camera 202 to generate a second finger vein image, the first reflection beam is transmitted to the second beam splitter 302 to form a third transmission beam and a third reflection beam, the third transmission beam is collected by the third camera 203 to generate a fourth finger vein image, and then the generated first finger vein image, the third finger vein image and the fourth finger vein image are subjected to pixel-level registration, multi-channel processing and feature map generation, finally four different multi-channel images can be obtained, and the prosthesis can be effectively identified and the light intensity can be effectively prevented from being attacked during living body detection.
In other embodiments of the present embodiment, more than three sets of beam splitters 3 and more than four sets of imaging devices 2 may be set according to the situation to obtain more finger vein images with different light intensities, where the above situations are all within the protection scope of the present application.
Embodiment III:
as shown in fig. 9, the difference between the third embodiment and the first embodiment is that, in the third embodiment, the imaging device 2 includes a fifth camera 205 and a sixth camera 206, the fifth camera 205 and the sixth camera 206 are located inside the housing, the beam splitter 3 is located inside the housing, the filter 5 is located at a radiography position of the housing, the beam splitter 3 is disposed at a preset angle with the filter 5 inside the housing, the preset angle is 45 ° in the present embodiment, the fifth camera 205 and the sixth camera 206 are disposed in mirror symmetry with respect to the beam splitter 3, when in use, the light source module 4 irradiates the finger sample, the transmitted light beam is transmitted to the beam splitter 3 through the filter 5, the beam splitter 3 forms a transmitted light beam and a reflected light beam by the filter 5, in the present embodiment, the transmitted light beam is collected by the fifth camera 205 to generate a first finger vein image, the reflected light beam is collected by the sixth camera 206 to generate a second finger vein image, the generated first finger vein image and the second finger vein image are processed in multiple channels to generate multiple channels, and then feature map is generated, and then the feature map is used for comparison.
The foregoing is merely exemplary of the present application, and specific structures and features well known in the art will not be described in detail herein, so that those skilled in the art will be aware of all the prior art to which the present application pertains, and will be able to ascertain the general knowledge of the technical field in the application or prior art, and will not be able to ascertain the general knowledge of the technical field in the prior art, without using the prior art, to practice the present application, with the aid of the present application, to ascertain the general knowledge of the same general knowledge of the technical field in general purpose. It should be noted that modifications and improvements can be made by those skilled in the art without departing from the structure of the present application, and these should also be considered as the scope of the present application, which does not affect the effect of the implementation of the present application and the utility of the patent. The protection scope of the present application is subject to the content of the claims, and the description of the specific embodiments and the like in the specification can be used for explaining the content of the claims.
Claims (8)
1. The finger vein recognition and detection method integrating texture and living body characteristics is characterized by comprising the following steps of: comprising the following steps:
s1: the imaging device, the beam splitters, the reflectors, the filter, the light source module and the processor are arranged at preset positions to form a finger vein detection device;
s2: the finger vein image processing method comprises the steps of obtaining a finger sample, controlling a light source module to emit light beams to transmit the finger sample through a processor, dividing the light beams transmitted by the finger sample into new transmitted light beams and reflected light beams by a beam splitter, reflecting the transmitted light beams and the reflected light beams to an imaging plane of an imaging device through a reflecting mirror, obtaining finger vein images with different light intensities through one-time imaging of the imaging device, cutting the finger vein images obtained through one-time imaging according to the different light intensities, performing pixel-level registration and region-of-interest cutting, and generating a plurality of finger vein images.
S3: carrying out quantitative calculation on a plurality of finger vein images through a transmission model and an illumination response curve to obtain a transmission illumination offset image of the finger sample, and putting the transmission illumination offset image serving as a fusion feature image of finger vein line distribution features and living body features into a feature library;
s4: and obtaining a finger to be detected, generating a fusion characteristic diagram and an illumination response curve of the finger vein line distribution characteristics and the living body characteristics to be detected by processing the finger to be detected through S2 and S3, and comparing the fusion characteristic diagram and the illumination response curve with the characteristic library to generate a comparison result.
2. The method for finger vein recognition and detection with texture and living body features fused according to claim 1, wherein: in the step S1, an imaging device, a beam splitter, a plurality of reflectors, a filter, a light source module and a processor are arranged at preset positions, specifically: the imaging device and the light source module are electrically connected with the processor, the beam splitter is arranged according to a preset angle, and the reflecting mirror and the beam splitter are arranged in mirror symmetry; the imaging plane of the imaging device corresponds to the reflection path of the reflector; the filter is used for filtering the wave band emitted by the light source module.
3. The method for finger vein recognition and detection with texture and living body features fused according to claim 1, wherein: the step S2 comprises the following steps:
s2-1: acquiring a finger sample, adjusting the light intensity of the light source module, and acquiring finger vein images of the finger sample under different light intensities through an imaging device;
s2-2: cutting the acquired finger vein images according to different light intensities to generate a plurality of finger vein images;
s2-3: and carrying out pixel level registration and region-of-interest clipping on finger areas in the plurality of finger vein images, and sequentially placing the plurality of finger vein images into the multi-channel image according to the light intensity to generate the multi-channel image.
4. The method for finger vein recognition and detection with texture and living body features fused according to claim 1, wherein: the step S3 comprises the following steps:
s3-1: acquiring an illumination response curve of the imaging device;
s3-2: a transmission model is built, the light intensity ratio of the multichannel image, the illumination response curve and the plurality of finger vein images is input into the transmission model, a transmission illumination deviation image of the finger sample is output, and the image is used as a fusion characteristic image of finger vein line distribution characteristics and living body characteristics;
s3-3: constructing a feature library, storing user registration information corresponding to a finger sample and an illumination response curve of an imaging device, and storing a transmission illumination offset image of the finger sample into the feature library as a fusion feature map of finger vein line distribution features and living body features.
5. The method for finger vein recognition and detection with texture and living body features fused as set forth in claim 4, wherein: the step S4 comprises the following steps:
s4-1: acquiring a finger to be detected, and processing the finger to be detected through S2 and S3 to generate a fusion characteristic diagram and an illumination response curve of vein line distribution characteristics and living body characteristics of the finger to be detected;
s4-2: constructing a classifier, comparing the fusion characteristic diagram and the illumination response curve of the finger to be detected and the fusion characteristic diagram and the illumination response curve in the characteristic library as inputs of the classifier, and outputting a comparison result.
6. The method for finger vein recognition and detection with texture and living body features fused according to claim 5, wherein: the S4-2 comprises the following steps:
s4-2-1: the output comparison result is a set comprising a first scalar and a second scalar, and the labels of the first scalar and the second scalar comprise 1 and 0;
if the scalar I and the scalar II in the set are both 1, the finger to be detected is a living body, and vein line characteristics are matched; if not, S4-2-2 is carried out;
s4-2-2: if the scalar I in the set is 1 and the scalar II is 0, the finger to be detected is a living body, but the vein line characteristics are not matched;
if the scalar I in the set is 0 and the scalar II is 1, the finger to be detected is not living, but vein line characteristics are matched;
if the first scalar in the set is 0 and the second scalar is 0, the finger to be detected is non-living body, and the vein line characteristics are not matched.
7. The finger vein recognition and detection device integrating textures and living body characteristics is characterized in that: the device comprises an imaging device, a plurality of beam splitters, a plurality of reflectors, a filter, a light source module and a processor, wherein the imaging device and the light source module are electrically connected with the processor, the beam splitters are arranged according to a preset angle, the reflectors are arranged in mirror symmetry with the beam splitters, and the mirror surfaces of the reflectors can reflect light beams emitted by the beam splitters into the imaging device; the filter is used for filtering wave bands emitted by the light source module, the processor is used for controlling the light source module to be turned on and turned off and controlling the light intensity of the light source module, the beam splitter splits a light beam emitted by the light source module into a transmission light beam and a reflection light beam, the reflection light beam is reflected to the imaging device by the reflection mirror, and the controller is also used for controlling the imaging device to receive the reflection light beam and the transmission light beam to generate a finger vein image.
8. The method for finger vein recognition and detection with texture and living body features fused as set forth in claim 7, wherein: the system also comprises a model construction module, a feature library, a data processing module and a comparison module;
the model construction module is used for constructing a transmission model and a classifier;
the data processing module is used for acquiring an illumination response curve of the imaging device, and is also used for calculating a transmission illumination offset image of the finger sample according to the transmission model and the illumination response curve and taking the transmission illumination offset image as a fusion characteristic diagram of finger vein line distribution characteristics and living body characteristics;
the feature library is used for storing a fusion feature map of finger vein line distribution features and living body features, an illumination response curve and user registration information corresponding to the finger sample;
the data processing module is also used for calculating the finger to be detected and acquiring a fusion characteristic diagram of the finger vein line distribution characteristic and the living body characteristic of the finger to be detected and a corresponding illumination response curve;
the comparison module is used for comparing the fusion characteristic graph of the finger vein line distribution characteristics and the living body characteristics of the finger to be detected and the illumination response curve with the stored data in the characteristic library through the classifier to generate a comparison result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311258660.5A CN117152802A (en) | 2023-09-26 | 2023-09-26 | Finger vein recognition and detection method and device integrating texture and living body characteristics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311258660.5A CN117152802A (en) | 2023-09-26 | 2023-09-26 | Finger vein recognition and detection method and device integrating texture and living body characteristics |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN117152802A true CN117152802A (en) | 2023-12-01 |
Family
ID=88910079
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311258660.5A Pending CN117152802A (en) | 2023-09-26 | 2023-09-26 | Finger vein recognition and detection method and device integrating texture and living body characteristics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117152802A (en) |
-
2023
- 2023-09-26 CN CN202311258660.5A patent/CN117152802A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10685215B2 (en) | Method and apparatus for recognizing face | |
| US9317761B2 (en) | Method and an apparatus for determining vein patterns from a colour image | |
| US20220280087A1 (en) | Visual Perception-Based Emotion Recognition Method | |
| JP2013506525A (en) | Method and system for performing photoplethysmography | |
| JP6567850B2 (en) | Imaging device | |
| JP2015026228A (en) | Blood vessel image capturing apparatus and terminal | |
| JP2004171350A (en) | Eye imaging device and information device using the same | |
| WO2015199067A1 (en) | Image analysis device, imaging system, surgery assistance system, image analysis method, and image analysis program | |
| CN112487921A (en) | Face image preprocessing method and system for living body detection | |
| WO2020180755A1 (en) | Apparatuses and methods involving multi-modal imaging of a sample | |
| CN110298273A (en) | A kind of 3D based on multispectral image refers to vein extracting method and system | |
| CN112232163A (en) | Fingerprint acquisition method and device, fingerprint comparison method and device, and equipment | |
| CN111297339A (en) | Method and device for generating signal of photoplethysmography | |
| CN115153397A (en) | Imaging method for endoscopic camera system and endoscopic camera system | |
| Borgen et al. | Visible-spectrum biometric retina recognition | |
| JP2010233584A (en) | Method and apparatus for quantifying photo-damage | |
| CN117152802A (en) | Finger vein recognition and detection method and device integrating texture and living body characteristics | |
| JP6844093B2 (en) | Devices and methods for capturing medical images for ulcer analysis | |
| CN112232157A (en) | Fingerprint area detection method, device, equipment and storage medium | |
| JP2011100317A (en) | Personal authentication method and personal authentication system using vein pattern during bending and stretching motion of finger | |
| CN106073801A (en) | A kind of external cavum nasopharyngeum vena systemica blood oxygen saturation formation method and device | |
| JP6923129B2 (en) | Information processing equipment, programs, methods and systems | |
| CN115474930A (en) | Hyperspectral image reconstruction-based noninvasive hemoglobin detection method | |
| CN115587981A (en) | Vein re-projection system method and terminal based on FPGA | |
| CN112232152B (en) | Non-contact fingerprint identification method and device, terminal 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 | ||
| CB02 | Change of applicant information |
Country or region after: China Address after: No. 20, East Road, University City, Chongqing, Shapingba District, Chongqing Applicant after: Chongqing University of science and technology Address before: No. 20, East Road, University City, Chongqing, Shapingba District, Chongqing Applicant before: Chongqing University of Science & Technology Country or region before: China |
|
| CB03 | Change of inventor or designer information |
Inventor after: Chen Liukui Inventor after: Luo Wenfu Inventor after: Guo Tengwen Inventor after: Ye Siyun Inventor after: Liu Dingfang Inventor after: Li Zuojin Inventor before: Chen Liukui |