CN110781708A - Finger vein image recognition system and finger vein image recognition method based on acquisition equipment - Google Patents
Finger vein image recognition system and finger vein image recognition method based on acquisition equipment Download PDFInfo
- Publication number
- CN110781708A CN110781708A CN201810854728.9A CN201810854728A CN110781708A CN 110781708 A CN110781708 A CN 110781708A CN 201810854728 A CN201810854728 A CN 201810854728A CN 110781708 A CN110781708 A CN 110781708A
- Authority
- CN
- China
- Prior art keywords
- image
- finger vein
- vein image
- identification
- information
- 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 125
- 238000000034 method Methods 0.000 title claims abstract description 48
- 238000012545 processing Methods 0.000 claims abstract description 12
- 238000004891 communication Methods 0.000 claims abstract description 7
- 235000002566 Capsicum Nutrition 0.000 claims description 18
- 239000006002 Pepper Substances 0.000 claims description 18
- 241000722363 Piper Species 0.000 claims description 18
- 235000016761 Piper aduncum Nutrition 0.000 claims description 18
- 235000017804 Piper guineense Nutrition 0.000 claims description 18
- 235000008184 Piper nigrum Nutrition 0.000 claims description 18
- 150000003839 salts Chemical class 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 12
- 230000008030 elimination Effects 0.000 claims description 9
- 238000003379 elimination reaction Methods 0.000 claims description 9
- 238000013139 quantization Methods 0.000 claims description 9
- 238000001514 detection method Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000005516 engineering process Methods 0.000 description 7
- 238000011161 development Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 210000002615 epidermis Anatomy 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000006467 substitution reaction Methods 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06K—GRAPHICAL DATA READING; PRESENTATION OF DATA; RECORD CARRIERS; HANDLING RECORD CARRIERS
- G06K7/00—Methods or arrangements for sensing record carriers, e.g. for reading patterns
- G06K7/10—Methods or arrangements for sensing record carriers, e.g. for reading patterns by electromagnetic radiation, e.g. optical sensing; by corpuscular radiation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Electromagnetism (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Toxicology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Collating Specific Patterns (AREA)
Abstract
A finger vein image recognition system based on an acquisition device and a finger vein image recognition method of the system are provided. The acquisition equipment is connected with the server through a local area network or the Internet, can acquire article information based on the two-dimensional code, and identifies operator information based on finger veins; the image sensor receives an article two-dimensional code image acquired by acquisition equipment or an identified user vein information image; the collected image information is transmitted to a remote server through a communication module of the equipment, and the scanned articles are inquired and fed back. The invention has the advantages of operating speed and processing efficiency, and can realize that not only the two-dimensional code can be scanned and identified, but also the identity authentication can be carried out on an operator or other related personnel on one device.
Description
Technical Field
The invention relates to the technical field of biological feature recognition, in particular to the technical field of finger vein recognition.
Background
With the development of the times and the progress of the society, particularly the development of economy, the finger vein recognition technology belongs to the hot spot field in the current biological feature recognition technology, compared with fingerprints and human face features, the finger vein information is hidden under the superficial epidermis, no print is left in daily activities, and vein lines of each finger are different, so that the finger vein recognition technology can be used for personal identity recognition, has the advantages of non-contact acquisition, high safety and strong uniqueness, and meanwhile, in the industries of logistics, security inspection and the like, the two-dimensional code scanner is widely applied and is applied in various links, which is related to operators.
The biometric identification technology is based on a technology of authenticating an identity by means of a human biometric characteristic, that is, a technology of collecting and processing a physiological characteristic or a behavioral characteristic inherent to a human body by a computer to authenticate an individual identity, rather than a conventional marker or marking knowledge. Finger vein recognition has become the mainstream research direction of second-generation identity authentication technology in many developed countries due to its advantages in speed, stability, safety, confidentiality and the like. At present, no equipment exists, the two-dimensional code of an article can be scanned, an operator can be authenticated at the same time, the authentication efficiency can be improved when the operator is authenticated, and the equipment is suitable for various occasions.
Disclosure of Invention
The invention aims to solve the problems of low operation processing speed, single application scene and low authentication efficiency of related equipment during the existing article identification and operator identity authentication, and provides a finger vein image identification system and a finger vein image identification method based on acquisition equipment.
The finger vein image recognition system based on the acquisition equipment comprises the acquisition equipment, an image sensor and a server, wherein the acquisition equipment is connected with the server through a local area network or the Internet;
the acquisition equipment can acquire article information based on the two-dimensional code and identify operator information based on the finger vein;
the image sensor is used for receiving the two-dimensional code image of the article collected by the collecting equipment or receiving the identified vein information image of the user;
the collected image information is transmitted to a remote server through a communication module of the equipment, and the scanned object is inquired and fed back, and corresponding operators are associated to provide different operation authorities and operation information; the communication module communicates with the server through a 4G network.
The acquisition equipment comprises a keyboard, an acquisition device, a display screen and a control circuit, wherein a USB port of the keyboard is connected with a USB port of the control circuit, an image signal output end of the acquisition device is connected with an image signal input end of the control circuit, and a display signal input end of the display screen is connected with a display signal output end of the control circuit.
Furthermore, the acquisition equipment consists of a near infrared LED lamp, a CMOS camera and a near infrared light emission unit, the two-dimensional code is scanned based on the LED lamp and the CMOS camera, and the vein information of the user is acquired based on the near infrared light emission unit.
The invention relates to a finger vein image recognition method based on a finger vein image recognition system, wherein a control circuit of acquisition equipment comprises a finger vein sub-gallery and a recognition module, a server is provided with the finger vein gallery and the recognition module, and the vein recognition method comprises the following steps:
the working flow of the control circuit in the acquisition equipment is as follows:
a1, receiving an original finger vein image by an acquisition thread, and processing the original finger vein image to obtain an acquired image; step B1 is executed;
step B1, the image preprocessing thread receives the acquired image sent by the acquisition thread, and preprocesses the acquired image to obtain a processed finger vein image; step C1 is executed;
c1, matching the processed finger vein image with the image in the finger vein sub-library in the acquisition equipment through a matching algorithm by the image matching thread; step D1 is executed;
d1, judging whether the matching is successful by the image matching thread, and executing the step E1 if the judgment result is yes; otherwise, go to step F1;
step E1, taking the identity information corresponding to the successfully matched image as an identification result, and sending the identification result to the server to complete the identification;
step F1, sending the processed finger vein image to a server, and waiting for return information; step G1 is executed;
g1, judging whether the feedback information is a recognition result, if so, executing the step E1; otherwise, step H1 is performed;
step H1, sending identification failure information to a display screen for displaying and outputting, and completing the identification;
the working flow of the server is as follows:
step A2, judging whether the information sent by the acquisition equipment is an identification result, if so, executing step B2; otherwise, go to step C2;
step B2, storing the received identification result of each acquisition device, and storing the identification result, the serial number of the acquisition device and the identification time information to complete the identification;
step C2, comparing and matching the received processed finger vein image information with images in a finger vein library; step D2 is executed;
d2, judging whether the matching is successful, if so, executing the step E2; otherwise, go to step F2;
step E2, sending the identity information corresponding to the successfully matched image as an identification result to a control circuit in the corresponding acquisition equipment, simultaneously storing the received identification result of each acquisition equipment, and storing the identification result, the serial number of the acquisition equipment and the identification time information to finish the identification;
and F2, sending identification failure information to a control circuit in the corresponding acquisition equipment to complete the identification.
Further, the processing procedure of image contrast matching in step C1 is as follows:
step a: filtering the normalized finger vein image by using a two-dimensional first-order Gaussian filter in the horizontal and vertical directions of the finger vein image after rotation and translation correction, and solving the angle of the gradient direction on each pixel point of the normalized finger vein image, wherein the value range is [0, 2 pi ];
step b: quantizing the gradient direction angles into 5 quantization levels according to the angle values, wherein the value range of quantization coding of each gradient direction angle is any integer of {0, 1, 2, 3, 4}, so that a two-dimensional finger vein image feature template based on the quantized gradient direction features is formed and stored in a storage device;
the gradient direction angle value is quantized into n levels according to the gradient direction angle value, when n is larger, the expression capability of the quantized coding on the texture details of the local image is enhanced, and when n is smaller, the robustness of the quantized coding on the noise of the local image is enhanced;
step c: in the characteristic comparison process, the similarity of the two finger vein image characteristic templates is measured by calculating the frequency of the same quantization gradient direction codes appearing at the corresponding positions of the two finger vein image characteristic templates;
step d: the value range of the similarity is a closed interval of [0, 1], and the larger the numerical value is, the more similar the corresponding two finger vein image feature templates are.
Further, the image preprocessing process in step B1 is as follows:
preprocessing the acquired vein image, wherein the preprocessing comprises the following steps: graying by adopting a weighted average value method, solving an optimal threshold value by adopting an iterative method to segment the image, filtering noise by adopting a combined filter, and carrying out high standardization treatment on the segmented vein image;
the formula for graying by the weighted average method is as follows: gray ═ 0.30 × R +0.58 × G +0.12B, where color information is represented by color (R, G, B);
the method for obtaining the optimal threshold value by adopting the iterative method to segment the image comprises the following steps: firstly, a threshold value is assumed in an initial condition, the assumed threshold value is continuously updated in the iterative operation of the image, the initial threshold value generally adopts a gray level average value, after the image is divided by an average gray level value, the average value of 2 types of divided areas is calculated, and the average value of the area lower than the initial threshold value is marked as T
bAnd the mean value of the other region is denoted as T
0Then calculate (T)
b+T
0) And/2, taking the value as a new threshold value, and repeating the steps until the threshold values calculated for 2 times are not changed any more, so that the optimal threshold value is obtained, and the iteration is stopped.
The combined filter is composed of 4 modules of salt and pepper noise detection, filter selection, salt and pepper noise elimination and Gaussian noise elimination, the salt and pepper noise detection is firstly carried out on an input original vein image, the corresponding filter can be selected for pixels affected by the salt and pepper noise to eliminate the salt and pepper noise, the corresponding filter is selected for pixels not affected by the salt and pepper noise to eliminate the Gaussian noise, and finally the two results are combined to obtain the finger vein image after noise elimination.
According to the finger vein image identification system and the finger vein image identification method based on the system, the vein identification module is arranged on the basis of common two-dimensional code scanning equipment, so that the two-dimensional code can be scanned and identified, and the personnel identification of an operator or other related personnel can be carried out. Meanwhile, the identification module in the control circuit and the identification module in the server identify the collected finger vein image, compared with the finger vein identification process operated on a computer, the operation speed and the processing efficiency are greatly improved, and the networked finger vein identification can be realized by arranging the server.
Detailed Description
The invention is described in more detail below with reference to specific examples:
the first embodiment is as follows:
the finger vein image recognition system based on the acquisition equipment comprises the acquisition equipment, an image sensor and a server, wherein the acquisition equipment is connected with the server through a local area network or the internet;
the acquisition equipment can acquire article information based on the two-dimensional code and identify operator information based on the finger vein; the acquisition equipment comprises keyboard, collection device, display screen and control circuit, the USB port of keyboard is connected with control circuit's USB port, and collection device's image signal output part is connected with control circuit's image signal input part, and the demonstration signal input part of display screen is connected with control circuit's demonstration signal output part. The user can use the keyboard to control the process, and the functions of suspending, continuing, quitting and the like of the process are realized. The acquisition equipment has an automatic acquisition function, and the acquisition work of the finger vein image is completed within 1-2 seconds after the finger is deeply inserted into the acquisition device. The linux system is operated on the control circuit, the finger vein identification process and the finger vein registration process are downloaded to the linux operating system to be operated, and the server is connected with the acquisition equipment based on the network to realize networked finger vein image identification.
The image sensor is used for receiving the two-dimensional code image of the article collected by the collecting equipment or receiving the identified vein information image of the user;
the collected image information is transmitted to a remote server through a communication module of the equipment, and the scanned object is inquired and fed back, and corresponding operators are associated to provide different operation authorities and operation information;
the acquisition equipment comprises a near infrared LED lamp, a CMOS camera and a near infrared light emission unit, the two-dimensional code scanning is realized based on the LED lamp and the CMOS camera, and the user vein information is acquired based on the near infrared light emission unit.
The second embodiment is as follows:
in the finger vein image recognition method based on the finger vein image recognition system according to the embodiment, the control circuit of the acquisition device includes a finger vein sub-gallery and a recognition module, and the server is provided with the finger vein gallery and the recognition module, and the vein recognition method includes:
the working flow of the control circuit in the acquisition equipment is as follows:
a1, receiving an original finger vein image by an acquisition thread, and processing the original finger vein image to obtain an acquired image; step B1 is executed;
step B1, the image preprocessing thread receives the acquired image sent by the acquisition thread, and preprocesses the acquired image to obtain a processed finger vein image; step C1 is executed;
c1, matching the processed finger vein image with the image in the finger vein sub-library in the acquisition equipment through a matching algorithm by the image matching thread; step D1 is executed;
d1, judging whether the matching is successful by the image matching thread, and executing the step E1 if the judgment result is yes; otherwise, go to step F1;
step E1, taking the identity information corresponding to the successfully matched image as an identification result, and sending the identification result to the server to complete the identification;
step F1, sending the processed finger vein image to a server, and waiting for return information; step G1 is executed;
g1, judging whether the feedback information is a recognition result, if so, executing the step E1; otherwise, step H1 is performed;
step H1, sending identification failure information to a display screen for displaying and outputting, and completing the identification;
the working flow of the server is as follows:
step A2, judging whether the information sent by the acquisition equipment is an identification result, if so, executing step B2; otherwise, go to step C2;
step B2, storing the received identification result of each acquisition device, and storing the identification result, the serial number of the acquisition device and the identification time information to complete the identification;
step C2, comparing and matching the received processed finger vein image information with images in a finger vein library; step D2 is executed;
d2, judging whether the matching is successful, if so, executing the step E2; otherwise, go to step F2;
step E2, sending the identity information corresponding to the successfully matched image as an identification result to a control circuit in the corresponding acquisition equipment, simultaneously storing the received identification result of each acquisition equipment, and storing the identification result, the serial number of the acquisition equipment and the identification time information to finish the identification;
and F2, sending identification failure information to a control circuit in the corresponding acquisition equipment to complete the identification.
The processing procedure of image contrast matching in step C1 is as follows:
step a: filtering the normalized finger vein image by using a two-dimensional first-order Gaussian filter in the horizontal and vertical directions of the finger vein image after rotation and translation correction, and solving the angle of the gradient direction on each pixel point of the normalized finger vein image, wherein the value range is [0, 2 pi ];
step b: quantizing the gradient direction angles into 5 quantization levels according to the angle values, wherein the value range of quantization coding of each gradient direction angle is any integer of {0, 1, 2, 3, 4}, so that a two-dimensional finger vein image feature template based on the quantized gradient direction features is formed and stored in a storage device; the gradient direction angle value is quantized into n levels according to the gradient direction angle value, when n is larger, the expression capability of the quantized coding on the texture details of the local image is enhanced, and when n is smaller, the robustness of the quantized coding on the noise of the local image is enhanced;
step c: in the characteristic comparison process, the similarity of the two finger vein image characteristic templates is measured by calculating the frequency of the same quantization gradient direction codes appearing at the corresponding positions of the two finger vein image characteristic templates;
step d: the value range of the similarity is a closed interval of [0, 1], and the larger the numerical value is, the more similar the corresponding two finger vein image feature templates are.
The image preprocessing process in the step B1 is as follows:
preprocessing the acquired vein image, wherein the preprocessing comprises the following steps: graying by adopting a weighted average value method, solving an optimal threshold value by adopting an iterative method to segment the image, filtering noise by adopting a combined filter, and carrying out high standardization treatment on the segmented vein image;
the formula for graying by the weighted average method is as follows: gray ═ 0.30 × R +0.58 × G +0.12B, where color information is represented by color (R, G, B);
the method for obtaining the optimal threshold value by adopting the iterative method to segment the image comprises the following steps: a threshold is initially assumed in an initial condition, and this assumed threshold is continuously updated in iterative operations on the image, initiallyThe threshold value is generally taken as a gray average value, after the image is divided by the average gray value, the average value of the divided 2 types of areas is calculated, and the average value of the area lower than the initial threshold value is recorded as T
bAnd the mean value of the other region is denoted as T
0Then calculate (T)
b+T
0) And/2, taking the value as a new threshold value, and repeating the steps until the threshold values calculated for 2 times are not changed any more, so that the optimal threshold value is obtained, and the iteration is stopped.
The combined filter is composed of 4 modules of salt and pepper noise detection, filter selection, salt and pepper noise elimination and Gaussian noise elimination, the salt and pepper noise detection is firstly carried out on an input original vein image, the corresponding filter can be selected for pixels affected by the salt and pepper noise to eliminate the salt and pepper noise, the corresponding filter is selected for pixels not affected by the salt and pepper noise to eliminate the Gaussian noise, and finally the two results are combined to obtain the finger vein image after noise elimination.
The method of the embodiment can be applied to the technical field of finger vein identification, for example, can be applied to a plurality of technical fields such as logistics, security inspection and the like. Explaining in order to be applied to the logistics field, in this embodiment, collection equipment can also realize detecting and discerning operating personnel's finger vein information based on collection equipment self near infrared light emission unit when carrying out the discernment detection of transporting article based on the two-dimensional code to the completion is authenticated operating personnel's identity, and, based on the communication between collection equipment, image sensor and the server, can guarantee finger vein information's discernment and processing speed.
Based on the above concept, it can be understood that, in this embodiment, on the basis of a common two-dimensional code scanning device, a vein recognition module is provided, so that not only can the two-dimensional code be scanned and recognized, but also an operator or other related personnel can be authenticated. Meanwhile, the identification module in the control circuit and the identification module in the server identify the collected finger vein image, compared with the finger vein identification process operated on a computer, the operation speed and the processing efficiency are greatly improved, and the networked finger vein identification can be realized by arranging the server.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solution of the present invention, and not to limit the same; while the invention has been described in detail and with reference to the foregoing embodiments, it will be understood by those skilled in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some or all of the technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the present invention, and they should be construed as being included in the following claims and description.
Claims (10)
1. A finger vein image recognition system based on acquisition equipment is characterized in that: the system comprises acquisition equipment, an image sensor and a server, wherein the acquisition equipment is connected with the server through a local area network or the Internet;
the acquisition equipment can acquire article information based on the two-dimensional code and identify operator information based on the finger vein;
the image sensor is used for receiving the two-dimensional code image of the article collected by the collecting equipment or receiving the identified vein information image of the user;
the collected image information is transmitted to a remote server through a communication module of the equipment, and the scanned object is inquired and fed back, and corresponding operators are associated to provide different operation authorities and operation information;
the acquisition equipment comprises a keyboard, an acquisition device, a display screen and a control circuit, wherein a USB port of the keyboard is connected with a USB port of the control circuit, an image signal output end of the acquisition device is connected with an image signal input end of the control circuit, and a display signal input end of the display screen is connected with a display signal output end of the control circuit.
2. The acquisition device-based finger vein image recognition system according to claim 1, wherein: the acquisition equipment comprises a near infrared LED lamp, a CMOS camera and a near infrared light emission unit, the two-dimensional code scanning is realized based on the LED lamp and the CMOS camera, and the user vein information is acquired based on the near infrared light emission unit.
3. The acquisition device-based finger vein image recognition system according to claim 1, wherein: the communication module communicates with the server through a 4G network.
4. The finger vein image recognition method of the finger vein image recognition system according to claim 1, characterized in that: the control circuit of the acquisition equipment comprises a finger vein sub-gallery and an identification module, the server is internally provided with the finger vein gallery and the identification module, and the vein identification method comprises the following steps:
the working flow of the control circuit in the acquisition equipment is as follows:
a1, receiving an original finger vein image by an acquisition thread, and processing the original finger vein image to obtain an acquired image; step B1 is executed;
step B1, the image preprocessing thread receives the acquired image sent by the acquisition thread, and preprocesses the acquired image to obtain a processed finger vein image; step C1 is executed;
c1, matching the processed finger vein image with the image in the finger vein sub-library in the acquisition equipment through a matching algorithm by the image matching thread; step D1 is executed;
d1, judging whether the matching is successful by the image matching thread, and executing the step E1 if the judgment result is yes; otherwise, go to step F1;
step E1, taking the identity information corresponding to the successfully matched image as an identification result, and sending the identification result to the server to complete the identification;
step F1, sending the processed finger vein image to a server, and waiting for return information; step G1 is executed;
g1, judging whether the feedback information is a recognition result, if so, executing the step E1; otherwise, step H1 is performed;
step H1, sending identification failure information to a display screen for displaying and outputting, and completing the identification;
the working flow of the server is as follows:
step A2, judging whether the information sent by the acquisition equipment is an identification result, if so, executing step B2; otherwise, go to step C2;
step B2, storing the received identification result of each acquisition device, and storing the identification result, the serial number of the acquisition device and the identification time information to complete the identification;
step C2, comparing and matching the received processed finger vein image information with images in a finger vein library; step D2 is executed;
d2, judging whether the matching is successful, if so, executing the step E2; otherwise, go to step F2;
step E2, sending the identity information corresponding to the successfully matched image as an identification result to a control circuit in the corresponding acquisition equipment, simultaneously storing the received identification result of each acquisition equipment, and storing the identification result, the serial number of the acquisition equipment and the identification time information to finish the identification;
and F2, sending identification failure information to a control circuit in the corresponding acquisition equipment to complete the identification.
5. The finger vein image recognition method according to claim 4, characterized in that: the processing procedure of image contrast matching in step C1 is as follows:
step a: filtering the normalized finger vein image by using a two-dimensional first-order Gaussian filter in the horizontal and vertical directions of the finger vein image after rotation and translation correction, and solving the angle of the gradient direction on each pixel point of the normalized finger vein image, wherein the value range is [0, 2 pi ];
step b: quantizing the gradient direction angles into 5 quantization levels according to the angle values, wherein the value range of quantization coding of each gradient direction angle is any integer of {0, 1, 2, 3, 4}, so that a two-dimensional finger vein image feature template based on the quantized gradient direction features is formed and stored in a storage device;
step c: in the characteristic comparison process, the similarity of the two finger vein image characteristic templates is measured by calculating the frequency of the same quantization gradient direction codes appearing at the corresponding positions of the two finger vein image characteristic templates;
step d: the value range of the similarity is a closed interval of [0, 1], and the larger the numerical value is, the more similar the corresponding two finger vein image feature templates are.
6. The finger vein image recognition method according to claim 4, characterized in that: the image preprocessing process in the step B1 is as follows:
preprocessing the acquired vein image, wherein the preprocessing comprises the following steps: graying by adopting a weighted average value method, obtaining an optimal threshold value by adopting an iterative method to segment the image, filtering noise by adopting a combined filter, and carrying out high standardization treatment on the segmented vein image.
7. The finger vein image recognition method according to claim 5, characterized in that: the gradient direction angle value is quantized into n levels according to the gradient direction angle value, when n is larger, the expression capability of the quantized coding on the texture details of the local image is enhanced, and when n is smaller, the robustness of the quantized coding on the noise of the local image is enhanced.
8. The finger vein image recognition method according to claim 6, characterized in that: the formula for graying by the weighted average method is as follows: gray ═ 0.30 × R +0.58 × G +0.12B, where color information is represented by color (R, G, B).
9. The finger vein image recognition method according to claim 6, characterized in that: the method for obtaining the optimal threshold value by adopting the iterative method to segment the image comprises the following steps: first in the initial conditionAssuming a threshold value, continuously updating the assumed threshold value in the iterative operation of the image, the initial threshold value generally takes the average value of gray scale, after the image is divided by the average gray scale value, the average value of the divided 2 types of areas is calculated, the average value of the area lower than the initial threshold value is recorded as T
bAnd the mean value of the other region is denoted as T
0Then calculate (T)
b+T
0) And/2, taking the value as a new threshold value, and repeating the steps until the threshold values calculated for 2 times are not changed any more, so that the optimal threshold value is obtained, and the iteration is stopped.
10. The finger vein image recognition method according to claim 6, characterized in that: the combined filter is composed of 4 modules of salt and pepper noise detection, filter selection, salt and pepper noise elimination and Gaussian noise elimination, the salt and pepper noise detection is firstly carried out on an input original vein image, the corresponding filter can be selected for pixels affected by the salt and pepper noise to eliminate the salt and pepper noise, the corresponding filter is selected for pixels not affected by the salt and pepper noise to eliminate the Gaussian noise, and finally the two results are combined to obtain the finger vein image after noise elimination.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810854728.9A CN110781708A (en) | 2018-07-31 | 2018-07-31 | Finger vein image recognition system and finger vein image recognition method based on acquisition equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810854728.9A CN110781708A (en) | 2018-07-31 | 2018-07-31 | Finger vein image recognition system and finger vein image recognition method based on acquisition equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110781708A true CN110781708A (en) | 2020-02-11 |
Family
ID=69382640
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810854728.9A Pending CN110781708A (en) | 2018-07-31 | 2018-07-31 | Finger vein image recognition system and finger vein image recognition method based on acquisition equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110781708A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639557A (en) * | 2020-05-15 | 2020-09-08 | 圣点世纪科技股份有限公司 | Intelligent registration feedback method for finger vein image |
| CN113705262A (en) * | 2021-09-06 | 2021-11-26 | 广州市远景达科技开发有限公司 | Hand-held type industry bar code scanning rifle |
| CN115761820A (en) * | 2022-11-29 | 2023-03-07 | 河南职业技术学院 | Computer-based biological characteristic acquisition and identification system and device |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106773762A (en) * | 2016-12-28 | 2017-05-31 | 重庆金鑫科技产业发展有限公司 | A kind of vein pattern identification terminal and intelligent domestic system |
-
2018
- 2018-07-31 CN CN201810854728.9A patent/CN110781708A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106773762A (en) * | 2016-12-28 | 2017-05-31 | 重庆金鑫科技产业发展有限公司 | A kind of vein pattern identification terminal and intelligent domestic system |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111639557A (en) * | 2020-05-15 | 2020-09-08 | 圣点世纪科技股份有限公司 | Intelligent registration feedback method for finger vein image |
| CN111639557B (en) * | 2020-05-15 | 2023-06-20 | 圣点世纪科技股份有限公司 | Intelligent registration feedback method for finger vein image |
| CN113705262A (en) * | 2021-09-06 | 2021-11-26 | 广州市远景达科技开发有限公司 | Hand-held type industry bar code scanning rifle |
| CN115761820A (en) * | 2022-11-29 | 2023-03-07 | 河南职业技术学院 | Computer-based biological characteristic acquisition and identification system and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Han et al. | Palm vein recognition using adaptive Gabor filter | |
| Lee | A novel biometric system based on palm vein image | |
| US10740636B2 (en) | Method, system and terminal for identity authentication, and computer readable storage medium | |
| CN111462379A (en) | Access control management method, system and medium containing palm vein and face recognition | |
| US11163972B2 (en) | Convergent biometric authentication method based on finger joint and finger vein, and apparatus therefor | |
| Wang et al. | An automatic physical access control system based on hand vein biometric identification | |
| CN110781708A (en) | Finger vein image recognition system and finger vein image recognition method based on acquisition equipment | |
| Kasiselvanathan et al. | Palm pattern recognition using scale invariant feature transform | |
| Patil et al. | A novel approach for fingerprint matching using minutiae | |
| Barua et al. | Fingerprint identification | |
| CN110443146A (en) | Auth method, device, equipment and readable medium based on bio-identification | |
| Raghavendra et al. | Exploring dorsal finger vein pattern for robust person recognition | |
| Tukur | Fingerprint recognition and matching using Matlab | |
| KR102375593B1 (en) | Apparatus and method for authenticating user based on a palm composite image | |
| JP2005259049A (en) | Face collation device | |
| EP3180736A1 (en) | A method of detecting a falsified presentation to a vascular recognition system | |
| Kumar et al. | Biometric authentication based on infrared thermal hand vein patterns | |
| Latha et al. | A robust person authentication system based on score level fusion of left and right irises and retinal features | |
| KR20200109977A (en) | Smartphone-based identity verification method using fingerprints and facial images | |
| Jose et al. | Towards building a better biometric system based on vein patterns in human beings | |
| Ganorkar et al. | IRIS recognition using discrete wavelet Transform | |
| Yazdani et al. | Verification based on palm vein by estimating wavelet coefficient with autoregressive model | |
| Choras | Personal identification using forearm vein patterns | |
| JP2659046B2 (en) | Identity verification device | |
| Poojary et al. | Biometric authentication system using dorsal hand vein pattern |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20200211 |
|
| WD01 | Invention patent application deemed withdrawn after publication |