CN114582008A - Living iris detection method based on two wave bands - Google Patents
Living iris detection method based on two wave bands Download PDFInfo
- Publication number
- CN114582008A CN114582008A CN202210207448.5A CN202210207448A CN114582008A CN 114582008 A CN114582008 A CN 114582008A CN 202210207448 A CN202210207448 A CN 202210207448A CN 114582008 A CN114582008 A CN 114582008A
- Authority
- CN
- China
- Prior art keywords
- iris
- image
- living
- tissue
- human eye
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 32
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 22
- 238000010586 diagram Methods 0.000 claims abstract description 18
- 238000010521 absorption reaction Methods 0.000 claims abstract description 6
- 238000002310 reflectometry Methods 0.000 claims abstract description 6
- 210000000554 iris Anatomy 0.000 claims description 75
- 238000000034 method Methods 0.000 claims description 25
- 210000003786 sclera Anatomy 0.000 claims description 23
- 210000001747 pupil Anatomy 0.000 claims description 13
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 230000011218 segmentation Effects 0.000 claims description 7
- 210000000720 eyelash Anatomy 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 3
- 230000008520 organization Effects 0.000 claims description 3
- 230000009977 dual effect Effects 0.000 claims description 2
- 238000007781 pre-processing Methods 0.000 claims description 2
- 210000003462 vein Anatomy 0.000 claims description 2
- 238000001727 in vivo Methods 0.000 claims 1
- 210000001508 eye Anatomy 0.000 abstract description 36
- 238000012984 biological imaging Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000005252 bulbus oculi Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 239000011347 resin Substances 0.000 description 1
- 229920005989 resin Polymers 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02B—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
- Y02B20/00—Energy efficient lighting technologies, e.g. halogen lamps or gas discharge lamps
- Y02B20/40—Control techniques providing energy savings, e.g. smart controller or presence detection
Abstract
The invention discloses a living iris detection method based on two wave bands, belonging to the technical field of biological image processing. Comprises the steps of carrying out living iris detection under the living detection authority, and collecting the human eye area of a user in a 530 nanometer wave band within the depth of field range of a cameraPreprocessing the human eye region image to obtain a gray iris image by the image I and a human eye region image II with a 700 nanometer wave band; obtaining a tissue characteristic map I of the iris and scleral region of interestf1And a vessel texture feature map If2(ii) a Calculating the difference between the texture characteristic diagram of the tissue and the blood vessel of the I and the texture characteristic diagram of the tissue and the blood vessel of the II by using a Hash algorithm, aiming at the tissue characteristic diagram If1And IIf1And a vessel texture feature map If2And IIf2And (4) extracting the living body detection characteristics according to the difference, and outputting an iris authenticity judgment result. The invention distinguishes true and false by the difference of the blood vessels and tissues in the eyes of the living body and the absorption reflectivity of the biological texture simulated by the forged sample in different wave bands, and can well defend the attack of the forged iris.
Description
Technical Field
The invention belongs to the technical field of biological image processing, and particularly relates to a living iris detection method based on two wave bands.
Background
The iris recognition technology is similar to the fingerprint recognition technology in concept, and performs identity recognition according to the unique physiological characteristics of the human body. However, due to the acquisition equipment and method of the iris image, the matching degree of an acquirer is required for iris identification and the friendliness of the method is not better than that of methods such as fingerprint identification, so that the commercialization degree of the method is not as good as that of fingerprint identification and face identification. In CN201910101762.3, in the patent of the anti-counterfeiting method and device based on living irises, a first face image of a user is acquired by using a visible light camera, and an iris image of the user is acquired, and whether the iris image is from a living iris is determined, if the iris image is from a living iris, it is detected whether the iris image is matched with an iris image pre-stored by the user, and if the iris image is matched with the iris image pre-stored by the user, the face image is true; thus, the anti-counterfeiting discrimination is carried out. In the digital information society of today, people inevitably leave their appearance, fingerprint texture or images containing iris texture for various reasons. Under the background, even if the iris recognition accuracy is higher, if the attack of a forged sample cannot be defended, once the physiological characteristics are acquired by a lawbreaker and thus property stealing or data stealing is caused, social order disorder can be brought. Therefore, the present invention provides a two-band-based living iris detection method to solve the above-mentioned problems in the background art.
Disclosure of Invention
The invention aims to provide a living body iris detection method based on two wave bands, which is characterized in that two wave bands with the largest variation difference of the texture feature quantity of a living body human eye and a forged sample are selected as two comparison wave bands in an algorithm, and authenticity is distinguished through the difference of the absorption reflectivity of intravascular tissue in the living body human eye and the simulated biological texture of the forged sample in different wave bands, and the method comprises the following steps:
s1, the administrator starts the living body detection authority at the background, and the user performs iris living body detection at the client;
s2, the lighting module is started to work under the control of the central controller, and a user is in the working range of the lighting module and the depth of field range of the camera;
s3, the central controller controls the light source to emit two groups of light with different wavelengths respectively, namely light with wavelengths of 530 nanometers and light with wavelengths of 700 nanometers, so that the camera respectively collects the human eye region image I of the user in the 530 nanometer wave band and the human eye region image II of the user in the 700 nanometer wave band, and image preprocessing operation is carried out to reduce noise interference in the positioning process;
s4, positioning the pupil, the iris and the sclera, firstly obtaining a roughly-segmented pupil area binary image by using an adaptive threshold segmentation method according to an iris image histogram, determining the pupil center position by using the binary image with pupil position information, setting an iris area search range according to the pupil center position, then accurately positioning the iris area by using a Hough transform algorithm in the search range and segmenting a sclera area with small interference to obtain an iris image I1And sclera image I2；
S5, comparing the iris image I1And sclera image I2Operating to obtain a tissue characteristic diagram I of the region of interestf1And a vessel texture feature map If2；
S6, repeating the steps S4-S5 on the preprocessed human eye region image II to obtain a region-of-interest tissue characteristic diagram IIf1And vein texture feature map IIf2；
S7 aiming at the lower organization characteristic diagram I of the dual wavebandf1And IIf1And a vessel texture feature map If2And IIf2And (4) extracting the living body detection characteristics according to the difference, inputting the living body characteristics into a classifier to judge the authenticity, and outputting an iris authenticity judgment result.
In step S3, the controller controls the light source of the camera to emit two sets of light with different wavelengths, that is, light waves of 530 nm and 700 nm, so that the camera collects the eye region image i of the user at 530 nm band and the eye region image ii at 700 nm band, performs graying and gaussian filtering denoising on the eye region images, and performs nonlinear enhancement on the filtered eye region images to reduce noise interference such as eyelashes.
In step S3, graying and gaussian filtering denoising are performed on the eye region image, and nonlinear enhancement is performed on the filtered eye region image according to formula (1) to reduce eyelash interference, wherein IgTo maximize pixels in the neighborhood of 7 × 7 of the filtered image, IhIs a pair IgTaking the minimum value of the pixels in 7 × 7 neighborhoods;
in step S4, the pupil portion is roughly segmented by using an adaptive threshold segmentation method to obtain a binary image I having pupil position informationb(x, y) determining the pupil center position (C) in the binary image by the centroid method of formula (2)x,Cy) In which Ib(x, y) is the gray value at the (x, y) point, a search range is set according to the position of the pupil center, the iris region is accurately positioned in the search range by utilizing a Hough transform algorithm, the sclera region with small interference is segmented, and a grayed iris image I is obtained1And graying sclera image I2；
In step S5, the iris image and the sclera image obtained from the human eye region image I are operated by using a gradient enhancement-based blood vessel and tissue texture segmentation algorithm to obtain a tissue and blood vessel texture feature map.
In the step S6, the steps S4 to S5 are repeated for the eye region image ii to obtain a tissue and blood vessel texture feature map of the region of interest.
In the step S7, the difference between the texture feature map of the tissue and blood vessel of the first segment and the texture feature map of the tissue and blood vessel of the second segment is calculated by using a hash algorithm, the difference is used as the two-band living iris detection feature of the invention, the feature is input into a classifier for authenticity judgment, and an iris authenticity judgment result is output.
The iris image I in the S51And sclera image I2Operating to obtain a tissue characteristic map I of the region of interestf1And a vessel texture feature map If2Characteristic diagram Ifi(i-1, 2) the general calculation method is shown in formula (3),
where t (x, y) is adaptive coefficient, k and b are empirical super parameter, where k is 1, b is 0.05, and G is selectedmax(x, y) is Ii(I is 1,2)5 × 5 window maximum gradient value, G is image global maximum gradient value, G is 255, and m (x, y) is Ii(i-1, 2)5 × 5 window, g (x, y) is the local gradient at that point.
The invention has the beneficial effects that: the invention takes the biological imaging characteristics of the iris and sclera of the living body under the dual-band light source as the starting point, carries out the research and development of the living body detection algorithm, can resist the attack of various forged samples, has universality, can finish the living body detection of the iris by only acquiring two frames of images, greatly shortens the detection time and has real-time property. The method is characterized in that two wave bands with the largest variation difference of texture characteristics of the living human eye and the forged sample are selected as two comparison wave bands in an algorithm, and authenticity is distinguished through the difference of absorption reflectivity of intravascular tissue in the living human eye and the biological texture simulated by the forged sample in different wave bands. The method can well defend attack means such as printing reproduction, color contact lenses, resin eyeball models and the like.
Detailed Description
The invention provides a living body iris detection method based on two wave bands, which selects two wave bands with the largest variation difference of the texture feature quantity of a living body human eye and a forged sample as two comparison wave bands in an algorithm, and distinguishes authenticity through the difference of the absorption reflectivity of different wave bands of intravascular tissue in the living body human eye and the biological texture simulated by the forged sample. The present invention will be described in further detail with reference to specific examples.
The living iris detection method based on the dual-waveband comprises the following steps:
s1, the administrator starts the living body detection authority at the background, and the user performs iris living body detection at the client;
s2, the lighting module is started to work under the control of the central controller, and a user is in the working range of the lighting module and the depth of field range of the camera;
s3, the central controller controls the light source of the camera to emit two groups of lights with different wavelengths respectively, namely lights with 530 nm and 700 nm, so that the camera respectively collects a human eye region image I of a user in a 530 nm wave band and a human eye region image II of a 700 nm wave band, graying and Gaussian filtering denoising are carried out on the human eye region images, nonlinear enhancement operation is carried out on the filtered human eye region images through a formula (1) to reduce eyelash interference, wherein IgTo maximize pixels in the neighborhood of 7 × 7 of the filtered image, IhIs a pair IgTaking the minimum value of the pixels in 7 × 7 neighborhoods;
s4, positioning the pupil, the iris and the sclera, and roughly segmenting the pupil part by using a self-adaptive threshold segmentation method according to the distribution characteristics of the histogram of the iris image to obtain a binary image I with pupil position informationb(x, y) determining the pupil center position (C) in the binary image by the centroid method of formula (2)x,Cy) In which Ib(x, y) is the gray value at the (x, y) point, a search range is set according to the position of the pupil center, the iris region is accurately positioned in the search range by utilizing a Hough transform algorithm, the sclera region with small interference is segmented, and a grayed iris image I is obtained1And graying sclera image I2；
S5, comparing the iris image I1And sclera image I2Operating to obtain a tissue characteristic map I of the region of interestf1And a vessel texture feature map If2Characteristic diagram IfiThe general calculation method (i ═ 1,2) is shown in formula (3), where t (x, y) is the adaptive coefficient, k and b are empirical parameters, where k is 1, b is 0.05, and G is selectedmax(x, y) is Ii(I is 1,2)5 × 5 window maximum gradient value, G is image global maximum gradient value, G is 255, and m (x, y) is Ii(i ═ 1,2)5 × 5 windows, average gray value, g (x, y) is the local gradient at that point;
s6, repeating the steps S4-S5 on the eye region image II to obtain a region-of-interest tissue characteristic map IIf1And blood vessel texture feature map IIf2；
S7, calculating an organization characteristic diagram I by utilizing a Hash algorithmf1And IIf1Degree of difference, blood vessel texture feature map If2And IIf2The difference degree is used as the two-waveband living iris detectionMeasuring characteristics, inputting the characteristics into a classifier for authenticity judgment, outputting iris authenticity judgment results, and using a characteristic diagram If1And IIf1The hash algorithm pseudo code is shown in table 1, taking the difference as an example.
Table 1 hash algorithm pseudo code
Specifically, the acquiring of the eye region image i and the eye region image ii in step S3 specifically includes: the controller controls a light source of the camera to respectively emit two groups of light with different wavelengths, namely light waves of 530 nanometers and 700 nanometers, so that the camera respectively collects a human eye region image I of a user in a 530 nanometer waveband and a human eye region image II of a 700 nanometer waveband, graying and Gaussian filtering denoising are carried out on the human eye region images, and nonlinear enhancement operation is carried out on the filtered human eye region images to reduce noise interference such as eyelashes.
Specifically, the step S5 of acquiring the texture feature map of the tissue and the blood vessel includes the specific steps of: and operating the iris image and the sclera image acquired from the human eye region image I by using a gradient enhancement-based blood vessel and tissue texture segmentation algorithm to obtain a tissue and blood vessel texture characteristic diagram.
Specifically, in the step S6, the steps S4 to S5 are repeated on the eye region image ii to obtain a tissue and blood vessel texture feature map of the region of interest.
Specifically, the step of extracting and discriminating the living body detection feature in step S7 includes: and calculating the difference degree of the tissue and blood vessel texture characteristic diagram I and the tissue and blood vessel texture characteristic diagram II by using a Hash algorithm, taking the difference degree as the detection characteristic of the two-waveband living iris of the text, inputting the characteristic into a classifier for judging authenticity, and outputting an iris authenticity judgment result.
In summary, the following steps: compared with other methods, the living iris detection method based on the two-waveband light source takes the biological imaging characteristics of the living iris and the sclera under the two-waveband light source as a starting point, researches and develops a living detection algorithm, can resist various forged sample attacks, has universality, can finish the living iris detection by only acquiring two frames of images, greatly shortens the detection time, and has real-time property.
The invention selects two wave bands with the maximum variation difference of the texture feature quantity of the living human eye and the forged sample as two comparison wave bands in the algorithm, and the authenticity is distinguished through the difference of the absorption reflectivity of the blood vessel tissue in the living human eye and the biological texture simulated by the forged sample in different wave bands. The method can well defend false iris attack.
Claims (8)
1. A living body iris detection method based on two wave bands is characterized in that two wave bands with the largest variation difference of the texture feature quantity of a living body human eye and a forged sample are selected as two comparison wave bands in an algorithm, and authenticity is distinguished through the difference of the absorption reflectivity of different wave bands of intravascular tissue in the living body human eye and the biological texture simulated by the forged sample, and the method comprises the following steps:
s1, the administrator starts the living body detection authority at the background, and the user performs iris living body detection at the client;
s2, the lighting module is started to work under the control of the central controller, and a user is in the working range of the lighting module and the depth of field range of the camera;
s3, the central controller controls the light source to emit two groups of light with different wavelengths respectively, namely light with wavelengths of 530 nanometers and light with wavelengths of 700 nanometers, so that the camera respectively collects the human eye region image I of the user in the 530 nanometer wave band and the human eye region image II of the user in the 700 nanometer wave band, and image preprocessing operation is carried out to reduce noise interference in the positioning process;
s4, positioning the pupil, iris and sclera, firstly obtaining a roughly divided pupil area binary image by using an adaptive threshold division method according to the iris image histogram, and utilizing the information with the pupil positionDetermining the pupil center position according to the binary image, setting a search range of an iris region according to the pupil center position, accurately positioning the iris region in the search range by using a Hough transform algorithm, and segmenting the sclera region with small interference to obtain an iris image I1And sclera image I2；
S5 comparison of Iris image I1And sclera image I2Operating to obtain a tissue characteristic diagram I of the region of interestf1And a vessel texture feature map If2；
S6, repeating the steps S4-S5 on the preprocessed human eye region image II to obtain a region-of-interest tissue characteristic diagram IIf1And vein texture feature map IIf2；
S7 aiming at the lower organization characteristic diagram I of the dual wavebandf1And IIf1And a vessel texture feature map If2And IIf2And (4) extracting the living body detection characteristics according to the difference, inputting the living body characteristics into a classifier to judge the authenticity, and outputting an iris authenticity judgment result.
2. The method for detecting a living iris according to claim 1, wherein in step S3, the controller controls the light source of the camera to emit two sets of light with different wavelengths, i.e. 530 nm and 700 nm, respectively, so that the camera respectively collects the eye region image i of the user in the 530 nm band and the eye region image ii of the user in the 700 nm band, performs graying and gaussian filtering and de-noising on the eye region image, and performs a nonlinear enhancement operation on the filtered eye region image to reduce noise interference such as eyelashes.
3. The dual-band-based living iris detection method of claim 2, wherein the step S3 is to perform graying and gaussian filtering denoising on the human eye region image, and perform the non-linear enhancement operation on the filtered human eye region image by formula (1) to reduce the eyelash interference, wherein IgTo maximize pixels in the neighborhood of 7 × 7 of the filtered image, IhIs a pair IgTaking the minimum value of the pixels in 7 × 7 neighborhoods;
4. the method for detecting a living iris according to claim 1, wherein the step S4 is performed by coarsely dividing the pupil portion by adaptive threshold segmentation to obtain a binary image I having pupil position informationb(x, y) determining the pupil center position (C) in the binary image by the centroid method of formula (2)x,Cy) In which Ib(x, y) is the gray value at the (x, y) point, a search range is set according to the position of the pupil center, the iris region is accurately positioned in the search range by utilizing a Hough transform algorithm, the sclera region with small interference is segmented, and a grayed iris image I is obtained1And graying sclera image I2；
5. The method for detecting living iris according to claim 1, wherein the iris image and sclera image obtained from the human eye region image I are operated by using a gradient enhancement based blood vessel and tissue texture segmentation algorithm in step S5 to obtain the tissue and blood vessel texture feature map.
6. The method for detecting a living iris according to claim 1, wherein the step S6 is repeated with the step S4 to the step S5 on the eye region image ii to obtain the tissue and blood vessel texture feature map of the region of interest.
7. The method for detecting living iris according to claim 1, wherein the difference between the texture feature map of tissue and blood vessel of step I and the texture feature map of tissue and blood vessel of step II is calculated by Hash algorithm in step S7, and the difference is used as the characteristic of the invention for detecting living iris, and the characteristic is inputted into a classifier for judging whether the iris is true or false, and the result of judging whether the iris is true or false is outputted.
8. The dual-band-based in-vivo iris detection method of claim 1, wherein said S5 is applied to iris image I1And sclera image I2Operating to obtain a tissue characteristic diagram I of the region of interestf1And a vessel texture feature map If2Characteristic diagram Ifi(i-1, 2) the general calculation method is shown in formula (3),
where t (x, y) is adaptive coefficient, k and b are empirical super parameter, where k is 1, b is 0.05, and G is selectedmax(x, y) is Ii(I is 1,2)5 × 5 window maximum gradient value, G is image global maximum gradient value, G is 255, and m (x, y) is Ii(i-1, 2)5 × 5 window, g (x, y) is the local gradient at that point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210207448.5A CN114582008A (en) | 2022-03-03 | 2022-03-03 | Living iris detection method based on two wave bands |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210207448.5A CN114582008A (en) | 2022-03-03 | 2022-03-03 | Living iris detection method based on two wave bands |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114582008A true CN114582008A (en) | 2022-06-03 |
Family
ID=81776708
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210207448.5A Pending CN114582008A (en) | 2022-03-03 | 2022-03-03 | Living iris detection method based on two wave bands |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114582008A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116110574A (en) * | 2023-04-14 | 2023-05-12 | 武汉大学人民医院（湖北省人民医院） | Neural network-based ophthalmic intelligent inquiry method and device |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1584917A (en) * | 2004-06-11 | 2005-02-23 | 清华大学 | Living body iris patterns collecting method and collector |
| CN1623506A (en) * | 2003-12-07 | 2005-06-08 | 倪蔚民 | Bioassay system based on iris texture analysis |
| KR20070004213A (en) * | 2005-07-04 | 2007-01-09 | 연세대학교 산학협력단 | Fake iris distinction method |
| CN101833646A (en) * | 2009-03-11 | 2010-09-15 | 中国科学院自动化研究所 | Living iris detection method |
| WO2013087026A1 (en) * | 2011-12-16 | 2013-06-20 | 北京天诚盛业科技有限公司 | Locating method and locating device for iris |
| US20170124394A1 (en) * | 2015-11-02 | 2017-05-04 | Fotonation Limited | Iris liveness detection for mobile devices |
| CN107273812A (en) * | 2017-05-22 | 2017-10-20 | 西安交通大学 | A kind of living body iris method for anti-counterfeit for authentication |
| US20190121427A1 (en) * | 2016-06-08 | 2019-04-25 | South China University Of Technology | Iris and pupil-based gaze estimation method for head-mounted device |
| CN110929705A (en) * | 2020-02-17 | 2020-03-27 | 京东数字科技控股有限公司 | Living body detection method and device, identity authentication method and system and storage medium |
-
2022
- 2022-03-03 CN CN202210207448.5A patent/CN114582008A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1623506A (en) * | 2003-12-07 | 2005-06-08 | 倪蔚民 | Bioassay system based on iris texture analysis |
| CN1584917A (en) * | 2004-06-11 | 2005-02-23 | 清华大学 | Living body iris patterns collecting method and collector |
| KR20070004213A (en) * | 2005-07-04 | 2007-01-09 | 연세대학교 산학협력단 | Fake iris distinction method |
| CN101833646A (en) * | 2009-03-11 | 2010-09-15 | 中国科学院自动化研究所 | Living iris detection method |
| WO2013087026A1 (en) * | 2011-12-16 | 2013-06-20 | 北京天诚盛业科技有限公司 | Locating method and locating device for iris |
| US20170124394A1 (en) * | 2015-11-02 | 2017-05-04 | Fotonation Limited | Iris liveness detection for mobile devices |
| US20190121427A1 (en) * | 2016-06-08 | 2019-04-25 | South China University Of Technology | Iris and pupil-based gaze estimation method for head-mounted device |
| CN107273812A (en) * | 2017-05-22 | 2017-10-20 | 西安交通大学 | A kind of living body iris method for anti-counterfeit for authentication |
| CN110929705A (en) * | 2020-02-17 | 2020-03-27 | 京东数字科技控股有限公司 | Living body detection method and device, identity authentication method and system and storage medium |
Non-Patent Citations (2)
| Title |
|---|
| 李志明;: "基于卷积神经网络的虹膜活体检测算法研究", 计算机工程, no. 05, 15 May 2016 (2016-05-15) * |
| 陈瑞;孙静宇;林喜荣;丁天怀;: "利用多光谱图像的伪造虹膜检测算法", 电子学报, no. 03, 15 March 2011 (2011-03-15) * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116110574A (en) * | 2023-04-14 | 2023-05-12 | 武汉大学人民医院（湖北省人民医院） | Neural network-based ophthalmic intelligent inquiry method and device |
| US11955240B1 (en) | 2023-04-14 | 2024-04-09 | Renmin Hospital Of Wuhan University (hubei General Hospital) | Neural-network-based-implemented ophthalmologic intelligent consultation method and apparatus |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Roychowdhury et al. | Blood vessel segmentation of fundus images by major vessel extraction and subimage classification | |
| Zhou et al. | A new human identification method: Sclera recognition | |
| Das et al. | A new efficient and adaptive sclera recognition system | |
| CN105426843B (en) | The single-lens lower vena metacarpea of one kind and palmprint image collecting device and image enhancement and dividing method | |
| Akram et al. | Retinal recognition: Personal identification using blood vessels | |
| CN107273812B (en) | A kind of living body iris method for anti-counterfeit for authentication | |
| Das et al. | Fuzzy logic based selera recognition | |
| Das et al. | A new method for sclera vessel recognition using OLBP | |
| Dixit et al. | An efficient fuzzy based edge estimation for iris localization and pupil detection in human eye for automated cataract detection system | |
| CN114582008A (en) | Living iris detection method based on two wave bands | |
| Du et al. | A one-dimensional approach for iris identification | |
| CN110443217A (en) | One kind being based on multispectral fingerprint method for anti-counterfeit and system | |
| Shashidhara et al. | A novel approach to circular edge detection for iris image segmentation | |
| Gokul Rajan et al. | A new approach for sclera segmentation using integro differential operator | |
| Sathya et al. | Contourlet transform and morphological reconstruction based retinal blood vessel segmentation | |
| Elangovan et al. | A review: person identification using retinal fundus images | |
| Mei et al. | Optic disc segmentation method based on low rank matrix recovery theory | |
| Maxwell et al. | A comparison between contrast limited adaptive histogram equalization and gabor filter sclera blood vessel enhancement techniques | |
| AU2021102309A4 (en) | An efficient iris recognition system with complete local ternary pattern feature extraction and classification method | |
| Rajalakshmi et al. | Enhancement of Vascular Patterns in Palm Images Using Various Image Enhancement Techniques for Person Identification | |
| Rawate et al. | Human identification using IRIS recognition | |
| Wang et al. | Overview of Living Iris Detection Based on Multi-spectral Characteristics | |
| Katke | Iris Recognition Systemby Using Discrete Cosine Transform | |
| David et al. | Robust Iris Image Recognition System Using Normalization Process and Neural Network Techniques | |
| CN117649688A (en) | Near infrared image-based image recognition method, system 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 |