CN111507208B - Identity verification method, device, equipment and medium based on sclera identification - Google Patents
Identity verification method, device, equipment and medium based on sclera identification Download PDFInfo
- Publication number
- CN111507208B CN111507208B CN202010241200.1A CN202010241200A CN111507208B CN 111507208 B CN111507208 B CN 111507208B CN 202010241200 A CN202010241200 A CN 202010241200A CN 111507208 B CN111507208 B CN 111507208B
- Authority
- CN
- China
- Prior art keywords
- blood vessel
- scleral
- information
- image
- region
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 238000012795 verification Methods 0.000 title claims abstract description 13
- 210000003786 sclera Anatomy 0.000 title claims description 69
- 210000004204 blood vessel Anatomy 0.000 claims abstract description 213
- 238000000605 extraction Methods 0.000 claims abstract description 37
- 238000001914 filtration Methods 0.000 claims description 21
- 238000012545 processing Methods 0.000 claims description 19
- 238000004422 calculation algorithm Methods 0.000 claims description 11
- 238000003062 neural network model Methods 0.000 claims description 11
- 230000004927 fusion Effects 0.000 claims description 9
- 230000002708 enhancing effect Effects 0.000 claims description 8
- 230000002792 vascular Effects 0.000 claims description 8
- 238000003709 image segmentation Methods 0.000 claims description 6
- 230000007797 corrosion Effects 0.000 claims description 4
- 238000005260 corrosion Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 abstract description 5
- 239000011159 matrix material Substances 0.000 description 7
- 238000004891 communication Methods 0.000 description 6
- 230000006870 function Effects 0.000 description 6
- 238000006116 polymerization reaction Methods 0.000 description 5
- 230000005540 biological transmission Effects 0.000 description 4
- 230000008859 change Effects 0.000 description 4
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 238000004590 computer program Methods 0.000 description 2
- 238000003708 edge detection Methods 0.000 description 2
- 238000009499 grossing Methods 0.000 description 2
- 210000003128 head Anatomy 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 239000013598 vector Substances 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000002776 aggregation Effects 0.000 description 1
- 238000004220 aggregation Methods 0.000 description 1
- 230000003321 amplification Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 210000000720 eyelash Anatomy 0.000 description 1
- 210000000744 eyelid Anatomy 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 239000012528 membrane Substances 0.000 description 1
- 238000010295 mobile communication Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 238000003199 nucleic acid amplification method Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000010363 phase shift Effects 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005316 response function Methods 0.000 description 1
- 230000004043 responsiveness Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/19—Sensors therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
- G06F21/31—User authentication
- G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/40—Analysis of texture
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Computer Security & Cryptography (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Multimedia (AREA)
- Human Computer Interaction (AREA)
- Ophthalmology & Optometry (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Molecular Biology (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Hardware Design (AREA)
- Prostheses (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention discloses an identity verification method, device, equipment and medium based on scleral identification. Or comparing the image information of the blood vessel structure with the preset sample information of the scleral blood vessel, and performing identity verification according to the matching degree of the two. The method reserves the integral contour feature and the detail texture difference in the feature extraction, so that the good identifiability is kept when the blood vessel feature changes, and meanwhile, the feature of the scleral blood vessel can be better extracted through a neural network during the classification identification.
Description
Technical Field
The invention relates to the field of identity authentication, in particular to an identity authentication method, device, equipment and medium based on scleral identification.
Background
The identity authentication method based on the eye features has the advantages of high accuracy, high reliability, difficulty in counterfeiting, non-contact property and the like. The sclera is influenced by genes due to abundant and complex blood vessel structures on the surface, has obvious difference among different individuals and does not change along with the time, and meanwhile, the collection of the sclera only needs common illumination, so that the application requirement is reduced, and the sclera is an ideal biological identification technology. At present, researches on sclera as a biological identification method are far from enough, and factors such as image acquisition illumination and angle, interference of characteristics of non-target areas such as eyelashes and eyelids and the like seriously influence identification precision.
A typical scleral identification system includes two parts, scleral blood vessel extraction and scleral identification. Wherein, the scleral blood vessel extraction comprises the specific steps of scleral area extraction, blood vessel segmentation, blood vessel enhancement and the like. With the development of deep learning, a neural network-based blood vessel extraction method also appears, but the method is highly dependent on a high-quality labeled data set, and is difficult to be applied to practical scenes under the conditions that a high-standard data set is difficult to obtain and the network generalization is not high.
Disclosure of Invention
The invention provides an identity verification method, device, equipment and medium based on scleral identification, which can be used for well identifying scleral blood vessels when external environmental factors change and the structure of the sclera is influenced, and improving the robustness of scleral identification.
In one aspect, the present invention provides an identity verification method based on scleral identification, the method comprising:
acquiring original eye image information of an object to be identified;
according to the brightness data of the original eye image information, carrying out segmentation and image processing on the original eye image information to obtain a scleral area image;
performing blood vessel structure enhancement on the sclera area image to obtain sclera blood vessel enhancement information;
extracting scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel region information;
based on a preset neural network model, carrying out feature extraction on the scleral blood vessel region information to obtain the feature information of the scleral blood vessel;
and verifying the identity information of the object to be identified according to the characteristic information of the scleral blood vessel.
Another aspect provides an authentication device based on scleral identification, the device comprising: the system comprises an original image acquisition module, an original image segmentation module, a blood vessel structure enhancement module, a blood vessel region extraction module, a blood vessel feature extraction module and an identity recognition module;
the original image acquisition module is used for acquiring original eye image information;
the original image segmentation module is used for segmenting the original eye image information according to the brightness data of the original eye image information to obtain a scleral area image;
the blood vessel structure enhancement module is used for carrying out blood vessel structure enhancement on the sclera area image to obtain sclera blood vessel enhancement information;
the blood vessel region extraction module is used for extracting the scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel region information;
the blood vessel characteristic extraction module is used for extracting characteristics of the scleral blood vessel region information according to a preset neural network model to obtain the characteristic information of the scleral blood vessel;
the identity recognition module is used for verifying the identity information of the object to be recognized according to the characteristic information of the scleral blood vessel.
Another aspect provides an apparatus comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement an authentication method based on scleral identification as described above.
Another aspect provides a storage medium, which includes a processor and a memory, where at least one instruction or at least one program is stored in the memory, and the at least one instruction or the at least one program is loaded and executed by the processor to implement an authentication method based on scleral identification as described above.
The method comprises the steps of obtaining a scleral region image in an original eye image of an object to be identified, enhancing and extracting a blood vessel structure in the scleral region image to obtain image information of the blood vessel structure in the scleral region image, extracting features of the image information of the blood vessel structure based on a neural network model to obtain feature information of the blood vessel structure, carrying out classification and identification on the feature information of the blood vessel of the sclera, and carrying out identity authentication according to a classification and identification result. Or comparing the image information of the blood vessel structure with the preset sample information of the scleral blood vessel, and performing identity verification according to the matching degree of the two. According to the method, through enhancement and extraction of the blood vessel structure, an improved non-learning blood vessel extraction method is adopted to get rid of dependence on an annotated data set, and overall contour features and texture differences of details are kept in feature extraction, so that good identifiability is kept when blood vessel features change, and meanwhile, the features of scleral blood vessels can be better extracted through a neural network during classification and identification.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic view of an application scenario of an identity authentication method based on scleral identification according to an embodiment of the present invention;
fig. 2 is a flowchart of an authentication method based on scleral identification according to an embodiment of the present invention;
fig. 3 is a flowchart of a method for obtaining an image of a sclera region in an identity authentication method based on sclera identification according to an embodiment of the present invention;
fig. 4 is a flowchart of a method for obtaining scleral blood vessel enhancement information in an authentication method based on scleral identification according to an embodiment of the present invention;
fig. 5 is a flowchart of a method for filtering a blood vessel structure in an identity authentication method based on scleral identification according to an embodiment of the present invention;
fig. 6 is a flowchart of a method for obtaining scleral blood vessel region information in an authentication method based on scleral identification according to an embodiment of the present invention;
fig. 7 is a flowchart of a method for obtaining initial region information of scleral blood vessels in an authentication method based on scleral identification according to an embodiment of the present invention;
fig. 8 is a flowchart of a method for obtaining characteristic information of scleral blood vessels in an authentication method based on scleral identification according to an embodiment of the present invention;
fig. 9 is a schematic structural diagram of a neural network with two branches in an identity authentication method based on scleral identification according to an embodiment of the present invention;
fig. 10 is a schematic block diagram of an authentication device based on scleral identification according to an embodiment of the present invention;
fig. 11 is a schematic hardware structure diagram of an apparatus for implementing the method provided in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a few embodiments of the invention, and not all embodiments. All other embodiments, which can be obtained by a person skilled in the art without any inventive step based on the embodiments of the present invention, are within the scope of the present invention.
In the description of the present invention, it is to be understood that the terms "first", "second" and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implying any number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. Moreover, the terms "first," "second," and the like, are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein.
Referring to fig. 1, a schematic view of an application scenario of an authentication method based on scleral identification according to an embodiment of the present invention is shown, the application scenario includes a user 110, a verification terminal 120, and a server 130, the verification terminal 120 captures an original eye image of the user 110, and sending to the server 130 for detection, the server 130 processing the original eye image information to obtain a sclera region image in the original eye image information, the server 130 enhancing and extracting the blood vessel structure in the sclera region image to obtain sclera blood vessel region information, then performing feature extraction on the sclera blood vessel region information to obtain the feature information of the sclera blood vessel, according to the comparison result of the feature information of the sclera blood vessel and the sclera blood vessel sample information, or classifying and identifying the characteristic information of the scleral blood vessel, and verifying the identity information of the user.
In the embodiment of the present invention, the server 110 may include a server operating independently, or a distributed server, or a server cluster composed of a plurality of servers. The server 110 may include a network communication unit, a processor, a memory, and the like. Specifically, the server 110 may be configured to process the original eye image information to finally obtain scleral blood vessel region information, perform feature extraction on the scleral blood vessel region information to obtain scleral blood vessel feature information, and verify the identity information of the user according to a comparison result between the scleral blood vessel feature information and the scleral blood vessel sample information.
Please refer to fig. 2, which shows an authentication method based on scleral identification, which can be applied to a server side, and the method includes:
s210, acquiring original eye image information of an object to be identified;
s220, segmenting and image processing the original eye image information according to the brightness data of the original eye image information to obtain a scleral area image;
further, referring to fig. 3, the segmenting and image processing the original eye image information according to the luminance data of the original eye image information to obtain a sclera area image includes:
s310, segmenting the original eye image information according to the brightness data of the original eye image information to obtain a first sclera area initial image;
s320, performing expansion operation on the initial image of the first scleral area to obtain an expanded initial image of the first scleral area;
s330, carrying out corrosion operation on the expanded initial image of the first scleral area to obtain an initial image of a second scleral area;
and S340, extracting the maximum connected region of the second scleral region initial image to obtain a scleral region image.
Specifically, the original eye image information is segmented by a clustering algorithm to obtain a non-scleral region and a scleral region, binarization processing is performed on the original eye image information according to the characteristic that the brightness of the scleral region is greater than that of the non-scleral region, pixels in the original eye image information after binarization processing are divided into pixels of the scleral region and pixels of the non-scleral region, and in a specific example, the pixels in the original eye image I can be divided into the scleral region and the non-scleral region { C by minimizing the following error function0,C1And f, two types.
Wherein the content of the first and second substances,
ip represents the gray value of the pixel point p in the image I.
The first sclera region initial image obtained by the method is a sclera region image with a fracture, a cavity or discontinuous contour line, and the blood vessel on the surface of the sclera can divide the complete sclera region into a plurality of small blocks during the clustering, so that the first sclera region initial image needs to be subjected to morphological operation middle closing operation, namely, an operation method of firstly expanding and then corroding is carried out, and a second sclera region initial image with a more complete image is obtained. And performing expansion operation on the initial image of the first scleral area, namely obtaining the local maximum value, and calculating the maximum value of pixel points in a scleral blood vessel coverage area in the initial image of the first scleral area by taking the fixed anchor point as the center, so that the area with higher brightness in the initial image of the first scleral area is gradually increased, and the expanded initial image of the first scleral area is obtained. And carrying out corrosion operation on the expanded initial image of the first scleral area, namely, obtaining the operation of a local minimum value, and calculating the minimum value of pixel points in a scleral blood vessel coverage area in the initial image of the first scleral area by taking a fixed anchor point as a center, so that the area with higher brightness in the initial image of the first scleral area is contracted to obtain the initial image of the second scleral area.
And extracting the maximum connected region of the second scleral region initial image to obtain a convex hull of the maximum connected region in the second scleral region initial image, wherein the convex hull is the scleral region image. Inputting a second sclera region initial image, initializing a connected region set Q, initializing a queue L for each pixel point p in the second sclera region initial image, and if the gray value Ip of the pixel is 1 and p is not marked, putting p into the queue L. Initializing a current connected domain Qi, taking out a queue head element e and putting the queue head element e into the Qi when L is not empty, and putting m into a queue L if m is 1 and m is not marked for each element m in an e four-adjacent domain. Put Qi into Q, take out the largest set in Q as the last connected domain Qmax. And obtaining a convex hull of the maximum connected domain Qmax by using a Graham scanning method, wherein the convex hull is the image of the scleral region. When scanning is carried out, the whole maximum connected domain is traversed from the origin, and the pit points in the maximum connected domain are removed, so that the convex hull of the maximum connected domain Qmax, namely the image of the scleral region, is obtained.
The fracture and the cavity in the initial image of the first scleral area can be removed after the expansion and corrosion operations, but a part of the cavity may be left, and the remaining few cavities can be processed by extracting the maximum communication area of the initial image of the second scleral area to obtain a complete scleral area image.
S230, performing blood vessel structure enhancement on the sclera area image to obtain sclera blood vessel enhancement information;
further, referring to fig. 4, the performing the blood vessel structure enhancement on the sclera region image to obtain the scleral blood vessel enhancement information includes:
s410, redistributing the image brightness of the scleral area image to obtain a scleral area image with redistributed brightness;
and S420, filtering the blood vessel structure in the sclera area image after the brightness redistribution to obtain sclera blood vessel enhancement information.
Specifically, the scleral region image is subjected to blood vessel structure enhancement, and the blood vessel structure is highlighted to obtain scleral blood vessel enhancement information. The contrast-limited adaptive histogram equalization method (CLAHE) can be firstly used for the scleral area image, the image brightness of the scleral area image is redistributed to change the image contrast, and the obtained scleral area image with redistributed brightness is recorded as ICLAHE。
The CLAHE algorithm achieves the functions of expanding the local contrast and displaying the details of a smooth area by performing histogram equalization in a rectangular area around the current processing pixel, and can effectively limit the noise amplification condition.
Then, a Gabor filter is used for enhancing the scleral region image I after brightness redistributionCLAHEAnd obtaining the scleral blood vessel enhancement information. The Gabor filter can extract local spatial and frequency domain information of the target, thereby enhancing the vascular structure.
Specifically, referring to fig. 5, the filtering the blood vessel structure in the sclera region image after the brightness redistribution to obtain the scleral blood vessel enhancement information includes:
s510, filtering different angles of the blood vessel structure in the sclera area image after the brightness redistribution to obtain blood vessel structure filtering results of different angles;
s520, taking the maximum filtering result in the filtering results of the blood vessel structures of different angles as scleral blood vessel enhancement information.
Specifically, because the blood vessels have multiple directions, when the filtering operation is performed, filtering needs to be performed from different angle blood vessel structures, and the maximum filtering result in each angle, that is, the clearest part of the blood vessel structure, is selected and output as scleral blood vessel enhancement information. A typical complex expression for a Gabor filter is as follows:
where (x, y) is the original pixel coordinate, (x ', y') is the rotated pixel coordinate, λ is the sine factor wavelength, θ is the angle of the Gabor kernel function, ψ is the phase shift, δ is the standard deviation of the gaussian function, and γ is the spatial aspect ratio, which represents the ellipticity of the Gabor filter. The calculation procedure for vessel enhancement using Gabor filters is as follows:
wherein ICLAHE(x, y) is the pixel value of the (x, y) location, and g (x, y; theta) is a Gabor filter with a particular angle theta, which can start at 0 degrees, each increment of pi/8 for eight different angles theta, due to the multidirectional nature of the vessel. Selecting the maximum value in the Gabor filtering results corresponding to different angles as the enhancement result I of the (x, y) positionGabor(x,y)。
After the blood vessel structure is enhanced, the difference between the blood vessel structure and the background area can be more obvious, and the image of the blood vessel is clearer, so that the subsequent extraction of the blood vessel area is facilitated, and a relatively complete blood vessel area image with more characteristics is obtained.
S240, extracting the scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel region information;
further, referring to fig. 6, the extracting the scleral blood vessels in the scleral blood vessel enhancement information to obtain the scleral blood vessel region information includes:
s610, determining initial region information of scleral blood vessels in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm;
s620, matching the tubular structures in the initial region information according to a preset blood vessel scale to obtain sclera blood vessel region information.
Specifically, the edge detection enhanced filtering Frangi filtering algorithm based on the Hessian matrix (Hessian) extracts the blood vessel characteristics. Gabor filtered image IGaborAnd performing Gaussian smoothing, wherein a parameter sigma of the Gaussian smoothing is a standard deviation. For a linear structure of a vessel, the output of the filter is maximum when the scale factor σ best matches the actual width of the vessel.
Specifically, referring to fig. 7, the determining the initial region information of the scleral blood vessel in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm includes:
s710, calculating a tubular characteristic parameter of each pixel in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm;
s720, classifying the pixels in the scleral blood vessel enhancement information according to the tubular characteristic parameters of each pixel to obtain the initial region information of the scleral blood vessel.
In particular, at the current scale σ, a vessel enhanced image I is computedGaborSecond-order partial derivatives G of each pixel point p in x and y directionsxx、GxyAnd Gyy。
Using second order partial derivatives Gxx、GxyAnd GyyFor image IGaborPerforming convolution operation to obtain:
Ixx＝Gxx*IE
Ixy＝Gxy*IE
Iyy＝Gyy*IE
use of Ixx、IxyAnd IyyConstructing an image Hessian matrix
Calculating the eigenvalue lambda of Hessian matrix1，λ2(let λ)1Smaller absolute value), the variable R is constructedbAnd S:
the blood vessel area in the sclera is a tubular structure, the response value of the Gaussian second derivative is larger, the background of the sclera of the eye is a uniform part, and the response value of the Gaussian second derivative is smaller. Therefore, the characteristic values of the Hessian matrix at the blood vessel point are one large and one small, the characteristic values of the Hessian matrix at the blood vessel intersection point are both large, the characteristic values of the Hessian matrix at the background point are both small, and a background area and a blood vessel area can be distinguished.
Thus, the responsiveness function of the vascular region in the scleral vascular enhancement information is:
where β is used to adjust and distinguish the sensitivity of the block structure of the background region and the tubular structure of the vessel region, and c affects the overall smoothness of the filtered image. The response function of the pixel point p belonging to the blood vessel region under the multi-scale is as follows:
pixels with tubular characteristics in the membrane blood vessel enhancement information are obtained through an edge detection enhancement filtering Frangi filtering algorithm based on a Hessian matrix, so that pixels belonging to a blood vessel region in the sclera blood vessel enhancement information can be extracted to form sclera blood vessel region information.
S250, performing feature extraction on the scleral blood vessel region information based on a preset neural network model to obtain feature information of scleral blood vessels;
further, please refer to fig. 8, the performing feature extraction on the scleral blood vessel region information based on the preset neural network model to obtain the scleral blood vessel feature information includes:
s810, performing multi-scale feature extraction on the scleral blood vessel region information to obtain blood vessel profile distribution feature information with different dimensions;
s820, carrying out feature fusion on the blood vessel profile distribution feature information with different dimensions to obtain fusion feature information of scleral blood vessels;
s830, performing dimensionality reduction on the fusion characteristic information of the scleral blood vessels to obtain scleral blood vessel characteristic information.
Specifically, the neural network model constructs a neural network structure including double branches (stem branch and leaf branch), as shown in fig. 9. Before branching, the network firstly uses multilayer convolution to extract the initial layer feature, and the branch feature dimensionality is reduced, so that the network calculated amount is reduced.
The stem branch is a multi-scale feature extractor which is stacked by a plurality of convolution structures and can extract blood vessel profile distribution features of different levels in the scleral blood vessel region information, wherein each convolution structure is composed of two convolution layers, the step length of convolution can be 1 and 2 respectively, and the output dimension is reduced to half of the input feature dimension.
The leaf branches are used as a multi-layer fusion device to enhance different dimensions through aggregation operationThe overall contour information and the local detail features of the blood vessel contour distribution feature information are fused. Polymerization characteristics of the l-th layer of leaf branches
Stem characteristics of the first layer from stem branches
And the polymerization characteristics of the l-1 st layer of the leaf branch are
Obtaining by polymerization:
wherein
In order to carry out the polymerization operation,
reducing dimensionality by maximum pooling, and performing 1 × 1 convolution to obtain a product
Features of the same dimension, mixing them with
And merging to finish the polymerization operation.
And S260, verifying the identity information of the object to be identified according to the characteristic information of the scleral blood vessel.
In particular, the top-most feature of the dual-branch network is defined
As a high-dimensional feature of the scleral vascular structure, a classifier consisting of a fully connected layer and a softmax layer was fed to complete scleral identification.
Via a full connection layer
And then, integrating and rearranging the vectors into a one-dimensional vector through dimension reduction operation, and then using a softmax classifier to obtain a final classification result T:
the classification result T is the category of the characteristic information of the scleral blood vessels, and the characteristics of the scleral blood vessels can be identified according to the obtained classification result, so that the identity information of the object to be identified is verified.
The regional information of the scleral blood vessels can also be compared with preset scleral sample information, and the identity information of the object to be identified is verified according to the matching degree.
The embodiment of the invention provides an identity verification method based on scleral identification, which comprises the steps of obtaining a scleral area image in an original eye image of an object to be identified, enhancing and extracting a blood vessel structure in the scleral area image to obtain image information of the blood vessel structure in the scleral area image, extracting features of the image information of the blood vessel structure based on a neural network model to obtain feature information of the blood vessel structure, carrying out classification identification on the feature information of the blood vessel of the sclera, and carrying out identity verification according to a classification identification result. Or comparing the image information of the blood vessel structure with the sample information of the preset scleral blood vessel, and performing identity verification according to the matching degree of the image information and the sample information of the preset scleral blood vessel.
An embodiment of the present invention further provides an identity authentication device based on scleral identification, please refer to fig. 10, where the device includes: an original image acquisition module 1010, an original image segmentation module 1020, a blood vessel structure enhancement module 1030, a blood vessel region extraction module 1040, a blood vessel feature extraction module 1050 and an identity recognition module 1060;
the original image obtaining module 1010 is configured to obtain original eye image information;
the original image segmentation module 1020 is configured to segment the original eye image information according to luminance data of the original eye image information to obtain a scleral area image;
the blood vessel structure enhancing module 1030 is configured to perform blood vessel structure enhancement on the sclera region image to obtain sclera blood vessel enhancement information;
the blood vessel region extraction module 1040 is configured to extract scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel region information;
the blood vessel feature extraction module 1050 is configured to perform feature extraction on the scleral blood vessel region information based on a preset neural network model to obtain feature information of scleral blood vessels;
the identity recognition module 1060 is configured to verify the identity information of the object to be recognized according to the characteristic information of the scleral blood vessel.
The device provided in the above embodiments can execute the method provided in any embodiment of the present invention, and has corresponding functional modules and beneficial effects for executing the method. Technical details that are not described in detail in the above embodiments may be referred to an authentication method based on scleral identification according to any embodiment of the present invention.
The present embodiment also provides a computer-readable storage medium, in which computer-executable instructions are stored, and the computer-executable instructions are loaded by a processor and execute an identity authentication method based on scleral identification as described in the present embodiment.
The present embodiment also provides an apparatus, which includes a processor and a memory, where the memory stores a computer program, and the computer program is adapted to be loaded by the processor and execute an identity authentication method based on scleral identification as described in the present embodiment.
The device may be a computer terminal, a mobile terminal or a server, and the device may also participate in forming the apparatus or system provided by the embodiments of the present invention. As shown in fig. 11, the server 11 (or the computer terminal 11 or the mobile terminal 11) may include one or more (shown as 1102a, 1102b, … …, 1102 n) processors 1102 (the processors 1102 may include but are not limited to a processing device such as a microprocessor MCU or a programmable logic device FPGA), a memory 1104 for storing data, and a transmission device 1106 for communication functions. Besides, the method can also comprise the following steps: a display, an input/output interface (I/O interface), a network interface, a power source, and/or a camera. It will be understood by those skilled in the art that the structure shown in fig. 11 is only an illustration and is not intended to limit the structure of the electronic device. For example, server 11 may also include more or fewer components than shown in FIG. 11, or have a different configuration than shown in FIG. 11.
It should be noted that the one or more processors 1102 and/or other data processing circuitry described above may be referred to generally herein as "data processing circuitry". The data processing circuitry may be embodied in whole or in part in software, hardware, firmware, or any combination thereof. Furthermore, the data processing circuit may be a single stand-alone processing module, or incorporated in whole or in part into any of the other elements in the server 11 (or computer terminal). As referred to in the embodiments of the application, the data processing circuit acts as a processor control (e.g. selection of a variable resistance termination path connected to the interface).
The memory 1104 may be used for storing software programs and modules of application software, such as program instructions/data storage devices corresponding to the method according to the embodiment of the present invention, and the processor 1102 may execute various functional applications and data processing by running the software programs and modules stored in the memory 1104, so as to implement the above-mentioned method for generating the self-attention-network-based time-series behavior capture block. The memory 1104 may include high-speed random access memory, and may also include non-volatile memory, such as one or more magnetic storage devices, flash memory, or other non-volatile solid-state memory. In some examples, the memory 1104 may further include memory located remotely from the processor 1102, which may be connected to the server 11 via a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The transmission device 1106 is used for receiving or transmitting data via a network. The above-described specific example of the network may include a wireless network provided by a communication provider of the server 11. In one example, the transmission device 1106 includes a Network adapter (NIC) that can be connected to other Network devices through a base station to communicate with the internet. In one example, the transmission device 1106 may be a Radio Frequency (RF) module, which is used for communicating with the internet in a wireless manner.
The display may be, for example, a touch screen type Liquid Crystal Display (LCD) that may enable a user to interact with the user interface of the server 11 (or computer terminal).
The present specification provides method steps as described in the examples or flowcharts, but may include more or fewer steps based on routine or non-inventive labor. The steps and sequences recited in the embodiments are but one manner of performing the steps in a multitude of sequences and do not represent a unique order of performance. In the actual system or interrupted product execution, it may be performed sequentially or in parallel (e.g., in the context of parallel processors or multi-threaded processing) according to the embodiments or methods shown in the figures.
The configurations shown in the present embodiment are only partial configurations related to the present application, and do not constitute a limitation on the devices to which the present application is applied, and a specific device may include more or less components than those shown, or combine some components, or have an arrangement of different components. It should be understood that the methods, apparatuses, and the like disclosed in the embodiments may be implemented in other manners. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the modules is merely a division of one logic function, and there may be other divisions when actually implemented, for example, a plurality of units or components may be combined or may be integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or unit modules.
Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
Those of skill would further appreciate that the various illustrative components and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, computer software, or combinations of both, and that the various illustrative components and steps have been described above generally in terms of their functionality in order to clearly illustrate this interchangeability of hardware and software. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
The above-mentioned embodiments are only used for illustrating the technical solutions of the present invention, and not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (10)
1. An identity verification method based on scleral identification, the method comprising:
acquiring original eye image information of an object to be identified;
segmenting the original eye image information according to the brightness data of the original eye image information to obtain a first sclera area initial image, wherein the first sclera area initial image is a sclera area image with a fracture, a cavity or discontinuous contour line;
performing image processing on the first sclera area initial image to obtain a second sclera area initial image;
extracting the maximum connected region of the second scleral region initial image to obtain a scleral region image;
performing blood vessel structure enhancement on the sclera area image to obtain sclera blood vessel enhancement information;
extracting scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel region information;
performing feature extraction on the scleral blood vessel region information based on stem branches and leaf branches in a preset neural network model to obtain feature information of scleral blood vessels, wherein the stem branches are used for extracting blood vessel profile distribution feature information of different levels in the scleral blood vessel region information, and the leaf branches are used for enhancing the overall profile information of the blood vessel profile distribution feature information of different dimensions and performing local detail feature fusion;
and verifying the identity information of the object to be identified according to the characteristic information of the scleral blood vessel.
2. The method of claim 1, wherein the segmenting the original eye image information according to the brightness data of the original eye image information to obtain the first sclera region initial image comprises:
segmenting the original eye image information according to the brightness data of the original eye image information to obtain a first sclera area initial image;
the image processing of the first sclera region initial image to obtain a second sclera region initial image comprises:
performing expansion operation on the initial image of the first scleral area to obtain an expanded initial image of the first scleral area;
and carrying out corrosion operation on the expanded initial image of the first scleral area to obtain an initial image of a second scleral area.
3. The method of claim 1, wherein the performing of the blood vessel structure enhancement on the sclera region image to obtain the sclera blood vessel enhancement information comprises:
redistributing the image brightness of the scleral area image to obtain a scleral area image with redistributed brightness;
and filtering the blood vessel structure in the sclera area image after the brightness redistribution to obtain sclera blood vessel enhancement information.
4. The method of claim 3, wherein the filtering the blood vessel structure in the sclera region image after the brightness redistribution to obtain the scleral blood vessel enhancement information comprises:
filtering different angles of the vascular structure in the scleral area image after the brightness redistribution to obtain vascular structure filtering results of different angles;
and taking the maximum filtering result in the vascular structure filtering results of different angles as scleral vascular enhancement information.
5. The method of claim 1, wherein the extracting the scleral blood vessels in the scleral blood vessel enhancement information to obtain the scleral blood vessel region information comprises:
determining initial region information of scleral blood vessels in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm;
and matching the tubular structure in the initial region information according to a preset blood vessel scale to obtain the scleral blood vessel region information.
6. The method of claim 5, wherein the determining the initial region information of the scleral blood vessels in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm comprises:
calculating a tubular characteristic parameter of each pixel in the scleral blood vessel enhancement information according to a preset blood vessel region extraction algorithm;
and classifying the pixels in the scleral blood vessel enhancement information according to the tubular characteristic parameter of each pixel to obtain the initial region information of the scleral blood vessel.
7. The method as claimed in claim 1, wherein the obtaining of the scleral blood vessel feature information by feature extraction of the scleral blood vessel region information based on stem branches and leaf branches in a preset neural network model comprises:
based on the stem branch, carrying out multi-scale feature extraction on the scleral blood vessel region information to obtain blood vessel profile distribution feature information of different levels;
performing feature fusion on the blood vessel profile distribution feature information of different dimensions based on the leaf branches to obtain fusion feature information of scleral blood vessels;
and performing dimensionality reduction on the fusion characteristic information of the scleral blood vessels to obtain scleral blood vessel characteristic information.
8. An authentication device based on scleral identification, the device comprising: the system comprises an original image acquisition module, an original image segmentation module, a blood vessel structure enhancement module, a blood vessel region extraction module, a blood vessel feature extraction module and an identity recognition module;
the original image acquisition module is used for acquiring original eye image information of an object to be identified;
the original image segmentation module is used for segmenting the original eye image information according to the brightness data of the original eye image information to obtain a first sclera area initial image, wherein the first sclera area initial image is a sclera area image with fracture, holes or discontinuous contour lines; performing image processing on the first sclera area initial image to obtain a second sclera area initial image; extracting the maximum connected region of the second scleral region initial image to obtain a scleral region image;
the blood vessel structure enhancement module is used for carrying out blood vessel structure enhancement on the sclera area image to obtain sclera blood vessel enhancement information;
the blood vessel region extraction module is used for extracting the scleral blood vessels in the scleral blood vessel enhancement information to obtain scleral blood vessel region information;
the blood vessel characteristic extraction module is used for extracting characteristics of the scleral blood vessel region information based on stem branches and leaf branches in a preset neural network model to obtain the characteristic information of scleral blood vessels, the stem branches are used for extracting blood vessel contour distribution characteristic information of different levels in the scleral blood vessel region information, and the leaf branches are used for enhancing the overall contour information of the blood vessel contour distribution characteristic information of different dimensions and performing local detail characteristic fusion;
the identity recognition module is used for verifying the identity information of the object to be recognized according to the characteristic information of the scleral blood vessel.
9. An apparatus comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the scleral identification-based authentication method according to any one of claims 1 to 7.
10. A storage medium comprising a processor and a memory, wherein the memory stores at least one instruction or at least one program, and the at least one instruction or the at least one program is loaded and executed by the processor to implement the scleral identification-based authentication method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010241200.1A CN111507208B (en) | 2020-03-30 | 2020-03-30 | Identity verification method, device, equipment and medium based on sclera identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010241200.1A CN111507208B (en) | 2020-03-30 | 2020-03-30 | Identity verification method, device, equipment and medium based on sclera identification |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111507208A CN111507208A (en) | 2020-08-07 |
| CN111507208B true CN111507208B (en) | 2021-06-25 |
Family
ID=71874489
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010241200.1A Active CN111507208B (en) | 2020-03-30 | 2020-03-30 | Identity verification method, device, equipment and medium based on sclera identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111507208B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778664A (en) * | 2016-12-29 | 2017-05-31 | 天津中科智能识别产业技术研究院有限公司 | The dividing method and its device of iris region in a kind of iris image |
| CN108712381A (en) * | 2018-04-16 | 2018-10-26 | 出门问问信息科技有限公司 | A kind of auth method and device |
| CN109190505A (en) * | 2018-08-11 | 2019-01-11 | 石修英 | The image-recognizing method that view-based access control model understands |
| CN110287813A (en) * | 2019-06-04 | 2019-09-27 | 武汉虹识技术有限公司 | Personal identification method and system |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| DE102010032193A1 (en) * | 2010-07-24 | 2012-01-26 | Chronos Vision Gmbh | Method and device for determining eye torsion |
| US20140358011A1 (en) * | 2013-05-29 | 2014-12-04 | University Of Miami | Single shot high resolution conjunctival small vessel perfusion method for evaluating microvasculature in systemic and ocular vascular diseases |
| US9390327B2 (en) * | 2013-09-16 | 2016-07-12 | Eyeverify, Llc | Feature extraction and matching for biometric authentication |
| US9934436B2 (en) * | 2014-05-30 | 2018-04-03 | Leidos Innovations Technology, Inc. | System and method for 3D iris recognition |
| BR122018007961B1 (en) * | 2015-09-11 | 2024-04-30 | Jumio Corporation | METHOD IMPLEMENTED BY COMPUTER AND SYSTEM |
| US10163010B2 (en) * | 2015-10-16 | 2018-12-25 | Magic Leap, Inc. | Eye pose identification using eye features |
| CN110348541B (en) * | 2019-05-10 | 2021-12-10 | 腾讯医疗健康(深圳)有限公司 | Method, device and equipment for classifying fundus blood vessel images and storage medium |
| CN110889356A (en) * | 2019-11-19 | 2020-03-17 | 广州恒龙信息技术有限公司 | Method and device for unlocking AR glasses based on infrared camera and AR glasses |
-
2020
- 2020-03-30 CN CN202010241200.1A patent/CN111507208B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106778664A (en) * | 2016-12-29 | 2017-05-31 | 天津中科智能识别产业技术研究院有限公司 | The dividing method and its device of iris region in a kind of iris image |
| CN108712381A (en) * | 2018-04-16 | 2018-10-26 | 出门问问信息科技有限公司 | A kind of auth method and device |
| CN109190505A (en) * | 2018-08-11 | 2019-01-11 | 石修英 | The image-recognizing method that view-based access control model understands |
| CN110287813A (en) * | 2019-06-04 | 2019-09-27 | 武汉虹识技术有限公司 | Personal identification method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111507208A (en) | 2020-08-07 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10789465B2 (en) | Feature extraction and matching for biometric authentication | |
| Song et al. | Finger-vein recognition based on deep DenseNet using composite image | |
| Yuan et al. | Difference co-occurrence matrix using BP neural network for fingerprint liveness detection | |
| Emambakhsh et al. | Nasal patches and curves for expression-robust 3D face recognition | |
| US10262190B2 (en) | Method, system, and computer program product for recognizing face | |
| Liao et al. | Learning invariant representations and applications to face verification | |
| Tuzel et al. | Global-local face upsampling network | |
| Pamplona Segundo et al. | Pore-based ridge reconstruction for fingerprint recognition | |
| Davy et al. | Reducing anomaly detection in images to detection in noise | |
| CN111814682A (en) | Face living body detection method and device | |
| Alonso-Fernandez et al. | Iris super-resolution using iterative neighbor embedding | |
| CN104200201B (en) | A kind of coding method and system applied to iris recognition | |
| CN111723762B (en) | Face attribute identification method and device, electronic equipment and storage medium | |
| Cintas et al. | Automatic ear detection and segmentation over partially occluded profile face images | |
| CN111507208B (en) | Identity verification method, device, equipment and medium based on sclera identification | |
| CN109165551B (en) | Expression recognition method for adaptively weighting and fusing significance structure tensor and LBP characteristics | |
| Ong et al. | Retina verification using a combined points and edges approach | |
| CN111027616B (en) | Line characteristic description system based on end-to-end learning | |
| Cohen et al. | Iris identification in 3D | |
| Yang et al. | Efficient method for high-resolution fingerprint image enhancement using deep residual network | |
| Gautam et al. | A review on Finger vein based Recognition | |
| CN108427937A (en) | Stability region choosing method and device | |
| Tang et al. | Forearm multimodal recognition based on IAHP‐entropy weight combination | |
| Adel Jalal | Convolution Neural Network Based Method for Biometric Recognition | |
| Savitha et al. | Locality-constraint Representation with Minkowski distance metric for an effective Face Hallucination |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |