Iris feature extraction method and system for human eye images
By using the iris feature extraction method of human eye images in the access control system, using photoelectric technology and image processing technology, the iris feature detection problem under the influence of light is solved, and the rapid and accurate iris feature extraction is achieved, and the identity of the access control system is improved. Verify efficiency.
Patent Information
- Application Number
- CN202110348316.X
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2021-03-31
- Publication Date
- 2024-11-22
- Estimated Expiration
- 2041-03-31
AI Technical Summary
The existing access control system during face recognition is affected by ambient light, resulting in dark face images collected and cannot be clearly identified, which reduces the recognition accuracy and efficiency, and lacks effective iris feature detection methods.
Using the iris feature extraction method of human eye images, facial images are collected by turning on the stimulation light source and camera, edge segmentation and image processing technology are used to extract the pupil area, determine the iris position range, and quickly extract the iris features with sliding window and edge detection algorithm to avoid light illumination. Inhomogeneous effects.
The objective and rapid extraction of iris features in a light-stimulating environment is achieved, which avoids the influence of light, improves recognition accuracy and efficiency, and reduces time waste.
Smart Images

Figure CN113095182B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of image processing, and in particular to a method and system for extracting iris features from human eye images. Background Art
[0002] When the existing access control system adopts the face recognition solution, due to the influence of ambient light, the camera easily collects the background light of the face image, resulting in the actual face image collected being very dark, making it impossible to clearly identify the collected face image, reducing the accuracy and efficiency of face recognition.
[0003] As an accurate expression of the human body's unique identity feature, the iris has a natural advantage when applied to access control systems. Iris recognition and feature detection are key links in access control. The detection results of iris features determine whether the access control identity authentication is passed. Iris features play a vital role in access control identity authentication. Therefore, it is necessary to provide a solution that can objectively and quickly extract iris features. Summary of the invention
[0004] The purpose of the present invention is to provide a method and system for extracting iris features from human eye images to solve one or more technical problems existing in the prior art and at least provide a beneficial choice or create conditions.
[0005] In order to achieve the above object, the present invention provides the following technical solutions:
[0006] A method for extracting iris features from a human eye image, the method comprising the following steps:
[0007] Step S100: when a human body is detected, turning on a stimulation light source and a camera, and collecting a facial image of the human body through the camera;
[0008] Step S200, extracting an eye image from the facial image using an edge segmentation method, and determining a pupil area in the eye image;
[0009] Step S300, determining the position range of the iris according to the pupil area;
[0010] Step S400: extracting iris features from the iris position range.
[0011] Further, in step S200, determining the pupil area in the eye image includes:
[0012] Preprocessing the eye image to obtain a grayscale image, wherein the preprocessing includes smoothing and denoising processing and grayscale processing;
[0013] Performing overall sharpening on the grayscale image to obtain an image to be processed;
[0014] Binarization is performed on the image to be processed according to a set threshold value to obtain a binary image;
[0015] Detecting a light-transmitting area from the binary image;
[0016] The pupil area in the eye image is determined according to the edge grayscale value distribution of the light-transmitting area.
[0017] Furthermore, the overall sharpening of the grayscale image includes:
[0018] The grayscale value of each pixel in the grayscale image is updated, and the calculation formula of the updated grayscale value is:
[0019]
[0020] Among them, (x i ,y i ) represents the pixel numbered i in the grayscale image, and (m,n) represents the pixel (x i ,y i )’s neighboring points, y i -1≤m≤y i +1,x i -3≤n≤x i +3, k∈[0.1,1], g(·) represents the gray value of the corresponding pixel, w(x i ,y i ,m,n) are update coefficients; k is the gray value adjustment coefficient; by adjusting the updated gray value, the overall image is prevented from being too bright, which is convenient for subsequent threshold segmentation;
[0021] The calculation formula of the update coefficient is:
[0022]
[0023] Wherein, σ is the standard deviation of the grayscale image.
[0024] Furthermore, the step S300 includes:
[0025] Step S310, determining the minimum outer rectangle of the pupil area, and obtaining the length and width of the minimum outer rectangle;
[0026] Step S320, extending the left and right sides of the minimum outer rectangle to the upper and lower ends of the eye image respectively to obtain left and right critical lines;
[0027] Step S330: determine the size of the sliding window, and set the sliding window at the outer boundary of any critical line;
[0028] Step S340, performing a longitudinal sliding search through the sliding window, and extracting a plurality of edge lines from the image to be processed using an edge detection algorithm;
[0029] Step S350, determining whether the plurality of edge lines are connected, if not, executing step S360; if yes, executing step S370;
[0030] Step S360, after sliding the sliding window horizontally by a set distance, executing step S340, the set distance being the width of the sliding window;
[0031] Step S370: connect the multiple edge lines into an arc line, obtain a circular area based on the arc line fitting, and use the circular area as the position range of the iris.
[0032] Furthermore, the length of the sliding window is equal to 0.8 to 3 times the length of the minimum outer rectangle, and the width of the sliding window is 1 / 5 to 1 / 3 of the width of the minimum outer rectangle.
[0033] A computer-readable storage medium stores an iris feature extraction program for human eye images, and when the iris feature extraction program for human eye images is executed by a processor, the steps of the iris feature extraction method for human eye images as described in any one of the above are implemented.
[0034] A system for extracting iris features from human eye images, the system comprising:
[0035] at least one processor;
[0036] at least one memory for storing at least one program;
[0037] When the at least one program is executed by the at least one processor, the at least one processor implements any one of the above methods for extracting iris features from human eye images.
[0038] The beneficial effects of the present invention are as follows: the present invention discloses a method for extracting iris features from human eye images, which avoids the influence of uneven illumination by performing image processing and iris feature extraction in a light stimulation environment, and the image processing result is more objective; since the light spot formed by the stimulation light source is located inside the pupil, the pupil area can be quickly located; since the iris to be located is located between the pupil and the sclera, the position of the iris can be quickly located in the subsequent process according to the roughly determined position range of the pupil, thereby avoiding the waste of time caused by blind searching and being able to quickly extract iris features. The present invention comprehensively utilizes optoelectronic technology and image processing technology, can avoid the influence of ambient illumination, and realize objective and rapid extraction of iris features. BRIEF DESCRIPTION OF THE DRAWINGS
[0039] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative labor.
[0040] Figure 1 is a flow chart of a method for extracting iris features from a human eye image in an embodiment of the present invention;
[0041] Figure 2 is a schematic structural diagram of a human eye image in an embodiment of the present invention;
[0042] Figure 3 Schematic diagram of the structure of the iris feature extraction system for human eye images in an embodiment of the present invention. DETAILED DESCRIPTION
[0043] The following will be combined with the embodiments and drawings to clearly and completely describe the concept, specific structure and technical effects of the present invention, so as to fully understand the purpose, scheme and effect of the present invention. It should be noted that the embodiments and features in the embodiments of the present invention can be combined with each other without conflict.
[0044] See also Figure 1 and Figure 2 The present invention provides a method for extracting iris features from human eye images, the method comprising the following steps:
[0045] Step S100: when a human body is detected, turning on a stimulation light source and a camera, and collecting a facial image of the human body through the camera;
[0046] In the embodiment provided by the present invention, a human body is detected by a human proximity sensor, and a controller is respectively connected to the human proximity sensor, a stimulation light source and a camera. When the controller receives a signal indicating that a human body is detected by the human proximity sensor, the controller drives the stimulation light source and the camera to start working; the LEDs in the stimulation light source are distributed in a circle to achieve uniform scattering of light.
[0047] Step S200, extracting an eye image from the facial image using an edge segmentation method, and determining a pupil area in the eye image;
[0048] In some embodiments, the edge of the eye is determined from the facial image by using an edge segmentation method, thereby extracting the eye image; since the light spot formed by the stimulation light source is located inside the pupil, the pupil area can be quickly located.
[0049] Step S300, determining the position range of the iris according to the pupil area;
[0050] Step S400: extracting iris features from the iris position range.
[0051] The present invention comprehensively utilizes optoelectronic technology and image processing technology, and discloses an objective and accurate image processing method. By performing image processing and iris feature extraction in a light stimulation environment, the influence of uneven illumination is avoided. After the eye image is determined, the pupil area in the eye image is then determined. Since the iris to be located is located between the pupil and the sclera, the position of the iris can be quickly located in the subsequent process according to the roughly determined position range of the pupil, thereby avoiding the time waste caused by blind searching and being able to quickly extract the iris features.
[0052] As a further improvement of the above embodiment, step S300 includes:
[0053] Step S310, determining the minimum outer rectangle of the pupil area, and obtaining the length and width of the minimum outer rectangle;
[0054] Step S320, extending the left and right sides of the minimum outer rectangle to the upper and lower ends of the eye image respectively to obtain left and right critical lines, namely, a left critical line and a right critical line;
[0055] Step S330, determining the size of the sliding window, and setting the sliding window at the outer boundary of any critical line; that is, any critical line of the left critical line and the right critical line;
[0056] Step S340, performing a longitudinal sliding search through the sliding window, and extracting a plurality of edge lines from the image to be processed using an edge detection algorithm;
[0057] Step S350, determining whether the plurality of edge lines are connected, if not, executing step S360; if yes, executing step S370;
[0058] Step S360, after sliding the sliding window horizontally by a set distance, executing step S340, the set distance being the width of the sliding window;
[0059] Step S370: connect the multiple edge lines into an arc line, obtain a circular area based on the arc line fitting, and use the circular area as the position range of the iris.
[0060] Since iris images are mostly circular, the circular area obtained based on the arc line fitting can basically include the iris area, and the extracted iris features are also sufficient for subsequent feature recognition.
[0061] As a further improvement of the above embodiment, the length of the sliding window is equal to 0.8 to 3 times the length of the minimum outer rectangle, and the width of the sliding window is 1 / 5 to 1 / 3 of the width of the minimum outer rectangle.
[0062] In this embodiment, since the pupil area is mostly circular, the minimum outer rectangle obtained is close to a square. By making the length of the sliding window as long as possible, the probability of extracting the iris edge line in one vertical sliding search is increased while avoiding wasting calculations; the width of the sliding window is as short as possible, which can improve the accuracy of edge line extraction.
[0063] As a further improvement of the above embodiment, the determining the pupil area in the eye image includes:
[0064] Preprocessing the eye image to obtain a grayscale image, wherein the preprocessing includes smoothing and denoising processing and grayscale processing;
[0065] Performing overall sharpening on the grayscale image to obtain an image to be processed;
[0066] Binarization is performed on the image to be processed according to a set threshold value to obtain a binary image;
[0067] Detecting a light-transmitting area from the binary image;
[0068] The pupil area in the eye image is determined according to the edge grayscale value distribution of the light-transmitting area.
[0069] The light-transmitting area refers to an area excluding the light-transmitting area in a circle with a set value as the radius and the center of the light-transmitting area as the center. In the eye image, compared with the gray value of the iris, the pupil, as a channel for light to enter the eye, will produce a light-transmitting area of a certain size, and the gray value of the light-transmitting area in the pupil is larger. Therefore, the eye image is binarized according to the set gray threshold, and the part above the gray threshold is taken as the light-transmitting area.
[0070] As a further improvement of the above embodiment, the overall sharpening of the grayscale image includes:
[0071] The grayscale value of each pixel in the grayscale image is updated, and the calculation formula of the updated grayscale value is:
[0072]
[0073] Among them, (x i ,y i ) represents the pixel numbered i in the grayscale image, and (m,n) represents the pixel (x i ,y i)’s neighboring points, y i -1≤m≤y i +1,x i -3≤n≤x i +3, k∈[0.1,1], g(·) represents the gray value of the corresponding pixel, w(x i ,y i ,m,n) are update coefficients; k is the gray value adjustment coefficient; by adjusting the updated gray value, the overall image is prevented from being too bright, which is convenient for subsequent threshold segmentation;
[0074] The calculation formula of the update coefficient is:
[0075]
[0076] Wherein, σ is the standard deviation of the grayscale image.
[0077] and Figure 1 Corresponding to the method, an embodiment of the present invention further provides a computer-readable storage medium, on which is stored an iris feature extraction program for a human eye image. When the iris feature extraction program for a human eye image is executed by a processor, the steps of the iris feature extraction method for a human eye image as described in any of the above embodiments are implemented.
[0078] refer to Figure 3 ,and Figure 1 Corresponding to the method, an embodiment of the present invention further provides an iris feature extraction system for human eye images, the system comprising: a controller, the controller is respectively connected to a human proximity sensor, a stimulus light source and a camera, the controller comprising:
[0079] at least one processor;
[0080] at least one memory for storing at least one program;
[0081] When the at least one program is executed by the at least one processor, the at least one processor implements the iris feature extraction method for a human eye image described in any one of the above embodiments.
[0082] Wherein, the stimulation light source includes a plurality of LEDs, and each LED in the stimulation light source is distributed in a circular shape, thereby achieving uniform scattering of light.
[0083] The contents of the above method embodiments are all applicable to the present system embodiments. The functions specifically implemented by the present system embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.
[0084] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the iris feature extraction system for human eye images, and uses various interfaces and lines to connect various parts of the entire iris feature extraction system for human eye images that can operate.
[0085] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the iris feature extraction system of the human eye image by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area can store data created according to the use of the mobile phone (such as audio data, a phone book, etc.), etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart-Media-Card, SMC), a secure digital (Secure-Digital, SD) card, a flash card (Flash-Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.
[0086] Although the description of the present invention has been quite detailed and specifically describes several described embodiments, it is not intended to be limited to any of these details or embodiments or any particular embodiment, but should be regarded as providing a broad possible interpretation of these claims by reference to the appended claims, taking into account the prior art, so as to effectively cover the intended scope of the present invention. In addition, the above description of the present invention is based on the embodiments foreseeable by the inventor, and its purpose is to provide a useful description, and those non-substantial changes to the present invention that have not yet been foreseen may still represent equivalent changes to the present invention.
Claims
1. A method for extracting iris features from human eye images. It is characterized in that The method comprises the following steps: Step S100: when a human body is detected, turning on a stimulation light source and a camera, and collecting a facial image of the human body through the camera; Step S200, extracting an eye image from the facial image using an edge segmentation method, and determining a pupil area in the eye image; Step S300, determining the position range of the iris according to the pupil area; Step S400, extracting iris features from the iris position range; In step S200, determining the pupil area in the eye image includes: Preprocessing the eye image to obtain a grayscale image, wherein the preprocessing includes smoothing and denoising processing and grayscale processing; Performing overall sharpening on the grayscale image to obtain an image to be processed; Binarization is performed on the image to be processed according to a set threshold value to obtain a binary image; Detecting a light-transmitting area from the binary image; Determining a pupil area in the eye image according to a distribution of edge grayscale values of the light-transmitting area; The overall sharpening of the grayscale image comprises: The grayscale value of each pixel in the grayscale image is updated, and the calculation formula for updating the grayscale value is: Among them, (x i ,y i ) represents the pixel numbered i in the grayscale image, and (m,n) represents the pixel (x i ,y i )’s neighboring points, y i -1≤m≤y i +1,x i -3≤n≤x i +3, k∈[0.1,1], g(·) represents the gray value of the corresponding pixel, w(x i ,y i ,m,n) are update coefficients; k is the gray value adjustment coefficient; by adjusting the updated gray value, the overall image is prevented from being too bright, which is convenient for subsequent threshold segmentation; The calculation formula of the update coefficient is: Wherein, σ is the standard deviation of the grayscale image.
2. The method for extracting iris features from human eye images according to claim 1, It is characterized in that The step S300 includes: Step S310, determining the minimum outer rectangle of the pupil area, and obtaining the length and width of the minimum outer rectangle; Step S320, extending the left and right sides of the minimum outer rectangle to the upper and lower ends of the eye image respectively to obtain left and right critical lines; Step S330: determine the size of the sliding window, and set the sliding window at the outer boundary of any critical line; Step S340, performing a longitudinal sliding search through the sliding window, and extracting a plurality of edge lines from the image to be processed using an edge detection algorithm; Step S350, determining whether the plurality of edge lines are connected, if not, executing step S360; if yes, executing step S370; Step S360, after sliding the sliding window horizontally by a set distance, execute step S340; wherein the set distance is the width of the sliding window; Step S370: connect the multiple edge lines into an arc line, obtain a circular area based on the arc line fitting, and use the circular area as the position range of the iris.
3. The method for extracting iris features from human eye images according to claim 2, It is characterized in that The length of the sliding window is equal to 0.8 to 3 times the length of the minimum outer rectangle, and the width of the sliding window is 1 / 5 to 1 / 3 of the width of the minimum outer rectangle.
4. A computer-readable storage medium, It is characterized in that The computer-readable storage medium stores an iris feature extraction program for human eye images, and when the iris feature extraction program for human eye images is executed by a processor, the steps of the iris feature extraction method for human eye images as claimed in any one of claims 1 to 3 are implemented.
5. A system for extracting iris features from human eye images, It is characterized in that The system comprises: at least one processor; at least one memory for storing at least one program; When the at least one program is executed by the at least one processor, the at least one processor implements the iris feature extraction method for a human eye image as described in any one of claims 1 to 3.
