Iris recognition method and system

Abstract

The invention belongs to the technical field of iris recognition, discloses an iris recognition method, and particularly relates to a near-distance wide-range imaging iris recognition method based on a maximum image plane imaging principle. The iris acquisition system can still accurately identify iris information of user groups with different heights in a short-distance use range without the support of a rotating mechanism. Mechanical structures are reduced, the service life and the repair rate of equipment are improved, the cost is reduced, and the production efficiency is improved. According to the invention, a face lens and a corresponding face algorithm are optimized, the recognition process is simplified, and the recognition rate is improved; the problem of short-distance and wide-range imaging under the condition of no rotating shaft is solved, and the problems of difficult equipment repair and the like caused by the problems of rotating shaft jamming and the like are avoided; the manufacturing cost and the maintenance cost of the equipment are reduced, and the customer satisfaction rate is improved to a certain extent.

Description

Technical Field

[0001] The present invention belongs to the technical field of iris recognition, and in particular relates to an iris recognition method and system. Background Art

[0002] With the technological iteration of image sensors and the rapid development of the manufacturing process of optical lenses, extremely small sensor pixel sizes are widely used with ultra-high lens resolution. Among them, as one of the core components of the iris acquisition system: there is a direct relationship between the number of pixels of the image sensor and the imaging size (or image resolution), but the two are not simply linearly corresponding. To understand the relationship between the two, several factors need to be considered: 1. Pixels are the basic units that make up a digital image. The more pixels on a sensor, the more details that can be captured in theory, which can lead to higher image resolution. For example, a 24-megapixel sensor can capture more details than a 12-megapixel sensor under the same conditions. Sensor size: The actual physical size of the sensor also affects the imaging effect. Larger sensors can have a larger single pixel area for a given number of pixels, or accommodate more pixels while keeping the size of a single pixel unchanged. Large-size sensors generally provide lower noise levels and better dynamic range at high ISO settings.

[0003] One of the core components in the iris acquisition system: the lens is responsible for focusing light onto the sensor, converging the light from the object to form a clear image. The clarity of each point on the image plane determines the quality of the final image. High resolution means more details can be captured. Advanced image sensors have very high pixel density and can capture extremely delicate images, but this also requires the lens to have excellent optical performance to match the capabilities of the sensor. To match the full-frame sensor size, the field of view (FOV) of the lens determines the width of the scene that can be captured. At the same time, high-resolution sensors place higher demands on the lens. Even if the lens can cover the entire image plane of the sensor, if its resolution is not enough to support the pixel density of the sensor, the final image will appear blurry or lack details. Therefore, it is very important to choose a lens that can provide sufficient resolution.

[0004] In order to meet the needs of close-range wide-range imaging and improve the application scope of the iris acquisition system, the iris acquisition system is optimized and designed. Generally, a height range of 35cm to 55cm can meet the user experience of most user groups. However, from an optical perspective, the field of view of the iris acquisition system needs to be larger and maintain high contrast, which leads to a conflict of requirements.

[0005] Patent CN111428654A mentions an iris recognition method: it is about an iris recognition method, device and storage medium, wherein the iris recognition method is applied to an electronic device, the electronic device includes a rotatable camera device, the method includes: obtaining world coordinate information of a target face image taken by the camera device; calculating the rotation angle of the camera device according to the world coordinate information, and controlling the camera device to locate to a specified position according to the rotation angle, wherein the specified position is the position corresponding to the target face image in the effective imaging range of the camera device; obtaining iris information of the target face image, and performing iris recognition based on the iris information. Through the present disclosure, through the positioning technology of face detection and camera device, while providing high-precision positioning and recognition, it can also realize the acquisition of iris information at different distances, even at a long distance or even in the presence of external environmental interference, iris information can still be collected and recognized.

[0006] Through the above analysis, the problems and defects of the prior art are as follows:

[0007] The existing method has a complex rotating structure, high cost, long process and needs to be combined with multiple algorithms such as face recognition, which directly affects the recognition rate. In a long-term use environment, the rotating mechanism is prone to problems such as stuck and angle deviation, causing after-sales difficulties and reduced customer satisfaction. Summary of the invention

[0008] In view of the problems existing in the prior art, the present invention provides an iris recognition method.

[0009] The present invention is implemented in this way: an iris recognition method comprises:

[0010] Step 1: Determine the parameters of the first iris module and the second iris module through the iris acquisition system according to the requirements;

[0011] Step 2, collecting chart images of the first iris module at different object distances, taking the center point of the chart as the reference point, measuring the coordinates of the center point of each chart, comparing them with the theoretical coordinate values ​​calculated by the second iris module based on the module parameters, structure position size and different object distances, and performing error calculation in combination with object distance compensation to measure the mapping error at different object distances;

[0012] Step 3, configuring an optical mapping relationship between the first iris module and the second iris module;

[0013] Step 4: When the user enters the device recognition range, the distance measurement module feeds back the distance information, triggering the infrared fill light module, as well as the module AE, AF and other functions, while obtaining the original infrared image of the entire working surface at the target distance;

[0014] Step 5, the algorithm crops the original image and determines whether there are human eye features;

[0015] Step 6: Obtain the user's iris features, compare them with the database, and finally complete identity recognition.

[0016] Furthermore, the iris acquisition system includes a first iris module, a second iris module, a first infrared light board, and a second infrared light board; and parameter confirmation of the image acquisition unit is performed.

[0017] Furthermore, the parameters of the first iris module and the second iris module are determined by the iris acquisition system according to the requirements:

[0018] The calculation formula is:

[0019] HL=2×arctan(Hpixel_count*Hpixel_size / 2 / f)

[0020] VL=2×arctan(Vpixel_count*Vpixel_size / 2 / f)

[0021] Where HL is the horizontal field of view of the image acquisition unit, in degrees; VL is the vertical field of view of the image acquisition unit, in degrees; f is the focal length of the lens, in millimeters; Hpixel_count is the number of pixels in the horizontal direction of the sensor; Hpixel_size is the pixel size in the horizontal direction of the sensor, in microns; Vpixel_count is the number of pixels in the vertical direction of the sensor; Vpixel_size is the pixel size in the vertical direction of the sensor, in microns;

[0022] According to the requirements, for the fill light unit, the design range of the angular deflection of the radiation intensity of the fill light unit is proposed, which is defined as:

[0023] in

[0024] where θ av is the deflection angle of the radiation intensity direction angle of the fill light unit; d is the horizontal distance from the center of the fill light unit to the center of the iris; L is the midpoint value within the working distance range;

[0025] Definition: the distance between the pupils of the human eye is 58mm to 65mm, and the center offset of the radiation intensity is 0mm to 15mm; limited by the half-size x of the equipment design, the value of L remains unchanged, and the value range of d is [0, x-30], unit: mm;

[0026] Then according to experience, we define, θ av -2°<θ av <θ av +5°, θav It is recommended to take an integer;

[0027] Get the deflection angle θ av After the value range of , the tracepro simulation software is used to perform ray tracing to obtain the irradiance / illuminance analysis diagram. Under the condition of good irradiance uniformity in the working image plane, the optimal deflection angle θ is determined. av .

[0028] Furthermore, the fill light unit, this patent proposes a design method for the number of infrared lamp beads used in the iris acquisition system:

[0029]

[0030] Where N is the number of infrared lamps required, unit: piece; E av is the average illumination on the working surface, unit: lx; S is the area of ​​the working area, unit: m 2 ; Φ is the luminous flux of the light source, unit: lm; U is the utilization factor of the infrared lamp; K is the maintenance factor of the lamp;

[0031] The average illumination on the working surface is proposed in the original design. Based on the maximum working distance, the brightness value of the iris area needs to be greater than 60, and the average illumination of the working surface area at the maximum working distance is required to meet xxx lx;

[0032] The working area is defined as the total field of view of the iris acquisition unit at the farthest working distance;

[0033] Define the utilization factor of infrared lamp:

[0034] Among them, Φ1 is the luminous flux emitted from the light source and finally projected onto the working surface, unit: lm; Φ0 is the luminous flux of the light source, unit: lm; according to the structural design of the fill light unit and the specifications of the infrared lamp beads (divergence angle, light intensity and light power) of the manufacturer used, the light source file is imported, and the ray tracing is performed through the tracepro simulation software to obtain the irradiance / illuminance analysis diagram, so as to obtain the luminous flux on the working surface and calculate the utilization coefficient; the maintenance coefficient of the lamp is designed to be 0.7-0.8 based on the fact that the main use environment of the iris acquisition system is a relatively clean environment.

[0035] Another object of the present invention is to provide an iris recognition system comprising:

[0036] A determination module, used to determine parameters of the first iris module and the second iris module according to requirements;

[0037] An acquisition module is used to acquire chart images of the first iris module at different object distances, measure the coordinates of the center points of each chart with the center point of the chart as a reference point, compare them with the theoretical coordinate values ​​calculated by the second iris module according to the module parameters, structure position size and different object distances, and perform error calculation in combination with object distance compensation to measure the mapping error at different object distances;

[0038] A configuration module, used to configure an optical mapping relationship between the first iris module and the second iris module;

[0039] The ranging module is used to feedback distance information when the user enters the device recognition range, trigger the infrared fill light module, and obtain the original infrared image of the entire working surface at the target distance while performing the module AE, AF and other functions;

[0040] The cropping module is used to crop the original image by algorithm and determine whether there are human eye features;

[0041] The identity recognition module is used to obtain the user's iris features, compare them with the database, and finally complete the identity recognition.

[0042] Another object of the present invention is to provide a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the iris recognition method.

[0043] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the iris recognition method.

[0044] Another object of the present invention is to provide an information data processing terminal, wherein the information data processing terminal is used to implement the iris recognition system.

[0045] In combination with the above technical solutions and the technical problems solved, the advantages and positive effects of the technical solutions to be protected by the present invention are as follows:

[0046] First, the present invention mainly solves an iris recognition method in which the iris acquisition system can satisfy a user group with a larger height range and complete identity authentication at the same time within a relatively close device use distance range (30cm-70cm), thereby starting the terminal operation. For this type of demand, the traditional solution is to design a rotating mechanism for the iris acquisition device or the device as a whole, so as to achieve close-range large-image image acquisition. The hardware design of the hinge solution is relatively complex and requires relevant technical support for the rotating mechanism, and there is a threshold for customer docking. At the same time, it also affects the recognition speed of the acquisition device and the shortened equipment life due to aging problems of the rotating mechanism after long-term use.

[0047] This invention provides an iris recognition method based on the principle of maximum image plane imaging and close-range wide-range imaging. It is mainly to meet the needs of close-range use. Without the support of a rotating mechanism, the iris acquisition system can still accurately identify the iris information of user groups of different heights. It reduces mechanical structures, increases the service life and repair rate of equipment, and reduces costs and improves production efficiency.

[0048] Compared with the existing technology, the face lens and the corresponding face algorithm have been optimized, the recognition process has been simplified, and the recognition rate has been improved; the problem of close-range and wide-range imaging without a hinge has been solved, and the difficulty of equipment repair caused by hinge jamming and other problems has been avoided; the equipment manufacturing cost and maintenance cost have been reduced, and to a certain extent, the customer satisfaction rate has been improved.

[0049] Second, the expected benefits and commercial value of the technical solution of the present invention after transformation are as follows: the rotation mechanism is optimized, the equipment cost is greatly reduced, and the usage requirements of different users can be met; at the same time, the stability of the equipment is also improved, and the customer satisfaction rate is increased.

[0050] The technical solution of the present invention provides a method and system for iris recognition at close range and with a large image surface without relying on a rotating mechanism, which solves the problem that people have always desired to simplify the system structure while expanding the range of iris recognition, while optimizing the rapid response problem of iris recognition technology and enhancing the practicality of the equipment.

[0051] Third, existing iris recognition technology faces the following problems in practical applications:

[0052] 1) Insufficient image acquisition accuracy: Due to the lack of consistent optical mapping relationship between the optical module under different object distances and environmental conditions, the collected iris image is distorted or offset, affecting the accuracy of feature extraction.

[0053] 2) Uneven lighting conditions: The infrared fill light system is not well designed and the light intensity is unevenly distributed, resulting in inconsistent image brightness and even overexposure or underexposure, which directly affects the extraction and matching of iris features.

[0054] 3) Poor adaptability to dynamic environments: Under dynamic conditions such as user movement or light changes, the existing system has difficulty in quickly adjusting focus and exposure parameters, causing iris image blur and reducing recognition accuracy.

[0055] 4) Insufficient recognition efficiency and reliability: Traditional iris recognition algorithms are easily affected by noise in highly complex environments, have a high misrecognition rate, and lack a dynamic feedback mechanism to optimize recognition performance.

[0056] Technical problems solved by the present invention:

[0057] The present invention solves the above problems through precise optical mapping relationship calibration, dynamic exposure control, optimized fill light system design and efficient iris feature extraction algorithm:

[0058] 1) Improve image acquisition accuracy: Utilize multi-module collaborative calibration to build an accurate optical mapping relationship, effectively solving the problem of iris image offset and distortion.

[0059] 2) Optimize illumination uniformity: Through infrared fill light system design and optical simulation, ensure illumination uniformity at different working distances and avoid the impact of inconsistent light intensity on feature extraction during image acquisition.

[0060] 3) Enhanced adaptability to dynamic environments: Combined with the real-time feedback and closed-loop control mechanism of the ranging module, the automatic exposure and focus functions are dynamically adjusted to ensure image quality under moving targets and complex lighting conditions.

[0061] 4) Improve recognition efficiency and reliability: Introduce deep learning optimized feature extraction and matching algorithms, combined with image data collected by multiple modules, to significantly improve the accuracy and stability of iris recognition.

[0062] Significant advancement in technical solutions:

[0063] 1) Accurate calibration and mapping: By introducing an optical error compensation mechanism and high-precision module parameter configuration, the present invention achieves consistency and high precision in iris image acquisition, providing a reliable data source for feature extraction.

[0064] 2) Lighting optimization and dynamic adaptation: The use of a simulation-optimized infrared fill light system and real-time adjustment mechanism significantly improves the interference of lighting conditions on image acquisition and improves the stability of the system in complex environments.

[0065] 3) Efficient feature extraction and comparison: Combining iris feature extraction technology with deep learning algorithms, the system recognition speed is accelerated and the misrecognition rate is significantly reduced, providing a reliable solution for industrial applications.

[0066] 4) Modular design and scalability: Through layered modular design, the iris collection and recognition system of the present invention has good scalability and can adapt to a variety of device scenarios (such as mobile phones, access control systems) to meet the needs of different industries.

[0067] The technical solution of the present invention can be widely used in the field of biometrics, including financial payment, security monitoring, access control management, and smart device unlocking. By optimizing the image acquisition and feature extraction methods, it not only improves the accuracy and efficiency of iris recognition, but also significantly enhances the system's adaptability in dynamic environments, providing industry users with a safer and more efficient biometric solution. BRIEF DESCRIPTION OF THE DRAWINGS

[0068] Figure 1 This is a flow chart of an iris recognition method provided by an embodiment of the present invention.

[0069] Figure 2 It is a structural block diagram of an iris recognition system provided by an embodiment of the present invention.

[0070] Figure 3 It is a design effect diagram of the iris acquisition system provided by an embodiment of the present invention.

[0071] Figure 4 This is a light path diagram of the imaging range of the iris acquisition unit provided in an embodiment of the present invention.

[0072] Figure 5 It is a vertical light diagram of the fill light unit provided by an embodiment of the present invention.

[0073] Figure 6 It is a horizontal light diagram of the fill light unit provided by an embodiment of the present invention.

[0074] Figure 7 It is a long-distance angle simulation design diagram of a fill light unit provided by an embodiment of the present invention.

[0075] Figure 8 It is a close-up angle design diagram of a fill light unit provided by an embodiment of the present invention.

[0076] Fig. 9 This is a flowchart of an iris recognition method according to an embodiment of the present invention.

[0077] Fig.10 This is a cropped iris image provided by an embodiment of the present invention.

[0078] Fig.11 It is a schematic diagram of the deflection design of the fill light unit provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0079] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0080] like Figure 1 , Fig. 9 As shown, an iris recognition method provided by an embodiment of the present invention includes the following steps:

[0081] S101, determining parameters of a first iris module and a second iris module through an iris acquisition system according to requirements;

[0082] S102, collecting chart images of the first iris module at different object distances, taking the center point of the chart as a reference point, measuring the coordinates of the center point of each chart, comparing them with the theoretical coordinate values ​​calculated by the second iris module according to the module parameters, structure position size and different object distances, etc., combining object distance compensation, performing error calculation, and measuring the mapping error at different object distances;

[0083] S103, configuring an optical mapping relationship between the first iris module and the second iris module;

[0084] S104, the user enters the device recognition range, the distance measurement module feeds back the distance information, triggers the infrared fill light module, and the module AE, AF and other functions while obtaining the original infrared image of the entire working surface at the target distance;

[0085] S105, the algorithm crops the original image and determines whether there are human eye features;

[0086] S106, obtaining the user's iris features, comparing them with the database, and finally completing identity recognition.

[0087] The image is collected by the first iris module and the second iris module of the iris acquisition system, and the system determines the module parameters according to the acquisition requirements. The formulas used include the calculation formulas for the horizontal field of view angle and the vertical field of view angle. The field of view angle range of the module is calculated according to the number of pixels, pixel size and lens focal length of the sensor to ensure that the image acquisition unit covers the complete area of ​​the iris. At the same time, the radiation intensity direction angle of the infrared fill light is precisely designed, and the irradiance analysis is performed through optical modeling tools to obtain the optimal direction angle of the fill light to avoid uneven lighting affecting image quality.

[0088] In the iris acquisition system, the optical mapping relationship between the first iris module and the second iris module is configured by object distance, optical focal length and installation position parameters. The center point coordinates are calculated using the chart images acquired at different object distances and compared with the theoretical calculated values ​​to calibrate the mapping error. The optical mapping relationship is corrected through the error compensation mechanism to ensure that the module can accurately capture iris images at various distances, laying the foundation for subsequent image processing.

[0089] During iris recognition, the distance measurement module provides real-time feedback on the distance between the target and the device, and the iris acquisition module dynamically adjusts the auto-exposure and auto-focus functions according to the distance. The infrared fill light combines the distance measurement information to provide fill light intensity, and dynamically adjusts the infrared light intensity and exposure time to optimize the image brightness and clarity at the target distance, avoiding the impact of image overexposure or underexposure on iris feature extraction.

[0090] When the user enters the device recognition range, the iris acquisition module starts working and acquires the original infrared image through autofocus. After the image acquisition is completed, the algorithm crops the infrared image, locates the human eye area, and further determines whether there are iris features. The size and position of the cropped image are calibrated in real time according to the geometric distribution of human eye features to ensure the accuracy of the subsequent feature extraction algorithm.

[0091] The cropped iris image is input into the feature extraction algorithm, which uses optical and digital processing methods to extract iris features. The extracted features include information such as iris texture, shape, and grayscale distribution, and are matched with iris features in the database. The feature similarity is calculated through the feature matching algorithm, and identity recognition is finally achieved. The feature extraction and comparison algorithms are optimized through deep learning, which enhances the accuracy and robustness of iris recognition.

[0092] The infrared fill light unit ensures uniform illumination in the fill light area through precise radiation intensity direction angle design. The number of fill lights and the luminous flux utilization coefficient are determined through precise calculation to meet the illumination requirements of the iris acquisition unit at the farthest working distance. Use simulation tools (such as TracePro) to analyze the light propagation path, optimize the angle, intensity and layout of the infrared light, and ensure the acquisition quality of the iris image in various environments. The infrared light maintenance factor is designed to be 0.7-0.8 to ensure the performance stability of the device in long-term use.

[0093] In step 1, according to actual needs, the key parameters of the first iris module and the second iris module are determined through the iris acquisition system. These parameters include the focal length, aperture, sensor size, and installation angle of the module. By setting the working parameters of each module in detail, a basis is provided for subsequent image acquisition and error calibration. At the same time, module-related hardware is configured, such as an infrared light board, to provide infrared light support to ensure clear iris images in different lighting environments.

[0094] In step 2, the chart image of the first iris module at different object distances is collected, and the center point of the chart is used as the reference coordinate, and the actual coordinate value of the center point is recorded by a precision measuring device. At the same time, the theoretical coordinate value is calculated based on the theoretical parameters, position and object distance relationship of the second iris module. By comparing the actual coordinates with the theoretical coordinates and combining the object distance compensation parameters, the mapping error at different object distances is calculated. These error data are used for subsequent optical mapping relationship configuration to achieve precise alignment between modules.

[0095] In step 3, the optical mapping relationship between the first iris module and the second iris module is configured according to the measured mapping error data. This configuration mainly includes projection calibration, image alignment, and position compensation of the two modules. The establishment of the mapping relationship ensures that the two modules can achieve consistency when collecting images, laying an accurate foundation for subsequent image processing and recognition.

[0096] In step 4, when the user enters the recognition range of the device, the distance measurement module feeds back the distance information between the target and the device through laser or infrared distance measurement technology. According to the distance data, the automatic exposure (AE) and auto focus (AF) functions of the infrared fill light module and the iris module are triggered to adjust the brightness and clarity of the image acquisition. At the same time, the system obtains the original infrared image of the entire working surface at the target distance to ensure that the image can achieve the best quality at different object distances.

[0097] In step 5, the algorithm crops the collected original image and extracts the part of the image containing the human eye area. The cropped image is further analyzed and the iris recognition algorithm is used to determine whether there are human eye features in the image. If human eye features are detected, the iris information in the human eye area is extracted to provide basic data for subsequent identity verification.

[0098] In step 6, the system extracts the iris features in the cropped image and compares them with the iris features stored in the database. During the comparison process, the algorithm calculates the similarity score based on the uniqueness of the iris features. If the similarity score exceeds the preset threshold, the user identity is determined to be matched successfully and the identity is identified. This process ensures high accuracy and high security of iris recognition, providing users with fast and reliable identity authentication services.

[0099] This iris recognition method achieves accurate and efficient iris recognition through precise module parameter configuration, mapping error calibration, image cropping and feature comparison technical steps, combined with infrared fill light and autofocus functions.

[0100] The iris acquisition system provided by the embodiment of the present invention includes a first iris module, a second iris module, a first infrared light board, and a second infrared light board; and performs parameter confirmation of an image acquisition unit.

[0101] According to the requirements, the embodiment of the present invention provides a method for determining the parameters of the first iris module and the second iris module through the iris acquisition system:

[0102] The calculation formula is:

[0103] HL=2×arctan(Hpixel_count*Hpixel_size / 2 / f)

[0104] VL=2×arctan(Vpixel_count*Vpixel_size / 2 / f)

[0105] Where HL is the horizontal field of view of the image acquisition unit, in degrees; VL is the vertical field of view of the image acquisition unit, in degrees; f is the focal length of the lens, in millimeters; Hpixel_count is the number of pixels in the horizontal direction of the sensor; Hpixel_size is the pixel size in the horizontal direction of the sensor, in microns; Vpixel_count is the number of pixels in the vertical direction of the sensor; Vpixel_size is the pixel size in the vertical direction of the sensor, in microns;

[0106] According to the requirements, for the fill light unit, considering the uniformity of the illumination in the working area and reducing the influence of the reflection of the radiation center on the imaging system, the design range of the angular deflection of the radiation intensity of the fill light unit is proposed, which is defined as:

[0107] in

[0108] where θ av is the deflection angle of the radiation intensity direction angle of the fill light unit; d is the horizontal distance from the center of the fill light unit to the center of the iris; L is the midpoint value within the working distance range;

[0109] Definition: the distance between the pupils of the human eye is 58mm to 65mm, and the center offset of the radiation intensity is 0mm to 15mm; limited by the half-size x of the equipment design, the value of L remains unchanged, and the value range of d is [0, x-30], unit: mm;

[0110] Then according to experience, we define, θ av -2°<θ av <θ av +5°, especially for the convenience of subsequent processing, the θ av It is recommended to take an integer;

[0111] Get the deflection angle θ av After the value range of , the tracepro simulation software is used to perform ray tracing to obtain the irradiance / illuminance analysis diagram. Under the condition of good irradiance uniformity in the working image plane, the optimal deflection angle θ is determined. av .

[0112] like Fig.11 As shown, the fill light unit provided by the embodiment of the present invention, this patent proposes a design method for the number of infrared lamp beads used in the iris acquisition system:

[0113]

[0114] Where N is the number of infrared lamps required, unit: piece; E av is the average illumination on the working surface, unit: lx; S is the area of ​​the working area, unit: m 2 ; Φ is the luminous flux of the light source, unit: lm; U is the utilization factor of the infrared lamp; K is the maintenance factor of the lamp;

[0115] The average illumination on the working surface is proposed in the original design. Based on the maximum working distance, the brightness value of the iris area needs to be greater than 60, and the average illumination of the working surface area at the maximum working distance is required to meet xxx lx;

[0116] The working area is defined as the total field of view of the iris acquisition unit at the farthest working distance;

[0117] Define the utilization factor of infrared lamp:

[0118] Among them, Φ1 is the luminous flux emitted from the light source and finally projected onto the working surface, unit: lm; Φ0 is the luminous flux of the light source, unit: lm; according to the structural design of the fill light unit and the specifications of the infrared lamp beads of the manufacturer (divergence angle, light intensity and light power, etc.), the light source file is imported, and the ray tracing is performed through the tracepro simulation software to obtain the irradiance / illuminance analysis diagram, so as to obtain the luminous flux on the working surface and calculate the utilization coefficient; the maintenance coefficient of the lamp is designed to be 0.7-0.8 based on the main use environment of the iris acquisition system, which is a relatively clean environment.

[0119] like Figure 2 As shown, an iris recognition system provided by an embodiment of the present invention includes:

[0120] A determination module, used to determine parameters of the first iris module and the second iris module according to requirements;

[0121] An acquisition module is used to acquire chart images of the first iris module at different object distances, measure the coordinates of the center points of each chart with the center point of the chart as a reference point, compare them with the theoretical coordinate values ​​calculated by the second iris module according to the module parameters, structure position size and different object distances, and perform error calculation in combination with object distance compensation to measure the mapping error at different object distances;

[0122] A configuration module, used to configure an optical mapping relationship between the first iris module and the second iris module;

[0123] The ranging module is used to feedback distance information when the user enters the device recognition range, trigger the infrared fill light module, and obtain the original infrared image of the entire working surface at the target distance while performing the module AE, AF and other functions;

[0124] The cropping module is used to crop the original image by algorithm and determine whether there are human eye features;

[0125] The identity recognition module is used to obtain the user's iris features, compare them with the database, and finally complete the identity recognition.

[0126] Another object of the present invention is to provide a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the iris recognition method.

[0127] Another object of the present invention is to provide a computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the iris recognition method.

[0128] Another object of the present invention is to provide an information data processing terminal, wherein the information data processing terminal is used to implement the iris recognition system.

[0129] The present invention is specifically implemented:

[0130] This application selects the module for the OV12895 sensor. The sensor parameters are as follows: pixel size 4096 (H) * 3072 (V), pixel size 1.55μm; lens parameters: focal length 15mm, field of view 32° (H) * 23° (V), lens resolution greater than 5MP; the fill light wavelength is 810m ~ 850nm, divergence angle 35° ~ 45°, and optical power greater than 800mW.

[0131] Use range requirements, 30cm-70cm away from the device

[0132] According to the simulation calculation of the module's field of view angle and the use distance, it can be used within the range of 45cm to 55cm in height (such as Figure 4 ).

[0133] Simulate the vertical direction of the large image plane at close range (such as Figure 5 ) and horizontal direction (such as Figure 6 ), uniform fill light, to obtain uniform grayscale iris image requirements, this application uses a 30° divergence angle infrared lamp, the first infrared lamp module is deflected 8° downward, the second infrared lamp module is deflected 8° upward, the left and right range, the first infrared fill light module and the second infrared fill light module cover the field of view of the iris lens, no change can meet the requirements (such as Figure 7 , 8 ).

[0134] In this application, it is proposed that the maximum average illumination of the image plane must meet 20000lx, and the brightness of the iris area meets the requirements. The number of lamp beads is calculated to be 12, and the layout design of the fill light unit is based on this number. (For example Figure 3 )

[0135] The chart images of the first iris module at different object distances are collected, and the coordinates of the center point of each chart are measured with the center point of the chart as the reference point. The coordinates are compared with the theoretical coordinate values ​​calculated by the second iris module based on module parameters, structural position and size, and different object distances. Combined with object distance compensation, error calculation is performed to measure the mapping error at different object distances.

[0136] configuring an optical mapping relationship between the first iris module and the second iris module;

[0137] When the user enters the device recognition range, the ranging module feeds back the distance information, triggering the infrared fill light module, as well as the module AE, AF and other functions, while obtaining the original infrared image of the entire working surface at the target distance;

[0138] The algorithm crops the original image and determines whether there are human eye features; (such as Fig.10 )

[0139] The user's iris features are obtained, compared with the database, and identity recognition is finally completed.

[0140] The present invention is applied in the field of biometric identification technology and is a method for realizing iris recognition technology in a short distance and wide range.

[0141] Table 1 shows the number of sensor pixels, sensor pixel size, lens focal length and positional relationship of the first iris module and the second iris module of the system. The collected pixel value of the first iris module is compared with the theoretical calculated value to obtain the mapping error.

[0142] Figure 4 Taking a person as a reference, the imaging optical path diagram of the height acquisition module is represented. Combined with the field of view information of the iris module and the required imaging image plane size, the imaging optical path is traced to determine the structural layout of the acquisition module.

[0143] Figure 5 Taking a person as a reference, the fill light optical path diagram of the height acquisition module is shown. Combined with the required imaging surface size and brightness requirements, the divergence angle of the infrared light emitted in the height direction that can meet the fill light of the full-frame imaging surface is designed to determine the illumination requirements of the infrared light;

[0144] Figure 6Taking a person as a reference, the fill light optical path diagram of the height acquisition module is shown. Combined with the required imaging surface size and brightness requirements, the divergence angle of the infrared light emitted in the height direction that can meet the fill light of the full-frame imaging surface is designed to determine the illumination requirements of the infrared light;

[0145] Figure 7 , Figure 8 Taking a person as a reference, the fill light illumination effect diagram of the height direction acquisition module is shown. Combined with the required imaging surface size and brightness requirements, the spatial structure layout and quantity of infrared lamps that can meet the full-frame imaging surface illumination requirements are designed.

[0146] Table 1

[0147]

[0148] It should be noted that the embodiments of the present invention can be implemented by hardware, software, or a combination of software and hardware. The hardware part can be implemented using dedicated logic; the software part can be stored in a memory and executed by an appropriate instruction execution system, such as a microprocessor or dedicated design hardware. It can be understood by a person of ordinary skill in the art that the above-mentioned devices and methods can be implemented using computer executable instructions and / or contained in a processor control code, such as a carrier medium such as a disk, CD or DVD-ROM, a programmable memory such as a read-only memory (firmware), or a data carrier such as an optical or electronic signal carrier. Such code is provided on the carrier medium. The device and its modules of the present invention can be implemented by hardware circuits such as very large-scale integrated circuits or gate arrays, semiconductors such as logic chips, transistors, etc., or programmable hardware devices such as field programmable gate arrays, programmable logic devices, etc., can also be implemented by software executed by various types of processors, and can also be implemented by a combination of the above-mentioned hardware circuits and software, such as firmware.

[0149] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any modifications, equivalent substitutions and improvements made by any technician familiar with the technical field within the technical scope disclosed by the present invention and within the spirit and principle of the present invention should be covered by the protection scope of the present invention.

Claims

1. An iris recognition method, characterized in that: The iris recognition method comprises the following steps: Step 1: Determine the parameters of the first iris module and the second iris module through the iris acquisition system according to the requirements; Step 2, collecting chart images of the first iris module at different object distances, taking the center point of the chart as the reference point, measuring the coordinates of the center point of each chart, and comparing them with the theoretical coordinate values ​​calculated by the second iris module according to the module parameters, structure position size and different object distances, and calculating the mapping error in combination with object distance compensation; Step 3, configuring an optical mapping relationship between the first iris module and the second iris module according to the mapping error; Step 4: The user enters the device recognition range, the ranging module feeds back the distance information, triggers the infrared fill light module, and the module's automatic exposure (AE) and automatic focus (AF) functions, and collects the original infrared image at the target distance; Step 5, the algorithm crops the original infrared image to determine whether there are human eye features; Step 6: extract iris features and compare them with iris features in the database to complete identity recognition.

2. The iris recognition method according to claim 1, characterized in that: The iris acquisition system comprises: The first iris module and the second iris module are respectively used for collecting iris images; The first infrared light board and the second infrared light board are used to provide infrared fill light; The distance measurement module is used to measure the distance between the target and the device.

3. The iris recognition method according to claim 1, characterized in that: The optical mapping relationship is configured by the following parameters: The object distance, optical focal length and installation position of the first iris module and the second iris module; The mapping error data is used to correct the optical projection deviation between the first iris module and the second iris module.

4. The iris recognition method according to claim 1, characterized in that: The automatic exposure (AE) and automatic focus (AF) functions are adjusted in real time according to the distance information fed back by the ranging module, and combined with infrared light intensity compensation, to ensure the clarity and brightness of the infrared image at the target distance.

5. The iris recognition method according to claim 1, characterized in that: According to the requirements, the parameters of the first iris module and the second iris module are determined by the iris acquisition system: The calculation formula is: HL=2×arctan(Hpixel_count*Hpixel_size / 2 / f) VL=2×arctan(Vpixel_count*Vpixel_size / 2 / f) Where HL is the horizontal field of view of the image acquisition unit, in degrees; VL is the vertical field of view of the image acquisition unit, in degrees; f is the focal length of the lens, in millimeters; Hpixel_count is the number of pixels in the horizontal direction of the sensor; Hpixel_size is the pixel size in the horizontal direction of the sensor, in microns; Vpixel_count is the number of pixels in the vertical direction of the sensor; Vpixel_size is the pixel size in the vertical direction of the sensor, in microns; According to the requirements, for the fill light unit, the design range of the angular deflection of the radiation intensity of the fill light unit is proposed, which is defined as: in where θ av is the deflection angle of the radiation intensity direction angle of the fill light unit; d is the horizontal distance from the center of the fill light unit to the center of the iris; L is the midpoint value within the working distance range; Definition: the distance between the pupils of the human eye is 58mm to 65mm, and the center offset of the radiation intensity is 0mm to 15mm; limited by the half-size x of the equipment design, the value of L remains unchanged, and the value range of d is [0, x-30], unit: mm; Then according to experience, we define, θ av -2°<θ av <θ av +5°, θ av It is recommended to take an integer; Get the deflection angle θ av After the value range of , the tracepro simulation software is used to perform ray tracing to obtain the irradiance / illuminance analysis diagram. Under the condition of good irradiance uniformity in the working image plane, the optimal deflection angle θ is determined. av .

6. The iris recognition method according to claim 5, characterized in that: The fill light unit, this patent proposes a design method for the number of infrared lamp beads used in the iris acquisition system: Where N is the number of infrared lights required, unit: piece; E av is the average illuminance on the working surface, unit: lx; S is the working area, unit: m 2 ; Φ is the luminous flux of the light source, unit: lm; U is the utilization factor of the infrared lamp; K is the maintenance factor of the lamp; The average illumination on the working surface is proposed in the original design. Based on the maximum working distance, the brightness value of the iris area needs to be greater than 60, and the average illumination of the working surface area at the maximum working distance is required to meet xxx lx; The working area is defined as the total field of view of the iris acquisition unit at the farthest working distance; Define the utilization factor of infrared lamp: Among them, Φ1 is the luminous flux emitted from the light source and finally projected onto the working surface, unit: lm; Φ0 is the luminous flux of the light source, unit: lm; according to the structural design of the fill light unit and the specifications of the infrared lamp beads (divergence angle, light intensity and light power) of the manufacturer, the light source file is imported, and the ray tracing is performed through the tracepro simulation software to obtain the irradiance / illuminance analysis diagram, thereby obtaining the luminous flux on the working surface and calculating the utilization coefficient; The maintenance factor of the lamp is designed to be 0.7-0.8 based on the fact that the main use environment of the iris acquisition system is a relatively clean environment.

7. An iris recognition system implementing the iris recognition method according to any one of claims 1 to 6, characterized in that: The iris recognition system comprises: A determination module, used to determine parameters of the first iris module and the second iris module according to requirements; An acquisition module is used to acquire chart images of the first iris module at different object distances, measure the coordinates of the center points of each chart with the center point of the chart as a reference point, compare them with the theoretical coordinate values ​​calculated by the second iris module according to the module parameters, structure position size and different object distances, and perform error calculation in combination with object distance compensation to measure the mapping error at different object distances; A configuration module, used to configure an optical mapping relationship between the first iris module and the second iris module; The ranging module is used to feedback distance information when the user enters the device recognition range, trigger the infrared fill light module, and obtain the original infrared image of the entire working surface at the target distance while performing the module AE, AF and other functions; The cropping module is used to crop the original image by algorithm and determine whether there are human eye features; The identity recognition module is used to obtain the user's iris features, compare them with the database, and finally complete the identity recognition.

8. A computer device, characterized in that: The computer device comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the iris recognition method according to any one of claims 1 to 6.

9. A computer-readable storage medium storing a computer program, wherein when the computer program is executed by a processor, the processor executes the steps of the iris recognition method according to any one of claims 1 to 6.

10. An information data processing terminal, characterized in that: The information data processing terminal is used to implement the iris recognition system as claimed in claim 7.

Images