Iris recognition method and system based on least square

Abstract

The invention discloses an iris recognition method and system based on least square. The method comprises the steps of determining an iris image range, selecting effective images and removing irrelevant images according to imaging ranges of eyes and irises; segmenting the pupil image, and extracting the center and radius of the pupil; obtaining artificial pupil change information, forming an artificial pupil change evaluation index by using the artificial pupil change information, and determining an accurate image range of the iris by taking the pupil geometric information as heuristic information; extracting an outer edge of the iris image, and extracting a circle from the outer edge by using a least square method to obtain a circle center and a radius; performing concentric transformation on the iris image by using center translation, and changing the centers of the pupil and the iris to the same point; if a correlation coefficient value is larger than a threshold value, matching succeeds, otherwise, matching fails, and images which will be processed at different angles due to shielding and the like are removed. According to the method, multiple types of irises of the human body are rapidly judged and recognized, level evaluation can be carried out, and the iris recognition accuracy is high.

Description

Technical Field

[0001] The invention belongs to the field of iris recognition, and in particular relates to an iris recognition method and system based on least squares. Background Art

[0002] Due to the objective needs of the times, biometric technology has gradually been widely used in various fields. Compared with other biometric technologies, iris recognition has obvious advantages and characteristics: non-contact: optical collection of iris images avoids possible contact transmission of diseases; high reliability: fingerprint and facial recognition are easy to modify, and the iris is inside the eye and is basically impossible to be modified or forged; stability: the iris does not change significantly for a long time.

[0003] Since the 1990s, with the advancement of electronic and information technology, various iris recognition algorithms and systems have emerged at home and abroad. However, the iris recognition system is a complex electronic system, facing the problems of difficulty in collecting high-quality images, low image quality, complex image processing algorithms, difficulty in fast database search, and universality of algorithms for different races. It is a very challenging task to develop a mature and complete iris recognition system. Through the efforts of different scholars, the various subsystems and algorithms of iris recognition are still being improved. Summary of the invention

[0004] The purpose of the embodiments of the present invention is to provide an iris recognition method and system based on least squares, aiming to solve the problems raised in the background technology.

[0005] To achieve the above objectives, the embodiments of the present invention provide the following technical solutions:

[0006] A least squares-based iris recognition method and system, the method specifically comprising the following steps:

[0007] S1. Obtaining eyeball posture information of a human body, using the eyeball posture information to form an eyeball posture assessment index, determining the iris image range according to the imaging range of the eye and iris, selecting a valid image, and removing irrelevant images;

[0008] S2, obtaining pupil change factor information under different light and dark environments, using the pupil change factor information to form pupil change factor evaluation indicators, segmenting the pupil image, and extracting the center and radius of the pupil;

[0009] S3, obtaining artificial pupil change information, using the artificial pupil change information to form an artificial pupil change assessment index, and using pupil geometry information as inspiration information to determine an accurate image range of the iris;

[0010] S4, obtaining vision information of people of different ages and genders, using the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders, extracting the outer edge of the iris image, extracting a circle from the outer edge using the least squares method, and obtaining the center and radius of the circle;

[0011] S5, grading the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders by iris index, forming eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and vision iris integrity of people of different ages and genders, and performing concentric transformation on the iris image by center translation to change the pupil and iris center to the same point;

[0012] S6. Use the rectangular expansion method to expand the circular iris image into a rectangle, match the rectangular iris image with the image stored in the database, and calculate the correlation coefficient value. If it is greater than the threshold, the match is successful, otherwise the match fails. Eliminate images at different angles due to occlusion and other reasons to improve the matching accuracy.

[0013] As a further limitation of the technical solution of the embodiment of the present invention, the step of obtaining the eye posture information of the human body and forming the eye posture assessment index using the eye posture information specifically includes the following steps:

[0014] Obtain the eye posture information of the human body;

[0015] Using the eyeball posture information, forming historical eyeball posture information and real-time eyeball posture information;

[0016] Using the historical eyeball posture information, forming average eyeball posture information;

[0017] The average eyeball posture information and the real-time eyeball posture information are used to form an eyeball posture assessment index.

[0018] As a further limitation of the technical solution of the embodiment of the present invention, the obtaining of pupil change factor information under different light and dark environments and forming pupil change factor evaluation indicators using the pupil change factor information specifically include the following steps:

[0019] Obtain information on pupil change factors under different light and dark environments;

[0020] Using the pupil change factor information, obtaining real-time pupil change factor information under different light and dark environments;

[0021] The real-time pupil change factor information under the different light and dark environments is analyzed to form pupil change factor evaluation indicators.

[0022] As a further limitation of the technical solution of the embodiment of the present invention, the obtaining of the artificial pupil change information and forming the artificial pupil change assessment index using the artificial pupil change information specifically includes the following steps:

[0023] Obtaining information about artificial pupil changes;

[0024] Using the artificial pupil change information, predicting the source of the artificial pupil change and the propagation path of the artificial pupil change;

[0025] The artificial pupil change source and the artificial pupil change propagation path are used to form an artificial pupil change evaluation index.

[0026] As a further limitation of the technical solution of the embodiment of the present invention, the step of obtaining vision information of people of different ages and genders and using the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders specifically includes the following steps:

[0027] Obtain vision information for people of different ages and genders;

[0028] Using the vision information of people of different ages and genders to form vision interpretation information of people of different ages and genders;

[0029] Using the vision interpretation information of people of different ages and genders to make normative predictions of the human body, and form normative prediction information;

[0030] The normative prediction information is used to form vision assessment indicators for people of different ages and genders.

[0031] As a further limitation of the technical solution of the embodiment of the present invention, the grading of the eyeball posture assessment index, the pupil change factor assessment index, the artificial pupil change assessment index and the vision assessment index of people of different ages and genders to form the eyeball posture iris integrity, the pupil change factor iris integrity, the artificial pupil change range and the vision iris integrity of people of different ages and genders specifically includes the following steps:

[0032] Grading the iris indexes of the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders to form an iris assessment conclusion;

[0033] The iris assessment conclusion is used to form the iris integrity of eyeball posture, the iris integrity of pupil change factors, the range of artificial pupil changes and the iris integrity of vision of people of different ages and genders.

[0034] As a further limitation of the technical solution of the embodiment of the present invention, the grading of the eyeball posture assessment index, the pupil change factor assessment index, the artificial pupil change assessment index and the vision assessment index of people of different ages and genders to form the eyeball posture iris integrity, the pupil change factor iris integrity, the artificial pupil change range and the vision iris integrity of people of different ages and genders also includes the following steps:

[0035] Multiple types of iris integrity are formed by using the eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and vision iris integrity of people of different ages and genders.

[0036] An iris recognition system based on least squares, the system comprising:

[0037] An eyeball information acquisition module, which obtains eyeball posture information of a human body, uses the eyeball posture information to form an eyeball posture assessment index, determines the iris image range according to the imaging range of the eye and iris, selects valid images, and removes irrelevant images;

[0038] An information feature extraction module, which obtains pupil change factor information under different light and dark environments, uses the pupil change factor information to form pupil change factor evaluation indicators, segments the pupil image, and extracts the center and radius of the pupil;

[0039] An iris image range module, which obtains information about artificial pupil changes, uses the information about artificial pupil changes to form an artificial pupil change assessment index, and uses pupil geometry information as inspiration information to determine an accurate image range of the iris;

[0040] A least squares calculation module, which obtains vision information of people of different ages and genders, uses the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders, extracts the outer edge of the iris image, extracts a circle from the outer edge using the least squares method, and obtains the center and radius of the circle;

[0041] An iris image concentric transformation module, which performs iris index grading on the eyeball posture evaluation index, pupil change factor evaluation index, artificial pupil change evaluation index and vision evaluation index of people of different ages and genders, forms iris integrity of eyeball posture, iris integrity of pupil change factor, artificial pupil change range and vision iris integrity of people of different ages and genders, and uses center translation to perform concentric transformation on the iris image, so as to change the pupil and iris centers to the same point;

[0042] Rectangular expansion method calculation module, this module uses the rectangular expansion method to expand the circular iris image into a rectangle, matches the rectangular iris image with the image stored in the database, and calculates the correlation coefficient value. If it is greater than the threshold, the match is successful, otherwise the match fails. The image at different angles due to occlusion and other reasons is eliminated to improve the matching accuracy.

[0043] As a further limitation of the technical solution of the embodiment of the present invention, the iris image concentric transformation module specifically includes:

[0044] An iris assessment conclusion forming unit is used to grade the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders to form an iris assessment conclusion;

[0045] The iris integrity forming unit is used to use the iris assessment conclusion to form the iris integrity of eyeball posture, the iris integrity of pupil change factors, the range of artificial pupil change and the iris integrity of vision of people of different ages and genders.

[0046] As a further limitation of the technical solution of the embodiment of the present invention, the iris image concentric transformation module further includes:

[0047] The iris integrity summary unit is used to use the iris assessment conclusion to form the iris integrity of eyeball posture, the iris integrity of pupil change factors, the range of artificial pupil changes and the iris integrity of vision of people of different ages and genders, forming multiple types of iris integrity.

[0048] Use algorithms to calculate different irises;

[0049] Establish the iris factor matrix, the expression is:

[0050]

[0051] Among them, A represents the collection of iris factors, x nm represents the mth iris factor of the nth person;

[0052] According to the initial data matrix A, the similarity between each iris index is calculated, and the expression is:

[0053]

[0054] Among them, c represents the clustering parameter, r ij represents the similarity matrix, k represents the kth iteration, m represents the total number of iterations required, i and j represent different irises, x ik and x jk The damage caused by different irises;

[0055] The iris index information is standardized using the translation range change strategy, and the expression is:

[0056]

[0057] Among them, x ij represents the importance score of the jth iris indicator of the i-th classification target, x′ ij Indicates the update of the iris indicator importance score;

[0058] The mathematical formula for establishing iris index evaluation is expressed as:

[0059]

[0060] Among them, E C represents the multi-class iris evaluation index, ω i represents the weight, f i (P1, P2, ..., P o ) is the influence value function of the i-th iris factor.

[0061] Compared with the prior art, the present invention has the following beneficial effects:

[0062] The present invention obtains eyeball posture information of a human body and forms an eyeball posture assessment index using the eyeball posture information; obtains pupil change factor information under different light and dark environments and forms a pupil change factor assessment index using the pupil change factor information; obtains artificial pupil change information and forms an artificial pupil change assessment index using the artificial pupil change information; obtains vision information of people of different ages and genders and forms vision assessment indexes of people of different ages and genders using the vision information of people of different ages and genders; uses the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders to form eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and vision iris integrity of people of different ages and genders. It can use the human eye posture information, pupil change factor information, artificial pupil change information and vision information of people of different ages and genders to quickly judge and identify multiple types of human irises, and can grade the eye posture iris, pupil change factor iris, artificial pupil change and vision iris of people of different ages and genders, respectively, and the iris recognition is highly accurate. The present invention fully considers the non-ideal situation of iris image acquisition and designs a recognition algorithm for non-ideal iris images. It has the advantages of strong anti-noise ability and high recognition accuracy. The present invention takes into account the situation where the pupil and iris centers are inconsistent, and the algorithm can adapt to more people and races and has stronger universality. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 A flow chart showing the method of the present invention is shown;

[0064] Figure 2 A schematic diagram of the module composition of the system of the present invention is shown. DETAILED DESCRIPTION

[0065] 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 accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention.

[0066] It is understandable that in the prior art, iris recognition is mostly performed using the experience of human workers. This type of multi-type iris recognition is usually not able to accurately identify the iris, and iris recognition is slow, which affects the development of the human body.

[0067] To solve the above problems, the embodiments of the present invention obtain eyeball posture information of a human body, and use the eyeball posture information to form an eyeball posture assessment index; obtain pupil change factor information under different light and dark environments, and use the pupil change factor information to form a pupil change factor assessment index; obtain artificial pupil change information, and use the artificial pupil change information to form an artificial pupil change assessment index; obtain vision information of people of different ages and genders, and use the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders; use the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment indicators of people of different ages and genders to form eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and vision iris integrity for people of different ages and genders. It can use the human eye posture information, pupil change factor information, artificial pupil change information and vision information of people of different ages and genders to quickly judge and identify multiple types of human irises, and can assess the level of eye posture irises, pupil change factor irises, artificial pupil changes and vision irises of people of different ages and genders respectively, so that iris recognition is accurate.

[0068] Figure 1 A flow chart of a method provided by an embodiment of the present invention is shown.

[0069] Specifically, a least squares-based iris recognition method and system, the method specifically comprises the following steps:

[0070] S1. Obtaining eyeball posture information of a human body, using the eyeball posture information to form an eyeball posture assessment index, determining the iris image range according to the imaging range of the eye and iris, selecting a valid image, and removing irrelevant images;

[0071] Eye posture information acquisition: Use sensors (such as cameras or eye tracking devices) to collect the spatial position and rotation posture information of the eye.

[0072] Posture information includes the rotation angle of the eyeball in three-dimensional space (horizontal angle, vertical angle and torsion angle), which is used to analyze the line of sight direction of the eyeball.

[0073] Forming evaluation indicators: Based on the collected posture information, define an evaluation standard to evaluate whether the eyeball is in a standard detectable position.

[0074] Determine the range of the iris image: Based on the position of the eyeball and the direction of sight, determine the visible range of the iris in the captured image, eliminate irrelevant areas in the image (such as eyelids, corneal reflections, etc.), and select a clear and complete iris image.

[0075] Irrelevant image removal: Remove invalid images caused by line of sight deviation, abnormal eye posture or other interference to ensure that subsequent processing is only for valid images.

[0076] In the embodiment of the present invention, the average eyeball posture information is compared with the real-time eyeball posture information, and the comparison conclusion is used to analyze and evaluate the current eyeball posture status of the human body to form an eyeball posture evaluation index.

[0077] Furthermore, the method further comprises the following steps:

[0078] S2, obtaining pupil change factor information under different light and dark environments, using the pupil change factor information to form pupil change factor evaluation indicators, segmenting the pupil image, and extracting the center and radius of the pupil;

[0079] Pupil change information acquisition: In different light and dark environments, pupil image data is collected to record the changes in pupil size and shape when the light intensity changes. Light and dark environment simulation can be achieved by controlling the brightness of the light source (such as LED light) or infrared light.

[0080] Forming evaluation indicators: Based on the lighting environment and the pupil's reaction speed and range of change, an evaluation standard is established to analyze the pupil's dynamic response ability.

[0081] Image segmentation: Segment the collected pupil image and extract the pupil area using image processing algorithms (such as threshold segmentation and edge detection).

[0082] Pupil center and radius extraction: Based on the segmentation results, geometric methods (such as circle fitting or Hough transform) are used to extract the center coordinates and radius of the pupil to provide a reference for subsequent iris position analysis.

[0083] The principle of least squares method to extract circles is as follows:

[0084] Let the equation of the circle be

[0085] (x) 2+(yb) 2 =r 2

[0086] (x i ,y i )(i=1,…,n) is the point on the edge of the pupil. According to the principle of least squares method, the center and radius of the circle are:

[0087]

[0088] S3, obtaining artificial pupil change information, using the artificial pupil change information to form an artificial pupil change assessment index, and using pupil geometry information as inspiration information to determine an accurate image range of the iris;

[0089] In the embodiment of the present invention, the historical data of the human body are screened to obtain the information of the artificial pupil change in the data, and the artificial pupil change information is analyzed and evaluated to form an artificial pupil change evaluation index.

[0090] It is understandable that the information of artificial pupil changes can reflect the channels of artificial pupil changes and the propagation pathways of artificial pupil changes, and can reflect the ability of the human body to resist iris changes. Therefore, artificial pupil changes are closely related to the various types of irises of the human body.

[0091] Acquisition of artificial pupil change information: simulate external stimuli (such as sudden changes in light intensity or flickering light sources) to induce pupil changes, and collect pupil change information under these conditions. Record the geometric shape, size, and reaction time of the pupil under these external conditions.

[0092] Formation of evaluation indicators: Analyze the dynamic change characteristics of the pupil under these artificial stimuli, and establish evaluation indicators to evaluate the sensitivity and integrity of the pupil under external stimuli.

[0093] Iris image range determination: Based on the geometric information of the pupil (such as center, radius) as the reference point, the accurate range of the iris area is derived, excluding invalid areas that may overlap or block the pupil.

[0094] Furthermore, the method further comprises the following steps:

[0095] S4, obtaining vision information of people of different ages and genders, using the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders, extracting the outer edge of the iris image, extracting a circle from the outer edge using the least squares method, and obtaining the center and radius of the circle;

[0096] In an embodiment of the present invention, vision information of people of different ages and genders is obtained through a website, changes in vision information of people of different ages and genders related to human production and management are analyzed, and vision information of people of different ages and genders is analyzed and evaluated to form vision evaluation indicators for people of different ages and genders.

[0097] It is understandable that the human body will be affected by factors such as the laws of various countries during driving, which will affect the vision of people of different ages and genders. If the vision of people of different ages and genders changes, the human iris will be directly enlarged. Therefore, the changes in vision of people of different ages and genders are closely related to the multiple types of irises in the human body.

[0098] Acquisition of vision information: Collect vision data of different age groups and genders (such as hyperopia, myopia, astigmatism, amblyopia, etc.), and associate it with the health status of the iris.

[0099] Forming evaluation indicators: Use these group data to establish an evaluation model to analyze the relationship between the health status of the iris and the characteristics of different ages and genders.

[0100] Iris outer edge extraction: Use image processing algorithms (such as edge detection or contour extraction) to extract the outer edge of the iris.

[0101] Least squares method to fit the circle: Use the least squares method to fit the edge of the iris into a circle, accurately determine the center coordinates and radius of the iris, and provide data support for subsequent image analysis and matching.

[0102] Furthermore, the method further comprises the following steps:

[0103] S5. Perform iris index grading on the eye posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders to form iris integrity of eye posture, iris integrity of pupil change factor, artificial pupil change range and vision iris integrity of people of different ages and genders, use center translation to perform concentric transformation on the iris image, and change the center of the pupil and iris to the same point.

[0104] In an embodiment of the present invention, by comprehensively analyzing and evaluating the eye posture assessment index, the pupil change factor assessment index, the artificial pupil change assessment index and the vision assessment index of people of different ages and genders, the eye posture, pupil change factors, artificial pupil changes and the iris conditions of the vision of people of different ages and genders are judged, and the iris integrity of the eye posture, the iris integrity of the pupil change factors, the artificial pupil change range and the iris integrity of the vision of people of different ages and genders are formed, so that the staff can identify the iris by comparing the iris integrity of the eye posture, the iris integrity of the pupil change factors, the artificial pupil change range and the iris integrity of the vision of people of different ages and genders, and can intuitively understand the degree of the iris in various aspects.

[0105] Iris index grading: Combine the evaluation indicators of the previous steps, including eye posture, pupil changes, iris edge and visual acuity information, to quantitatively evaluate the health status and function of the iris.

[0106] Generate multiple iris integrity indicators to describe the health of the iris in different aspects.

[0107] Center translation and concentric transformation: If the center points of the pupil and iris do not completely coincide, perform a translation operation to align the centers of the two to the same point. Concentric transformation can avoid deviation and make subsequent analysis more accurate.

[0108] S6. Use the rectangular expansion method to expand the circular iris image into a rectangle, match the rectangular iris image with the image stored in the database, and calculate the correlation coefficient value. If it is greater than the threshold, the match is successful, otherwise the match fails. Eliminate images at different angles due to occlusion and other reasons to improve the matching accuracy.

[0109] Rectangular expansion method: Expand the circular iris area into a rectangular image according to the angle. This form is more suitable for comparison with the standard iris image in the database. Polar coordinate transformation is usually used to complete this operation.

[0110] Iris matching: Use the unfolded rectangular iris image to match the standard iris template saved in the database.

[0111] The iris match is determined by calculating the correlation coefficient or similarity measure of the images.

[0112] Eliminate invalid images: If the match fails (the correlation coefficient is lower than the set threshold), analyze the reasons for the failure (such as occlusion or angle problems) and eliminate these invalid images to improve the matching accuracy. For valid images, the matching algorithm can be further optimized to improve the accuracy of the final recognition.

[0113] The calculation of the correlation coefficient is as follows. Suppose X and Y are two images, and their correlation coefficient is

[0114]

[0115] x i and i are the i-th pixel values ​​in the X and Y images respectively, and are the average values ​​of pixels in the two images respectively. N is the total number of pixels. The range of the correlation coefficient ρ is [-1,1]. The larger the |ρ| is, the more correlated the two images are.

[0116] In an embodiment of the present invention, multiple categories of iris integrity are formed by comprehensively analyzing the iris integrity of eye posture, the iris integrity of pupil change factors, the range of human pupil changes, and the iris integrity of vision of people of different ages and genders, wherein the multiple categories of iris integrity reflect the multiple categories of iris degrees of the human body as a whole.

[0117] Furthermore, Figure 2 The application architecture diagram of the system provided by the embodiment of the present invention is shown.

[0118] Specifically, in another preferred embodiment of the present invention, a least squares-based iris recognition system comprises:

[0119] An eyeball information acquisition module, which obtains eyeball posture information of a human body, uses the eyeball posture information to form an eyeball posture assessment index, determines the iris image range according to the imaging range of the eye and iris, selects valid images, and removes irrelevant images;

[0120] An information feature extraction module, which obtains pupil change factor information under different light and dark environments, uses the pupil change factor information to form pupil change factor evaluation indicators, segments the pupil image, and extracts the center and radius of the pupil;

[0121] An iris image range module, which obtains information about artificial pupil changes, uses the information about artificial pupil changes to form an artificial pupil change assessment index, and uses pupil geometry information as inspiration information to determine an accurate image range of the iris;

[0122] A least squares calculation module, which obtains vision information of people of different ages and genders, uses the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders, extracts the outer edge of the iris image, extracts a circle from the outer edge using the least squares method, and obtains the center and radius of the circle;

[0123] An iris image concentric transformation module, which performs iris index grading on the eyeball posture evaluation index, pupil change factor evaluation index, artificial pupil change evaluation index and vision evaluation index of people of different ages and genders, forms iris integrity of eyeball posture, iris integrity of pupil change factor, artificial pupil change range and vision iris integrity of people of different ages and genders, and uses center translation to perform concentric transformation on the iris image, so as to change the pupil and iris centers to the same point;

[0124] Rectangular expansion method calculation module, this module uses the rectangular expansion method to expand the circular iris image into a rectangle, matches the rectangular iris image with the image stored in the database, and calculates the correlation coefficient value. If it is greater than the threshold, the match is successful, otherwise the match fails. The image at different angles due to occlusion and other reasons is eliminated to improve the matching accuracy.

[0125] Among them, in the preferred embodiment provided by the present invention, the iris image concentric transformation module specifically includes:

[0126] The iris assessment conclusion forming unit is used to grade the iris indexes of the eyeball posture assessment index, the pupil change factor assessment index, the artificial pupil change assessment index and the vision assessment index of people of different ages and genders to form an iris assessment conclusion.

[0127] In an embodiment of the present invention, the iris assessment conclusion forming unit grades the iris comprehensive index by the eyeball posture assessment index, the pupil change factor assessment index, the artificial pupil change assessment index and the vision assessment index of people of different ages and genders, and forms the iris assessment conclusion by utilizing the mutual influence of the eyeball posture, the pupil change factor, the artificial pupil change and the vision of people of different ages and genders on the iris.

[0128] The iris integrity forming unit is used to use the iris assessment conclusion to form the iris integrity of eyeball posture, the iris integrity of pupil change factors, the range of artificial pupil change and the iris integrity of vision of people of different ages and genders.

[0129] In the embodiment of the present invention, the iris integrity forming unit uses the iris assessment conclusion to respectively grade the eyeball posture iris, pupil change factor iris, artificial pupil change and the iris of vision of people of different ages and genders, and forms the eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and the iris integrity of vision of people of different ages and genders, so that the staff can identify the iris by comparing the eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and the iris integrity of vision of people of different ages and genders, and can intuitively understand the degree of the iris in various aspects.

[0130] Among them, in the preferred embodiment provided by the present invention, the iris image concentric transformation module further includes:

[0131] The iris integrity summary unit is used to use the iris assessment conclusion to form the iris integrity of eyeball posture, the iris integrity of pupil change factors, the range of artificial pupil changes and the iris integrity of vision of people of different ages and genders, forming multiple types of iris integrity.

[0132] In an embodiment of the present invention, the iris integrity summary unit forms multiple categories of iris integrity by comprehensively analyzing the iris integrity of eyeball posture, the iris integrity of pupil change factors, the range of human pupil changes, and the iris integrity of vision of people of different ages and genders, wherein the multiple categories of iris integrity reflect the multiple categories of iris degrees of the human body as a whole.

[0133] Use algorithms to calculate different irises;

[0134] Establish the iris factor matrix, the expression is:

[0135]

[0136] Among them, A represents the collection of iris factors, x nm represents the mth iris factor of the nth person;

[0137] According to the initial data matrix A, the similarity between each iris index is calculated, and the expression is:

[0138]

[0139] Among them, c represents the clustering parameter, r ij represents the similarity matrix, k represents the kth iteration, m represents the total number of iterations required, i and j represent different irises, x ik and x jk The damage caused by different irises;

[0140] The iris index information is standardized using the translation range change strategy, and the expression is:

[0141]

[0142] Among them, x ij represents the importance score of the jth iris indicator of the i-th classification target, x′ ij Indicates the update of the iris indicator importance score;

[0143] The mathematical formula for establishing iris index evaluation is expressed as:

[0144]

[0145] Among them, EC represents the multi-class iris evaluation index, ω i represents the weight, f i (P1, P2, ..., P o ) is the influence value function of the i-th iris factor.

[0146] In summary, the embodiments of the present invention obtain eyeball posture information of a human body and use the eyeball posture information to form an eyeball posture assessment index; obtain pupil change factor information under different light and dark environments and use the pupil change factor information to form a pupil change factor assessment index; obtain artificial pupil change information and use the artificial pupil change information to form an artificial pupil change assessment index; obtain vision information of people of different ages and genders and use the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders; use the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment indicators of people of different ages and genders to form eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and vision iris integrity for people of different ages and genders. It can use the human eye posture information, pupil change factor information, artificial pupil change information, vision information and algorithms of people of different ages and genders to quickly judge and identify multiple types of human irises, and can assess the level of eye posture irises, pupil change factor irises, artificial pupil changes and vision irises of people of different ages and genders respectively, so that iris recognition is accurate.

[0147] In the description of the present invention, it should be noted that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", "connect", and "fix" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood by specific circumstances.

[0148] Although embodiments of the present invention have been shown and described, it will be understood by those skilled in the art that various equivalent changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A least squares based iris recognition method, characterized in that: The method specifically comprises the following steps: S1. Obtaining eyeball posture information of a human body, using the eyeball posture information to form an eyeball posture assessment index, determining the iris image range according to the imaging range of the eye and iris, selecting a valid image, and removing irrelevant images; S2, obtaining pupil change factor information under different light and dark environments, using the pupil change factor information to form pupil change factor evaluation indicators, segmenting the pupil image, and extracting the center and radius of the pupil; S3, obtaining artificial pupil change information, using the artificial pupil change information to form an artificial pupil change assessment index, and using pupil geometry information as inspiration information to determine an accurate image range of the iris; S4, obtaining vision information of people of different ages and genders, using the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders, extracting the outer edge of the iris image, extracting a circle from the outer edge using the least squares method, and obtaining the center and radius of the circle; S5, grading the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders by iris index, forming eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and vision iris integrity of people of different ages and genders, and performing concentric transformation on the iris image by center translation to change the pupil and iris center to the same point; S6. Use the rectangular expansion method to expand the circular iris image into a rectangle, match the rectangular iris image with the image stored in the database, and calculate the correlation coefficient value. If it is greater than the threshold, the match is successful, otherwise the match fails. Eliminate images at different angles due to occlusion and other reasons to improve the matching accuracy.

2. The least squares based iris recognition method according to claim 1, characterized in that: The step of obtaining the eyeball posture information of the human body and using the eyeball posture information to form an eyeball posture assessment index specifically comprises the following steps: Obtain the eye posture information of the human body; Using the eyeball posture information, forming historical eyeball posture information and real-time eyeball posture information; Using the historical eyeball posture information, forming average eyeball posture information; The average eyeball posture information and the real-time eyeball posture information are used to form an eyeball posture assessment index.

3. The least squares based iris recognition method according to claim 1, characterized in that: The method of obtaining pupil change factor information under different light and dark environments and using the pupil change factor information to form pupil change factor evaluation indicators specifically includes the following steps: Obtain information on pupil change factors under different light and dark environments; Using the pupil change factor information, obtaining real-time pupil change factor information under different light and dark environments; The real-time pupil change factor information under the different light and dark environments is analyzed to form pupil change factor evaluation indicators.

4. The least squares based iris recognition method according to claim 1, characterized in that: The step of obtaining the artificial pupil change information and using the artificial pupil change information to form an artificial pupil change assessment index specifically comprises the following steps: Obtaining information about artificial pupil changes; Using the artificial pupil change information, predicting the source of the artificial pupil change and the propagation path of the artificial pupil change; The artificial pupil change source and the artificial pupil change propagation path are used to form an artificial pupil change evaluation index.

5. The least squares based iris recognition method according to claim 1, characterized in that: The step of obtaining vision information of people of different ages and genders and using the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders specifically includes the following steps: Obtain vision information for people of different ages and genders; Using the vision information of people of different ages and genders to form vision interpretation information of people of different ages and genders; Using the vision interpretation information of people of different ages and genders to make normative predictions of the human body, and form normative prediction information; The normative prediction information is used to form vision assessment indicators for people of different ages and genders.

6. The least squares based iris recognition method according to claim 1, characterized in that: The iris index grading of the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders to form the iris integrity of eyeball posture, the iris integrity of pupil change factor, the artificial pupil change range and the vision iris integrity of people of different ages and genders specifically includes the following steps: Grading the iris indexes of the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders to form an iris assessment conclusion; The iris assessment conclusion is used to form the iris integrity of eyeball posture, the iris integrity of pupil change factors, the range of artificial pupil changes and the iris integrity of vision of people of different ages and genders.

7. The least squares based iris recognition method according to claim 6, characterized in that: The iris index grading of the eyeball posture assessment index, pupil change factor assessment index, artificial pupil change assessment index and vision assessment index of people of different ages and genders to form eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and vision iris integrity of people of different ages and genders also includes the following steps: using the eyeball posture iris integrity, pupil change factor iris integrity, artificial pupil change range and vision iris integrity of people of different ages and genders to form multiple categories of iris integrity.

8. An iris recognition system based on least squares, characterized in that: The system comprises An eyeball information acquisition module, which obtains eyeball posture information of a human body, uses the eyeball posture information to form an eyeball posture assessment index, determines the iris image range according to the imaging range of the eye and iris, selects valid images, and removes irrelevant images; An information feature extraction module, which obtains pupil change factor information under different light and dark environments, uses the pupil change factor information to form pupil change factor evaluation indicators, segments the pupil image, and extracts the center and radius of the pupil; An iris image range module, which obtains information about artificial pupil changes, uses the information about artificial pupil changes to form an artificial pupil change assessment index, and uses pupil geometry information as inspiration information to determine an accurate image range of the iris; A least squares calculation module, which obtains vision information of people of different ages and genders, uses the vision information of people of different ages and genders to form vision assessment indicators for people of different ages and genders, extracts the outer edge of the iris image, extracts a circle from the outer edge using the least squares method, and obtains the center and radius of the circle; An iris image concentric transformation module, which performs iris index grading on the eyeball posture evaluation index, pupil change factor evaluation index, artificial pupil change evaluation index and vision evaluation index of people of different ages and genders, forms iris integrity of eyeball posture, iris integrity of pupil change factor, artificial pupil change range and vision iris integrity of people of different ages and genders, and uses center translation to perform concentric transformation on the iris image, so as to change the pupil and iris centers to the same point; Rectangular expansion method calculation module, this module uses the rectangular expansion method to expand the circular iris image into a rectangle, matches the rectangular iris image with the image stored in the database, and calculates the correlation coefficient value. If it is greater than the threshold, the match is successful, otherwise the match fails. The image at different angles due to occlusion and other reasons is eliminated to improve the matching accuracy.

9. The least squares based iris recognition system as claimed in claim 8, characterized in that: The iris image concentric transformation module specifically includes: The iris assessment conclusion forming unit is used to grade the iris index of the eyeball posture assessment index, the pupil change factor assessment index, the artificial pupil change assessment index and the vision assessment index of people of different ages and genders to form an iris assessment conclusion; the iris integrity forming unit is used to use the iris assessment conclusion to form the iris integrity of eyeball posture, the iris integrity of pupil change factor, the artificial pupil change range and the vision iris integrity of people of different ages and genders.

10. The least squares based iris recognition system according to claim 9, characterized in that: The iris image concentric transformation module also includes: The iris integrity summary unit is used to use the iris assessment conclusion to form the iris integrity of eyeball posture, the iris integrity of pupil change factors, the range of artificial pupil changes and the iris integrity of vision of people of different ages and genders, forming multiple types of iris integrity.

Images