155 results about "Iris image" patented technology

The present application provides an iris recognition method and apparatus, an electronic device, and a storage medium. The method comprises: obtaining an iris image group acquired for an object to be recognized, wherein the iris image group comprises at least two iris images acquired at different acquisition angles for a same eye region of said object; performing stereo matching on the at least two iris images to obtain a disparity map between the at least two iris images, wherein the disparity map comprises disparity elements, and each disparity element represents a displacement amount in a specified direction between two pixel points corresponding to a same eye region element in the at least two iris images; in one iris image among the at least two iris images, determining a pupil edge on the basis of the displacement amounts; determining an iris region in the iris image on the basis of the pupil edge, and performing feature extraction on the iris region to obtain an iris feature; and performing identity recognition on said object on the basis of the iris feature.

The invention discloses a digital currency transaction system based on an iris and a block chain, and the system comprises an iris registration module which is used for collecting an iris image, extracting an iris feature vector based on a deep hash network, and generating a unique identity label; the iris identity authentication module is used for extracting a current iris feature and calculating an identity hash value when a digital currency transaction request is obtained; the anti-counterfeiting iris detection module is used for detecting a texture abnormal condition of the current iris feature based on the anti-counterfeiting sample detection module, and confirming the validity of the iris when the detection is passed; and the transaction validity verification module is used for verifying the validity of the digital currency transaction based on zero-knowledge proof verification. Based on the iris features and the block chain technology, the defects of traditional digital currency in the aspects of identity authentication, account security and privacy protection are overcome.

The present invention discloses a dual identity authentication method for an automobile electronic anti-theft system, which relates to the field of automobile safety technology, and includes: a fingerprint acquisition module, a fingerprint recognition module, an iris acquisition module, an iris recognition module, a data storage module, a processing module, an automobile control module, and a time analysis module; the authentication steps are: S1, the data storage module pre-records the fingerprint and iris information of the owner, and stores them to provide data for subsequent comparison; S2, the fingerprint acquisition module acquires the fingerprint of the visitor; S3, the iris acquisition module acquires the iris image of the visitor. The present invention uses a dual identity authentication method, and in the vehicle electronic anti-theft system, the fingerprint and iris data can be uniformly stored in a secure database for centralized management. Compared with the traditional single information authentication method, it is more secure and anti-theft, protects the owner's vehicle, reduces the possibility of the owner's identity information being copied by criminals, and brings protection to the safety of the car.

The invention discloses an iris pupil real-time segmentation method based on deformable convolution and ellipse prior constraint, and relates to the technical field of computer vision and biological feature recognition. The method comprises the following steps: acquiring an original iris image, and preprocessing the original iris image by adopting dynamic shielding enhancement; constructing a lightweight encoder-decoder network, wherein the lightweight encoder-decoder network comprises an encoder, a decoder and a post-processing module; the encoder adopts a cascaded deformable convolution module and an elliptical attention mechanism module to perform feature extraction; training and optimizing the lightweight encoder-decoder network; carrying out multi-task loss calculation, introducing an elliptical parameter regression constraint design loss function on the basis of segmentation loss, and optimizing a segmentation result; and ellipse parameter refinement is carried out through a post-processing module, and ellipse fitting optimization is carried out on a segmentation result. Compared with the prior art, the iris pupil real-time segmentation method has the advantages that the precision is improved, the speed is optimized, and the robustness is high.

The invention relates to a target detection-based iris rapid and accurate segmentation method, which comprises the following steps of: obtaining an eye image for training, establishing a three-dimensional coordinate system and obtaining parameters of an iris ellipse by utilizing a three-dimensional mathematical relationship; constructing a directional bounding box fitted with the contour of the iris ellipse, the four edges of the directional bounding box being tangent to the iris ellipse, and solving the coordinates of the four vertexes of the directional bounding box; carrying out model training by taking the coordinates of the four vertexes of the directional bounding box and the parameters of the iris ellipse as model training labels so as to obtain a network model; the network model is used for detecting a directional bounding box surrounding an iris ellipse of the target eye image, and calculating and segmenting the iris ellipse according to the directional bounding box surrounding the iris. According to the method, a traditional iris segmentation mode depending on edge detection or pixel classification is abandoned, a brand new technical route based on deep learning target detection is adopted, and the limitation of a traditional method in processing a low-quality iris image is effectively overcome.

The present invention relates to a multimodal recognition device for realizing health screening based on eye imaging and eye movement tracking, comprising a desktop end and a remote end, wherein the desktop end comprises: an image acquisition unit, which is arranged in the first screen display unit and acquires image information and eye movement information of the patient's eye along a first direction, wherein the image information comprises: an iris image, an eye surface image, an eye fundus image, and an eye position image; a first control unit, which recognizes the identity of the user in real time according to the iris image, and determines the health status of the user according to the eye surface image, the eye fundus image, the eye position image, and the eye movement tracking information. By acquiring the patient's iris image, real-time iris recognition and identity authentication are performed to ensure that the patient is always the same person, thereby improving the effectiveness of health screening. By acquiring the patient's eye surface image, the eye fundus image, the eye position image, and the eye movement data, the patient's health status is analyzed from multiple modalities to ensure the diversity and accuracy of health screening.

The invention provides an iris acquisition identity verification method and system based on a smart watch, and the method comprises the steps: obtaining an iris image, and carrying out the missing judgment of the iris image, so as to mark a missing part and a real part of an iris; wherein the iris image is shot by an iris acquisition module on the smart watch; complementing the missing part based on a deep learning model to obtain a complemented image corresponding to the missing part, performing feature extraction on the complemented image to obtain a simulation feature, performing feature extraction on the real part of the iris image to obtain a real feature, and processing the simulation feature and the real feature based on a weighted average algorithm to obtain a comprehensive feature vector; and performing identity verification through the comprehensive feature vector, and outputting an identity verification result. According to the method for identity verification through combination of the real features and the simulation features, the verification precision under the condition that the iris image is partially missing can be improved, meanwhile, the number of times of repeated shooting of the smart watch is reduced, and the verification efficiency is improved.

The invention discloses an iris image quality evaluation method and system, and the method comprises the following specific steps: 1, image preprocessing: improving the image quality, and highlighting the iris features; 2, feature region segmentation: detecting iris and pupil boundaries by adopting a Hough circle transformation or ellipse fitting technology, and detecting eyelid and eyelash boundaries by adopting Canny edge detection gradient intensity; 3, multi-dimensional quality evaluation: comprehensively quantifying the image quality through four indexes of available iris region calculation, contrast analysis, geometric characteristic evaluation and image quality evaluation; 4, adjustable weight scoring: generating a comprehensive quality score through a comprehensive quality scoring formula in combination with the adjustable weight of the user; and 5, interactive manual adjustment: the user can manually adjust the boundary of the iris and the pupil, and the evaluation result is updated in real time. The method is suitable for the fields of iris recognition, eye movement tracking, human-computer interaction, medical diagnosis and the like, and has remarkable practicability and flexibility.

A server for predicting a disease through AI-based iris analysis and a method for operating same are disclosed. The server for predicting a disease through AI-based iris analysis comprises: an image preprocessing unit that performs preprocessing on an iris image received from a user terminal; a prediction model training unit that trains an iris-based disease prediction model in a supervised manner using pre-collected learning data; a prediction model tuning unit that performs additional learning on the supervised iris-based disease prediction model; and a disease prediction unit that determines a predicted disease corresponding to the iris image using candidate diseases obtained from the additionally trained iris-based disease prediction model and transmits disease prediction information including the determined predicted disease to the user terminal.

The present invention discloses a three-dimensional iris reconstruction and expansion method, which relates to the field of intelligent medical care. The method comprises the following contents: step one, generating a three-dimensional iris tag; step two, establishing an iris depth map prediction model; and step three, expanding the iris. The present invention utilizes the anatomical constraint relationship between multiple iris images in a video stream to accurately predict iris depth information, realize three-dimensional iris reconstruction, and expand the iris into a two-dimensional rectangular image and depth map. The method overcomes the defect of insufficient depth of a traditional single image and utilizes multiple pictures in a video to predict iris image depth information. The iris textures between the iris pictures have an anatomical constraint relationship, which can effectively predict iris image depth information, improve the robustness of iris recognition, and is suitable for a variety of application scenarios.

The application discloses an iris recognition method and device, system and storage medium, and performs preprocessing such as polar coordinate unfolding on an input original iris image in sequence; multi-level image features are extracted through an inverse residual module; subsequently, a global depth convolution GDConv operator is introduced to replace a global average pooling layer, so that spatial structure distribution features of iris textures are retained under the premise of extremely low calculation complexity; finally, an ArcFace loss function is used to optimize the distribution of features in a hyperspherical space, and the class separability of the features is enhanced by introducing an additive angle interval. By using the technical scheme of the application, the technical problems that spatial topological information is lost due to a global average pooling GAP operation in iris feature extraction by using an existing lightweight convolutional neural network, and the feature discrimination is reduced due to network lightweight are solved.

A computing system receives a code that is generated based upon an image of an iris of a first user. The image of the iris of the first user is captured by way of an iris scanning device that is under control of a second user. The computing system executes a search over a plurality of codes stored in a data store based upon the code, where the plurality of codes are generated based upon images of irises of a plurality of users. The computing system determines whether the code is included in the plurality of codes based upon search results for the search. Based upon a determination that the code is not included in the plurality of codes, the computing system causes an amount of cryptocurrency to be transferred to a cryptocurrency wallet of the second user.

The application relates to the field of image processing, in particular to an iris image matching method and device, equipment and medium, which are used to solve the problem of large calculation error in the iris image matching process. The method determines a plurality of target Mahalanobis distances based on each feature point of a to-be-detected iris image. It should be noted that each target Mahalanobis distance is determined based on the gradient parameters corresponding to any two target feature points of the to-be-detected iris image. Based on the sum of the plurality of target Mahalanobis distances and the sum of a plurality of standard Mahalanobis distances, the matching degree between the to-be-detected iris image and a pre-stored standard iris image is determined, wherein the standard Mahalanobis distance is determined based on the standard iris image. The above-mentioned iris image determination method based on Mahalanobis distance considers the internal relationship between the feature points, improves the matching accuracy between the to-be-detected iris image and the pre-stored standard iris image, and improves the reliability of the safe box in use.

In the Iris based biometric recognition systems, iris needs to be segmented before comparison and hence iris segmentation is a crucial process in iris based biometric recognition systems. Existing techniques are unable to segment iris due to occlusions and require complex and time consuming algorithms to remove these occlusions. Other deep learning based solutions require precise annotations of the iris regions along with eyelids and eyelashes. The present disclosure initially generates polygons on the iris and pupil area using a pre-trained detection model. Internally covered vertices and externally exposed vertices of the generated polygons are computed to construct curvature of the iris region. A pupil region is generated by filtering the plurality of vertices lying inside pupil circle region from the plurality of externally exposed vertices. Further, a segmented iris image is generated by removing the pupil region from the input image based on the curvature of the iris region.

This information processing system is provided with an acquisition unit, a calculation unit, and a first output unit. The acquisition unit acquires an iris image including an iris. The calculation unit uses the acquired iris image to calculate, with regard to each of a plurality of degradation factors indicating a factor that causes the quality of the iris image to degrade, a factor score indicating a degree of quality corresponding to the relevant degradation factor. The first output unit outputs first output information in which the plurality of degradation factors and the factor scores corresponding respectively to the plurality of degradation factors are associated.

The present application provides an iris registration method, an iris recognition method, a computer device and a storage medium, the iris registration method comprising: acquiring an iris image combination corresponding to a target user, the iris image combination comprising a plurality of iris images of the target user, the plurality of iris images being iris images corresponding to different angles; calculating three-dimensional iris point cloud data based on the iris image combination, the three-dimensional iris point cloud data being used for reflecting iris features of the target user and spatial positions of the iris features; and according to the three-dimensional iris point cloud data, generating a target three-dimensional iris model of the target user, the target three-dimensional iris model being used for reflecting iris curved surface features of the target user. According to the technical scheme, the security of the iris recognition technology can be improved.

The invention discloses an iris biological feature comparison method based on three-dimensional fold embedding matching, and relates to the technical field of biological feature recognition, and the method comprises the following components: S1, iris image acquisition preparation, S2, iris segment acquisition, S3, three-dimensional structure extraction, S4, three-dimensional fold embedding matching, and S5, matching result output. According to the method, through the three-dimensional wrinkle embedding matching technology, the three-dimensional structure information, including the three-dimensional coordinates, the wave crest position, the wave trough position and the like of the wrinkles, of the iris wrinkles is deeply utilized for accurate matching, compared with a traditional two-dimensional iris recognition method, the three-dimensional structure information provides richer feature dimensions, and the recognition accuracy is improved. According to the method, the recognition accuracy and reliability are remarkably improved, particularly when tiny differences and complex textures in the iris image are processed, the features can be captured more accurately through three-dimensional wrinkle embedding matching, and therefore more accurate identity verification is achieved.

This invention discloses a method, apparatus, storage medium, and device for iris inner boundary localization, belonging to the field of iris recognition. The invention first performs initial localization of the iris inner boundary as a circle. Then, the annular region image containing the initially located iris inner boundary is unfolded into a rectangular region image. Next, gradient calculations are performed along the column directions of the rectangular region image, followed by binarization. The boundary points of the iris inner boundary are determined on the resulting binarized image. Finally, the boundary points are returned to the iris image to obtain the precisely located iris inner boundary. This invention is a universal method for iris inner boundary localization, capable of locating both irregular and regular circular iris inner boundaries, while ensuring accuracy and improving the accuracy of iris recognition.

This information processing system comprises a first acquisition unit, a second acquisition unit, and a generation unit. The first acquisition unit acquires a first iris image. The second acquisition unit acquires a second iris image of which the quality is lower than that of the first iris image. On the basis of the first iris image and the second iris image, the generation unit generates a degraded iris image obtained by degrading the first iris image to approach the quality of the second iris image.

An information processing device detects iris images of cosmetic lenses. A candidate extraction means extracts different iris images corresponding to the same person to be a cosmetic lens candidate. A confidence level calculation means matches iris features of the cosmetic lens candidate with iris features of other cosmetic lenses, and calculates a confidence level indicating a cosmetic lens likelihood. A determination means determines that the cosmetic lens candidate is a cosmetic lens with respect to the calculated confidence level that is equal to or higher than a predetermined threshold value.

The invention discloses an iris modeling method, device and equipment, a medium and a program product, and belongs to the field of iris modeling. The method comprises the following steps: acquiring an iris image; constructing an inner and outer contour model based on the iris image, wherein the inner and outer contour model is used for representing curve features of an inner contour and an outer contour of an iris in a two-dimensional plane; for at least one feature point on the iris, elevation information of the at least one feature point is calculated, and the elevation information is used for indicating height information of the feature point relative to the two-dimensional plane; and constructing a three-dimensional curved surface model of the iris based on the inner and outer contour models and the elevation information of the at least one feature point. According to the method, the three-dimensional curved surface model of the iris is constructed based on the iris image, the three-dimensional curved surface model can be applied to the fields of iris recognition, ophthalmology medical treatment, iris reconstruction and the like, particularly, a three-dimensional iris model, namely the three-dimensional curved surface model is used in the field of iris recognition, curved surface information in the iris can be better utilized, and the iris recognition efficiency is improved. And the accuracy of iris recognition is improved.

The invention discloses an ordering method and platform based on individual health, and the method comprises the steps: obtaining an iris image of a user, and recognizing the body health risk information of the user through iris detection, analysis and processing; generating a catering recommendation rule according to the obtained body health risk information of the user; the ordering platform screens a food list according to the ordering condition of the user and the catering recommendation rule, and then presents catering recommendation information; or the ordering platform screens the food list according to the ordering condition of the user, generates risk prompt information according to the catering recommendation rule, and presents the catering recommendation information and the risk prompt information; the user performs ordering selection; according to the scheme, by combining the iris detection technology and the Internet ordering platform, the health risk of the user can be effectively recognized, personalized diet recommendation and health risk prompt are provided, the user is helped to enjoy online ordering and online take-out convenience, diet health can be guaranteed, and chronic diseases can be prevented and controlled.

According to the iris information amount and complex field feature low-computing-power scene identity verification method, after feature data of template iris convolution data of a template tester after convolution processing is carried out, the optimal partitioning dimension is obtained through an analysis result of each sub-block based on the information amount of the iris so as to partition an image, and then the feature data of the template iris convolution data of the template tester are obtained; the method comprises the following steps: determining whether a stable relationship exists between sub-blocks according to a preset threshold value, further determining whether the sub-blocks with the stable relationship are a constant relationship, performing two-stage verification on test iris feature data of a tester based on an established constant relationship set, and finally determining whether the tester belongs to a template tester. According to the method, a segmentation scheme which can best reflect iris texture features is accurately selected through a texture region guide segmentation strategy based on the information amount, traditional real number field feature expression is expanded to a complex number space, complex changes of iris textures can be more comprehensively described, the problem of uncertainty of iris image acquisition is effectively solved, and the iris image acquisition accuracy is improved. And the practicability and adaptability of the system are enhanced.

The invention relates to the technical field of information verification, and discloses a multi-identity information verification device, which comprises an information collector, a central processing unit and a display, and is characterized in that the central processing unit comprises a data preprocessing module, a feature extraction module and an information verification module; according to the invention, identity card numbers, fingerprints, face images and iris information are covered; identity card number verification can screen out format errors, fingerprint noise reduction enables lines to be clear, face image graying retains key features and reduces data volume, and iris image enhancement facilitates subsequent operation. Key features are extracted by adopting corresponding effective methods for various types of information; the verification accuracy is ensured through a rigorous comparison means; whether notification is passed or not and specific inconsistent types are clearly determined, so that a user can conveniently know; and all links cooperate with one another, so that the reliability, accuracy and convenience of identity verification are effectively improved, and strict identity verification requirements in multiple scenes can be met.

An embodiment of the present invention provides an iris image anti-counterfeiting detection method based on a cyclic attention mechanism, including: inputting a global iris image into an iris anti-counterfeiting detection network model; processing the global iris image through a first-level network structure unit to obtain a prediction probability and key region parameters at a first-level feature scale; performing, through each level of network structure unit: based on the input image at the current feature scale input to the current-level network structure unit and the key region parameters at the current-level feature scale output by the current-level network unit, obtaining an input image at the next-level feature scale, and processing the input image at the next-level feature scale by the next-level network structure unit to obtain a prediction probability and key region parameters at the next-level feature scale corresponding to the next-level network structure unit; fusing the prediction probabilities at at least two different-level feature scales to obtain a determination result as to whether the global iris image is a real iris image or a forged iris image.

The invention relates to the technical field of identity recognition, and discloses a vehicle owner identity information recognition system based on artificial intelligence. Comprising a data acquisition module used for acquiring an iris image of a current vehicle operator; the sub-region division module is used for generating an identification region and dividing the identification region into sub-regions; the parameter extraction module is used for generating iris feature coefficients; the comparative analysis module is used for judging whether the vehicle owner identity information exists or not and generating a corresponding vehicle control instruction; the instruction execution module is used for controlling the vehicle to execute corresponding actions according to the vehicle control instruction; according to the invention, an overall identification and judgment mode of the iris image is converted into a local identification and judgment mode, so that the data volume used for vehicle owner identity identification can be reduced, the data calculation workload can be reduced, the control instruction can be generated at the first time, the efficient vehicle owner identity identification effect is realized, and the user experience is improved. And the processing ordering effect of the iris data is also realized.

The application discloses an image processing-based dry eye iris detection method, and relates to the technical field of dry eye detection, and comprises the following steps: 1, in the process of collecting the human eye iris projection image, four light supplementing white lamps are turned on, and the white lamps are projected onto the iris surface; 2, in the collecting process, the four points projected onto the iris are kept in the delimited green circle, and the relative position relationship of the four points is detected and calculated in real time; 3, before the comparison threshold value, whether the four white lamp projection images of the image reach the set clear range is judged first, when the clear range is reached, whether the relative position relationship of the four points is less than the threshold value of the preset value calibration is judged, and when the threshold value is less than the preset threshold value, the iris image is collected; 4, then, the image processing technology is applied to extract the iris position of the collected image and the position of the four LED projection white lamps; 5, finally, the size of the iris diameter is calibrated through the position relationship of the white lamps. The detection method has the advantages of fast detection speed and accurate detection result.

The present application discloses a method and a device for localizing a cutting center in refractive surgery using femtosecond lasers and relates to the field of localizing a cutting center in refractive surgery. The method comprises: capturing eye images of a patient to be operated on in a supine position or...In a seated position under a predetermined illumination level, a first iris image and a first relative position are determined; a second iris image is determined based on the eye image in a supine position; a first rotation angle of the eyeball is determined based on the first and second iris images, and subsequently a second visual axis center and a second relative position of the patient to be operated on are calculated, based on which negative pressure suction is performed, whereby a third iris image is recorded during negative pressure suction if a displacement is detected before negative pressure suction or after aligning the center of a negative pressure suction ring with the second visual axis center; subsequently a third visual axis center is calculated, the center of the negative pressure suction ring is aligned with the third visual axis center, and the third visual axis center is defined as the cutting center for the operation.The present application enables precise localization of the cutting center.

The invention discloses an iris recognition device and method in a complex illumination environment. An iris image acquisition unit acquires iris images of eyes of a user; the intelligent exposure control unit adjusts exposure parameters based on the iris image according to the association between the pupil size and the ambient light; the iris quality evaluation unit evaluates the quality of the iris images by adopting a plurality of quality measures, filters the iris images which are unqualified in quality evaluation, and obtains a multi-measure quality evaluation result for the iris images which are qualified in quality; the iris quality enhancing unit is used for enhancing the quality of the iris image of which the quality is lower than a preset threshold value; the iris feature coding unit is used for representing the iris image subjected to quality compensation in an iris feature coding form; and the iris feature comparison unit calculates the similarity between different iris feature codes, and identifies the iris feature code to be identified in the registered iris feature code library by comparing the iris feature code to be identified with the registered iris feature code library.

The present disclosure relates to the field of iris recognition technology and provides an iris recognition method, apparatus, medium, and device based on uncertainty modeling, comprising: obtaining iris image data and inputting it into a pre-built iris recognition model; performing pixel-level modeling on the image data using an uncertainty modeling module to extract the mean and variance features of each pixel, and generating an uncertainty feature representation and an iris feature template based on the extraction results and a re-parameter sampling strategy; generating a variance scaling map based on a dynamic mask generation module and image data, and generating a dynamic feature mask using the variance scaling map and a dynamic threshold judgment strategy; and determining target identity information based on a preset iris template database, the iris feature template, and the dynamic feature mask to complete identity recognition. By combining the iris feature template and the dynamic feature mask of the iris image, the present disclosure improves the accuracy and robustness of iris recognition, maintaining high recognition accuracy under varying conditions such as different lighting conditions.