11 results about "Iris localization" patented technology

The embodiment of the invention provides an elliptic iris positioning method, system and device based on a deep convolutional neural network. The method is applied to the technical field of iris recognition, and comprises the following steps: marking a training data set to obtain ellipse parameter information of an ellipse frame in the training data set; designing elements of the deep neural network model, and constructing the deep neural network model; using the training data set to train the deep neural network model; performing forward reasoning on the iris image to be processed by using the trained deep neural network model to obtain a reasoning result, the reasoning result including ellipse parameter information of a prediction frame in the iris image; and performing post-processing on the reasoning result, and analyzing ellipse parameters corresponding to the iris and pupil boundary in the iris image according to the ellipse parameter information of the prediction frame, thereby realizing high-precision iris positioning. In this way, the technical problems that in the prior art, the anti-interference capacity is low, and the iris positioning precision needs to be further improved can be solved.

The present invention relates to the field of biometric recognition technology, and particularly to a real-time iris localization and segmentation system and method. The system includes: a backbone network for extracting image features from an original image to obtain an image feature map; a semantic segmentation subnet for performing iris segmentation on the image feature map; a center point localization subnet for locating the inner and outer circle positions of the iris; and a size regression subnet for predicting the radii and offsets of the inner and outer circles of the iris. The RISNet of the present invention performs inner and outer circle localization in a manner of double center point confidence prediction and double-branch regression, shares the same feature map with the segmentation network, outputs the localization result and the iris mask simultaneously, and does not require post-processing; optimizes the loss function and proposes PairLoss; the experimental results show that the method of the present invention has strong robustness, high accuracy, improved localization accuracy and segmentation accuracy, and realizes speed improvement.

The invention discloses an eye movement tracking dynamic error compensation method and system in the technical field of communication, and the method comprises the steps: obtaining iris ROI positioning region data, head movement original data and environment illumination intensity through image collection, calculating and outputting a multi-scale iris vector through vector parameters, and carrying out the calculation of the multi-scale iris vector. The predicted motion trail, the multi-scale iris vector and the environment illumination intensity are used as input quantities of the dynamic error compensation module, the dynamic error compensation module adjusts deformation compensation parameters in real time by using a dynamic weight matrix optimized based on a genetic algorithm, and coordinates are output to an output layer after calibration; the dynamic error compensation module receives visual error feedback of the output layer to form closed-loop correction; based on the dynamic weight matrix optimized by the genetic algorithm, the deformation compensation parameter can be adjusted in real time, the static tracking error is obviously reduced, the system delay is also obviously reduced, the robustness of the dark light environment is improved, and the power consumption is obviously reduced.

This invention provides a method, apparatus, device, and storage medium for real-time iris tracking and localization. The method includes: performing multi-level convolution processing on a real-time input iris image to extract iris features at different scales, obtaining a feature map set; inputting the feature map set into a preset mask prediction model for mask prediction, obtaining a pupil boundary mask and an outer iris boundary mask; extracting the boundary contours of the pupil boundary mask and the outer iris boundary mask, obtaining a pupil boundary contour point set and an outer iris boundary contour point set; performing geometric fitting based on the pupil boundary contour point set and the outer iris boundary contour point set, and optimizing and correcting the fitting parameters according to the concentric constraint relationship between the iris and the pupil to obtain the iris localization result. This invention, by combining boundary enhancement feature fusion with geometric constraint optimization, can accurately locate the inner and outer boundaries of the iris in non-cooperative environments, improving the accuracy and robustness of iris localization.

The invention discloses a multi-modal biological characteristic acquisition method and an all-in-one machine, and the method comprises the steps: guiding a user to carry out face pre-positioning through a face positioning frame displayed by a main display screen and face positioning prompt information displayed by an auxiliary display screen; controlling a main display screen to display an iris positioning ring and a virtual glasses frame, displaying iris positioning prompt information through an auxiliary display screen, and guiding a user to coincide the virtual glasses frame with the iris positioning ring by moving the head; the method comprises the following steps: respectively monitoring a face image and an iris image of a user through a telescope type iris acquisition module and a wide-angle face acquisition camera, and evaluating quality scores of the images; and capturing the face image and the iris image of the user at the same moment under the condition that the quality scores of the initially acquired face image and the iris image are both greater than the corresponding threshold values. According to the method, seamless integration of a user multi-modal biological characteristic acquisition process, high self-service of an acquisition process and real-time controllability of acquisition quality can be realized.

The invention discloses an iris positioning and segmentation method and device based on joint learning, equipment and a storage medium, and relates to the technical field of image processing, and the method comprises the steps: extracting multi-scale features through a shared backbone network, and dynamically screening the most relevant iris positioning and segmentation features through a feature selection gating module fusing space and channel attention. The positioning branch uses a B-spline curve to precisely fit an iris boundary, and the segmentation branch generates an iris region pixel mask. And the bidirectional cross attention task interaction gating module realizes deep interaction between tasks, and the optimization process adopts a loss function based on a Wasserstein distance to ensure the precision, so that the synchronism of iris positioning and segmentation is realized, and the precision and stability of iris positioning and segmentation are improved.

Embodiments of the present disclosure provide an elliptical iris localization method, system, and device based on a deep convolutional neural network. Applied to the field of iris recognition technology, the method includes marking a training data set to obtain elliptical parameter information of elliptical frames in the training data set; designing elements of a deep neural network model and constructing the deep neural network model; training the deep neural network model using the training data set; using the trained deep neural network model to perform forward inference on an iris image to be processed to obtain an inference result, where the inference result includes elliptical parameter information of a prediction box in the iris image; and performing post-processing on the inference result, and parsing elliptical parameters corresponding to the boundaries between the iris and the pupil in the iris image according to the elliptical parameter information of the prediction box to achieve high-precision iris localization. In this way, the technical problems of low anti-interference ability and the need for further improvement in iris localization accuracy in the prior art can be solved.

The present application discloses a method, apparatus, device, and storage medium for iris localization and segmentation based on joint learning, relating to the field of image processing technology. The method comprises: extracting multi-scale features through a shared backbone network, and dynamically screening the most relevant iris localization and segmentation features using a feature selection gating module that integrates spatial and channel attention. The localization branch uses a B-spline curve to accurately fit the iris boundary, while the segmentation branch generates a pixel mask of the iris region. The bidirectional cross-attention task interaction gating module enables deep interaction between tasks. The optimization process uses a loss function based on the Wasserstein distance to ensure accuracy, achieving the simultaneity of iris localization and segmentation, and improving the accuracy and stability of iris localization and segmentation.

Embodiments of the present application provide a pupil and iris positioning method and device, electronic equipment and storage medium. The method comprises: obtaining a target eye image; inputting the target eye image into a pre-trained target detection network model to obtain a plurality of candidate iris regions and a candidate pupil region corresponding to each candidate iris region, wherein the target detection network model is pre-trained based on sample data, and the sample data comprises: sample eye images labeled with the regions where the pupil and iris are located; determining a target iris region from each candidate iris region, wherein the size ratio of the target iris region to the corresponding candidate pupil region is within a preset range; determining the target iris region as the region where the iris is located in the target eye image, and determining the candidate pupil region corresponding to the target iris region as the region where the pupil is located in the target eye image. The embodiments can improve the efficiency and accuracy of determining the regions where the pupil and iris are located in the target eye image.

The application discloses an iris positioning method, device and equipment and a storage medium. The method comprises the following steps: acquiring an iris image, wherein the iris image contains an iris to be positioned and a pupil; calculating a gray histogram of the iris image; calculating a pupil threshold of the pupil by using the gray histogram; performing a binary processing on the iris image based on the pupil threshold to obtain a pupil gradient image; calculating the iris image according to a pupil center and a pupil radius on the pupil gradient image; calculating iris edge points, an iris center and an iris radius of the iris image according to an optimal path of the iris image; determining an iris safe area according to the iris edge points, the iris center and the iris radius; calculating a mean value and a variance of the iris safe area to obtain an iris noise mask; and performing an exclusive or calculation on the iris noise mask and a ring mask to obtain an iris mask. The application can quickly position the iris and is not easily affected by noise, improves the positioning efficiency and positioning accuracy of the iris, and has wide applicability.

The invention provides an iris real-time tracking and positioning method and device, equipment and a storage medium, and the method comprises the steps: carrying out the multi-level convolution processing of an iris image inputted in real time, extracting the iris features under different scales, and obtaining a feature map set; inputting the feature map set into a preset mask prediction model for mask prediction to obtain a pupil boundary mask and an iris outer boundary mask; performing boundary contour extraction on the pupil boundary mask and the iris outer boundary mask to obtain a pupil boundary contour point set and an iris outer boundary contour point set; and performing geometric fitting according to the pupil boundary contour point set and the iris outer boundary contour point set, and performing optimization correction on fitting parameters according to a concentric constraint relationship between the iris and the pupil to obtain an iris positioning result. According to the method, the boundary enhancement feature fusion and geometric constraint optimization are combined, so that the inner and outer boundaries of the iris can be accurately positioned in a non-cooperative environment, and the accuracy and robustness of iris positioning are improved.