31 results about "Iris localization" patented technology

The present invention disclose an iris recognition method, which utilizes a matching pursuit algorithm to simplify the extraction and reconstruction of iris features and reduce the memory space required by each iris feature vector without the penalty of recognition accuracy. The iris recognition method of the present invention comprises an iris-localization component and a pattern matching component. The iris-localization component locates the iris region via the color difference between different portions of the eyeball. The primary iris features are extracted from iris information and transformed into a sequence of iris feature vectors by a matching pursuit algorithm. Thus, the iris image can be represented by a sequence of atoms, and each atom contains base, amplitude and location. Then, the comparison between the feature vectors of two irises is performed to determine whether the two irises match.

The invention provides an iris identifying system and a realizing method based on field programmable gate array (FPGA) which uses FPGA chip of Altera company as a main control chip, an iris collecting device, a LCD screen and a PS / 2 keyboard compose a hardware platform with integrated system. The whole system can realize functions of collecting iris image, displaying iris image, evaluating iris image quality, recording iris object and identifying iris object, wherein, a novel, simple and rapid localization algorithm is provided in iris object recording and iris identifying processes. The irischaracteristic extracting algorithm uses two-dimension Gabor filter algorithm for realizing perfect characteristic extraction. The accurate iris localization effect and special characteristic extraction algorithm realize the iris identifying system with high identifying rate and high reliability for authentication.

The invention discloses a novel pupil rapid positioning method, comprising the following steps: (1) marking the connected areas in the binarized iris image; (2) calculating the number of pixels in each connected area; (3) ) Use the points on the four outermost directions of each connected region to define the window of the smallest circumscribed circle for the region, and calculate the window area; (4) select the threshold value of the number of pixels to initially screen the connected region; (5) calculate The ratio of the number of pixels in the connected region to the area of ​​the smallest circumscribed circle window of the connected region, and the connected region with the largest ratio is taken as the connected region of the pupil. The invention proposes an improved iris positioning algorithm, which effectively improves the accuracy and efficiency of iris recognition under non-ideal conditions. The advantage of searching for the largest connected region is that the interference points are automatically removed according to the gray feature of the pupil, which avoids the errors caused by the extraction of invalid edge points and the mistaken entry of illegal points when fitting the inner boundary of the iris.

The invention discloses a method for quickly locating the iris of the human eye during the iris collection process. The method includes Gaussian smoothing, median filter processing, edge detection, non-maximum value suppression, double threshold value processing, and Hough transform flow. Innovatively in the field of iris positioning, Gaussian smoothing assisted improved fast median filter is used to preprocess the image, and then the fastest Sobel edge detection operator is used to extract iris edge features, and a large number of samples are trained for iris positioning to extract the best The high and low threshold parameters are subjected to double-thresholding processing, and then the binary image obtained after double-thresholding processing is compressed using the invariance of the human eye iris annular concentric circle compression structure, and finally the human iris is subjected to Hough transform for sample training to extract the most Optimal iris inner and outer edge search radius returns parameters. Performing Hough transform within this parameter can effectively reduce the number of edge pixel traversals and improve the efficiency and accuracy of iris positioning.

The invention discloses an iris positioning method for iris recognition during long-distance travel, comprising: removing randomly distributed light spots and noise interference in an iris image; detecting the transition edge between the pupil and the iris, locating the inner boundary of the iris; and detecting the iris and the sclera the transition edge of the iris, which locates the outer border of the iris. The iris positioning method in the present invention is insensitive to imaging conditions such as illumination and blur, and has low computational complexity, which can effectively improve the robustness and real-time performance of the iris positioning of the iris identification system during long-distance travel, thereby helping to improve the identification of the system. speed and accuracy.

The invention relates to an iris identification method based on blanket dimension and lacunarity, belonging to the technical field of iris identification. The method comprises the following main steps of iris identification, iris image normalization, iris feature extraction and pattern matching. In the invention, the blanket dimension and lacunarity of iris texture are respectively calculated, and then two types of feature indexes are combined so as to obtain excellent identification effect; therefore, the method solves the problem that the existing iris identification method is incapable of efficiently utilizing iris fractal geometric feature and radiation physiological property.

An iris localization and feature extraction method and system are provided in the embodiments of the present application, wherein the steps of the method include: S1. Selecting an iris region segmentation threshold based on a pre-built local grayscale distribution statistical model; S2. Using an iris-based segmentation threshold The double-threshold coupled classifier constructed by the regional segmentation threshold filters the area where the iris is located to obtain the pupil area image and the iris area image; S3. Use the boundary detector constructed based on the pupil area image and the iris area image to determine the effective iris area; S4 . Using the local wavelet high-frequency energy tower transition model constructed based on the effective iris area, the effective iris pixels in the effective iris area are encoded to obtain the iris feature code. This scheme overcomes the influence of noise interference and unstable features in low-quality iris images, thereby improving the accuracy and robustness of the iris recognition system.

The invention discloses an iris image feature extraction method based on an odd-symmetric 2D Log-Gabor filter, which comprises the following steps: (1) acquiring an iris image by using an iris acquisition device; (2) preprocessing the iris image, including iris positioning, iris image quality evaluation and normalization; (3) extracting the original iris features by using an improved algorithm based on the odd-symmetric 2D Log-Gabor filter: exporting the function of the 2D Log-Gabor filter, transforming the 2D Log-Gabor filter to rectangular coordinates from polar coordinates, resolving the 2D Log-Gabor filter into a two-dimensional odd-symmetric filter function, dividing iris subblocks and extracting the features; (4) fusing the features: extracting the amplitude value and phase of each subblock, and fusing the features; (5) and matching and classifying the features: encoding the features, encoding the Hamming distance, selecting the threshold of the Hamming distance and identifying the iris feature. The method breaks through the iris acquisition distance limit (2 meters) and enhances the accuracy and reliability for long-distance iris identification.

The invention discloses an iris positioning method and device. Among them, the method includes: obtaining the image information of the target iris, and roughly positioning the pupil in the image information; constructing a tripartite map of the target object according to the rough positioning result of the pupil, and using a preset algorithm to obtain extract the target object, wherein the target object includes: the pupil, eyelid and iris outer circle of the target iris; determine the positioning information of the target iris according to the extracted pupil, eyelid and iris outer circle, wherein the positioning information includes at least one of the following: pupil border, eyelid border, and iris outer border. The invention solves the technical problem of inaccurate iris positioning results in the prior art when the iris image is a non-ideal iris image such as non-circular pupils, uneven illumination, over- or under-exposure, and the like.

The invention provides an iris localization and segmentation system based on a hole residual attention structure, which includes a feature extraction structure, a segmentation structure and a scoring structure; The output is respectively related to the input of the scoring structure and the input of the segmentation structure; the segmentation structure includes M-1 upsampling modules and M-2 feature fusion modules that are connected in series at intervals, and the output of the i-th feature extraction module is to the M-i-th The first level feature fusion module has one input, and the other input of the feature fusion module is connected to the output of the upsampling module of this level, and the M-1st level upsampling module outputs the mask image after segmentation. The feature extraction module includes N hole attention residual structure DARB and 1 down-sampled hole attention residual structure DADRB. The invention uses DARB to build a neural network, realizes accurate and rapid iris area division by designing a multi-branch network, and realizes automatic evaluation of the quality of the iris area.

The invention discloses a small multi-rotor drone camera control method based on eyeball recognition and tracking technology, which relates to the field of robot control technology; the invention uses eyeball recognition and tracking technology to assist the operator to control the small multi-rotor drone camera, and its technology The main points are: collect the operator's eyeball image and complete the iris recognition and positioning, reacquire the iris positioning information in each control cycle to complete the eye tracking, and use the difference between the real-time iris positioning information and its reference value to complete the control of the UAV camera; The invention can make the operator no longer need to manually control the shooting direction of the camera when acquiring the image information shot by the camera of the small multi-rotor UAV, thereby reducing the control variables and reducing the difficulty of operation, so that the independent person can independently complete the small The control of the multi-rotor UAV makes up for the deficiencies of the existing technology.