32 results about "Gabor wavelet transform" patented technology

The present invention may be embodied in a method, and in a related apparatus, for classifying a feature in an image frame. In the method, an original image frame having an array of pixels is transformed using Gabor-wavelet transformations to generate a transformed image frame. Each pixel of the transformed image is associated with a respective pixel of the original image frame and is represented by a predetermined number of wavelet component values. A pixel of the transformed image frame associated with the feature is selected for analysis. A neural network is provided that has an output and a predetermined number of inputs. Each input of the neural network is associated with a respective wavelet component value of the selected pixel. The neural network classifies the local feature based on the wavelet component values, and indicates a class of the feature at an output of the neural network.

The invention relates to a face recognition method based on Gabor wavelet transform and local binary pattern (LBP) optimization. Two-dimensional Gabor wavelet transform can associate pixels of adjacent areas so as to reflect the change conditions of image pixel gray values in a local range from different frequency scales and directions. The feature extraction and the classification recognition are carried out on the basis of a face image two-dimensional Gabor wavelet transform coefficient. For a high-dimensional Gabor wavelet transform coefficient, overall histogram features are extracted by adopting the LBP, and then the image is blocked by utilizing priori knowledge to extract the features of each piece of LBP local histogram. The method has better recognition rate, better robustness to illumination and wide using prospect in the fields of biometric recognition and public security monitoring.

An innovative optical system and method is disclosed for analyzing and uniquely identifying high-order refractive indices samples in a diverse population of nearly identical samples. The system and method are particularly suitable for ultra-fine materials having similar color, shape and features which are difficult to identify through conventional chemical, physical, electrical or optical methods due to a lack of distinguishing features. The invention discloses a uniquely configured optical system which employs polarized sample light passing through a full wave compensation plate, a linear polarizer analyzer and a quarter wave retardation plate for producing vivid color bi-refringence pattern images which uniquely identify high-order refractive indices samples in a diverse population of nearly visually identical samples. The resultant patterns display very subtle differences between species which are frequently indiscernable by conventional microscopy methods. When these images are analyzed with a trainable with a statistical learning model, such as a soft-margin support vector machine with a Gaussian RBF kernel, good discrimination is obtained on a feature set extracted from Gabor wavelet transforms and color distribution angles of each image. By constraining the Gabor center frequencies to be low, the resulting system can attain classification accuracy in excess of 90% for vertically oriented images, and in excess of 80% for randomly oriented images.

The invention provides an En-ULLELDA-based (ensemble-unified locally linear embedding and linear discriminant analysis) method of multi-view model recognition. The method comprises the following steps: firstly, selecting a vehicle ROI (region of interest); secondly, extracting the high-level information that can reflect the model as features through Gabor wavelet transform; then, carrying out the dimension reduction of features on the basis of a novel manifold learning algorithm En-ULLELDA, so as to transform the features to a low-dimensional space; and obtaining the corresponding models from the features of a test sample by a classifier during the recognition. According to test results, the invention can effectively handle the problem of multi-view model recognition on urban roads; and the invention can eliminate the effects of parameter variation on the recognition results by employing the integration technology, so that the invention has higher robustness.

The invention discloses a remote sensing image variation detecting method on the basis of weighted Gabor wavelet characteristics and two-stage clusters. The processed objects include optical remote sensing images and SAR (synthetic aperture radar) images and the remote sensing image variation detecting method includes (1) generating difference images according to remote sensing image types; (2) subjecting the difference images to Gabor wavelet transform; (3) extracting multiscale and multidirectional characteristics of the Gabor wavelet transform of the difference images; (4) designing the weighting coefficient and acquiring the weighted Gabor wavelet characteristics; (5) clustering the weight Gabor wavelet characteristics by means of the two-stage cluster strategy; (6) acquiring variation detecting results. By the remote sensing image variation detecting method, loss of marginal information is reduced, stronger, weak and slight varying areas can be detected at the same time, the total mistake pixel number is decreased, more detail information is reserved and variation results can be effectively extracted.

The invention relates to a non-fluorescent eye fundus image based automatic segmentation method for retinal blood vessels. The method comprises following steps: step one, an image is preprocessed, blood vessel characteristics are enhanced, and background noise is weakened; step two, morphological characteristics of the retinal image are extracted with a multi-scale linear operator, and a refined blood vessel framework is segmented with two-dimensional Gabor wavelet transform; step three, after the refined blood vessel framework is segmented, the image is subjected to path morphology filtering, the maximum path length is combined with geometrical characteristics of a blood vessel region, and an adjacent map is constructed; step four, a binaryzation process is performed with regional connectivity analysis and a hysteresis threshold technology for auxiliary segmentation of microvessels, and the segmentation is finished. Compared with the prior art, the method has the advantages as follows: the blood vessel location accuracy is higher, the adhesion phenomena are reduced, and a retinal blood vessel network of the eye fundus image is effectively segmented.

The invention provides a multi-modal emotion analysis method and system based on deep learning for acupuncture, and belongs to the technical field of emotion recognition. According to the method, feature extraction is carried out on facial expression features by adopting Gabor wavelet transform, feature extraction and dimension reduction processing are carried out on electroencephalogram signals by adopting UPLBP, then sparse linear fusion is carried out on the facial expression features and the electroencephalogram signal features to fuse the facial expression features and the electroencephalogram signal features into a unified and normalized feature vector, and the feature vector is transformed into a tensor form; training is carried out in a CNN-LSTM network, redundant information is removed and predicted emotion classification information is obtained, and a loss function and a correct rate of the network ar calculated by comparing the predicted emotion classification information with actual emotion classification information. According to the invention, the expression features and the electroencephalogram signal features are fused, redundant information is removed, training isconducted through the CNN-LSTM network, the predicted emotion classification information is obtained, and the emotion recognition accuracy is improved.

The invention discloses a multi-temporal high-resolution remote sensing image building extraction method based on a multi-feature LSTM network, and belongs to the technical field of satellite remote sensing image processing and application. The method aims to solve the problems of low accuracy, high error rate, fuzzy boundary and the like of a building extraction result of an existing method. According to the invention, a plurality of multi-temporal high-resolution No.2 remote sensing images are used as data sources; building spectral characteristics are extracted by using a method based on HSI color transformation; based on a method of combining graph segmentation and conditional random field post-processing, shape features of a building are extracted, based on a Gabor wavelet transform method, texture information features of the building are extracted, and based on a DSBI index method, index features of the building are extracted. A building characteristic set with 60 characteristicwave bands is formed by the extracted spectrum, shape, texture and index characteristics of the multi-temporal building, a manufactured building sample and a label are sent into an LSTM network to obtain a building coarse extraction result, and a final result is obtained after morphological processing.

The invention relates to a facial expression recognition feature extraction algorithm based on the Weber multi-direction descriptor. The algorithm mainly comprises the steps of: performing Gabor wavelet transform on a facial expression image and fusing Gabor features in all directions of the same scale; dividing a Gabor feature image into non-overlapping sub-blocks and building graph structures inthe horizontal direction, in the vertical direction and in the directions of two diagonals; calculating the features values of the graph structures in the direction of 0 degree, 45 degrees, 90 degrees and 135 degrees, wherein the highest one in the four feature values is used as the differential excitation of the Weber multi-direction descriptor; calculating the gradients of a central pixel in two mutually vertical directions, wherein the direction of the bigger gradient in the two gradients is used as the main direction of the Weber multi-direction descriptor. The algorithm is reasonable indesign; the algorithm can extract more effective and identifiable texture detail features, thereby remarkably improving the facial expression recognition rate; the algorithm has great recognition stability and generalization ability and can be widely applied to image processing fields such as facial expression recognition.

The invention provides a forming method and a system of a facial expression intensity calculation model. The model is used for estimating the facial expression intensity under expression classification. The method comprises the steps of acquiring an expression database firstly, preprocessing image data in the expression database, extracting the data of a face part, performing feature extraction inthe three modes of face geometric features, local binary patterns and Gabor wavelet transform respectively, training data outputted in the previous step respectively in the full-supervision mode, thesemi-supervised mode and the non-supervision mode so as to obtain the relation between a feature and a facial expression intensity, respectively adopting trained data as the input of an ordinal random forest algorithm to train the data and respectively obtain facial expression intensity calculation sub-models, and forming a final facial expression intensity calculation model according to each ofthe sub-models. According to the invention, the facial expression intensity calculation model under the expression classification is trained by means of the database. The model is used for processingimage data, so that the intensity under the trained expression classification can be obtained.

The invention discloses a face feature-based gender classifying method and a face feature-based gender classifying device. The face feature-based gender classifying method comprises the following steps: preprocessing a face image based on eye positioning coordinates; performing image scaling on the face image to form a multi-resolution Gaussian pyramid; performing Gabor wavelet transform for different scales and directions; performing local binary pattern transformation on the Gabor face image, and equably dividing the face image in horizontal and vertical directions; extracting histogram dataof each region of the Gabor local binary pattern face image; acquiring sample data with male and female tags in multi-resolution local Gabor binary pattern MLGBP features, and reducing the dimensionof a central connecting line for a feature vector of each divided region; training in a gender classifying model based on a support vector machine to obtain the gender classifying model; inputting thefeatures into the gender classifying model to obtain an analysis result.

A front gait recognition method based on feature fusion belongs to the technical field of mode recognition. The method mainly aims at solving the problem that the gait recognition rate of a single feature is low, firstly, a dynamic region in a gait energy diagram is extracted, features are extracted through Gabor wavelet transform, dimension reduction processing needs to be conducted due to the fact that the extracted features are high in dimension, and for the defect that traditional PCA dimension reduction classification is poor, dimension-reduced data serve as static features. The gait period is obtained according to the change of the ratio of the number of pixel points on the left side to the number of pixel points on the right side of the lower quarter area of the human body and used for describing the dynamic characteristics of the gait sequence, and based on the idea of characteristic fusion, static data characteristics obtained after PCA and LDA dimension reduction are fused with the dynamic characteristics describing the gait sequence for the first time; and finally, inputting the fused feature vectors into a support vector machine based on multi-classification to finish gait classification and recognition. Compared with a gait recognition method with a single feature, the fusion algorithm provided by the invention shows better recognition performance.

The invention discloses a facial expression recognition method and device based on Gabor wavelets. The method comprises the following steps: carrying out graying and size normalization processing on an input image; according to a preset gray average value and a gray variance, carrying out gray equalization processing on the image after graying and size normalization processing, and the image aftergray equalization processing is used as a to-be-identified image; carrying out Gabor wavelet transform on the image to be identified by adopting a two-dimensional Gabor wavelet filter bank; extracting an expression feature vector of the to-be-recognized image; and carrying out matching identification on the extracted expression feature vector by using a non-uniform elastic grid template. The device comprises a preprocessing module, a feature extraction module and an identification matching module. According to the invention, the Gabor wavelet filtering is improved, the interference is effectively reduced, the recognition rate is greatly improved, and the operation time is greatly reduced.

The invention provides a face feature and dynamic attribute authentication method based on a WeChat applet platform, and relates to the technical field of biological recognition, information securityand control science, and the method comprises the following steps: S1, collecting a face image of a user through a smart phone, detecting face key points, and registering face information; S2, collecting a user face video frame through a smart phone, judging a face posture through face key points, carrying out blink detection on the video frame under the assistance of Gabor wavelet transform, andfinally carrying out face comparison; and S3, performing security judgment on the authentication request through a key authentication system. According to the invention, a dynamic face recognition authentication mode is adopted; in combination with a security authentication mode of a key authentication system, the defects of single face authentication are overcome, a face recognition function is added by utilizing a smart phone, password-based customer authentication is expanded into an authentication system organically combining identity authentication of dynamic face recognition and customerpassword authentication, and the security and reliability of authentication operation are improved.