488 results about "Gabor filter" patented technology

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

A robot includes a face extracting section for extracting features of a face included in an image captured by a CCD camera, and a face recognition section for recognizing the face based on a result of face extraction by the face extracting section. The face extracting section is implemented by Gabor filters that filter images using a plurality of filters that have orientation selectivity and that are associated with different frequency components. The face recognition section is implemented by a support vector machine that maps the result of face recognition to a non-linear space and that obtains a hyperplane that separates in that space to discriminate a face from a non-face. The robot is allowed to recognize a face of a user within a predetermined time under a dynamically changing environment.

Fingerprint recognition and matching systems and methods are described that utilize features at all three fingerprint friction ridge detail levels, i.e., Level 1, Level 2 and Level 3, extracted from 1000 ppi fingerprint scans. Level 3 features, including but not limited to pore and ridge contour characteristics, were automatically extracted using various filters (e.g., Gabor filters, edge detector filters, and / or the like) and transforms (e.g., wavelet transforms) and were locally matched using various algorithms (e.g., the iterative closest point (ICP) algorithm). Because Level 3 features carry significant discriminatory and complementary information, there was a relative reduction of 20% in the equal error rate (EER) of the matching system when Level 3 features were employed in combination with Level 1 and Level 2 features, which were also automatically extracted. This significant performance gain was consistently observed across various quality fingerprint images.

A facial expression recognition system that uses a face detection apparatus realizing efficient learning and high-speed detection processing based on ensemble learning when detecting an area representing a detection target and that is robust against shifts of face position included in images and capable of highly accurate expression recognition, and a learning method for the system, are provided. When learning data to be used by the face detection apparatus by Adaboost, processing to select high-performance weak hypotheses from all weak hypotheses, then generate new weak hypotheses from these high-performance weak hypotheses on the basis of statistical characteristics, and select one weak hypothesis having the highest discrimination performance from these weak hypotheses, is repeated to sequentially generate a weak hypothesis, and a final hypothesis is thus acquired. In detection, using an abort threshold value that has been learned in advance, whether provided data can be obviously judged as a non-face is determined every time one weak hypothesis outputs the result of discrimination. If it can be judged so, processing is aborted. A predetermined Gabor filter is selected from the detected face image by an Adaboost technique, and a support vector for only a feature quantity extracted by the selected filter is learned, thus performing expression recognition.

The invention belongs to the technical field of vehicle identification and particularly discloses a number plate identification method and an identification system of the number plate identification method. The method comprises the steps of number plate image positioning, character separation and character identification, wherein the character identification step comprises pre-treatment, coarse classification, Chinese character identification and number and letter identification. Through the improvement on a Chinese character identification method (through a Gabor filter and a minimum distance classifier) and a number and letter identification method (based on correlation feature selection (CFS) and a Bayes classifier), the number plate Chinese character identification rate and the number plate number and letter identification rate are greatly improved.

The invention relates to a texture-based insulator fault diagnostic method. According to the invention, a visible light image collected in the inspection process of a high voltage transmission line by a helicopter is used as an object to be processed, and the diagnosis can be carried out based on an insulator fault of the visible light image. The method comprises the following steps of: inputting an insulator image, carrying out gray processing, obtaining a bounding rectangle and rotating, carrying out a GLCM (gray level co occurrence matrix) method, blocking, obtaining textural features, carrying out Gabor filtering, blocking, calculating block-mean value and variance, performing feature fusion, and determining whether to have a string-drop phenomenon based on a threshold value. The method provided by the invention diagnoses the insulator string-drop characteristic by texture, integrates the thoughts of the most classical GLCM texture diagnostic method in the texture diagnosis and the recent research focus Gabor filter texture diagnosis, adjusts the parameter settings of the GLCM and the Gabor filter and efficiently and accurately finds out the string-drop insulators. The method can effectively improve the efficiency of the thermal defect detection of the power transmission line and can be effectively applied to the inspection business of the vehicle-mounted or helicopter power transmission line.

The invention discloses a contour extraction method based on the brightness characteristic and the contour integrity, and belongs to the crossing field of computer vision and pattern recognition. The contour extraction method aims to completely extract a contour of an object out of a complex environmental background. The contour extraction method includes the step of obtaining a maximum energy response diagram, the step of carrying out non-classic receptive field restraint on brightness characteristic modulation, the step of extracting the contour of the object and carrying out postprocessing on a high-low self-adaptive threshold value and the like based on a probability model, and the step of processing the nearest neighbor orientation consistency connection rupture contour based on the contour integrity. A Gabor filter is used for simulating response of a human simple cell classic receptive field to obtain the maximum Gabor energy response diagram; the brightness characteristic of images is used for restraining the maximum Gabor energy response diagram and rejecting grain and other non-target contours; the postprocessing on the high-low self-adaptive threshold value and the like based on the probability model is carried out on the obtained target contour; rupture points of the nearest neighbor orientation consistency connection contour based on the contour integrity are processed. The contour of the object can be extracted well, and a contour diagram of integrity connection is obtained after the contour of the object is processed.

An object detection apparatus is provided for detecting both stationary objects and moving objects accurately from an image captured from a moving mobile unit.The object detection apparatus of the present invention applies Gabor filter to two or more input images captured by an imaging device such as CCD camera mounted on a mobile unit, and calculates optical flow of local areas in the input images. Then the object detection apparatus closely removes optical flow produced by motion of the mobile unit by estimating optical flow produced from background of the input images. In other words, the object detection apparatus clarifies the area where object is not present (“ground”) in the input images. By removing such “ground” part, the area where objects seems to be present (“feature”) is extracted from the input images. Finally, the object detection apparatus determines whether objects are present or not using flow information of the extracted “feature” part.

The invention provides an image recognition method based on biological vision and a precise pulse drive neural network. The method is enlightened by a biological vision layering system, on a feature extraction part of an image, an HMAX model is adopted for simulating and sensing a wild cell running mechanism, Gabor filtering is firstly utilized for enhancing marginal information of an image, images obtained after Gabor filtering in various directions are subjected to max pooling processing, and the aims of extracting major features and carrying out dimension reduction processing are achieved. According to the feature image data processing method, a phase encoding method is selected, pixel information of the images is converted into a pulse phenomenon, thus, space information of the images is considered, and time information of the images is also considered. The method has certain biological basis, and has good feasibility and robustness, and the accuracy of image recognition and classification, especially in noise images is greatly improved.

The invention relates to the field of image identification, in particular to a deep learning-based image fuzzy region detection method and apparatus. The invention provides the deep learning-based image fuzzy region detection method and apparatus for the problems existent in the prior art. The method mainly comprises the following steps of creating a sample picture set; performing gabor filtering and creating a 4-channel image according to multi-scale information; constructing a deep convolutional network to learn image characteristics, performing training by taking the obtained sample 4-channel image as an input of the deep convolutional network, and generating an optimal model of a deep learning network; performing regional small block extraction on an image required to be identified, establishing a 4-channel image, inputting the established 4-channel image in the optimal model of the deep learning network, and obtaining a classification result; and analyzing the classification result to obtain a fuzzy attribute and a clear region of the to-be-identified image.

The invention relates to the field of fingerprint image processing, in particular to a fingerprint image orientation enhancement method. The technical proposal adopted in the invention comprises the following steps of: 1) adding a step of Gabor pre-filtering, adjusting filtering parameters again after conducting preliminary directional filtering enhancement on the original image, and conducting secondary accurate Gabor filtering; and 2) adopting a self-adaptive measure of a Gabor filter transmission band to calculate respective numerical characteristics of the original fingerprint image and the pre-filtered fingerprint image and dynamically adjust the width of the filter transmission band. The fingerprint image orientation enhancement method has the beneficial effects: 1) the method improves the defects of the prior art that filtering is only implemented for once, the filtering parameter is an fixed experience value, and the filtering effect is too rough; 2) fingerprint ridges obviously separate, the edges of the ridges are smooth, the noise points are removed from the fingerprint ridges, and the original features such as scar and the like are kept simultaneously; and 3) compared with the prior art, the uniformity and definition of the fingerprint ridges, the capability of recovering the broken ridges and the like are remarkably improved.

The invention provides a facial expression recognizing method based on Gabor transform optimal channel blur fusion, comprising the following steps of: S1, dividing a Gabor filter into 11 channels, carrying out Gabor wavelet transform on a facial expression image subjected to normalization by the Gabor filter to extract texture characteristics of the facial expression image; S2, establishing classifiers corresponding to the channels one by one, respectively sending the texture characteristics extracted from the channels into the classifiers for classifying and recognizing, calculating the recognition rate and the definition of each classifier to various expressions, selecting 4 classifiers with top comprehensive ranking of the recognition rate and the definition to be used as optimal classifiers; and S3, carrying blur fusion on the four optimal classifiers to obtain a facial expression recognition result. The facial expression recognition method has the advantages of small calculated amount, high calculating speed and high recognition precision.

The invention provides a synthetic aperture radar (SAR) image bionic recognition method based on sample generation and nuclear local feature fusion and belongs to the field of image processing technologies and SAR target recognition. According to the method, a super complete training sample set is firstly constructed for training to obtain geometry manifold, then a sample to be recognized is recognized, specifically, each sample is firstly subjected to image denoising by a K-SVD dictionary learning method, and object region extraction is achieved by means of an object centroid method; and feature extraction is performed respectively by combining local phase quantization (LPQ) and a Gabor filtering method, feature fusion is performed, finally, classification is performed by covering of high-dimensional geometry manifold, and recognition is performed by a bionic mode. According to the SAR image bionic recognition method based on sample generation and nuclear local feature fusion, inhibiting effects of image coherent noises are obvious, SAR image features can be effectively extracted, the problem of the unstable extracted features, which is caused by changes of attitude angles of SAR images, is solved, the recognition accuracy is high, and the method has good robustness.

A Gabor filter is approximated as a block-Gabor filter. The Gabor filter is represented by a matrix of numbers in which each number is a sample derived from a continuous Gabor function. The block-Gabor filter is partitioned into a set of blocks. Identical filter values are assigned to all the pixels in any particular block based on the Gabor filter. Then, a feature can be extracted from an image by filtering the image with a set of the block-Gabor filters to obtain a corresponding set of filtered images. Each filtered image is partitioned into regions of pixels. For each pixel, an N-bit signature is determined. Histograms of the N-bit signatures of the pixels in each region are combined to form the feature. The features of multiple images can be used for face recognition.

A statistical system and method for generating patterns and performing online handwriting recognition based on those patterns. A plurality of predetermined patterns may be generated by performing feature extraction operations on one or more character samples utilizing a Gabor filter. An online handwritten character may be acquired. The online handwritten character may be pre-processed. One or more feature extraction operations, utilizing a Gabor filter, may be performed on the online handwritten character to produce a feature vector. One or more patterns may be generated, using a statistical algorithm, for the online handwritten character, based on the feature vector. The online handwritten character may be statistically classified based on a comparison between the one or more patterns generated for the online handwritten character and the plurality of predetermined patterns.

A face recognition apparatus and method. Sub-images having different face sizes are generated using a received face image of a person to be identified. Feature vectors of the sub-images are generated and observation nodes are generated based on the feature vectors. The observation nodes corresponding to the sub-images are compared with stored reference nodes of sub-images of a registered person on a face size by face size basis to calculate similarity scores between the observation nodes and the reference nodes. State nodes are generated based on the respective similarity scores of the face sizes, the observation and state nodes are compared, and the state nodes are compared to perform face recognition. This improves face recognition performance and face recognition speed. Face recognition performance robust to facial expression variation or type information is achieved by performing I-shaped curvature Gabor filtering on a plurality of sub-images based on the eye distance.

The invention discloses a design patent image retrieval method with multi-characteristic fusion. The method comprises the steps: according to the characteristics of the design patent image, designing a characteristic extracting method and the process of image retrieval; in the aspect of characteristic extraction, adopting a method for fusing the whole characteristics and local characteristics, and adopting a boundary direction histogram algorithm and structural characteristics to describe the shape characteristics; adopting a Gabor filter algorithm and a blocking characteristic statistical method to extract textural characteristics, and in the process of image retrieval, firstly adopting geometrical characteristics for comparison, and screening the images according to threshold values; and secondly using the shape characteristics and the textural characteristics to carry out similarity matching, and sorting and returning the images according to the size of similarity. The invention provides the design patent image retrieval method with high efficiency and high accuracy by extraction of wholly and locally more comprehensive characteristics of the design patent images and step screening in the retrieval process.

The invention discloses a fingerprint identification method. The fingerprint identification method comprises steps that a fingerprint image is segmented and filtered, the pre-processing steps comprise a segmentation sub step and a filtering sub step, for the segmentation sub step, the Harris corner energy of each pixel of the fingerprint image is calculated, the Harris corner energy smaller than a preset threshold is filtered to acquire a binary graph, and expansion and corrosion processing on the binary graph is carried out; for the filtering sub step, the direction field, the frequency field and the curvature field of the binary graph are respectively calculated, and a Log-Gabor filter is utilized to filter the processed binary graph. Through the method, computational complexity is reduced through the fingerprint method. The invention further provides a fingerprint identification system.

The invention discloses a facial expression recognition method based on an ELM. The method comprises the steps that a facial expression image is processed to obtain a facial region, image segmentation is conducted on an expression region containing expression features to obtain an eye expression region body, a nose expression region body and a lip expression region body, then Gabor filters are used for conducting expression feature extraction on the expression region bodies to obtain a total feature vector of each expression, the obtained expression feature vectors are used for training ELM models, the ELM models for all the expressions are combined to form an ELM expression classifier, and at last, the ELM classifier is tested to achieve the purpose of expression classified recognition. The facial expression recognition method based on the ELM increases the expression recognition rate on the condition that illumination influences are avoided.

The invention provides a user registration authentication method and a system based on facial features. The user registration authentication method is characterized by comprising the following steps: (1) obtaining a facial picture through a camera, conducting AdaBoost detection, gray level conversion and Gabor filtering to the facial picture, and obtaining facial information, (2) generating a login name and a secret key through combination of the new facial information input by a user and a realm name, and filling the login name and the secret key into a login form, and (3) when the user logs in, requiring content of the login form according the facial information, detecting whether the user is a registered user, if the user is the registered user, logging in successfully, modifying the secret key, and if the user is a unregistered user, conducting the step (1). According to the user registration authentication method and the system based on the facial features, the facial information and a secret system are combined, the process of authentication identification is enabled to be guaranteed, and meanwhile convenience is brought to use.

The invention discloses a finger multimodal preprocessessing method based on maximum circumscribing matrix region-of-interest extract and bilateral filtering. The method comprises the following steps: firstly, gathering finger vein and finger phalangeal print images; secondly, performing finger multimodal preprocessessing on the gathered images, based on maximum circumscribing matrix region-of-interest extract and bilateral filtering, and removing background areas in the finger images through binaryzation, obtaining a final finger vein ROI area by solving the maximum circumscribing matrix among key areas, and then cutting an finger phalangeal print ROI area in the finger phalangeal print image according to the finger vein ROI area; finally normalizing the images, and performing filtering on the normalized images through a bilateral filter; thirdly, performing image layer fusion on the processed images, based on wavelet transform and Gabor filtering. The method is rich in information and high in security.

The invention provides a face authentication method and device, and belongs to the field of image processing and pattern recognition. The method comprises the following steps: extracting Gabor texture features of an acquired face image sample pair through a Gabor filter, and separating real parts from virtual parts of the extracted Gabor texture features to obtain a plurality of feature graphs; summarizing the plurality of obtained feature graphs through an LBP (Local Binary Pattern) statistical histogram to serve as face feature expression of the face image pair; performing feature selection on the face feature expression of the face image sample pair through an AdaBoost (Adaptive Boosting) algorithm; and performing feature dimension reduction, feature judgment processing and the like on the face feature expression of the face image sample pair subjected to the feature selection through a PCA (Principal Components Analysis) algorithm and an LDA (Linear Discriminant Analysis) algorithm in sequence. Compared with the prior art, the face authentication method provided by the invention has the advantages of full extraction of sample texture information, low sample quantity demand, short algorithm time and low space complexity.

The invention relates to a facial expression recognition and interaction method based on GPU acceleration, and belongs to the field of mode recognition. The method establishes a method framework of rapidly recognizing micro-expression based on GPU acceleration. The method comprises: firstly, acquiring user facial images through an ordinary camera or a video, performing facial detection and facial feature point recognition by using a recognition method based on Haar characteristics and AdaBoost, to recognize position coordinates of user pupils, apex nasi, etc., dividing a face into a plurality of critical areas, using a Gabor filtering method based on GPU acceleration, performing Gabor filtering on the whole face in five dimensions and eight directions, and performing feature extraction on the critical areas near the facial feature points. According to the method, features of CK, CK+, MMI extracted from a database are marked in labels according to whether micro-expression occurs or not, and through putting the features with the labels to a SVM, a recognition model is obtained. A user puts the extracted features into the recognition model to obtain specific information of the micro-expression.

In a face recognition apparatus adapted to recognize an input face image on the basis of one or more registered face images, similarity between an input face image and a registered face image is determined based on a Gabor jet calculated by performing Gabor filtering using Gabor filters defined by a Gaussian function representing a window and sine and cosine functions representing a frequency response for each of predetermined frequency values and for each of predetermined angles of the response function. Values of the filter window are calculated in advance based on the Gaussian function and stored in a filter window data ROM. Values of the response function are calculated in advance for respective angles based on the sine and cosine functions and stored in sine data ROMs and cosine data ROMs. In the Gabor filtering process, coefficients of the Gabor filters are determined from values read from these ROMs.

The invention discloses a gesture detecting method for a human face and an application of the gesture detecting method in human face identification, and relates to human face identification. The method comprises the following steps: classifying images in a training set, calculating a gesture estimation filter group corresponding to three human face gestures according to HOG (Histograms of Oriented Gradients) characteristic of the training set; calculating an identifying filter group corresponding to three human face gestures through Gabor characteristic of the training set; and judging the gesture direction of the human face in the image according to HOG characteristic of a test picture and identifying by means of corresponding identifier filer group. The human face gesture is divided into three types: a left gesture human face, a front gesture human face and a right gesture human face. HOG and Gabor characteristics of the three human face gestures are respectively extracted. Noise and dimension are reduced for HOG and Gabor characteristics of the three human face gestures by PCA (Principal Component Analysis) respectively. The contour information of each type of human face is extracted. The HOG characteristic of the test image is extracted and the gesture direction of the human face is judged by the information. The test image is identified by corresponding Gabor filter group according to the gesture direction of the tested human face.

The invention discloses a method for re-identifying vehicles in sequence images of a mentoring video. The method comprises the following steps of performing image feature extraction: for all shot video data, firstly detecting out vehicle images appearing under a camera, dividing the vehicle images of the monitoring video into a plurality of equilong vehicle image sequences according to the vehicles and the camera, calculating grayscale histograms of two channels Cr and Cb in a YCrCb space, and finally obtaining vehicle contour images by using a Gabor filter and original image convolution; performing a set-to-set-based metric learning method: training a step of learning a metric function of relative distances between vehicle target image sequences, namely, performing metric learning based on a thought of maximization of a probability that inner-class distances are shorter than between-class distances; and performing between-set metric learning-based vehicle re-identification. According to the method, the complexity of an algorithm is lowered while feature dimensions are reduced; and after between-set distance measure is added based on a re-identification effect, the identification rate of the algorithm is increased and the identification effect is improved.

The invention describes a three-dimensional face recognition device based on three-dimensional point cloud and a three-dimensional face recognition method based on three-dimensional point cloud. The device includes a feature region detection unit used for locating a feature region of the three-dimensional point cloud, a mapping unit used for mapping the three-dimensional point cloud to a depth image space in a normalizing mode, a statistics calculation unit used for conducting response calculating on three-dimensional face data in different scales and directions through Gabor filters having different scales and directions, a storage unit obtained by training used for storing a visual dictionary of the three-dimensional face data, a map calculation unit used for conducting histogram mapping on the visual dictionary and a Gabor response vector of each pixel, a classification calculation unit used for roughly classifying the three-dimensional face data, a recognition calculation unit used for recognizing the three-dimensional face data.

The invention discloses a non-reference asymmetric distorted stereo image objective quality assessment method. The method comprises the following steps: firstly, filtering a left viewpoint image and a right viewpoint image of a to-be-assessed asymmetric distorted stereo image respectively by virtue of a Gabor filter and a Gaussian filter so as to obtain corresponding Gabor filter image and Gaussian image; then, establishing a valid mathematical model integrated with asymmetric distorted stereo visual perception characteristics by simulating a human visual system, and obtaining a left and right viewpoint characteristic integrated image of the to-be-assessed asymmetric distorted stereo image according to the mathematical model; then, carrying out local binarization model operation on the left and right viewpoint characteristic integrated image so as to obtain a local binarization model structural characteristic image, and obtaining a histogram statistic characteristic vector by virtue of a histogram statistic method; and finally, according to the histogram statistic characteristic vector, forecasting an objective quality assessment predicted value by virtue support vector regression. The objective quality assessment method disclosed by the invention has the advantage that the correlation between an objective assessment result and subjective perception can be effectively improved.

The invention discloses a three-dimensional face recognition device and method based on three-dimensional point cloud; the device comprises a characteristic area detection unit for positioning a three-dimensional point cloud characteristic area; a mapping unit for normalized mapping the three-dimensional point cloud to a depth image space; a data calculating unit using Gabor filters in different dimensions and directions to calculate responses in different dimensions and directions of three-dimensional face data; a storage unit for training a visual dictionary of the obtained three-dimensional face data; a mapping calculating unit for implementing histogram projection to the visual dictionary with respect to the Gabor response vector obtained by each pixel; a classification calculating unit for coarse classification of the three-dimensional face data; and an identification calculating unit for identifying the three-dimensional face data. By employing the disclosed technical scheme, the detail texture description ability of the three-dimensional data is stronger, and the adaptability to the quality of the input three-dimensional point cloud face data is better, thus the application foreground is better.