73 results about "Fisher vector" patented technology

An apparatus and method for detecting a region of interest in an image are disclosed. Image representations for a set of images that have been manually annotated with regions of interest are stored, along with positive and negative representations of each image which are similarly derived to the image representations except that they are based on features extracted from patches within the region of interest and outside it, respectively. For an original image for which a region of interest is desired, the stored information for K similar images is automatically retrieved and used to train a classifier. The trained classifier provides, for each patch of the original image, a probability of being in a region of interest, based extracted features of the patch (represented, for example, as a Fisher vector), which can be used to determine a region of interest in the original image.

In an image classification method, a feature vector representing an input image is generated by unsupervised operations including extracting local descriptors from patches distributed over the input image, and a classification value for the input image is generated by applying a neural network (NN) to the feature vector. Extracting the feature vector may include encoding the local descriptors extracted from each patch using a generative model, such as Fisher vector encoding, aggregating the encoded local descriptors to form a vector, projecting the vector into a space of lower dimensionality, for example using Principal Component Analysis (PCA), and normalizing the feature vector of lower dimensionality to produce the feature vector representing the input image. A set of mid-level features representing the input image may be generated as the output of an intermediate layer of the NN.

The invention discloses a track and convolutional neural network feature extraction-based behavior identification method, and mainly solves the problems of computing redundancy and low classification accuracy caused by complex human behavior video contents and sparse features. The method comprises the steps of inputting image video data; down-sampling pixel points in a video frame; deleting uniform region sampling points; extracting a track; extracting convolutional layer features by utilizing a convolutional neural network; extracting track constraint-based convolutional features in combination with the track and the convolutional layer features; extracting stack type local Fisher vector features according to the track constraint-based convolutional features; performing compression transformation on the stack type local Fisher vector features; training a support vector machine model by utilizing final stack type local Fisher vector features; and performing human behavior identification and classification. According to the method, relatively high and stable classification accuracy can be obtained by adopting a method for combining multilevel Fisher vectors with convolutional track feature descriptors; and the method can be widely applied to the fields of man-machine interaction, virtual reality, video monitoring and the like.

The invention relates to a human movement significant trajectory-based video classification method. The human movement significant trajectory-based video classification method comprises the following steps that: a video set M is divided into a training set Mt and a test set Mv, and human movement information in each video is tracked in a multi-scale space by using SIFT and dense optical flow technologies, so that movement significant trajectories in each video can be obtained; feature description vectors of each trajectory are extracted; redundant information in the feature description vectors are eliminated through using a PCA method, and dimension reduction is performed on each class of feature description vectors; the feature description vectors in the training set Mt are clustered by suing a Gauss mixture model, and then, Fisher vectors of each video in the video set M are generated by using a Fisher Vector method; a linear SVM classification model is constructed on the training set Mt; and on the test set Mv, videos in the test set are classified through using the linear SVM classification model. Compared with the prior art, the human movement significant trajectory-based video classification method of the invention has the advantages of excellent robustness, higher computational efficiency and the like.

The invention relates to an automatic recognition method of the standard section of the fetus face of an ultrasound image. The method includes the following steps that the original ultrasound image is preprocessed; features of the preprocessed ultrasound image are extracted through RootSIFI; the extracted features are transformed through a Gaussian mixture model, Fisher vector encoding is performed on the transformed Gaussian mixture model, and values of a vector encoding histogram are obtained; normalization is performed on the histogram to obtain feature vectors; the standard sector is learned and recognized according to the feature vectors through an SVM classifier based on a random dual coordination mechanism. The invention further relates to an automatic recognition system of the standard section of the fetus face of the ultrasound image. Through the method and system, the accuracy of the diagnosis result obtained by a doctor can be improved, workloads can be reduced, and diagnosis time can be shortened.

The invention discloses a three-dimensional depth data based dynamic gesture recognition method, which can improve the recognition effect of the dynamic gesture recognition and Includes such steps asobtaining a dynamic gesture sequence to be recognized by a somatosensory controller Leap Motion, obtaining position coordinates of each skeletal joint in each effective frame of the dynamic gesture sequence to be recognized, and extracting a hand shape change feature vector and a motion direction feature vector frame by frame; solving the Fisher vector coding form of the hand shape change featurevector by a Gaussian mixture model; extracting feature vectors containing test gesture sequence local time information by using a time pyramid model; and classifying the feature vectors containing to-be-recognized gesture sequence local time information by a support vector machine SVM, matching with known feature vectors with local time information in an existing dynamic gesture database, and taking a dynamic gesture corresponding to the matching result as a recognition result.

In an image classification method, a feature vector representing an input image is generated by unsupervised operations including extracting local descriptors from patches distributed over the input image, and a classification value for the input image is generated by applying a neural network (NN) to the feature vector. Extracting the feature vector may include encoding the local descriptors extracted from each patch using a generative model, such as Fisher vector encoding, aggregating the encoded local descriptors to form a vector, projecting the vector into a space of lower dimensionality, for example using Principal Component Analysis (PCA), and normalizing the feature vector of lower dimensionality to produce the feature vector representing the input image. A set of mid-level features representing the input image may be generated as the output of an intermediate layer of the NN.

The invention discloses a scene recognition method based on convolution multi-features and deep random forest. A sparsely coded spatial pyramid matching method and a Fisher vector are applied to a convolutional neural network (CNN) for feature extraction and the extracted features are applied to the scene recognition method for the deep random forest to improve scene recognition accuracy. The method includes training a training image by using the CNN, performing Fisher vector encoding on the output of the last convolutional layer in the CNN, deconvolving the output of the CNN, calculating theimage feature point distribution of the output at different resolutions by using the spatial pyramid matching method to form a multi-scale spatial local feature, and then using the deep random forestfor classification, thereby improving scene recognition accuracy.

Methods, systems and processor-readable media for vehicle classification. In general, one or more vehicles can be scanned utilizing a laser scanner to compile data indicative of an optical profile of the vehicle(s). The optical profile associated with the vehicle(s) is then pre-processed. Particular features are extracted from the optical profile following pre-processing of the optical profile. The vehicle(s) can be then classified based on the particular features extracted from the optical feature. A segmented laser profile is treated as an image and profile features that integrate the signal in one of the two directions of the image and Fisher vectors which aggregate statistics of local “patches” of the image are computed and utilized as part of the extraction and classification process.

An embodiment of the invention discloses an image identification method and device and relates to the technical field of image processing. The method comprises the following steps: carrying out image enhancement on an obtained image to be identified to obtain an enhanced image to be identified; carrying out feature extraction on the enhanced image to be identified according to a preset deep residual neural network to obtain feature information; carrying out Fisher vector coding on the feature information to obtain a Fisher feature vector; and then, identifying the image to be identified according to a preset classifier and the feature vector to obtain an identification result. Therefore, more identification features of the image to be identified can be extracted by utilizing the deep residual neural network and Fisher vector coding; and then, the features are subjected to classification processing, and the image to be identified can be identified quickly according to the classification result. The method is simple to operate, is more efficient and more accurate, and is high in applicability.

The invention discloses an improved method for learning discriminative segments in fine-grained identification. The method comprises the following steps of: extracting segments with discrimination properties in an original image: obtaining a feature map by the original image through a convolutional pooling layer in a convolutional neural network, considering a vector of each space fixed position as a detector of a corresponding position segment in the original image, assuming that a detector, a discriminative region of which has highest response, in the original image is learnt, carrying out convolutional operation on the detector and the feature map so as to obtain a new response map, and selecting a position with a maximum value in the new response map so as to obtain the segments with discriminative properties; and learning features of the segments with the discriminative properties and carrying out classification by using the features: obtaining a local saliency map according to the segments with the discriminative properties, and encoding the local saliency map by using a space weighted Fisher vector. The method is capable of learning discriminative features more suitable forfine-grained identification tasks, and decreasing the interferences of background information in the discriminative segments so as to improve the classification precision.

The invention discloses a cross-media Chinese herbal medicine plant image searching method based on deep learning. The method comprises the following steps that 1, on the basis of OCR, text structural processing is performed, and plant classification description characters are extracted from books such as 'plant taxonomy'; 2, a Chinese word segmentation tool is used for performing preprocessing including word segmentation and stop word removal on all plant classification description characters; 3, a word2vec algorithm is used for generating word vectors according to a description text; 4, Fisher Vector is used for encoding the description text; 5, a convolutional neural network is used for performing training on an image set, and the network structure is made to converge to the best state; 6, the full last but one connection layer output of the convolutional neural network is extracted as an image feature vector; 7, textual features and image features are fused; 8, a linear kernel SVM classifier is used for performing model training; 9, during user retrieval, images can be input, plant texts can be described, and then a final image retrieval result is obtained through the steps 4, 6, 7 and 8.

A cross-media search method using a VGG convolutional neural network (VGG net) to extract image features. The 4096-dimensional feature of a seventh fully-connected layer (fc7) in the VGG net, after processing by a ReLU activation function, serves as image features. A Fisher Vector based on Word2vec is utilized to extract text features. Semantic matching is performed on heterogeneous images and the text features by means of logistic regression. A correlation between the two heterogeneous features, which are images and text, is found by means of semantic matching based on logistic regression, and thus cross-media search is achieved. The feature extraction method can effectively indicate deep semantics of image and text, improve cross-media search accuracy, and thus greatly improve the cross-media search effect.

The invention discloses a micro expression recognition method based on optical flow and Fisher Vector coding. The method comprises the following steps that: HOF (Histogram of Oriented Optical Flow) feature extraction is performed on a micro expression image sequence in a test sample, and first feature data X which are expressed by an equation described in the descriptions of the invention are obtained; Fisher Vector coding is performed on the first feature data X, so that second feature data F are obtained; and the second feature data F are identified based on a pre-trained classifier. According to the micro expression recognition method of the invention, the optical flow features are adopted to describe the micro movement of a micro expression; the optical flow features are coded through using Fisher Vector, so that desired information and variance information can be obtained; and therefore, the features of the micro expression can be expressed more fully, the influence of local noises can be reduced, and the robustness of the features of the micro expression can be improved, and the recognition rate of the micro expression can be improved.

A system for detecting a vehicle occupancy violation includes an image capture module that acquires an image including a vehicle cabin from a camera positioned to view oncoming traffic. The system includes a violation determination device, which includes a feature extraction module that processes the image pixels for determining an image descriptor. The process is selected from a group consisting of a Successive Mean Quantization Transform; a Scale-Invariant Feature Transform; a Histogram of Gradients; a Bag-of-Visual-Words Representation; a Fisher Vector Representation; and, a combination of the above. The system further includes a classifier that determines a distance that the vehicle image descriptor / representation is positioned in the projected feature space relative to a hyper-plane. The classifier determines whether the distance meets a threshold and classifies the image when the threshold is met. A processor implements the modules. A graphic user interface outputs the classification.

The invention discloses a spatial Fisher vector based image classification method which mainly solves the problems of 'foreground and background visual ambiguities' of images and lack of feature point space distribution information in image description vectors in the prior art. The method includes the implementation steps: (1) extracting 'scale-invariant feature transformation' feature points of all images; (2) in a feature point space of images in a training set, clustering the feature points by the aid of a Gaussian hybrid clustering algorithm to obtain a code book; (3) utilizing gradient vectors and Cholesky components for generating a Fisher vector of each image; (4) performing 2X2 space region division on each image, and making statistics on number of feature points and coordinates of each cell block; (5) utilizing a Fisher vector of each cell block for stitching to generate a space Fisher vector of each image; and (6) utilizing a support vector mechanism for constructing a classification hyperplane to achieve image classification. The method has the advantages that image information can be described accurately, accuracy rate of image classification is improved, and the method can be used for large-scale image classification and retrieval system construction.

The invention discloses a figure behavior identification method based on random projection and Fisher vectors. The method employs a random projection theorem method to replace a principal component analysis method for characteristic dimension reduction, for the purpose of solving the problems of large time consumption, indeterminate reservation of principle components and the like. A random projection theorem indicates that through a compression measurement matrix, original signals with a sparse property can be projected to a certain low-dimension subspace, and the point distance between a vector after mapping and an original high-dimension characteristic vector maintains basically unchanged, i.e., data distortion is not generated in a whole compression process. Besides, different from hard division of a BoW model, the method provided by the invention employs a GMM-Fisher vector hybrid model for soft division of locus characteristic vectors, is integrated with the characteristics of a Fisher nucleus generation mode and a discrimination mode, can calculate the occurrence frequency of each characteristic descriptor, can also describe the probability distribution conditions of these characteristic descriptors in the perspective of statistics, enriches characteristic expression of behavior motion and also improves the behavior identification efficiency.

The invention provides an iris image classification method. The method comprises steps that a sample iris image is processed at a construction stage of an iris texture primitive, and the iris texture primitive is acquired; an iris classifier is constructed based on the iris texture primitive and a support vector machine at a construction stage of the iris classifier; target iris images are classified through utilizing the iris classifier at a discrimination stage. The method is advantaged in that iris image classification can be effectively accomplished, high effectiveness and security of iris identification are improved; characteristics acquired through depth learning are utilized to replace characteristics acquired through traditional manual design to extract the iris texture primitive, high precision, high robustness and high reliability are realized, and the method is suitable for iris image classification of multiple application demands such as in vivo detection, race recognition and sex identification; a system safety problem and a large-scale data retrieval problem existing in an iris system productization process are effectively solved.

The invention discloses an RGB-D object identification method which comprises the following steps of acquiring a gray scale image which is generated by a color image, and a surface normal vector thatis generated by a depth image, using the color image, the gray scale image, the depth image and the surface normal vector as multi-data mode information; respectively extracting high-layer characteristics in the color image, the gray scale image and the surface normal vector through a convolutional-recurrent neural network; extracting the high-layer characteristic of the depth image by means of aconvolutional-Fisher vector-recurrent neural network; and performing characteristic fusion on the plurality of high-layer characteristics, obtaining a total characteristic of the object, and inputtingthe total characteristic of the object into a characteristic classifier for realizing an object identification task. According to the RGB-D object identification method, a plurality of data modes arecombined; more accurate RGB-D object characteristics are extracted; and furthermore object identification accuracy is improved.

The invention discloses a model identification method based on video Fisher vector descriptors. The method comprises the following steps: first of all, tacking a vehicle for training, tracking an image of each model in a video, and extracting an SIFT characteristic of each frame of the image of the model; then, performing Fisher vector coding calculation on all the SIFT characteristics of the model image; then performing PCA dimension reduction on obtained Fisher vector descriptors; then performing binarization on the descriptors after the dimension reduction to obtain the video Fisher vector descriptors of the model; performing SVM training on all the obtained descriptors to obtain an identification system with N model types; and for a vehicle video for testing, extracting the video Fisher vector descriptors of the vehicle video, introducing the video Fisher vector descriptors into a well trained SVM classifier for the testing, and identifying the model of the test vehicle video.

The invention discloses an automatic detection method of corn tassel traits. The method comprises the following steps: performing target detection on an acquired farmland corn bottom view image at first to generate a tassel candidate frame to acquire a tassel potential area; subsequently, performing feature description and target detection on the tassel by utilizing a multi-view image characteristic and a Fisher vector coding method so as to confirm an affiliated area of the tassel; further completing the segmentation on tassel fine forms by utilizing semantic segmentation based on a detection result; finally establishing a mapping relation of the image characteristic and seven biomasses, such as length trait, width trait, perimeter trait, diameter trait, tassel color trait, branch quantity trait and total tassel quantity trait which have the physical significance. According to the method, the growth state of the corn tassel can be continuously monitored in real time, so that the detection result is high in correction rate, and the method has the great significance in corn reproductive growth research, corn genomics and genetics research and yield estimation.

The invention relates to a clothes sketch input cloth material identification simulation method based on deep learning, and the method comprises the steps: obtaining a clothes sketch as a training image, and obtaining a preprocessed clothes sketch image and a corresponding cloth material image through data filtering; adopting a hand-drawn sketch identification method fusing a convolutional neuralnetwork and a Fisher vector to train a collected clothing sketch; inputting the obtained preprocessed clothing sketch image serving as training data into a convolutional neural network and Fisher vector hand-drawn sketch recognition method to obtain a clothing sketch image classification result of the cloth material image; after an obtained clothing sketch image classification result is obtained,selecting the closest real cloth according to a cloth matching algorithm to perform simulation; according to the method, the corresponding real cloth material is obtained in a simple sketch mode, andthe dynamic effect of the material cloth matched with the sketch after human body try-on is simulated in a three-dimensional mode.

The invention discloses a foundation cloud picture classification method based on a heterogeneous feature fusion network. The foundation cloud picture classification method comprises the following steps: (1) preprocessing a plurality of foundation cloud pictures with noise; (2) features of the processed foundation cloud images are extracted respectively, and a manual feature extraction method is combined with Fisher vector coding to obtain a feature vector corresponding to each foundation cloud image; (3) inputting the output of the step (2) into a four-layer full connection layer network, wherein the output of the network is recorded as fc; and (4) after the training set is amplified, training a convolutional neural network model, fusing fc with the deep semantic feature fg obtained by the last pooling layer, and obtaining a classification probability corresponding to each class through a full connection layer. According to the method, the generalization ability of a foundation cloudpicture classification and recognition task can be remarkably improved, the robustness of the model is high, visual information is combined from multiple angles, the cloud shape can be accurately positioned even if noise is manually added, and a good recognition result is obtained.

The invention relates to the technical field of medical lesion image recognition, in particular to a medical lesion image feature expression method based on region division and a Fisher vector. The method uses an expanded lesion region as a region of interest (ROI), divides the ROI into N sub regions according to the gray values of all pixels in the ROI; in each sub region, extracts small image blocks as local feature descriptors; aggregates the local feature set of each sub region into a vector by using a Fisher vector (FV) algorithm, and then connects the obtained N vectors end to end to obtain the feature expression of a medical lesion image. The feature expression method of the present invention utilizes the region information and space position information around the lesion, and uses the FV algorithm which is more effective than a conventional bag-of-word model to make the constructed feature expression more discriminative, thereby contributing to improving the accuracy of clinical adjuvant diagnosis.

The invention provides a target classifying method based on a local and depth feature assembling. The method mainly includes the steps of depth convolution feature extracting, local feature extracting, encoding and assembling through classifiers, wherein in the process, Fisher vectors of descriptors and scale invariant feature transformation (SIFT) descriptors are extracted in a final complete connection layer of a depth network, a support vector machine (SVM) is trained for each feature with the Fisher vectors as the encoding strategies, the assembling through the classifiers is trained and tested, an input data set is optimized and classified, and finally voting is conducted and a final decision is made. By means of an intermediate layer of the depth network, the classification capacityof the features obtained from the complete connection layer can be enhanced, one independent classifier is trained for each feature, and therefore good classification performance is achieved; meanwhile, computation cost is low, and various applications of the target classification technology can be easily obtained.

The invention discloses a case matching method based on semantic similarity, and the method comprises the following steps: obtaining a case word vector through the training of a Word2Vec model, and automatically extracting features from training data, i.e., extracting the features as one part of the model, thereby neglecting the particularity of a case text. According to the method, the keywords of the case are automatically extracted on the basis of the case word vector, and through converting multiple examples into a single example, a plurality of keyword vectors are converted into fisher vectors of the cases to perform semantic similarity calculation, so that a common user can obtain similar cases only by inputting case description or judgment documents, and the usability of the methodis greatly enhanced.

Methods, systems and processor-readable media for vehicle classification. In general, one or more vehicles can be scanned utilizing a laser scanner to compile data indicative of an optical profile of the vehicle(s). The optical profile associated with the vehicle(s) is then pre-processed. Particular features are extracted from the optical profile following pre-processing of the optical profile. The vehicle(s) can be then classified based on the particular features extracted from the optical feature. A segmented laser profile is treated as an image and profile features that integrate the signal in one of the two directions of the image and Fisher vectors which aggregate statistics of local “patches” of the image are computed and utilized as part of the extraction and classification process.

The invention provides a mobile visual search framework based on a CRBM and Fisher network and relates to the image retrieval of a mobile terminal. The method comprises the following steps of 1) constructing and training a continuous restricted Boltzmann machine network; 2) constructing and training a Fisher layer network. According to the invention, the sub-space feature information of the localfeature nature of non-Gaussian distribution is found by adopting the nonlinear dimensionality reduction algorithm CRBM in the aggregation global compact binary feature algorithm. Meanwhile, more efficient global features are obtained through adopting a fisher-based network structure aggregation fisher vector. A compact self-adaptive feature is obtained by adopting the scalar quantization algorithmand the bit self-adaptation algorithm. Therefore, the length of the transmitted image feature information can be selected according to different self-adaptive selections of the network bandwidth of amobile terminal. During the retrieval stage, global features are roughly matched to obtain a candidate set, and the accurate matching of the geometric consistency test is conducted by adopting localfeatures. Therefore, the mobile visual search framework can be adapted to large-scale image retrieval tasks.

The invention discloses an image classification method based on a noise reduction sparse automatic encoder and density space sampling. The image classification method based on a noise reduction sparseautomatic encoder and density space sampling includes the steps: constructing an image block training set; constructing a noise reduction sparse automatic encoder of single hidden layer, inputting the image block training set, and training the noise reduction sparse automatic encoder; performing density space sampling on each image in a training image data set and a test image data set; using thenoise reduction sparse automatic encoder to extract local characteristic set information from the space area obtained by performing density space sampling on each image; using two layers of laminatedFisher Vector to encode the characteristic set information, so as to obtain the final Fisher vector of each image; and training a classifier by means of the Fisher vector, so as to realize image classification. The image classification method based on a noise reduction sparse automatic encoder and density space sampling can accurately acquire the image information, can improve the classificationaccuracy of images, and can be used for construction of a large scale image classification and retrieval system.