6229 results about "Classification result" patented technology

A vehicle information display system includes a head-up display for reflecting an image on a windshield of a vehicle and displaying the image so that a driver recognizes the image as a virtual image. Information is collected for being displayed by the head-up display. A circumstance of the vehicle, a circumstance of surrounding of the vehicle, or a circumstance of the driver is detected. The collected information is classified in accordance with a detection result. Then, display contents of the head-up display are controlled in accordance with a classification result.

An imaging apparatus includes an imaging section converting an image into image data, an image classifying section classifying the image data, and a display section for displaying information regarding a recommended image as a shooting object based on a classification result by the image classifying section. Further, a server having a shooting assist function receives image data from an imaging apparatus that has an imaging section converting an image into the image data and includes a scene determining section classifying the received image data and determining whether a typical image has been taken repeatedly, a guide information section outputting information regarding a recommended image as a shooting object based on a determination result by the scene determining section, and a communication section outputting the information to the imaging apparatus.

A document classification system and method reflects operator's intention in a result of classification of document so that an accurate result of classification can be achieved. The document to be classifies has contents contains a plurality of items. At least one of the items contained in the document is designated. The document data is converted into converted data so that the converted data contains only data corresponding to the designated item. Classification of the document is done by using the converted data.

Packets received at a network appliance are classified according to packet classification rules based on flow state information maintained by the network appliance and evaluated for each packet as it is received at the appliance on the basis of OSI Level 2-Level 4 (L2-L4) information retrieved from the packet. The received packets are acted upon according to outcomes of the classification; and the flow state information is updated according to actions taken on the received packets. The updated flow state information is then made available to modules performing additional processing of one or more of the packets at OSI Layer 7 (L7).

The present invention relates to a general-purpose programmable packet-processing platform for accelerating network infrastructure applications which have been structured so as to separate the stages of classification and action. Network packet classification, execution of actions upon those packets, management of buffer flow, encryption services, and management of Network Interface Controllers are accelerated through the use of a multiplicity of specialized modules. A language interface is defined for specifying both stateless and stateful classification of packets and to associate actions with classification results in order to efficiently utilize these specialized modules.

The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.

A method, and corresponding system, for identifying e-mail messages as being unwanted junk or spam. The method includes converting the outputs of a set of e-mail classification tools into a standardized format, such as a probability having a value between zero and one. The standardized outputs of the classification tools are then input to a voting mechanism which uses a voting algorithm based on fuzzy logic to combine the standardized outputs into a single classification result. The use of a fuzzy logic algorithm creates a more useful result as the classifier results are not merely averaged. In one embodiment, the single classification result is itself a probability that is provided to a spam classifier or comparator that functions to compare the single classification result to a spam threshold value and based on the comparison to classify the e-mail message as spam or not spam.

Systems and methods are described for classifying a cardiac rhythm. A cardiac rhythm is classified using a classification process that includes a plurality of cardiac rhythm discriminators. Each rhythm discriminator provides an independent classification of the cardiac rhythm. The classification process is modified if the modification is likely to produce enhanced classification results. The rhythm is reclassified using the modified classification process.

A fast handover method optimized for IEEE 802.11 networks. In a wireless local area system including a mobile terminal and at least two wireless access points (APs) that communicate with the mobile terminal over a unique radio channel, the fast handover method includes receiving a beacon frame signal from the serving AP and the neighbor APs of the mobile terminal; generating a first signal to determine a state of each of the neighbor APs based on the beacon frame signal received from each of the neighbor APs; comparing the first signal with predefined thresholds, classifying the neighbor APs into a detected AP, a candidate AP, and a target AP according to a result of the comparison, and storing the classification result in a neighbor AP list; and selecting an AP for the handover based on the classification result in the neighbor AP list.

The invention relates to the technical field of image information processing, in particular to a multiclass image classification method based on active learning and semi-supervised learning. The method comprises five steps: initial sample selection and classifier model training, BvSB active learning sample selection, CST semi-supervised learning, training sample set and classifier model updating and assorting process iteration. Through the operations of BvSB active learning sample selection, CST semi-supervised learning and SVM classification, the invention has efficient image classification effect under the condition of less manual tagging, does not increase overmuch computation burden, can quickly provide classification effects and also can take consideration of the demand of a classification system on the computation complexity.

The invention relates to the field of computer vision recognition and transfer learning, and provides a small sample and zero sample image classification method based on metric learning and meta-learning, which comprises the following steps of: constructing a training data set and a target task data set; selecting a support set and a test set from the training data set; respectively inputting samples of the test set and the support set into a feature extraction network to obtain feature vectors; sequentially inputting the feature vectors of the test set and the support set into a feature attention module and a distance measurement module, calculating the category similarity of the test set sample and the support set sample, and updating the parameters of each module by utilizing a loss function; repeating the above steps until the parameters of the networks of the modules converge, and completing the training of the modules; and enabling the to-be-tested picture and the training picture in the target task data set to sequentially pass through a feature extraction network, a feature attention module and a distance measurement module, and outputting a category label with the highestcategory similarity with the test set to obtain a classification result of the to-be-tested picture.

The invention relates to an image segmentation method based on a multi-supervision full-convolution neural network. According to the invention, further improvement is carried out based on the full convolution neural network, so a novel network structure is provided. The network structure has three edge output layers with supervision which are capable of guiding a network to learn multi-scale features and allowing the network to acquire local features and global features of images. Meanwhile, in order to keep context information in the images, in the upper sampling parts of the network, upper sampling is performed on output feature images by sue of multiple feature channels. Finally, a fusion layer with the weight is used for fusing the classification results of the multiple edge output layers, so the final image segmentation result is obtained. The method is characterized by high segmentation precision and quick segmentation speed. In osteosarcoma CT data segmentation, the DSC coefficient of the acquired segmentation result by use of the provided algorithm reaches 86.88%, which is higher than that of a traditional FCN algorithm.

Methods and systems are provided for delaying local information classification until global intelligence has an opportunity to be gathered. According to one embodiment, an initial information identification process, e.g., an initial spam detection, is performed on received electronic information, e.g., an e-mail message. Based on the initial information identification process, classification of the received electronic information is attempted. If the received electronic information cannot be unambiguously classified as being within one of a set of predetermined categories (e.g., spam or clean), then an opportunity is provided for global intelligence to be gathered regarding the received electronic information by queuing the received electronic information for re-evaluation. The electronic information is subsequently classified by performing a re-evaluation information identification process, e.g., re-evaluation spam detection, which provides a more accurate categorization result than the initial information identification process. Handling the electronic information in accordance with a policy associated with the categorization result.

The invention provides an industrial character identification method based on a convolution neural network. The method comprises the steps of establishing character data sets, carrying out data enhancement and preprocessing on the character data sets and establishing a CNN (Convolution Neural Network) integrated model, wherein the model comprises three different individual classifiers, training is carried out through utilization of the model, the training is finished by two steps, a first step is offline training, an offline training model is obtained, a second step is online training, the offline training model is used for initialization, a special production line character data set is trained, and an online training model is obtained; carrying out preprocessing, character positioning and single character image segmentation on a target image; sending the segmented character images to the trained online training model, and probability values of classifying the single target images into classes by the three classifiers in the CNN integrated model is obtained; final decision is carried out in a voting mode, thereby obtaining a classification result of test data. According to the method, characters on different production lines can be identified rapidly and efficiently.

In an apparatus of a communication network first packets of a data flow in a first direction are acquired, each having a first service chain identifier identifying a first chain of services which have been applied to the first packets in the first direction of the data flow. The first service chain identifier represents a classification result of classification functions used for selecting the first chain of services. Based on the first service chain identifier, a packet filter is calculated, which is associated with a second chain of services to be applied to second packets of the data flow in a second direction of the data flow when the second packets enter the communication network in the second direction.

The invention discloses a bidirectional long short-term memory unit-based behavior identification method for a video. The method comprises the steps of (1) inputting a video sequence and extracting an RGB (Red, Green and Blue) frame sequence and an optical flow image from the video sequence; (2) respectively training a deep convolutional network of an RGB image and a deep convolutional network of the optical flow image; (3) extracting multilayer characteristics of the network, wherein characteristics of a third convolutional layer, a fifth convolutional layer and a seventh fully connected layer are at least extracted, and the characteristics of the convolutional layers are pooled; (4) training a recurrent neural network constructed by use of a bidirectional long short-term memory unit to obtain a probability matrix of each frame of the video; and (5) averaging the probability matrixes, finally fusing the probability matrixes of an optical flow frame and an RGB frame, taking a category with a maximum probability as a final classification result, and thus realizing behavior identification. According to the method, the conventional artificial characteristics are replaced with multi-layer depth learning characteristics, the depth characteristics of different layers represent different pieces of information, and the combination of multi-layer characteristics can improve the accuracy rate of classification; and the time information is captured by use of the bidirectional long short-term memory, many pieces of time domain structural information are obtained and a behavior identification effect is improved.

The invention discloses a remote sensing image classification method based on multi-feature fusion, which includes the following steps: A, respectively extracting visual word bag features, color histogram features and textural features of training set remote sensing images; B, respectively using the visual word bag features, the color histogram features and the textural features of the training remote sensing images to perform support vector machine training to obtain three different support vector machine classifiers; and C, respectively extracting visual word bag features, color histogram features and textural features of unknown test samples, using corresponding support vector machine classifiers obtained in the step B to perform category forecasting to obtain three groups of category forecasting results, and synthesizing the three groups of category forecasting results in a weighting synthesis method to obtain the final classification result. The remote sensing image classification method based on multi-feature fusion further adopts an improved word bag model to perform visual word bag feature extracting. Compared with the prior art, the remote sensing image classification method based on multi-feature fusion can obtain more accurate classification result.

The invention discloses a semi-supervised classification method of unbalance data, which is mainly used for solving the problem of low classification precision of a minority of data which have fewer marked samples and high degree of unbalance in the prior art. The method is implemented by the following steps: (1) initializing a marked sample set and an unmarked sample set; (2) initializing a cluster center; (3) implementing fuzzy clustering; (4) updating the marked sample set and unmarked sample set according to the result of the clustering; (5) performing the self-training based on a support vector machine (SVM) classifier; (6) updating the marked sample set and unmarked sample set according to the result of the self-training; (7) performing the classification of support vector machines Biased-SVM based on penalty parameters; and (8) estimating a classification result and outputting the result. For unbalance data which have fewer marked samples, the method improves the classification precision of a minority of data. And the method can be used for classifying and identifying unbalance data having few training samples.

The invention discloses an unsupervised domain adaptive image classification method based on a conditional generative adversarial network. The method comprises the following steps: preprocessing an image data set; constructing a cross-domain conditional confrontation image generation network by adopting a cyclic consistent generation confrontation network and applying a constraint loss function; using the preprocessed image data set to train the constructed conditional adversarial image generation network; and testing the to-be-classified target image by using the trained network model to obtain a final classification result. According to the method, a conditional adversarial cross-domain image migration algorithm is adopted to carry out mutual conversion on source domain image samples andtarget domain image samples, and consistency loss function constraint is applied to classification prediction of target images before and after conversion. Meanwhile, discriminative classification tags are applied to carry out conditional adversarial learning to align joint distribution of source domain image tags and target domain image tags, so that the source domain image with the tags is applied to train the target domain image, classification of the target image is achieved, and classification precision is improved.

The invention belongs to the field of data processing technology and discloses a text sentiment classification method facing Chinese Web comments. The text sentiment classification method includes a training process and a classification process. The training process includes the steps of carrying out training text preprocessing, carrying out feature selecting, carrying out vectorization representation of a text and obtaining a training classifier. The classification process includes the steps of carrying out test text preprocessing, carrying out feature selecting, utilizing the classifier to classify and outputting a classification result. On the basis of an original document classification method, document frequency (DF) and information gain (IG) are used and a sentiment dictionary of negative words, degree adverbs and dynamic sentiment words are built to distinguish sentiment tendency of Chinese feature words, select feature words, calculate a feature weight value and build a feature vector. Moreover, a NaiveBayes classification algorithm is used for training to obtain the classifier, carrying out sentiment classification on the text, providing effective data mining for users and then carrying out analysis processing.

The invention provides a vehicle license plate recognition method based on a video. According to the vehicle license plate recognition method based on the video, moving vehicles are detected and separated out with the vehicle video which is obtained through actual photographing by means of a camera serving as input, the accurate position of a vehicle license plate area is determined by conducting vertical edge extraction on a target vehicle image obtained after pre-processing, a vehicle license plate image is separated out, color correction, binaryzation and inclination correction are conducted on a vehicle license plate image, each character in the positioned vehicle license plate area is separated to serve as an independent character, feature extraction is conducted one each character, obtained feature vectors are classified through a classifier which is well trained in advance, a classification result serves as a preliminary recognition result, secondary recognition is conducted on the stained vehicle license plate characters according to a template matching algorithm imitating the visual characteristics of human eyes, and then a final vehicle license plate recognition result is obtained. The vehicle license plate recognition method based on the video has the advantages that hardware cost is reduced, the management efficiency of an intelligent transportation system is improved, the anti-jamming performance and the robustness are high, the recognition efficiency is high, and the recognition speed is high.

The present disclosure relates to systems and methods for classifying videos based on video content. For a given video file including a plurality of frames, a subset of frames is extracted for processing. Frames that are too dark, blurry, or otherwise poor classification candidates are discarded from the subset. Generally, material classification scores that describe type of material content likely included in each frame are calculated for the remaining frames in the subset. The material classification scores are used to generate material arrangement vectors that represent the spatial arrangement of material content in each frame. The material arrangement vectors are subsequently classified to generate a scene classification score vector for each frame. The scene classification results are averaged (or otherwise processed) across all frames in the subset to associate the video file with one or more predefined scene categories related to overall types of scene content of the video file.

The invention relates to a graph-based semi-supervised high-spectral remote sensing image classification method. The method comprises the following steps: extracting the features of an input image; randomly sampling M points from an unlabeled sample, constructing a set S with L marked points, constructing a set R with the rest of the points; calculating K adjacent points of the points in the sets S and R in the set S by use of a class probability distance; constructing two sparse matrixes WSS and WSR by a linear representation method; using label propagation to obtain a label function F<*><S>, and calculating the label prediction function F<*><R> of the sample points in the set R to determine the labels of all the pixel points of the input image. According to the method, the adjacent points of the sample points can be calculated by use of the class probability distance, and the accurate classification of high-spectral images can be achieved by utilizing semi-supervised conduction, thus the calculation complexity is greatly reduced; in addition, the problem that the graph-based semi-supervised learning algorithm can not be used for large-scale data processing is solved, and the calculation efficiency can be improved by at least 20-50 times within the per unit time when the method provided by the invention is used, and the visual effects of the classified result graphs are good.

The invention discloses a deep learning-based vulnerability detection method and system. The method comprises an offline vulnerability classifier training part and an online vulnerability detection part. The offline vulnerability classifier training part comprises the following steps of: calling candidate code sections for a training program extraction library/API function; adding type label for the candidate code sections; converting the candidate code sections into vectors; inputting the vectors into a neural network model to carry out training; and finally outputting a vulnerability classifier. The online vulnerability detection part comprises the following steps of: calling candidate code sections for a target program extraction library/API function; converting the candidate code sections into vectors; classifying the candidate code sections by adoption of the trained vulnerability classifier; and finally outputting the code sections which contain online vulnerabilities in the classification result. According to the method and system, vulnerability features aiming at library/API function calling can be automatically generated, and the operation does not depend on expert knowledges and is not restricted to vulnerability types, so that the false report rate and missing report rate of vulnerability detection in target programs can be remarkably reduced and vulnerability positions can be given.

The invention discloses an electric power user figure establishment and analysis method based on the big data technology. The method comprises steps that the historical electricity information, basic attributes, the fee-paying information and the appeal information of electric power users are acquired; classification category sets of user figures are determined, an influence factor set of a classification result is determined, and a mapping relationship between the influence factor set and the classification set is determined; random extraction of the acquired data is carried out, one part of the data is taken as a training sample, and other data is taken as prediction sample; normalization processing, discretization processing and attribute reduction for the training sample and the prediction sample are carried out, and an influence factor set after correction is determined; the training sample is trained, ten-fold cross validation is taken as a test mode, an electric power user figure prediction model based on a naive Bayes classifier is established, data classification mining analysis on the prediction sample is carried out through utilizing the prediction model, and electric power user figures are acquired. The method is advantaged in that electric power electric quantity prediction and management can be facilitated.

The invention relates to a color image three-dimensional reconstruction method based on three-dimensional matching, comprising the following steps of: (1) simultaneously and respectively taking an image from proper angles by using two color cameras; (2) respectively calibrating the internal parameter matrixes and the external parameter matrixes of the two cameras; (3) carrying out polar line correction and image transformation according to calibrated data; (4) working out matching cost for each pixel point in the two corrected images by applying a self-adaption weight window algorithm and acquiring an initial parallax image; (5) marking the reliability coefficient of the pixel initial matching result by adopting matching cost reliability detection and left and right consistency verification; (6) carrying out color segmentation on the images through a Mean-Shift algorithm; (7) carrying out global optimization by a selective confidence propagation algorithm on the basis of color segmentation and pixel reliability classification results to obtain a final parallax image; and (8) working out the three-dimensional coordinates of actual object points on the images according to the calibrated data and the matching relation, thereby reconstructing the three-dimensional point cloud of an object.

The invention provides a method for generating a user feature database and a personalized website navigation method, wherein the method for generating the feature database comprises the steps of: obtaining a search log which includes inquiry words and web pages clicked correspondingly; classifying the inquiry words in the search log according to classification information of the clicked web pages; summarizing all the inquiry words of a user, determining feature parameters of the user according to the classification result of all the inquiry words; storing a user identifier and the feature parameters thereof, and forming the user feature database. The invention takes the differences in user needs into account and adds user interest features to the recommended website sorting or screening calculation, thereby preferentially recommending a website which is most in line with the personalized needs of the current user for meeting the personalized needs of the current user.

The invention provides a classification engine for classifying documents that makes use of functions included in a similarity search engine. The classification engine executes a classify command from a client that makes use of similarity search results, and rules files, classes files, and a classification profile embedded in the classification command. When the classification receives a classify command from a client, it retrieves a classification profile and input documents to be classified, sends extracted values from the input documents based on anchor values to a XML transformation engine to obtain a search schema, requests a similarity search by a search manager to determine the similarity between input documents and anchor values, and classifies the input documents according to the rules files, classes files, and the classification profile. The client is then notified that the classify command has been completed and the classification results are stored in a database.

The invention relates to a scene and target identification method and device based on multi-task learning. The method comprises the steps that pictures containing different scenes and targets are collected as image sample data; the image sample data is subjected to manual label marking, and target class labels and scene class labels are obtained; a multi-layer convolutional neural network model is built, and network initialization is conducted; the image sample data and the corresponding target class labels are adopted for pre-training the built model till convergence, and a target identification model is obtained; based on a multi-task learning technology, network branches are added into a specific layer of the target identification model, random initialization is conducted, and a multi-task network is obtained; the image sample data and the corresponding scene class labels and target class labels are adopted for e-training the multi-task network till convergence, and a multi-task learning model is obtained; new image data is input to the multi-task learning model, and classification results of scene and target identification of images are obtained. Accordingly, the single task identification precision is improved.

The invention provides an abnormal information text classification method based on a knowledge graph. According to the method, first, a domain knowledge graph is constructed, and an entity identifierand an entity link based on the domain knowledge graph are constructed; second, text feature representation vectors v<text> and entity feature representation vectors v<ent> are constructed; and last,the text feature representation vectors and the entity feature representation vectors are merged to obtain new text representation vectors v<merge> fusing knowledge features, classified training is performed on the new text representation vectors, and a final classification result is obtained.