674results about How to "Quick classification" patented technology

A novel solution for fast packet classification includes a novel data structure to store classifier rules which enables fast packet classification, which structure employs bitmaps for each field of the incoming packet for which classification is desired. A fast packet classification algorithm using the novel data structure allows the matching rule with the highest priority to be quickly obtained. A novel rule update algorithm allows new classifier rules to be added into the data structure incrementally. In one practical implementation of a classification engine employing the structures and algorithms of the present invention, a configurable processor with customized instructions is used to accelerate packet classification.

Embodiments of methods and devices for classifying background noise contained in an audio signal are disclosed. In one embodiment, the device includes a module for extracting from the audio signal a background noise signal, termed the noise signal. Also included is a second that calculates a first parameter, termed the temporal indicator. The temporal indicator relates to the temporal evolution of the noise signal. The second module also calculates a second parameter, termed the frequency indicator. The frequency indicator relates to the frequency spectrum of the noise signal. Finally, the device includes a third module that classifies the background noise by selecting, as a function of the calculated values of the temporal indicator and of the frequency indicator, a class of background noise from among a predefined set of classes of background noise.

The invention is applicable for the technical field of classification processing, and provides an application program display and classification method, an application program display and classification and a mobile terminal. The display method comprises the following steps of: presetting classifications to which application programs belong in an application program management setting interface; and displaying the at least one preset classification and application program icons in the classifications on the display interface. The classification method comprises the following steps of: when a user touches an application program iron, displaying a classification file folder; acquiring a command of dragging the application program icon to a corresponding file folder by the user; and classifying a dragged application program to the classification corresponding to the corresponding file folder. By the method and the system, the user can conveniently classify the application programs rapidly and can rapidly search desired application programs and enter an operation interface of an application program.

An image focus assessment method is provided that works reliably for images of a variety of relatively dissimilar workpieces or workpiece features. The focus assessment method is based on analysis of a single image (without the benefit of comparison to other images). The robustness of the focus assessment method is enhanced by the use of at least one classifier based on a plurality of focus classification features. In one application, a primary advantage of assessing focus from a single image is that an overall workpiece inspection time may be reduced by avoiding running an autofocus routine if an image is already in focus. In various embodiments, the focus assessment method may include an ensemble of classifiers. The ensemble of classifiers can be trained on different training data (sub)sets or different parameter (sub)sets, and their classification outcomes combined by a voting operation or the like, in order to enhance the overall accuracy and robustness of the focus assessment method.

Text information analysis apparatus arranges a plurality of texts according to the content of each text. In the text information analysis apparatus, a category decision unit classifies text to one of a plurality of predetermined categories. A cluster generation unit clusters texts having similar contents from the plurality of texts. A control unit controls the category decision unit and the cluster generation unit to simultaneously execute a category decision and clustering for the plurality of texts.

The present invention relates to a system, method, and computer program product for recognition objects in a domain which combines feature-based object classification with efficient search mechanisms based on swarm intelligence. The present invention utilizes a particle swarm optimization (PSO) algorithm and a possibilistic particle swarm optimization algorithm (PPSO), which are effective for optimization of a wide range of functions. PSO searches a multi-dimensional solution space using a population of “software agents” in which each software agent has its own velocity vector. PPSO allows different groups of software agents (i.e., particles) to work together with different temporary search goals that change in different phases of the algorithm. Each agent is a self-contained classifier that interacts and cooperates with other classifier agents to optimize the classifier confidence level. By performing this optimization, the swarm simultaneously finds objects in the scene, determines their size, and optimizes the classifier parameters.

The distribution states of defects are analyzed on the basis of the coordinates of defects detected by an inspection apparatus to classify them into a distribution feature category, or any one of repetitive defect, congestion defect, linear distribution defect, ring/lump distribution defect and random defect. In the manufacturing process for semiconductor substrates, defect distribution states are analyzed on the basis of defect data detected by an inspection apparatus, thereby specifying the cause of defect in apparatus or process.

The invention provides a clustering based point cloud segmentation method and system. The method comprises the following steps: calculating the normal vector, plane curvature and compatible set of each point, realized as follows, firstly constructing a k-d tree for the inputted point clouds, and then using the neighbor K points nearest to one point to get the normal vector and plane curvature of the point; clustering the point clouds, constructing a link table and a clustering center table to obtain a set of all clusters; conducting patch processing which includes constructing initial patches, including for each cluster in the set of clusters, and using a plane for approximate fitting to the corresponding point clouds for an MCS fitting plane, the normal vector, plane curvature and compatible set; and conducting patch combination for the final cloud point segmentation result. On the basis of the traditional region growing algorithm, the method and system provided by the invention directly use the normal vector and the plane curvature of the point clouds to carry out rapid classification, and does not need extra calculations to achieve fast segmentation.

The invention discloses a road marking automatic detection and classification method based on a mobile laser scanning point cloud. The method comprises the following steps: S1, performing pavement segmentation on original point cloud data to obtain pavement point cloud data; S2, performing intensity correction on the pavement point cloud data by use of an incident angle; S3, performing binary processing on the pavement point cloud data, and extracting road marking points; S4, segmenting the road marking points to separate mutually independent road marking targets; S5, calculating feature parameters of the road marking targets; and S6, by use of the feature parameters, constructing a decision tree, and classifying the road marking targets. The method can rapidly and accurately perform automatic detection and classification of road marks from the mobile laser scanning point cloud, greatly reduces the data processing time and the labor cost, and effectively guarantees the traffic safety and the reliability of intelligent driving.

The invention relates to a road edge detection system and method based on laser radar and fan-shaped space segmentation. The method comprises the steps of 1, a laser radar scanning the surrounding environment of a vehicle to obtain reflection point cloud information and convert the reflection point cloud information into a locally constructed three-dimensional coordinate system; 2, preprocessing the point cloud data, and separating and extracting ground data in each frame of point cloud; 3, dividing the space in the coordinate system into fan-shaped structural bodies according to the data characteristics of the laser radar and the point cloud, and identifying the road extension direction according to the ground information and the fan-shaped structural bodies; 4, extracting road edge candidate points in the point cloud by using a parallel road edge retrieval algorithm; 5, clustering the road edge candidate points, and eliminating an interference point set according to fan-shaped spatial features; and 6, performing B spline curve fitting on the finally determined road edge point to obtain a road edge detection result. The method is high in adaptability, capable of adapting to roadsof various shapes and reducing the influence of obstacles, high in precision and reduction degree, high in reliability and low in error rate.

Provides methods, apparatus, and systems for processing an electronic document and its corresponding device, a method for browsing an electronic document and its corresponding browser, and an electronic document classification and query method and its corresponding system for the same. The method for processing an electronic document comprises generating at least one category names to which the document belongs according to the content of said electronic document when being written by an author; and correspondingly storing said category name information with the electronic document. Wherein the category name(s) which the document belongs has passed the verification in order to ensure its reliability.

The invention discloses a skeleton data behavior identification method based on a graph convolutional neural network, and the method comprises the steps: carrying out the downsampling of the time dimension of each segment of skeleton data in a training set, obtaining skeleton data with a fixed time dimension for training the neural network; dividing the input data into three channels according tothree-dimensional coordinates, conducting graph convolution with double attention on each space channel, and then combining the three channels; performing space-time convolution on the combined vectors; updating the weight of the neural network by labeling the action category; and finally, obtaining a behavior recognition model strongly related to the specified labeling result. According to the method, the topological structure and the space-time relationship of skeleton data are fully utilized, and the behavior recognition performance is improved.

The invention relates to a silicon chip surface defect detector capable of classifying defects and a defect classifying method. The flat surface of the silicon chip to be detected on a highly reliablesilicon chip working platform is irradiated by a laser from an inclination direction. Circular narrow channel collection and annular narrow channel collection are carried out on scattered lights produced by the silicon chip surface defect by two paraboloidal mirrors with different calibers in a direction near the silicon chip face normal and parallel with silicon chip face. Two photoelectric detectors detect intensities of the collected electrooptical signals in two channels respectively and then take a ratio of two intensities, then compare the ratio with a given threshold value, and at lastthe silicon chip surface defects can be classified. The defect detector has the advantages of simple structure, high sensitivity, fast detecting speed, capability of classifying the defects on the silicon chip surface, etc.

A method and device are provided for the objective evaluation of voice quality of a speech signal. The device includes: a module for extracting a background noise signal, referred to as a noise signal, from the speech signal; a module for calculating the audio parameters of the noise signal; a module for classifying the background noise contained in the noise signal on the basis of the calculated audio parameters, according to a predefined set of background noise classes; and a module for evaluating the voice quality of the speech signal on the basis of at least the resulting classification relative to the background noise in the speech signal.

The invention discloses a transformer area line loss calculation method based on correlation analysis and data mining. The transformer area line loss calculation method selects the characteristic index data with greater influence as the input of the deep belief network by comparing and analyzing the influence of the electrical characteristic indexes of different transformer areas on the line lossrate of the transformer areas, carries out training by distinguishing different types of transformer areas by using a clustering algorithm respectively so as to mine the complex incidence relation between the input parameters and the transformer area line loss rate, and finally, generates a transformer area line loss prediction model which is rapid and efficient in calculation and relatively highin result accuracy, so that the transformer area line loss is calculated and analyzed by utilizing the model, and the problems that an existing transformer area line loss calculation method cannot accurately and effectively mine association of transformer area line loss influence factors, the calculation working efficiency and accuracy are low and the like are solved.

A method for providing qualitative analysis of solid forms of a chemical compound/or drug candidate including polymorphous, hydrates, solvates and amorphous solids that does not require an a prior knowledge of either the solid form or the total number of groups of solid forms.

The invention discloses a deep learning-based haze visibility detection method. The method comprises the following steps of: firstly creating a road traffic haze image library which comprises a training sample set and a cross validation sample set; preprocessing all the haze images in the traffic haze image library; extracting farthest visibility edge features of the preprocessed haze images I the training sample set by adoption of a convolutional neural network so as to obtain a plurality of feature maps; forwardly propagating the feature maps to a configured convolutional neural network to be trained, adjusting weights between layers in the convolutional neural network through a counter-propagation algorithm, carrying out repeated iteration to solve a convolutional neural network model for haze image classification, and optimizing the convolutional neural network model through the preprocessed cross validation sample set so as to finally obtain a visibility detection model for haze image classification; and carrying out classification judgement on pictures shot by a pavement by utilizing the obtained visibility detection model so as to detect the haze condition in real time.