5724 results about "Feature parameter" patented technology

Systems and methods are provided for automated assessment of regional myocardial function using wall motion analysis methods that analyze various features/parameters of patient information (image data and non-image data) obtained from medical records of a patient. For example, a method for providing automatic diagnostic support for cardiac imaging generally comprises obtaining image data of a heart of a patient, obtaining features from the image data of the heart, which are related to motion of the myocardium of the heart, and automatically assessing regional myocardial function of one or more regions of a myocardial wall using the obtained features.

The invention provides a voice recognition system comprising a storage unit, a voice acquisition and pre-processing unit, a feature extraction unit and a pattern matching unit, wherein the storage unit is used for storing at least one user's voice model; the voice acquisition and pre-processing unit is used for acquiring a to-be-identified voice signal, transforming the format of the to-be-identified voice signal and encoding the to-be-identified voice signal; the feature extraction unit is used for extracting voice feature parameters from the encoded to-be-identified voice signal; and the pattern matching unit is used for matching the extracted voice feature parameters with at least one voice model so that the user to which the to-be-identified voice signal belongs is identified. Based on the voice generation principle, voice features are analyzed, MFCC (mel frequency cepstrum coefficient) parameters are used, a speaker voice feature model is established, and speaker feature recognition algorithms are achieved, and thus, the purpose to improve speaker detection reliability can be achieved, and the speaker identification function can be finally realized on an electronic product.

The invention provides a voiceprint identification method based on a Gauss mixing model and a system thereof. The method comprises the following steps: voice signal acquisition; voice signal pretreatment; voice signal characteristic parameter extraction: employing a Mel Frequency Cepstrum Coefficient (MFCC), wherein an order number of the MFCC usually is 12-16; model training: employing an EM algorithm to train a Gauss mixing model (GMM) for a voice signal characteristic parameter of a speaker, wherein a k-means algorithm is selected as a parameter initialization method of the model; voiceprint identification: comparing a collected voice signal characteristic parameter to be identified with an established speaker voice model, carrying out determination according to a maximum posterior probability method, and if a corresponding speaker model enables a speaker voice characteristic vector X to be identified to has maximum posterior probability, identifying the speaker. According to the method, the Gauss mixing model based on probability statistics is employed, characteristic distribution of the speaker in characteristic space can be reflected well, a probability density function is common, a parameter in the model is easy to estimate and train, and the method has good identification performance and anti-noise capability.

The invention provides an auto-tracking recognition system and a method. The system comprises a fixed viewing field camera, a suspicious object determination module, a trail tracking module, a control module, a variable viewing field camera, a picture recognition module, a contrast module and an alarm module, wherein, the suspicious object determination module is used for analyzing a video picture collected by the fixed viewing field camera, determining a suspicious object, and acquiring the position of the suspicious object; the trail tracking module is used for determining the motion trail of the suspicious object; the control module is used for outputting a control signal according to the position and the motion trail of the suspicious object; the variable viewing field camera is used for acquiring the video picture in accordance with the feature recognition requirement based on an adjustment parameter of the control signal; the picture recognition module is used for acquiring a feature parameter of the suspicious object; the contrast module is used for contrasting the acquired feature parameter with the feature information of the contrasted object in a feature database; and the alarm module is used for giving an alarm to the suspicious object in accordance with the set alarm condition. The invention can automatically track and collect detail pictures of the suspicious object, and efficiently realize the recognition of the suspicious object, thereby giving an early and reliable alarm.

Automatically characterizing a behavior of an object or objects by processing object data to obtain a data set that records a measured parameter set for each object over lime, providing a learning input that identifies when the measured parameter set of an object is associated with a behavior, processing the data set in combination with the learning input to determine which parameters of the parameter set over which range of respective values characterize the behavior; and sending information that identifies which parameters of the parameter set over which range of respective values characterize the behavior for use in a process that uses the characteristic parameters and their characteristic ranges to process second object data and automatically identify when the behavior occurs. Also disclosed is a method of tracking one or more objects.

A video quality evaluation method based on artificial neural network, which belongs to the field of computer digital video processing. The evaluation algorithm computes damage extent of an image by analyzing spatial characters (blur, entropy, blocking effect, frequency-domain energy analysis, saturation) and time behaviors (frame-to-frame differences). Evaluation effect of the algorithm can be effectively modified by using colour space saturation as one of the parameters for non-reference evaluation algorithm. The system is designed based on artificial neural network, therefore, training process and testing process of the network are included in realization of the algorithm. To the selected training sample (video image sequence), firstly extracts six parameters of the sample, then obtains expected output (subjective evaluation result) in training through subjective evaluation. Characteristic parameters of the training sample and the corresponding subjective evaluation result are inputted to the artificial neural network as training parameters. The experiment shows that evaluation result obtained by the objective evaluation system is highly-consistent with visual sense of human eyes.

To provide a data process unit and data process unit control program which are suitable for generating acoustic models for unspecified speakers taking distribution of diversifying feature parameters into consideration under such specific conditions as the type of speaker, speech lexicons, speech styles, and speech environment and which are suitable for providing acoustic models intended for unspecified speakers and adapted to speech of a specific person.

A data process unit 1 comprises a data classification section 1a, data storing section 1b, pattern model generating section 1c, data control section 1d, mathematical distance calculating section 1e, pattern model converting section 1f, pattern model display section 1g, region dividing section 1h, division changing section 1i, region selecting section 1j, and specific pattern model generating section 1k.

There are disclosed an apparatus for calculating a posteriori probabilities of phoneme symbols and a speech recognition apparatus using the apparatus for calculating a posteriori probabilities of phoneme symbols. A feature extracting section extracts speech feature parameters from a speech signal of an uttered speech sentence composed of an inputted character series, and a calculating section calculates a a posteriori probability of a phoneme symbol of the speech signal, by using a bidirectional recurrent neural network. The bidirectional recurrent neural network includes (a) an input layer for receiving the speech feature parameters extracted by the feature extracting means and a plurality of hypothetical phoneme symbol series signals, (b) an intermediate layer of at least one layer having a plurality of units, and (c) an output layer for outputting a a posteriori probability of each phoneme symbol. The input layer includes (a) a first input neuron group having a plurality of units, for receiving a plurality of speech feature parameters and a plurality of phoneme symbol series signals, (b) a forward module, and (c) a backward module.

The invention belongs to the field of intelligent automobile road detection and relates to a method for detecting road information and identifying forward vehicles based on vision. The method comprises image preprocessing, lane line characteristic parameter extraction, region-of-interest segmentation and vehicle outline identification. According to the method for detecting the road information and identifying the forward vehicles based on vision, the complexity of computation is simplified by extracting the regions of interest, filtering out background regions and reducing the processing scope; the processing result of each frame of image is obtained through fixed computation times by use of a line-by-line retrieval method, and differing from the characteristic, namely linear fitting on each bright spot, of Hough conversion, the method has outstanding advantages in algorithm instantaneity; the instantaneity of the Robinson direction model operator is improved, and an intermediate variable is set to reduce the computation times of each pixel point. The regions of interest are screened and judged by use of an information entropy and a vehicle tail symmetry characteristic in the target region, and therefore, the omission factor and the false drop rate of the algorithm are reduced.

A method is provided for manufacturing, the method comprising processing a workpiece, measuring a parameter characteristic of the processing, and forming an output signal corresponding to the characteristic parameter measured by using the characteristic parameter measured as an input to a transistor model. The method also comprises predicting a wafer electrical test (WET) resulting value based on the output signal, detecting faulty processing based on the predicted WET resulting value, and correcting the faulty processing.

Methods and apparatus which characterize the ionospheric error across a network of GNSS reference stations are presented. The method relies on dual-frequency phase measurements in a geometry-free linear combination. The data are filtered for ambiguities and the characteristic parameters of the ionosphere. In combination with filter results from other combinations of phase measurements (ionosphere free combination), the physically-based model provides rapid and reliable ambiguity resolution.

The invention discloses an image communication method and system based on facial expression/action recognition. In the image communication method based on facial expression recognition, firstly, an image is collected at the sending end, and the facial area in the image is determined; The facial expression feature parameters in the region are extracted; then the extracted facial expression feature parameters are sent to the receiving end; finally, the receiving end uses the facial expression feature parameters to control the local facial model of the receiving end to pass the The facial model reproduces the facial expression. The application of the present invention can not only enhance user experience, but also greatly reduce the requirement on the information transmission rate of the video bearer network, realize more effective video communication, and is especially suitable for wireless communication networks with limited network bandwidth and capacity.

The invention discloses a myoelectricity feedback based upper limb training method and system. The myoelectricity feedback based upper limb training system orderly combines signal acquisition, mode identification, biological feedback and real-time fatigue evaluation, thereby being capable of helping a user train the movement function of the upper limb. The upper limb training method includes steps of acquiring movement signals and myoelectric signals of the upper limb joint of the user when the user acts correspondingly such as forearm rotation and wrist bending/stretching as completing virtual game tasks, adjusting movement parameters of virtual control targets on the basis of the movement signals acquired by the users, identifying several muscle contraction modes of the user according to the characteristic parameters of the myoelectric signals, and utilizing the identified modes as selection basis for a myoelectric feedback control method. In addition, the upper limb training system is capable of extracting fatigue characteristics in real time according to the acquired myoelectric signals, analyzing fatigue states of muscles so as to judge muscle fatigue and send an alarm during the whole interaction system.

The invention discloses a pronunciation quality assessment and error detection method based on the fusion of multiple characteristics and multiple systems, which carries out assessment and error detection on pronunciation quality by a method utilizing multiple characteristic parameters to describe pronunciation quality and utilizing multiple inspecting systems to mutually fuse, and comprises the following steps: recognizing voice and automatically segmenting and aligning the voice; extracting the characteristic parameters used for voice quality assessment and error detection; acquiring pronunciation quality assessment and error detection model training data; training a plurality of pronunciation quality assessment and error detection systems; fusing a plurality of pronunciation quality assessment and error detection systems; and assessing pronunciation quality and detecting pronunciation errors. By utilizing the invention, multiple voice characteristics are effectively utilized, and multiple assessment and detection system are fully utilized and perform information fusion, thereby maximally exerting the advantages of various characteristics and systems, and ensuring the accuracy and reliability of pronunciation assessment and error detection.

The invention relates to identification, image processing and the like, in particular to an artificial neural network-based multi-source gait feature extraction and identification method, which aims to reduce inferences with external factors such as complex background and shelters so as to more accurately extract the effective information reflecting the walking characteristics of the moving people and improve the gait identification accuracy. The technical scheme of the invention comprises the following steps: separately acquiring the gait data by using a camera and a pyroelectric infrared sensor; extracting the skeleton feature parameter and Radon change peak characteristic parameter from the image source information acquired by the camera, and for the pyroelectric infrared source information, converting an acquired voltage signal into frequency domain characteristic parameter; merging the skeleton feature parameter, the Radon change peak feature parameter and the frequency domain characteristic parameter which are subjected to dimension reduction and corresponding signal process; and finally, realizing classified identification of the merged characteristics by using a BP neutralnetwork as the classifier and evaluating the identification effect. The method is mainly applied to identification.

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 universal machine learning data analysis platform. The universal machine learning data analysis platform comprises an interface module, a data storage module, a preprocessing module, a feature extraction module, a feature conversion module, an algorithm module and a selection optimization module, wherein the feature extraction module extracts feature parameters from to-be-analyzed data according to the feature parameters set by a user; the feature conversion module is used for converting features set by the user to be in a representation form required by the user; the algorithm module comprises a plurality of algorithm models for the user to select and build, and the user builds at least one group of models; the selection optimization module selects out an optimal model and an optimal parameter from the built models and then stores the optimal model; and data generated by the modules is stored in the data storage module. According to the platform, the user can freely combine and use the modules and the algorithm models, and also can build a complex model and quickly and iteratively develop a novel analytic model, so that the working efficiency is greatly improved.

A method is provided, the method comprising sampling at least one parameter characteristic of processing performed on a workpiece in at least one processing step, and modeling the at least one characteristic parameter sampled using an adaptive sampling processing model, treating sampling as an integrated part of a dynamic control environment, varying the sampling based upon at least one of situational information, upstream events and requirements of run-to-run controllers. The method also comprises applying the adaptive sampling processing model to modify the processing performed in the at least one processing step.

The invention discloses a method for quick vehicle type recognition under video monitoring mode, which is implemented according to the following steps: setting up a road monitoring device and classifying the vehicles into cars, taxis marked by special color, microbuses, middle-sized vehicles, public buses and large trucks; step 1, initialization, conducting training to the video monitoring device; step2, extracting the area of the vehicle target area and the length and the width of the boundary rectangle of the area, constructing corresponding characteristics and roughly classifying the vehicles into minitype vehicles, middle-sized vehicles and large vehicles; step 3, extracting the main colors of bodyworks of a plurality of minitype vehicle targets to recognize the taxis, then extracting the characteristic parameter of window position of the minitype vehicles, and furthermore, determining the microbuses or cars; and step 4, extracting the characteristic parameters of roof brightness and roof texture to determine whether the large vehicles are public buses or not. Through the method, a variety of vehicles can be recognized quickly and accurately according to the classification characteristics.

The invention discloses a speaker recognition method based on depth learning. The method comprises the following steps: S1) carrying out pre-emphasis and overlapping-type framing windowing on collected voice signals; S2) carrying out endpoint detection on the collected voice signals by utilizing a dual-threshold endpoint detection method based on short-time energy and short-time zero-crossing rate, and judging and indentifying the staring moment, transition stage , noise section and ending moment of the voice; S3) carrying out feature extraction on the voice signals; S4) forming a depth belief network model based on restricted boltzmann machine hierarchy, training the established depth belief network model by utilizing layer-by-layer greedy algorithm and with speaker voice feature parameters being combined, and adding a Softmax classifier to the top layer of the depth belief network model; and S5) inputting the voice features of a speaker to the depth belief network model obtained after being subjected to training, calculating the probability that the model outputs voice features similar to the voice features of the other speakers, and selecting the speaker corresponding to the maximum probability as recognition result.

The system comprises preprocessing board connecting key phase signal to fast signal, key phase board controlling whole period of sampling, high speed collecting board for vibration signal, low speed data collecting board for graded signal. In the method, they are connected to down level server to fulfil data collection, signal analysis, and automatic identification as well as picking up characteristic parameters of operatino of machine set and down level server can make high speed communication with up level server through network card or IP protocol as up level server is equipped with an intelligent reasoning machine integrating professional knowledge rule, fuzzy logic and neural network in one component to carry trend prediction and intelligent diagnosis for operation and failure of machine.

The invention relates to an online automatic detection method of fabric defects based on machine vision and a device thereof, wherein the clear and integral standard fabric images without the defects of the fabric are shot on a batching and burling machine as a standard image template by utilizing an industrial camera in order to solve the problems of great labor intensity and poor detection quality of the traditional manual detection method; the corresponding characteristic parameters are extracted and stored into a computer; the range of the fabric defect detection characteristic parameters is set according to the requirements of users; the fabric images which are shot in real time are transmitted to the computer to be compared with the standard image template by utilizing the industrial camera and compared with the standard characteristic parameters; if the fabric characteristic parameters are not in conformity with the set requirements, the alarm is started by detection software; the defects are analyzed; and the printing of defects labels is executed. The invention has the advantages of high detection accuracy and high speed; and the labor intensity is greatly reduced.

The present invention relates to a method and an apparatus for determining which one or more time series parameters of a plurality of time series parameters relating to operation of a system are correlated with a first operation state of the system. According to the invention, the method comprises providing time series data including data relating to a time series of each of the plurality of time series parameters; determining at least two first time periods, wherein the system is in the first operation state during the at least two first time periods; determining at least one second time period, wherein the system is in a second operation state during the at least one second time period; determining, for each respective time series parameter of the plurality of time series parameters, a first characteristic parameter relating to a first characteristic of the time series of the respective time series parameter for each of the at least two first time periods and the at least one second time period; and determining which one or more time series parameters of the plurality of time series parameters relating to the operation of the system are correlated with the first operation state of the system by determining, for each respective time series parameter of the plurality of time series parameters, whether or not the respective time series parameter is correlated with the first operation state of the system based on the first characteristic parameters of the respective time series parameter determined for each of the at least two first time periods and the at least one second time period.

A system automatically recognizes a vehicle operating condition through a microphone positioned within the vehicle. The microphone detects acoustic signals. A database stores speech templates and operating noise templates. A feature extracting module receives microphone signals and extracts a set of operating noise feature parameters or speech feature parameters from the microphone signals. A speech and noise recognition module may determine an operating noise template that best matches a set of extracted operating noise feature parameters and/or a speech template. The speech template best matches the set of extracted speech feature parameters.