968results about How to "Improve recognition rate" patented technology

A voice recognition device used as a peripheral device for a game machine including a voice input device, a voice recognition section for recognizing the player's voice by comparing the voice signal output from the voice input device with data from previously defined voice recognition dictionaries and generating control signals relating to the game on the basis of the recognition result. The voice recognition section includes a non-specific speaker voice recognition dictionary which is previously defined for unspecified speakers, and a specific speaker voice recognition dictionary which is defined by the player.

A mobile phone which is an example of electronic equipment includes an infrared camera and an infrared LED. The infrared camera is arranged above a display and the infrared LED is arranged below the display. A user, by an eye-controlled input, designates a button image or a predetermined region on a screen. When a line of sight is to be detected, an infrared ray (infrared light) emitted from the infrared LED arranged below the display is irradiated to a lower portion of a pupil. Accordingly, even in a state that the user slightly closes his/her eyelid, the pupil and a reflected light of the infrared light can be imaged.

A method of changing a display mode in a car navigation system, the method including: acquiring distance information from a current vehicle location to a guide point; and gradually changing the display mode into any one of a two-dimensional display mode and a three-dimensional display mode based on the distance information.

A system and method for correcting data in data fields of financial documents containing unreadable characters is described. Data fields include MICR and OCR data files on financial documents such as checks. A controller receives MICR or OCR data from a document processor that is operable to retrieve MICR or OCR data from a plurality of financial documents, and performs data correction functions on the MICR or OCR data. Data corrections functions include comparing an erroneous number in the MICR or OCR data with a plurality of correct numbers and electronically replacing the erroneous number with a number from said plurality of possible numbers.

The invention discloses a psychological stress assessment method based on multi-physiological-parameter integration. The method includes: designing a reasonable stimulation program, acquiring four types of electrophysiological signals, namely electrocardiogram signals, electromyographic signals, pulse wave signals and electroencephalogram signals from people suffering psychological stress; extracting affective features of the four types of electrophysiological signals; subjecting the extracted features to feature selection by means of Relief algorithm, genetic algorithm optimization and the like; acquiring related integration functions on the basis of basic probability assignment mass. According to the method, multi-parameter signals are subjected to acquisition, preprocessed, feature selection and psychological stress affective recognition and are integrated; compared to single-parameter classified recognition or multi-parameter data-level or feature-level integration, the method allows data information to be more fully utilized and psychological stress emotions to be more accurately recognized.

The invention discloses a method for recognizing voice. The method comprises the following steps of: acquiring audio data; acquiring a Lattice result of the audio data, wherein the Lattice result comprises time point information, a plurality of pieces of candidate information and matching likelihood scoring information; acquiring confidence scoring information according to the plurality of piecesof candidate information and the matching likelihood scoring information; rearranging the plurality of pieces of candidate information by using a stronger voice model and providing the optimal recognition result; positioning a voicing position corresponding to the audio data and simultaneously displaying other candidate words; selecting or inputting a correct text to finish amendment and freezingthe amended text; and searching a related text training language model by using a search engine according to the amended text serving as a key word, interpolating to acquire an adaptive language model, and returning and newly recognizing the rest part of audio data by using the adaptive voice model. By using the technical scheme, the voice recognition rate can be improved, and the workload of manual checking can be reduced.

The invention discloses a coal-rock interface identifying method and system based on an image. The method comprises the following steps of: acquiring multiple color images of coal and rock on a coal mining working face; extracting a vector based on an image characteristic serving as a sample characteristic vector specific to each color image to obtain a known sample set of coal and rock; and establishing a coal-rock classifier model by adopting a Fisher linear judging method and taking the known sample set of the coal and rock as a training sample set. In the working process of a coal mining machine, a color image of the coal and rock which is cut by using a drum is acquired in real time, and the extracted characteristic vector is input into the coal-rock classifier model to identify a coal-rock type. The system consists of a light source module, an imaging module, a processing module and an anti-explosion shell. The coal-rock interface identifying method and the system provided by the invention have the characteristics of simple structure, easiness for distributing, high suitability and the like, the coal-rock type cut by using the drum can be automatically identified in real time, and reliable coal-rock interface information is provided for automatic heightening of the drum of the coal mining machine.

In conventional systems using an onboard camera disposed rearward of a vehicle for recognizing an object surrounding the vehicle, the object is recognized by the camera disposed rearward of the vehicle. In the image recognized by the camera, a road surface marking taken by the camera appears at a lower end of a screen of the image, which makes it difficult to predict a specific position in the screen from which the road surface marking appears. Further, an angle of depression of the camera is large, and it is a short period of time to acquire the object. Therefore, it is difficult to improve a recognition rate and to reduce false recognition. Results of recognition (type, position, angle, recognition time) made by a camera disposed forward of the vehicle, are used to predict a specific timing and a specific position of a field of view of a camera disposed rearward of the vehicle, at which the object appears. Parameters of recognition logic of the rearwardly disposed camera and processing timing are then optimally adjusted. Further, luminance information of the image from the forwardly disposed camera is used to predict possible changes to be made in luminance of the field of view of the rearwardly disposed camera. Gain and exposure time of the rearwardly disposed camera are then adjusted.

The invention discloses a method of two-dimensional face image recognition, pertaining to the field of pattern recognition and computer vision. The method includes that: building a three-dimensional face deformation model according to the known three-dimensional face database; inputting a two-dimensional face image to register, and rebuilding in three dimension the registered two-dimensional face image using the three-dimensional face deformation model to obtain the three-dimensional rebuilt result of the registered two-dimensional face image; by constructing an illumination model, generating a virtual image with the changing posture and illumination in the three-dimensional rebuilt result; designing a change limitation classifier using the virtual image; inputting the two-dimensional face image to be recognized, implementing feature extraction and compression processing, then inputting the features processed by extraction and compression processing to the change limitation classifier, outputting the classified result, and finally realizing the face image recognition. The method in the invention realizes the full automation of the recognition procedure, enhances the recognition accuracy, and largely improves the recognition speed.

The invention relates to a character extracting method in a digital video based on character segmentation and color cluster, which comprises the following steps: (1) character segmentation: utilizing the characteristic differences of a character area and a character interval area to carry out vertical projection to segment images in the character area, namely, segmenting each row of area image containing a plurality of characters into a plurality of subarea images only containing a single character so as to reduce the post operating and treating difficulties and improve the identifying accuracy rate of OCR; and (2) character extraction: firstly, using the character color characteristic in the image to cluster colors, finding out an image layer containing maximum character information as a target image layer, and deleting the background area; and then, using the communicating characteristics of the characters to analyze a communicating area of the target image layer, and removing non-character areas to obtain such three results as single character images, an integral image of the character area and an integral image spliced by the single character images respectively, wherein all the three results are input to an OCR system to be identified, and the latter two results use the semantic processing function of the OCR and can accurately determine the characters with similar forms according to the context to improve the identifying effect.

The invention discloses a vehicle information detecting and recognizing system under the multilane condition. The vehicle information detecting and recognizing system comprises a computer system and a portal frame stretching over lanes, wherein a laser scanner and a high-definition license plate recognition device are arranged on the portal frame, a first dot matrix type wheel shaft sensor, a shaft weight sensor and a second dot matrix type wheel shaft sensor are sequentially arranged on the lane under the portal frame, and the laser scanner, the high-definition license plate recognition device, the first dot matrix type wheel shaft sensor, the shaft weight sensor and the second dot matrix type wheel shaft sensor are respectively connected with the computer system. The vehicle information detecting and recognizing system has the advantages that the two-dimension cross section size and the running position of a vehicle are detected through the laser scanner, and the vehicle three-dimension reconstitution and the vehicle separation are realized; the license plate information and the human face information are precisely collected through the license plate recognition device; the vehicle information such as the shaft distance, the shaft length, the shaft number, the shaft type, the wheel distance, the wheel width and the wheel number are measured according to signals output after a vehicle tyre presses the wheel shaft sensor; and the shaft weight and the total weight are measured through the shaft weight sensor.

The invention relates to an attendance system and method, in particular to a position-based attendance system and method. The attendance system comprises a mobile phone attendance client and an attendance device; and the attendance method comprises the following steps that: a user logs in the attendance device through the mobile phone attendance client; when the mobile phone attendance client judges that a mobile phone is in an attendance range through a position positioning module arranged in the mobile phone, biological characteristics of the user are acquired through the mobile phone attendance client and are transmitted to the attendance device; and the attendance device finishes the attendance after the identification is successful. By adoption of the technical scheme, personnel is not required to reach the position where the attendance device is positioned to perform attendance; and moreover, the attendance system can be operated by multiple persons simultaneously, the attendance efficiency is improved, and the personnel identification rate is high.

The embodiment of the invention discloses a method for recognizing face images, which comprises the steps of: accurately positioning two-dimensional face images in a preset database; conducting three-dimensional reconstruction to the two-dimensional face images according to a preset three-dimensional face image model and the accurate positioning results of the two-dimensional face images to obtain three-dimensional face images; conducting illumination model treatment to the three-dimensional face images to obtain virtual images with changing postures and illumination; classifying the virtual images to obtain classification results and taking the classification results as preset classification results; and recognizing the two-dimensional face images to be recognized by using the preset classification results. The method increases the sample space of the posture and illumination change of images by the three-dimensional reconstruction and illumination model treatment of the two-dimensional face images to generate virtual images and accelerates the three-dimensional reconstruction to a great extent simultaneously, thus leading the recognition of face images to have higher efficiency and recognition rate.

The present invention provides a fixed bayonet electron police shoot device, including a CCD close-up vidicon, a panoramic camera, an embedded industrial personal computer, a topomorph floor sensing detector, a L type fixing support, a speed detecting radar for police; the floor sensing coil couples the coil signal in the topomorph floor sensing detector; the topomorph floor sensing detector analyzes the coil sensing signal changes and informs the embedded industrial personal computer by signal; the detecting radar for police real-time detects the vehicle speed, and informs the speed to the embedded industrial personal computer; the embedded industrial personal computer controls the detecting radar for police and detects the speed of the vehicle, when overspeed signal is present, and the vehicle detector acquires processed signal, the embedded industrial personal computer controls CCD close-up vidicon to collect close-up picture, and controls the panoramic camera to collect panoramic picture. The invention greatly improves detecting ratio of the violation of laws of the overspeed vehicle, and processing real-time violation of laws detection, real-time shoot to the bayonet vehicle, no laborer required.

The invention discloses a three-dimensional convolutional neural network (3D CNN) based video classifying method and belongs to the technical field of video processing. According to the method, a video is sampled at equal intervals to obtain a plurality of video segments, a video database is amplified, three-dimensional video segments are directly input into a 3D CNN, and time domain and space domain characteristics of the video are extracted, so that the limitation of a conventional video classifying method in manually selecting video characteristics and video modeling modes is improved. A parallel distributed 3D CNN multi-classification model lowers the complexity in learning the 3D CNN and enables a classification system to realize distributed parallel computation more conveniently. Relatively high identification rate can be achieved with only fewer video segments based on a 3D CNN multi-classification system, and videos not belonging to any type can be classified into new type, so that the classification error of the new type is avoided.

The invention relates to a video monitoring system and method for target detection and tracking. The system comprises a video collection device, a target detection device, an information processing device, an information transmission device and an image collection device, wherein the image collection device is composed of a front end image collection device and a video decoding device and is usedfor obtaining a real-time video stream of a target object; the target detection device analyzes the position and the size of the target object in a video image; the information processing device performs real-time processing on related information of the target object within a continuous time to obtain a moving speed, a trajectory and direction information of the target object, and judges the number, the location and the size information of the target object in advance; the information transmission device sends the related information of the target object to the image collection device; and the image collection device controls the target object to always locate in a middle area of the screen and tracks the target object in real time. According to the video monitoring system and method, thetracking of numerous small targets is facilitated according to the deep neural network with multiple features, the recognition rate is improved, and it is beneficial to the good running of the tracking algorithm, and real-time tracking of the target object is achieved.

A method for detecting the legitimacy of an application program behavior comprises the following steps: monitoring one or more system interfaces of a computer to cause the monitored system interfaces to jump to a monitoring module for execution when the monitoring system interfaces receive a call; blocking the application program of a caller and judging the validity of the caller: permitting the caller to call an interface function and continuously perform the application program of the caller if the caller is legal; and, pausing the behavior of the application program of the caller and issuing an intrusion alarm if the caller is illegal. The detection method finds out whether an executor of the application program behavior is legal or not by monitoring the system interfaces of the computer so as to intercept the program behavior executed by illegal executors and give an alarm. Compared with the existing fuzzier behavioral analysis technology, the detection method has the advantages of low false alarm rate, high recognition rate and the like, especially has good defense effect against the intrusion behavior due to overflow vulnerability, so the detection method is an effective supplement to the existing behavior analysis defense technology.

The invention relates to a face recognize system, comprising a network interface module, a dual-core chip SOC module connected with the network interface module, a CPLD address code, a DDR2 high-speed operation memory, and an external program memory, or even with a hard disk with an IDE. The dual-core chip module is connected with the high-speed operation memory via a data bus. The CPLD address code via an EMIF bus is connected with the external program memory NAND Flash or connected with the IDE hard disc too. And the whole system is powered by a power module. The recognize method comprises video code compression, pretreatment, motion check, face positioning, organ positioning, normalizing, character extraction, face comparison, and data communication. The invention has the advantages in high recognize rate and high recognize speed, strong data processing ability, better compatibility with prior detect network, stable operation, easy upgrade and maintenance, with low cost.

The invention discloses a polling robot for a transformer substation. The robot comprises a body, a data acquisition module, a master control module, a motion control module, a temperature control module, a communication module and a power supply management module, wherein the robot body is of a four-wheeled robot trolley structure; the data acquisition module detects the surrounding environment,including a video image, an infrared temperature, a real-time position and an operating state, by means of a sensor and transfers the detected information to the master control module; the master control module is a data processing and logic control center of the robot; the motion control module controls actions of moving parts of the robot in a centralized manner; the temperature control module comprises a fan, a temperature sensor, an electric heater and a PLC; the communication module transmits data of the video image, infrared temperature, real-time position and operating state to a localbackground monitoring sub system by way of wireless communication. The robot provided by the invention is suitable for rigorous working environments, is high in image recognition rate and is good in obstacle crossing and climbing ability.

The invention discloses a method for quickly identifying two-dimension code system type in images, comprising a learning training process and a classification identifying process. The learning training process is as follows: collecting and building a sample image set of various two-dimension code images; converting each sample image into a grey image, performing Gaussian smoothing filtering and binaryzation to obtain binaryzation images; scanning prospect boundaries of the binaryzation images in the horizontal and vertical directions, obtaining an outer boundary point set of the two-dimension code; enabling the two-dimension code to be horizontal by rotating images, achieving horizontal correction of the two-dimension code; performing partitioning, combining and normalizing for the two-dimension code; performing fast wavelet transform for the normalized sample image to obtain a wavelet characteristic sample set. The classification identifying process is as follows: extracting wavelet characteristic of the to-be-identified image to build a distance measurement model; using the K nearest neighbor algorithm to identify code system type. The method is convenient and quick, has real-time performance, accuracy and high identification rate.

The invention discloses a face recognition method and device. The method comprises collecting images including a face image; acquiring facial features of a face in the images; matching the acquired facial feature in a facial feature database, and determining a match range, a mismatch range or an to-be-recognized range, to which the match result belongs; sending a target person recognition prompt information if the match result belongs to the match range; sending a non-target person prompt information if the match result belongs to the mismatch range; and returning and executing the step of collecting images including the face image until detecting an end instruction or sending the target person recognition prompt information and the non-target person prompt information if the match result belongs to the to-be-recognized range. According to the invention, a processor can recollect the images until the image is recognized accurately when the match result belongs to the to-be-recognized range resulting from the fact that the camera picked up a blur image or the deflection angle between the target person and the camera exceeds a definite angle.

The invention relates to a method for identifying sound scenes based on a CNN (convolutional neural network) and random forest classification. The method comprises the following steps of generating Mel energy spectrum and a segment sample set of the sound scene through a Mel filter; utilizing the segment sample set to perform two-phase training on the CNN, and cutting off the feature output of a whole connecting layer, so as to obtain the CNN features of the segment sample set; finally, utilizing a random forest to classify the CNN features of the segment sample set, so as to obtain a final identifying result. Proofed by related experiment results, the method has the advantage that the identification rate on an IEEE DCASE2016 sound scene evaluation data set is better than the identification rate of an MFCC-GMM (Mel frequency cepstrum coefficient-gaussian mixed model) method, and is also better than the identification rate of the existing related identifying methods.

A decision feedback equalizing apparatus selectively using a feedback filter and a method thereof are provided. The apparatus includes: an equalizing unit including a feed forward filter (FFF) for correcting a distorted transmission channel by receiving a match-filtered signal and a feedback filter (FBF) for reducing inter symbol interference ISI of the corrected transmission channel for driving only the FFF in a blind mode and driving the FFF and the FBF in a decision directed mode; a diverge/converge determining unit for determining whether the decision feedback equalizing apparatus is diverged or converged using a unit square error obtained through a least unit square algorithm; and a filter controlling unit for controlling the equalizing unit in a blind mode if the decision feedback equalizing apparatus is determined as divergence, and for controlling the equalizing unit in a decision directed mode if the decision feedback equalizing apparatus is determined as convergence.

The invention discloses a dynamic gesture identification method in an interactive system, comprising the following four steps of: acquiring an image, and obtaining a current image frame after denoising; obtaining a moving region of the image by calculating the difference of the current image frame and a reference image frame, and obtaining a binary image by a skin color detection method; carrying out gesture segmentation on the binary image by a gray level projection method to obtain a gesture region and a barycentric position; and obtaining a final identification result by a classification identification method according to the barycentric position and fingertip characteristics. The method can be used for overcoming the problems of high complexity, low real-time quality and low identification rate in traditional algorithms, has the advantages of simplicity in implementation, good real-time quality and high identification rate, and can be applied to the dynamic gesture identification very well. Moreover, the method can tolerate the translation of a definition gesture, the scale and the transformation of a rotation angle, and has a good robustness.

The invention discloses a convolutional neural network-based method for recognizing targets in front of vehicles. The method comprises the following steps that: 1, a large number of traffic-related images are obtained and are adopted as samples, left-and-right mirroring transformation is performed on the collected images, data sets are expanded, and labels are fabricated; color channel combinationis performed on each color image, and a grayed training data set and a test data set are fabricated; 3, a convolutional neural network model is constructed on an MATLAB platform; and 4, the trainingdata set is inputted into the convolutional neural network, so that a trained convolutional neural network is obtained; and 5, the test data set is inputted to the trained convolutional neural network, so that a recognition rate can be obtained. The method of the invention can detect vehicles and pedestrians in pictures taken by monocular cameras, has a high recognition rate and can realize the function of classifying obstacles in front of different types of vehicles.

The invention provides a text recognition method and device. The method comprises: determining convolutional neural network (CNN) features of a text image and obtaining an eigenvector sequence of a preset dimension; and using a recurrent neural network (RNN) to decode the eigenvector sequence of the preset dimension, and obtaining texts in the text image to be recognized. According to the technical scheme provided by embodiments of the invention, the method combines the CNN and RNN to achieve integral recognition of the text image to be recognized, so that the method avoids the problem that texts need to be separated character by character and then recognized character by character in the prior art which leads to accumulated errors, and the text recognition rate can be improved.

The invention discloses an SAR image target recognition method based on sparse representation. The SAR image target recognition method based on sparse representation mainly resolves the problem that an existing method is complex in preprocessing and difficult in estimation of an azimuth angle. The SAR image target recognition method based on sparse representation comprises the steps of (1) extracting partial features of an image and studying a recognizable dictionary through a diversity density function; (2) carrying out sparse encoding on each partial feature through the dictionary, and then carrying out space pooling on each divided sub-area through a space domain pyramid structure to obtain feature vectors of the sub-areas samples of a training set and a test set; (3) weighing the corresponding sub-areas of a test sample according to the sparsity of each sub-area of the test sample; and (4) combining the weighed sub-areas together and recognizing the image through a sparse representation method. Compared with the prior art, the SAR image target recognition method based on sparse representation has high robustness for shielded and partial noise, improves the recognition accuracy of an SAR target without estimating the azimuth angle, and can be used for image processing.

The invention discloses a face recognition method based on reference features. The method comprises the following steps that: scale invariant features and local binary pattern features of a face image to be recognized are extracted; a principal component analysis method is utilized for dimensionality reduction to obtain the image features of the face image to be recognized; the similarity of the image features to a cluster center is calculated by utilizing the obtained image features to obtain the reference features of the face image to be recognized; and the similarity of the reference features of the face image to be recognized and the reference features of training data concentration is calculated to obtain an analysis result. The reference features of the face image provided by the invention comprise texture information and structure information of the face image, so that the method provided by the invention can more comprehensively represent the face compared with the method in the prior art, which only represents the texture information or the structure information of the face. The process of feature extraction is simple and easy to realize; the recognition result is highly precise; high recognition rate of different facial gestures of the same person is realized.

The invention provides a registering method and system of face identification access control. The system comprises a mobile terminal, a server and at least one access control device; the method comprises following steps of associating the mobile terminal with an indoor unit; sending the associated mobile terminal information to the server; collecting face data through the build-in camera of the mobile terminal; sending the collected face data information to the server; receiving and storing the face data information sent from the mobile terminal by the server; searching the access control device associated with the mobile terminal information; informing the access control device of downloading the face data information; receiving the downloading notice of the server by the access control device; downloading the face data from the server; registering the downloaded face data in the access control device; associating with a user; and finishing registering. According to the method and the system provided by the invention, the face data can be updated timely; the face can be identified and registered very conveniently; moreover, the face database is enriched; and the identification rate of the access control device in identifying the face is improved.

The present invention provides a system and method to enhance speech intelligibility and improve the detection rate of automatic speech recognizer in noisy environments. The present invention reduces an acoustically coupled loudspeaker signal from a plurality of microphone signals to enhance a near end user speech signal. A decision unit checks a system configuration parameter to determine if the cleaned speech is intended for human communication and/or Automatic Speech Recognition (ASR). A formant emphasis filer and a spectrum band reconstruction unit are used to further enhance the speech quality and improve the ASR recognition rate. The present invention can also apply to devices which has a foreground microphone(s) and a background microphone(s).