2932results about How to "Realize identification" patented technology

The embodiment of the invention provides a touch display panel with a pressure detection function, a display device and a driving method and relates to the technical field of display. Compared with the prior art, the mechanism design of a display does not need to be changed. The touch display panel comprises a plurality of touch electrodes arranged on a box combining substrate, touch electrode walking lines electrically connected with the touch electrodes, a plurality of pressure detection electrodes arranged on the box combining substrate or an array substrate and pressure detection electrode walking lines electrically connected with the pressure detection electrodes. Any pressure detection electrode corresponds to at least one touch electrode. Relative to the pressure detection electrodes, the touch electrodes are closer to the light emitting side of the touch display panel. The touch display panel is used for meeting the requirement for the pressure detection function.

The embodiment of the invention provides a fraud recognition method and a fraud recognition device. The method comprises steps: a transaction data sample set is acquired, wherein each piece of transaction data in the sample set at least comprises fund flow information, transaction party correlation information and transaction data fraud risk attributes; a fraud spreading relation graph is built according to the sample set, wherein each node in the fraud spreading relation graph is built according to the transaction party correlation information, and the directed edge between the nodes is builtaccording to the fund flow information and the transaction party correlation information; an initial node value is assigned to each node in the fraud spreading relation graph; according to a PageRankiterative updating algorithm, the node value of each node is subjected to iterative updating until iterative convergence to obtain a final node value; and if the final node value is higher than a preset threshold, the corresponding node is determined to be a fraud person node, and the transaction data correlated to the fraud person node are fraud risk data.

The invention discloses a method and a system for recognizing images, which relate to a method and a system for recognizing static target images by adopting the image recognition technology. The invention solves the problem that the recognition speed is relatively slower in the prior image recognition technology. The method and the system for recognizing the images are characterized in that image information in the identification area and characteristic information in the identification area are stored as template information, then the area to be recognized in the images to be recognized is confirmed by adopting the identification area, then the characteristic information in the identification area is compared with that in the area to be recognized, when the similarity of both characteristic information in the identification area and that in the area to be recognized is in the error range, users consider that the images to be recognized and the target images are mutually matched, so as to realize image recognition, in the recognition process, the characteristic information in the area to be recognized is just needed to compare, the data quantity is less, and the logical reasoning and the mathematical operation of the characteristic information are not required, thereby quickening the speed of image recognition. The invention is mainly used for searching matched images, for example, bill recognition, seal recognition and the like.

The invention discloses a method and a system for effectively realizing anti-cheating remote online examination. According to the method, a face recognition technology is used for performing identity recognition on examinees, relative positions of faces, computer display screens for examination, keyboards and mice are compared for positioning recognition, and face information acquired during examination enrollment is compared by using a database technology; in an examination process, when the faces or eyes of the examinees are identified to leave a set identification range of the system, or faces acquired in an examination area are discovered to be inconsistent with faces acquired during application for examination paper for the first time after the system regularly or irregularly transmits identity recognition face comparison requests, the remote online examination system acquires set processing modes of the system, such as the operation of screen blacking, vibration prompting, sound production prompting, forcible paper collection and the like; and before the end of the examination, when the faces of the examinees leave the identification area for a set time, the system automatically collects the paper.

The invention discloses a two-dimensional image recognition and object reconstruction method based on a three-dimensional model database. The method includes the following steps: a three-dimensional model of an object used for a two-dimensional projection is constructed, the three-dimensional model database is established and an correspondingly correlative attribute database is built up; the two-dimensional projection matching degrees of a two-dimensional image of the object to be recognized and the three-dimensional model of the relative object are compared; as for the two-dimensional projections being in accordance with the matching degree requirement, the object in the correlative attribute database is recognized as the object in the two-dimensional image; and the three-dimensional model in the three-dimensional model database which is correlative to the object in the attribute database is used for reconstructing the object. Due to the adoption of the comparison of the two-dimensional image of the object with the two-dimensional projection of the relative three-dimensional model, the aim of recognizing the object in the two-dimensional image of the object is realized and the two-dimensional images of the object which are photographed in a plurality of angles and from a plurality of directions are recognized; moreover, the aim of reconstructing the object in the two-dimensional image is achieved by using the correlative three-dimensional model; in addition, a paralleling calculation method is adopted to accelerate the speed of the reorganization and the reconstruction.

The invention relates to an event trigger word extraction method, in particular to an event trigger word extraction method based on a document level attention mechanism, comprising the following steps: (1) preprocessing training corpus; (2) performing word vector training by using PubMed database corpus; (3) constructing a distributed representation way of a sample; (4) constructing a characteristic representation way based on BiLSTM-Attention; (5) adopting CRF learning, and acquiring an optimal sequence labeling result of the current document sequence; and (6) extracting event trigger words.The method provided by the invention has the advantages that firstly a BIO tag labeling way is adopted, and recognition including multi-word trigger word recognition is realized; secondly a corresponding simple word and characteristic distributed representation way is constructed for a trigger word recognition task; and thirdly, a BiLSTM-Attention model is proposed, a distributed representation structure specific to the currently input document level information is realized by introducing an Attention mechanism, and trigger word recognition effect is improved.

The invention discloses a plane and barrier detection method based on an RGB-D camera and an attitude sensor, and the method achieves the environmental three-dimensional information recognition with higher resolution, higher refresh rate and higher precision based on the RGB-D camera and the attitude sensor. The method can achieve the recognition of a ground passage, the judgment and early-warning of a ground cavity and various types of barriers and the recognition of scenes of going upstairs and downstairs, and is close to the visual sensing of an environment. Through the cooperation of the attitude sensor, a whole system is more flexible and portable, and the camera does not need to keep a fixed relative position with a user or any other ground reference object. When a visually-impaired person goes out, the camera can be placed at any body part which can photograph a three-dimensional environment. A portable computer or pad compatible with the RGB-D camera can be selected by himself or herself to achieve the same function.

The invention discloses a method for carrying out joint learning on space-time information of an image pulse sequence and an image recognition method. The method comprises the following steps of establishing a pulse sequence unit Spike cube and LIF neuron model on the basis of the pulse neural network, and learning synaptic weights and excitation thresholds, which are connected with each other, ofneurons of the pulse neural network by adopting an STDP mechanism; and using the trained model to carry out image classification and identification. The invention provides a new technical scheme forstructural design and learning of a pulse neural network and image pulse sequence learning and recognition, and also provides a new processing method for pulse data output by a DVS and other bionic vision cameras.

The invention discloses a partially covered face identification method based on data enhancement. By means of the artificial intelligence depth convolution neural network, the face alignment, facial detection, face feature extraction, and face matching are carried out for many times; through the principle of data enhancement, the pre-judgment of the covering type of the object covering a standard face, and the pre-judgment of the identity of the covered face, the two pre-judgment results are integrated to carry out the data enhancement, a covered face database is reconstructed by taking the standard face as the basis, and at the end, the original covered face and the reconstructed covered face are subjected to matching. The method solves the technical problems that the existing covered face identification method is easy to loss characteristic information due to the covering, is difficult to carry out the face identification, and low in identification accuracy, thereby achieving the technical effects of improving the face identification accuracy and efficiency.

The invention discloses an optical fingerprint sensor module. The optical fingerprint sensor module comprises an optical fingerprint sensor, a protective layer, a backlight source and a touching sensing layer, wherein the optical fingerprint sensor comprises a light-transmitting substrate and a device layer located on the surface of the light-transmitting substrate, the device layer comprises a pixel area, the pixel area has a plurality of pixels, all the pixels comprise light-transmitting areas and non-light-transmitting areas, the non-light-transmitting areas comprise photosensitive elements, and the light-transmitting areas allow a light ray to be capable of penetrating through the pixel area of the device layer; the protective layer is located above the optical fingerprint sensor; the backlight source is located below the optical fingerprint sensor, and an included angle formed between a light ray emitted by the backlight source and the surface of the pixel area is an acute angle; the touching sensing layer is located between the protective layer and the optical fingerprint sensor. According to the optical fingerprint sensor module, the structure and the performance are improved, and the function is enhanced.

The embodiment of the invention discloses a two-dimension code recognition method and a device, wherein the method comprises the following steps: a local image of the device is subjected to two-dimension code positioning to determine whether the local image contains a two-dimensional code, and if the local image contains the two-dimensional code, positioning, segmenting and decoding operations on the local image are carried out. The two-dimension code recognition method has the advantages that the local image is subjected to two-dimension code positioning to determine whether the local image contains the two-dimensional code, if the local image contains the two-dimensional code, the two-dimension code is recognized, and the two-dimension code image recognition can be realized without camera photographing.

The invention discloses a Hough transform-based lane line detection method. In view of defects that the existing lane line detection technology needs to build a specific model, the algorithm is complicated, the efficiency and the real-time performance is poor, as for an image containing the lane line after Hough transform, the position information of a lane line pixel is used for lane line detection and tendency judgment, the algorithm has good real-time performance, and a detected lane line can be obtained efficiently. The method does not need to introduce many parameters to help to tell a curve, a tedious method of lane line modeling and the like is not needed, the method can be applied to a common lane and an expressway, recognition on the curve tendency is realized simply and quickly, and the real-time performance and the accuracy are good.

The invention provides a voice recognition system and a voice recognition method used for individual equipment. The voice recognition method includes the steps of of: acquiring user voice input and recognizing the input voice on the basis of a limited grammar recognition network so as to acquire a first recognition result; in response to the first recognition result which does not satisfy the recognition acceptability condition, recognizing the voice input on the basis of a large vocabulary continuous voice recognition network to acquire a second recognition result; selecting a preferential result from the first recognition result and the second recognition result to be used as the final decoding result for the voice input. The embodiment of the invention provides a new voice recognition method and a new voice recognition device which are capable of supporting intelligent response to continuous voice inputs and quick response to a short voice command under uniform system interfaces.

The invention provides a method and a device for identifying touch gestures. The method comprises the following steps: orderly acquiring coordinate data of at least four points in a gesture track detected on a resistive touch screen; determining angles rotated by the acquired points relative to the acquired first point and comparing the angles rotated by the various points relative to the first point by utilizing the coordinate data; and determining that the touch gestures are rotary motion or telescopic motion according to an acquired comparison result. Aiming at the defect that the resistivetouch screen cannot detect respective positions of two points when the two points are touched, and can only detect a track formed by an intermediate point between the two points, the method determines the angels rotated by the acquired points relative to the acquired first point and determines a motion trend according to the angles rotated by the various points relative to the first point so as to skillfully identify the two-point touch gestures on the resistive touch screen.

The invention discloses a memory network-based intention recognition method under multi-round dialogues. A neural network model combining a recurrent neural network, a memory network and an attentionmechanism is mainly adopted. The method comprises the steps of firstly performing mathematical processing on a language; secondly encoding each round of the dialogue by utilizing the recurrent neuralnetwork to obtain an encoding vector of the dialogue; thirdly storing historical dialogue information by utilizing an external memory; fourthly, selecting the historical dialogue information related to an intention of the current round of the dialogue from the memory through an attention mechanism, thereby obtaining an encoding vector of the historical information; fifthly, for the current dialogue encoding vector and the historical dialogue encoding vector, judging whether the historical information is introduced in a classifier or not by utilizing a control gate, thereby obtaining encoding information which is finally used for classification; and finally, obtaining the intention of each round of the dialogue by utilizing the multi-label classifier.

The invention discloses a system for real-time identifying urban traffic lights based on single eye vision and a GPS integrated navigation system. The system establishes a map of traffic lights in an off-line manner through the methods of interactive image annotation, camera calibration, 3D position recovery, etc., and provides position coordinates and semantic attributes of the traffic lights under the globally positioned GPS coordinate system. Upon online detection, with the established offline map of traffic lights as a prior, an area of interest is determined by solving the substantial scope of the traffic lights in images in combination with the pose position, and the identification of the color segmentation and shapes of the traffic lights are carried out by using form information of the traffic lights in the area of interest. The system is applicable to road conditions and scenarios of different kinds, implements stable and long-distance detection sensing of the traffic lights under various environments. Since the system adopts a low-cost and low-power consumption navigation device, an image acquisition device and a computer platform, the system can be widely applied to the fields of vision navigation of driverless vehicles, vision auxiliary driving of intelligent vehicles, etc.

The invention relates to a telcom phone phishing-resistant method and a telcom phone phishing-resistant system based on discrimination and identification content analysis. By improving the efficiency and the accuracy rate of the voice and semanteme identification during calling, and using a Chinese semanteme determining technology, the cold call transmitter is determined whether or not to be a phishing call. The method specifically comprises the following steps of: analyzing the voice by large vocabulary provided by the invention and the large vocabulary continuous speech recognition (LVCSR) of nonspecific person during calling between two parts, determining the analyzed key words or key numbers, constructing a strategy engine by an algorithm, analyzing and classifying the semanteme of a calling party at a cloud service side by the algorithm, analyzing key information in the voice, synchronously matching the information of the bank to which the calling person belongs, and determining whether or not the call is the phishing call. Generally speaking, according to the method, the happening of the phone phishing can be effectively avoided particularly, the user safety can be protected through the discrimination and identification identifying and determining mode and the cloud platform information mining and matching mode, and the voice identification and the suspicious call relevance ratio can meet the normal use as well.

The invention which relates to an optical instrument and detection imaging technique discloses a large field depth iris image acquisition system and a method based on a plurality of fixed-focus cameras. The system comprises an iris image collecting device and an image recognition device. The method comprises the following steps: respectively imaging the iris by means of the fixed-focus cameras having different imaging object distance ranges and producing a multi-path fixed-focus image results; choosing one or a plurality of multi-path fixed-focus image results through distance measurement or image quality evaluation method; carrying out image processing and identification of chosen qualified iris image data. The invention effectively integrates the imaging ranges of different fixed-focus cameras in the mode of self-adapting switchover, thereby taking advantages of the cameras and at same time removing disadvantages of the cameras, enlarging the integral imaging range of the acquisition system, and improving the feasibility of an iris recognition system. Compared with the prior iris imaging method adopting a zoom camera, the invention has the advantages of low cost, quick and noiseless focusing.

The invention discloses a parking line parking space recognition method and device based on information fusion. The parking line parking space recognition method comprises the steps that a parking space angular point is recognized from an aerial view of the side face of a car body, when the parking space angular point and a camera are parallel, coordinates of the parking space angular point at themoment are recorded, and the parking space angular point is made as the first parking space angular point; an ultrasonic radar of the car starts to detect whether or not a barrier exists in the sidedirection of the car towards the first parking space angular point, if yes, the last step is executed, and if not, the next step is executed; similarly, a second parking space angular point is obtained; according to the two parking space angular points, the approximate parking space width of the parking line parking space and the later distance between the parking line parking space and the car are calculated. Detection recognition for the parking space with standard parking marking lines can be achieved, the ultrasonic radar is used for recognizing whether or not a barrier exists inside the parking space for detection, a running distance value obtained by a wheel speed sensor and visual information are fused to obtain coordinates of the parking space angular point, and finally recognitionof the parking line parking space is achieved.

The invention relates to an automatic WEB client man-machine identification method. The method comprises steps that: a request from a client is received, an identification secret key KEY which can identify the client is generated according to an IP address of the client and partial information of an HTTP request header, the KEY is placed in one Javascript code segment, and the progress returns back to the client. After the client receives and carries out the Javascript code, a client identity Cookie containing the KEY is generated, and the Cookie is used for accessing the WEB server for another time. If the request contains a correct Cookie value, the client is taken as a browser, the access is ok. If the request does not contain the correct Cookie value, the client is taken as a non-browser, and the request is neglected. The method realizes browser and non-browser identification of the transparent client, can effectively reduce accesses of automatic tools, e.g., WEB crawlers, WEB scanners and webpage information acquisition programs, is especially suitable for being applied to a website which requires public announcement of information and hopes that the published information is not acquired by an automation WEB.

The invention relates to a method capable of identifying and recognizing an ultrasonic probe and an ultrasonic treatment device. The ultrasonic treatment device comprises a device body and the ultrasonic probe. The device body comprises a controller, a power output circuit and an identification access module. The ultrasonic probe comprises an ultrasonic wave transducer and an identification and storage circuit with unique identification information. The identification and storage circuit is a storage type electronic device where data can be written and read. The ultrasonic wave transducer is connected with the power output circuit. The identification and storage circuit is connected with the identification access module. Writing-in data set in storage space of the identification and storage circuit comprise use duration parameter information of the ultrasonic probe which is arranged in the storage space by the controller through the identification access module. According to the ultrasonic treatment device, the ultrasonic probe is effectively managed by identifying and recognizing the ultrasonic probe, and the stability of the effect during treatment is guaranteed.

The invention discloses a transmission tower modal parameter identification method based on an improved subspace algorithm and used for completing the modal parameter identification of a large span transmission tower structure through individually utilizing response data under the excitation of a field environment. According to the identification process, multi-group packet response data are integrated into synchronous pulse response data based on a random subspace identification principle; the integrated data avoid fitting errors caused by the packet identification, so the synchronous integrated identification of the data is realized; and a stable graph is constructed by utilizing modal parameter identification results under different system orders, so a modal parameter identification order determination problem under the environment excitation is solved, modal omission and repetition phenomena of traditional methods of a peak value method and the like are avoided, the obtained identification result is accurate and stable, and bases are established for subsequent structure damage detection and life estimation.

The invention belongs to the technical field of rotation machinery fault diagnosis, especially relates to a planetary gear case fault diagnosis method based on order complexity, and is specially applied to a fault diagnosis method of a wind power planetary gear case under a variable working condition. The method comprises the following steps: preprocessing vibration signals; dividing faults of a planetary gear train into two kinds; obtaining a fault feature parameter; analyzing the vibration signals under a variable working condition of a planetary gear case; and performing instance verification discovery. According to the invention, the influence of the variable working condition can be avoided by use of an order analysis method, and the Lempel-Ziv complexity of angle-domain signals after order analysis processing is more stationary than that of time-domain signals. According to the Lempel-Ziv complexity of the vibration angle-domain signals of the planetary gear case, local faults and distribution faults of planetary gears can be identified, through simulation and analysis of actual cases, the effectiveness of the method is verified, and at the same time, under the condition of lack of fault data, the complexity can also be taken as the feature parameter for determining whether there is a fault or not.

The embodiment of the invention provides an array substrate, a display device and a fingerprint recognition control method, and relates to the technical field of display. Fingerprints can be recognized through a display area of a display panel under the condition that the display panel displays a picture. Grid lines and data lines which are horizontally and vertically staggered to each other are arranged on a base substrate, and the grid lines and the data lines interact to define at least one sub pixel; and a plurality of photosensitive elements are arranged on the array substrate, the photosensitive elements are arranged between two adjacent sub pixels, the photosensitive elements are connected with driving signal lines and reading signal lines, and the photosensitive elements are used for receiving finger reflected light under the control of the driving signal lines, carrying out photoelectric conversion and outputting converted electric signals from the reading signal lines connected with the photosensitive elements.

The invention provides a device for monitoring heart rate and physical state. Sensors are mounted on a waistband, and the device comprises a data acquisition module, an FPGA (Field-Programmable Gate Array) control module and a DSP (Digital Signal Processor) data processing module. When the heart rate and the physical state of a subject change, the sensors collect body dynamic signals generated from the changes; the body dynamic signals generated from heartbeat after being processed by an analog, amplification and filter circuit and the body dynamic signals generated from changes of the physical state are output to the FPGA respectively through A/D (Analog/Digital) conversion circuits; the FPGA sends the body dynamic signals to the DSP to perform body dynamic signal processing by selectingone or multiple paths sensors, so as to calculate the heart rate and judge the physical state, and obtained data are fed back to the FPGA; and the FPGA sends the data to a monitoring center workstation by externally connecting a serial port with a communication module according to the information fed back by the DSP. The device provided by the invention can complete real-time, quick and accurate acquisition of multi-path signals to obtain physiological information of human body, and is combined with the wearing technology to realize long-term dynamic monitoring and identification of physiological information.

The invention discloses an information processing method and an information processing system for handwriting on paper. The method comprises the following steps of: acquiring clues of a real page currently written by a user, and determining a background page according to the clues; determining the handwriting of the user and the corresponding position of the handwriting in the background page; and associating the handwriting and/or the literal contents of the handwriting and contents at the corresponding position in the background page according to the corresponding position of the handwriting in the background page. By the method and the system, the handwriting and the background page corresponding to the handwriting can be recognized.