271results about How to "Guaranteed recognition effect" patented technology

The invention discloses an automatic guided vehicle navigation control system and a navigation control method thereof. The automatic guided vehicle navigation control system comprises a central controller, sub controllers, a QR (Quick Response) code positioning system, a grid path navigation system and a goods register system, wherein the sub controllers are arranged on each automatic guided vehicle and connected with the central controller; and the QR code positioning system, the grid path navigation system and the goods register system are arranged on each automatic guided vehicle and respectively connected with the corresponding sub controller. According to the automatic guided vehicle navigation control system and the navigation control method thereof disclosed by the invention, the QR acquisition sensing technology is adopted for acquiring coordinate information of the automatic guided vehicle in a storehouse, so that unified monitoring and management are convenient; the grid path navigation system is adopted for judging the deviation between the practical operation track of the automatic guided vehicle and the predetermined track, so that two wheel differential base plates are adjusted to carry out track compensation, and therefore, the automatic guided vehicle is enabled to drive according to the planned path. Moreover, the structure is simple, the installation is convenient and the navigation transportation of the automatic guided vehicle is convenient.

The invention discloses a method and a system for identifying a faked identity by preventing faked recordings based on voiceprint and voice. The method comprises the following steps: building a voiceprint model and a voice model for a user according to a voice read by the user of a fixed text with a user ID, and storing the fixed text with the user ID as well as the voiceprint model and the voice model; generating an alerting text; acquiring the voice of a to-be-identified person when the to-be-identified person reads the alerting text; identifying the acquired voice of the to-be-identified person and the stored the voiceprint model of the user, and identifying the voice of the to-be-identified person according to the stored voice model, if both the voiceprint identification and the voice identification are successfully, the identity of the to-be-identified person is accepted, and otherwise, the identity of the to-be-identified person is not accepted. According to the method provided by the invention, the method using the fixed text with the user ID and a random text are adopted, so that the required voice length for the voiceprint modeling and the voiceprint verification are greatly reduced on the premise of guaranteeing the identification performances, thereby facilitating the use of the user.

The invention discloses an identification and authentication device based on finger biometric. The device comprises a handle part, a fingerprint collection part, a light source, an image pickup part, a tact switch and a processing part. The processing part is respectively connected with the tact switch, the fingerprint collection part, the light source and the image pickup part. The device is usually in standby state, and a system starts to work when the tact switch is triggered: first, the light source is started to illuminate the position between the knuckle at a proximal interphalangeal joint of a finger and a distal interphalangeal joint of the finger, and the image pick-up part obtains a finger vein image; meanwhile, the fingerprint collection part collects a thumb fingerprint image, then the two images are subject to preprocessing and feature extraction respectively, and matched with the finger vein feature and the fingerprint feature stored in a database; finally, the judgment whether the authentication is successful is obtained by evaluating the similarity thereof. The invention fully utilizes two different biometrics at different cutaneous layers of the finger, can enhance the anti-counterfeiting property, the security and the accuracy of the system.

The invention provides a trusted computing cryptogram platform suitable for a general computation platform of an electric system. The cryptogram platform comprises a trusted computing cryptogram module and a trusted software system, wherein the trusted computing cryptogram module comprises a trusted measurement root, a trusted storage root and a trusted report root and is a transferring starting point of a platform trust chain; and the trusted software system comprises a trusted computing cryptogram driving module, a measurement module and an auditing module and provides an interface which uses the trusted computing cryptogram platform for an operating system and application software. The trusted computing cryptogram module is the trusted root which provides trusted environment for the operation of the trusted computing cryptogram platform, and the trusted software system is a core for realizing the functions and the service of the trusted computing cryptogram platform and provides guarantee for the management of the trusted computing cryptogram platform. The trusted computing cryptogram platform can provide functions including static measurement, dynamic measurement, white lists, access control and the like for a business system, and manages the sources and the operation of the system software to guarantee that the software is trusted, recognizable and controllable.

The invention provides a mobile phone interconnection-based vehicle-mounted speech recognition system and recognition method. With the mobile phone interconnection-based vehicle-mounted speech recognition system and recognition method adopted, recognition rate and recognition speed can be ensured, and a problem of much occupation of the memory of a vehicle-mounted terminal by network resources of speech recognition can be solved. The system includes a microphone, a vehicle-mounted terminal which sends speech information to a mobile phone end and receives speech recognition result of the mobile phone end or a cloud speech recognition engine, the mobile phone end which analyzes and recognizes the speech information through mobile phone application software so as to obtain the speech recognition result of the mobile phone end, sends the speech information to the cloud speech recognition engine, receives the speech recognition result of the cloud speech recognition engine, performs arbitration on the speech recognition result of the mobile phone end and the speech recognition result of the cloud speech recognition engine through mobile phone application software, and sends the speech recognition result of the mobile phone end or the cloud speech recognition engine to the vehicle-mounted terminal according to an arbitration result, and the cloud speech recognition engine which analyzes and recognizes the speech information and sends the speech recognition result to the mobile phone end.

The invention discloses a voiceprint model training method, a voice recognition method, devices, equipment and a medium. The voiceprint model training method includes the following steps: using training voice data in at least two business scenarios to carry out universal background model training to obtain a universal background model; using the universal background model to carry out feature extraction on intra-domain voice data and out-of-domain voice data to obtain corresponding intra-domain voiceprint features and out-of-domain voiceprint features; carrying out probability linear discriminant analysis model training based on the out-of-domain voiceprint features to obtain an out-of-domain probability linear discriminant analysis model; and adaptively training the out-of-domain probability linear discriminant analysis model based on the intra-domain voiceprint features to obtain a target probability linear discriminant analysis model. The voiceprint model training method overcomes the problem that it is impossible to obtain multiple pieces of voice data of a single person in some business scenarios, and ensures the recognition effect of the target probability linear discriminantanalysis model.

The invention provides a control system for the information safety to solve the safe problems existed in the business system, and prevent the important data from leakage and illegal interpolation. The system includes: key management module, key negotiation module, code interface module, log management module, security management module and mistake processing module. The control system for the information safety provided by the invention can combine with the business system closely, and it is classified following the business system on the structure design, the business logic of every hierarchy has the corresponding security control to protect the every aspects of business, and the business safety technical measures cover the every aspect of business system that includes data transmission, data storage, database, files, logs and operation certification and so on, and it can assure the confidentiality, integrality, anti-aggression, usability, anti-repudiation, ID identify and authority control of business system.

The invention discloses a self-adaptive identification method and system wherein the system comprises: according to a user's historical corpus, establishing a customized dictionary; clustering the customized words in the user's customized dictionary to obtain the type number of each customized word; constructing language models according to the type numbers of the customized words; during the identification of the inputted information of the user, if the words contained in the information exist in the user's customized dictionary, expanding the de-coding paths according to the type numbers of the customized words corresponding to the words; decoding the information according to the expanded decoding paths to obtain a plurality of selective decoding results; according to the language models, calculating the scores of the language models of the selective decoding results; and selecting the selective decoding result whose language model obtains the highest score as the information identification result. With the method and system of the invention, it is possible to increase the identification accuracy for a user's customized words and the consumption of the system can be reduced.

The invention belongs to the field of computer vision and specifically relates to a human action recognition method based on a noise reduction automatic encoder and particle filter. The human action recognition method randomly divides a to-be-sorted action video set into a training video set and a test video set, the training video set and the test video set are respectively used for calculating training tracks and test tracks of the action, distances between the training tracks and the test tracks are calculated, a track distance set is obtained and is inputted to a support vector machine, and a sort result of the action is obtained. According to the invention, the method has an advantage of substantial human action recognition effect, accuracy of action recognition can be effectively improved, and the method has certain robustness on shielding and view change and can further be used for human body abnormal behavior recognition in video monitoring.

The invention relates to a face and iris image fusion and recognition method based on a hierarchical structure, which comprises a registration step R and a recognition step S, wherein in the registration step R, after a feature extraction link R1 for face and iris images of a registered user is carried out, the images are stored in a registration database; and in the recognition step S, the face and iris images are used for recognizing and searching on the basis of the given registration database. The method of the invention improves the accuracy, the usability and the searching efficiency of a biological feature recognition system and has excellent expansibility and compatibility. In the method, the biological feature recognition system based on face and iris fusion can effectively recognize remote pedestrians and has wide application prospects in airports, stations, banks and other safe occasions.

A method of transmitting data from a sensor (1) to a receiver (4) in which each original data word is split in positional fashion into at least two separate short data words (MSN, LSN). The separate short data words (MSN, LSN) are each converted by digital-to-analog conversion (15) into an analog pseudosignal and transmitted in a multiplex mode via an output of the sensor and a transmission path (3) to the receiver (4). In the receiver, the analog pseudosignals are converted back into short data words (MSN, LSM) and joined together in correct bit sequence by means of an analog-to-digital converter (15), so that the resulting data word corresponds to the original word.

The invention relates to a vehicle-bone navigation and video recording integration system and method, wherein the system comprises a master processing module, a navigation module which is connected with the master processing module by a circuit and in charge of transmitting a received navigation signal to the master processing module, a video capturing module which is connected with the master processing module by a circuit and in charge of transmitting captured original video data to the master processing module, a storage module circuit connecting the master processing module and a display module which is connected with the master processing module by a circuit; wherein the master processing module transmits processed data to a storage module. The system and method combine satellite navigation information and content of video recording and adopt a flow of controlling the video recording by the satellite navigation information, thus not only space of a storage device is effectively utilized, but also video information during accident is reliably stored. The invention can play an important role in responsibility determination in traffic accident management.

The invention discloses a method of realizing pulmonary nodule medical sign recognition based on image retrieval with semantic features and supervised Hashing. The method includes a step A of extracting pulmonary nodule mixed sign region in a lung CT image, and cutting off the same for each single sign regions; a step B of extracting semantic features expressing pulmonary nodule sign information using a convolutional neural network (CNN) based on parameter sharing; a step C for realizing similar pulmonary nodule image retrieval; and a step D for recognizing pulmonary nodule signs. The method of the invention is based on the pulmonary nodule image retrieval with the semantic features and supervised Hashing, the sign category shown in the pulmonary nodule image is thus recognized, a doctor is assisted in judging the benign and malignant degrees of pulmonary nodules, and over-reliance of the doctor on diagnostic experience is reduced.

The invention provides a double-antigen specific T cell, a method for preparing the same and application of the double-antigen specific T cell. The double-antigen specific T cell comprises mesothelin antigen specific T cell receptor genes and antibody Fc (fibrillar center) fragment specific T cell receptor genes. The antibody Fc fragment specific T cell receptor genes can be mediated by HIF-1 alpha (hypoxia inducible factor-1 alpha) antibodies to specifically recognize HIF-1 alpha antigens. The method includes simultaneously infecting T cells by slow viruses with mesothelin antigen specific T cell receptor genes and slow viruses with antibody Fc fragment specific T cell receptor genes. The double-antigen specific T cell, the method and the application in an embodiment of the invention have the advantages that the double-antigen specific T cell has two specific binding domains and double-specificity for targeting to Meso (mesothelin) and being mediated by the HIF-1 alpha antibodies to specifically recognize the HIF-1 alpha antigens, accordingly, TNBC (triple negative breast cancer) cells can be assuredly specifically recognized and killed by the double-antigen specific T cell, and normal cells of organisms can be prevented from being mistakenly killed.

The invention provides a traffic monitoring image-based automatic detection system for a safety belt non-fastening behavior of a driver. The system comprises a module for extracting a to-be-detected region of the safety belt and a module for judging whether the driver fastens the safety belt or not; the module for extracting the to-be-detected region of the safety belt comprises a license plate detection sub-module, a driver region extraction sub-module, an image enhancement sub-module, a human face detection sub-module and a safety belt detection region extraction sub-module; the module for judging whether the driver fastens the safety belt or not adopts a straight line detection-based safety belt judgment method; and the straight line detection-based safety belt judgment method is used for detecting an edge straight line section of the safety belt by using a Canny edge detection algorithm and a progressive probabilistic Hough transform straight line detection algorithm. The safety belt non-fastening behavior of the driver can be accurately and quickly detected and recorded, so that the disadvantages of high labor cost of manual identification, easy fatigue, easy negligence and the like are effectively overcome, and the safety belt non-fastening driving behavior of the driver is effectively inhibited.

The invention discloses an intelligent dustbin with a classification function. The intelligent dustbin with the classification function comprises a unified feed inlet. Waste thrown into the intelligent dustbin through the feed inlet is received, recognized and classified in a waste storage area and then enters a waste collection area (classification sub-dustbin) of a corresponding type through a feed guide channel and a guide mechanism, the waste storage area is opened, and then the waste automatically falls into a sub-dustbin of a corresponding type. The whole process of throwing the waste into the intelligent dustbin, recognizing the waste and automatically guiding the waste into the corresponding classification sub-dustbin is automatic, and manual intervention is not needed. The waste does not need to be recognized before being thrown into the intelligent dustbin, so that users does not need to wait for a classification and recognition result by holding the waste by hand, and user experience is good and is similar to that of common dustbins. The guide mechanism comprises an I-shaped guide rail. The I-shaped guide rail is arranged so that the guide mechanism can move more flexibly within a wider range and can adapt to dustbins arranged in a plurality of rows and columns, such as dustbins arranged in two rows and two columns or dustbins arranged in two rows and three columns.

The invention discloses a radar high resolution range profile (HRRP) target recognition method based on a convolution factor analysis (CFA) model. The radar HRRP target recognition method mainly solves the problem of poor target recognition performance under the condition of small samples in the prior art, and is implemented by the steps of: (1) carrying out framing on HRRPs of various kinds of targets according to angular domains, and carrying out modulus operation on each frame of data to obtain time domain features; (2) carrying out per-processing on each frame of data; (3) constructing a CFA model for each frame of HRRP after preprocessing, and calculating condition posterior distribution of each model parameter; (4) initializing each parameter and performing I-th iterative updating; (5) carrying out intensity normalization on a test sample, and translating and aligning frames of average profiles; (6) calculating frame probability density function values of the test sample according to a posterior mean of parameters of the CFA model; (7) and finding out the maximum probability density function value, and determining a type of the test samples. The radar HRRP target recognition method has the advantages of being low in model complexity, and being capable of applied to radar target recognition under the condition of small samples.

The present invention relates to a key frame acquisition method for a human image video system. The method comprises the following steps of: 1) acquiring a video image, and performing key point detection on each frame of image; 2) performing attribute classification on each frame of image according to the detected key points, and calculating confidence level under each attribute; and 3) selecting P key frames according to the confidence level of each frame of image under different attributes as a basis of face recognition. Compared to the prior art, the selecting process of the key frame is improved, so that the speed is ensured and relatively high recognition performance is achieved.

The invention provides a method for identifying products based on commodity attribute unification and clustering. The method comprises the following steps that a standard library is built; commodities are subjected to attribute tidying according to commodity page information and the standard library; standard commodity information is output; the commodity attributes are clustered according to the standard commodity information and the standard library; the standard commodity information of product ID (identification) is obtained. The method has the advantage that the efficient obtaining of commodity information required by users can be realized.

The invention discloses an action recognition based living body face recognition method and system. The method includes steps of collecting a static face image of a user; outputting an action command generated randomly; collecting video information of the user responding to the action command; extracting an image in which the action of the user is matched with the action command in the video information as a dynamic face image; comparing the static face image with the dynamic face image, determining living body face recognition success when the matching degree is greater than a recognition threshold value or else determining living body face recognition failure.

The invention provides a method and a device for recognizing a human face in a fog day image. The method for recognizing the human face in the fog day image comprises a first step of processing an input color image by utilizing a dark channel priority defogging method and regarding the processed image as a first image, a second step of detecting the human face in the first image by using a preset human face detector to extract a human face image in the first image, and a third step of recognizing the human face image by adopting an algorithm which combines principal component analysis and linear identification analysis to output the recognizing result. Defogging process is started before the human face is recognized aiming at the image shot at a specific scene in a foggy day, defogging calculated amount is small, so that efficiency and speed of image process are guaranteed, recognizing efficiency in foggy environment is effectively improved, the purpose that the human face recognizing is not affected by the foggy environment is guaranteed, and human face recognizing effect is guaranteed.

The embodiment of the invention provides a safe 6LoWPAN communication method and system based on a block chain. The method comprises the following steps: constructing a plurality of 6LoWPAN boundary gateways into nodes on a block chain network; electing a master node, and taking the rest nodes as slave nodes; enabling the master node to package a transaction list, including transaction informationreflecting node operation conditions and / or security factors, of each node into a block, and enabling each node to verify and chain the legality of the block through a block consensus algorithm; andacquiring malicious nodes and cutting off an upper cloud channel in the verification process. According to the embodiment of the invention, a plurality of 6LoWPAN boundary gateways form a block chain;transaction lists are generated from transaction information reflecting node operation conditions and / or security factors and packaged into blocks, the blocks are chained through a block consensus algorithm, malicious nodes are confirmed in the block verification process, the security of the 6LoWPAN wireless sensor network is improved, and the 6LoWPAN communication method and system are convenient to trace afterwards.

The invention provides a method for searching keywords based on image content, and a device thereof. The device for searching keywords searches and locates an input keyword in an input file image and comprises a global matching unit, a checking unit and a filtering unit; wherein the global matching unit extracts a plurality of candidate keyword image areas from the file image, extracts the image characteristics of the plurality of candidate keyword image areas, and matches the image characteristics with the keyword so as to obtain a matching distance corresponding to the plurality of candidate keyword image areas; the checking unit carries out identification to the front N candidate keyword image areas with small matching distance and calculates the checking distance between an identification candidate and the keyword; the filtering unit calculates the combining distance of the matching distance and the checking distance and filters the candidate keyword image areas with large combining distance according to the combining distance.

The invention discloses a banknote splicing seam or crease recognition method and system. A method of combination of a differential edge detection operator and a proportional coefficient method for binarization is adopted so that weak splicing seam signals can be extracted and recognized. Besides, special processing and limiting modes that the number and length of splicing seams or creases to be recognized are set and angle range of the splicing seams or creases to be recognized on a banknote is limited are applied, an image vertical and horizontal projection method is adopted when a polar angle theta is close to a horizontal or vertical angle, and a Hough transformer detection algorithm is adopted when the polar angle theta largely deviates from the horizontal or vertical angle so that algorithm time is greatly shortened, the objective of rapid detection of the splicing seams or creases can be achieved, algorithm real-time performance can be greatly solved and recognition performance can be guaranteed, the recognition effect of relatively precise splicing seams or creases is great and universality is high. The banknote splicing seam or crease recognition method and system can be widely applied to the field of banknote recognition.

The invention discloses a method for recognizing Chinese characters in a natural scene. The method recognizes characters by a modeling training stage and a character recognition stage. The modeling training stage comprises successively establishing a tree structure expression of template characters, synthesizing a training set, training a convolutional nerve network, extracting the deep template characteristic of a node, and establishing and training a Markov random field. The character recognition stage comprises preprocessing a picture to be recognized, extracting the deep characteristic of an input picture, minimizing a Markov random field energy function, and finally recognizing characters. The method takes account of the local characteristic and the global structure of the characters while recognizing the characters, overcomes an influence on a recognition effect due to fuzzy characters and large deformation in the natural scene by combining the Markov random field technique with the deep characteristic of the node in the tree structure, thereby increasing recognition efficiency.

In the process of obtaining codebook by using the clustering algorithm for the voice eigenvector set, the step of dynamic uniting and splitting subclass is added based on the number of vectors in the set and the total distance measured of vectors in the set. Thus, the sum of the distance measured between the vectors and the corresponding code words in the set is reduced after clustering algorithm to raise accuracy of the clustering algorithm. The method guarantees the recognition performance and reduces the storage quantity of the system. The invention also discloses a voice recognition system, which uses the feature codebook to replace the acoustic model. Gauss probability is not needed to calculate in the decoding process, and the probability value can be obtained by looking up the probability table stored in advance. Thus, the quantity of decoding operation is reduced greatly as well as the recognition speed is raised.

The invention discloses a method and a related device for detecting messages including Cookie information. The method includes: receiving an HTTP (hyper text transport protocol) response message including first Cookie information and sent by a server; acquiring a value corresponding to a preselected Cookie name in the first Cookie information, computing a signature value according to the acquired value, and sending the HTTP response message added with an additional Cookie name / value pair to a client side; receiving an HTTP response message including second Cookie information and sent by the client side; acquiring a value corresponding to a preselected Cookie name in the second Cookie information, computing a signature value according to the acquired value, and comparing the recomputed signature value with a value in an additional Cookie name / value pair included in the second Cookie information; and detecting according to a comparison result. By the scheme, message detecting efficiency can be improved, and subsequent normal recognition and operation can be guaranteed.

The invention is a training method used in embedded voice automatic-recognizing system in the field of intelligent information processing: (1) modified multistage vector quantization template training: using dynamic time regulating method to divide training sentences of a kind into several voice segments with regard to time, gathering the most related voice frames in a voice segment, and setting the total number of voice segments of a template with regard to syllabic number in a command word to be recognized, according to voice time sequence characteristic and statistical characteristics of various voice segments as well as Chinese syllabic structure; (2) generalization probability reduction distinguishing training: combining with the multistage vector quantization template, embedding the distinguishing training algorithm in a recognizer based on dynamic time regulating method, making distinguishing training on a reference template set based on a training set by defining the distance between training sentence and reference template as a distinguishing function, strengthening the ability to distinguish between templates by multiple repeated distinguishing training, and obtaining a more optimized voice template.

A construction method of a star database of a triangle matching-type star sensor includes steps of: S1) determining basic cut-off magnitude and candidate cut-off magnitude; S2) rejecting peculiar stars; S3) performing fixed star proper motion compensation algorithm; S4) determining threshold of angular distances of neighboring fixed stars; S5) performing whole-celestial sphere helical line traversal; S6) determining relative bright stars; and S7) generating database of angular distances between stars.

The present invention can recognize both English and Chinese at the same time. The most important skill is that the features of all English words (without samples) are entirely extracted from the features of Chinese syllables. The invention normalizes the signal waveforms of variable lengths for English words (Chinese syllables) such that the same words (syllables) can have the same features at the same time position. Hence the Bayesian classifier can recognize both the fast and slow utterance of sentences. The invention can improve the feature such that the speech recognition of the unknown English (Chinese) is guaranteed to be correct. Furthermore, since the invention can create the features of English words from the features of Chinese syllables, it can also create the features of other languages from the features of Chinese syllables and hence it can also recognize other languages, such as German, French, Japanese, Korean, Russian, etc.