567results about How to "Avoid misidentification" patented technology

The invention relates to a full-automatic poker machine, which comprises a mounting bottom plate and a plurality of support legs. A card inlet is disposed on the mounting bottom plate, card cutting and primary card distributing equipment is arranged at one end of the card inlet, card sorting and secondary card distributing equipment is arranged at the other end of the card cutting and primary card distributing equipment, card flopping and dealing equipment is disposed at the other end of the card sorting and secondary card distributing equipment, card pushing equipment is arranged at the other end of the card flopping and dealing equipment, and card lifting equipment is disposed on one side of the card pushing equipment. When the full-automatic poker machine works, disorder poker cards are primarily separated by the aid of the card cutting and primary card distributing equipment, then are adjusted to face the same direction and separated from each other by the card sorting and secondary card distributing equipment, then by the aid of the card flopping and dealing equipment, the single poker cards with front surfaces facing upwards and downwards are adjusted so that the front surfaces of the single poker cards face upwards or downwards in a unified manner and the single poker cards are dealt, the poker cards are pushed to specified positions by the card pushing equipment, and finally are lifted to a tabletop by the card lifting equipment, and card cutting and dealing actions are completed. The full-automatic poker machine brings convenience for reducing labor intensity of game, waiting time is shortened, and simultaneously, automation degree of the machine is improved.

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.

The invention provides a method for network equipment identity recognition. The method for the network equipment identity recognition includes the following steps: receiving visit requests sent by network equipment through a webpage browser; searching corresponding webpage codes and collection codes according to an address of a target webpage and returning the codes to the webpage browser; receiving an attribute vector set collected from the network equipment and sent by the collection codes through the request of hyper text transport protocol (HTTP); searching attribute groups matched with the attribute vector set from a preset attribute bank based on the attribute vector set; carrying out similarity computation on the attribute vector set and the searched attribute groups and selecting the attribute group which has high similarity with the attribute vector set; and comparing the highest similarity value with a preset new equipment threshold value and an old equipment threshold value and determining the type of the network equipment according to comparison results. The invention further provides a network equipment identity recognition system for realizing the method. The method and the system for network equipment identity recognition can reduce occupation on network equipment resources, and improve visit speed and recognition accuracy.

The invention discloses a search intention identification method and device. The method comprises the steps that massive historical search statements in the historical search record are obtained and classified, a classification model is built based on the historical search statements, candidate search statements related to the historical search statements are obtained by exploring the classification model, and a special-item search word bank of a preset special-item class is formed by the historical search statements and the candidate search statements corresponding to the same preset special-item class. Compared with white lists, fuzzy search threshold values, pattern matching keywords and the like in the prior art, search statements in the special-item search word bank are more accurate and more comprehensive, the generalization is great, therefore according to the search intention identification method and device, a search intention is identified according to the special-item search word bank, the intention class of a target search statement can be identified more accurately, and the misidentification caused by inconsistency between the manually-specified rule and the actual judgment standard of a user can be avoided.

A user operates a remote control to enter an authentication code shared by a plurality of radio transmission devices performing radio transmission. Remote control transmission / reception unit 1 converts an infrared signal received from the remote control to an electric signal, and extracts the authentication code from the electric signal. The authentication code is recorded on an authentication code record region in a nonvolatile storage region. In an authentication communication mode, a radio unit encrypts a radio unit MAC address with the authentication code used as a key, and transmits it. Further, the radio unit decrypts the radio unit MAC address returned from the radio transmission device of the opposite party of the transmission with the authentication code used as the key. The radio transmission device obtains the radio unit MAC address of the opposite party of the transmission, and ends the authentication mode.

The invention discloses a multi-mode non-contact emotion analyzing and recording system. The system is characterized by being composed of a voice receiving module, a voice feature extracting and processing module, a speech recognition module, a textural feature extracting and processing module, a comprehensive scheduling module, a displaying module and a clock module; the voice receiving module is used for completing receiving of voice from outside environment, the voice feature extracting and processing module is used for acquiring voice frequency emotion labeling information of speech, the voice recognition module is used for completing conversion from speech content to textural content, the textural feature extracting and processing module is used for acquiring textural emotion labeling information of the speech, the comprehensive scheduling module is used for completing processing, storing and scheduling of all data, the displaying module is used for completing displaying of detected speech emotion state, and the clock module is used for completing time recording and providing a time labeling function. By the multi-mode non-contact emotion analyzing and recording system, a textural mode and a voice frequency mode can be integrated to recognize speech emotions, so that accuracy of recognition is improved.

The invention discloses a financial reimbursement total-bill intelligent auditing system. The system comprises a power supply module, a scanner interface module, an OCR module, an invoice verification module, a file uploading processing module, a peripheral financial system interface module, a barcode printing control module and an Ethernet interface module. The scanner interface module realizes data exchange and transmission of a scanner and a system; the power supply module provides a power supply for the scanner interface module and the Ethernet interface module; the OCR module provides image identification and processing functions; the invoice verification module realizes an internal control check function for files subjected to scanning processing; the file uploading processing module realizes a file classification storage function; the peripheral financial system interface module realizes data exchange and transmission with a peripheral financial system; the barcode printing control module generates a barcode according to a number and outputs the barcode to a barcode printer; and the Ethernet interface module is used for realizing transmission of barcode printing data, uploading of the files subjected to the scanning processing and data transmission of the peripheral system.

The invention discloses a convolutional neural network training method and apparatus for human face identification and an application, and belongs to the field of human face identification. The method comprises: constructing a sample training library, wherein the sample training library comprises a plurality of sample classes, and the sample classes comprise human face image samples same in quantity; training a convolutional neural network by using the sample training library; extracting eigenvectors of all the human face image samples in the sample training library by using the trained convolutional neural network; classifying the eigenvectors by using a classifier; calculating classification accuracy of each sample class; and judging whether the convolutional neural network meets a set requirement or not, if yes, ending, otherwise, deleting a certain quantity of correctly classified human face image samples from the sample class with highest classification accuracy, adding the same quantity of human face image samples into the sample class with lowest classification accuracy, and re-training the convolutional neural network. The method avoids identification errors caused by influences of facial makeup and external environment, and avoids over-fitting.

The invention discloses a method for carrying out synthetic target recognition through information of different types. The method includes the following steps that (1) movement information and attribute information of a target are obtained through sensors of various types; (2) attribute association based on the DS evidence theory is carried out on the collected attribute information, and track correlation based on target movement information is carried out on the movement information; (3) the degree of association between the attribute information and the movement information of the target is synthesized, and a synthetic recognition result is given out in a probability mode so that later processing of various tasks can use the recognition result according to demands respectively. The accuracy and availability of synthetic target recognition are improved by changing typical synthetic target recognition processing procedures.

The invention provides a vehicle navigation method and system based on a track topological map and obstacle avoidance, and a medium. The method comprises the steps of: a map constructing step: constructing an environment map, and generating a track topological map for navigation according to the constructed environment map; a global planning step: searching the global shortest path connecting a starting point and an end point on the generated track topological map by using a path searching algorithm A*; and a local obstacle avoidance step: generating a local target point in real time by using the obtained global shortest path, and generating a vehicle control signal by combining the local target point and the environmental information detected by the laser sensor in real time to control the vehicle to avoid the obstacle and reach the destination. The safe passages in all directions are detected by a ball body, and the found safe passages can be ensured to pass through a small vehicle. The controller combining the local target point of the global path and the safe passages is creatively constructed, and the small vehicle can be controlled to avoid obstacles and safely reach the destination under the condition that the track is not planned in advance.

The invention relates to a license number identification method and device. The method comprises the steps: a sample license number obtained by performing identification for a license plate image on a first preset position is acquired, and the sample license number is recorded in a license plate white list; an initial license number obtained by performing identification for a license plate image on a second preset position is acquired, and the license plate image shot on the first preset position has higher definition than the license plate image shot on the second preset position; the initial license number and the sample license number in the white list are performed a similarity match process to acquire a corresponding similarity value; when the similarity value meets a preset similar condition, the license number in the license plate image shot on the second preset position is identified as the sample license number corresponding to the similarity value. According to the invention, the identification accuracy of the license number in the license plate image can be improved.

The embodiment of the invention discloses a user group identification method and device, electronic equipment and a storage medium. The method comprises the following steps: constructing a user relation graph according to a specific online behavior of a user; calculating the behavior similarity between every two users in the user relationship diagram based on the number of times that the users have specific online behaviors in a set time period; cutting the user relationship graph according to the behavior similarity so as to delete an association relationship between users whose behavior similarity is lower than a set threshold; and identifying the target user group on the basis of the clipped user relationship diagram according to the number of terminal devices used by the user during the online behavior and the number of Internet protocol IP addresses. By adopting the technical scheme, the identification precision of the target user group is improved.

The invention discloses a video multi-vehicle outline detection method, which comprises the following steps of: drawing a virtual fence to define a monitoring area, and drawing a virtual detector to acquire parameters such as vehicle width and minimum vehicle length; obtaining a vehicle body outline set through a series of steps such as background subtraction, binarization, morphological opening operation and outline extraction; tracking a vehicle by tracking pixel blocks forming the vehicle, thus obtaining an initial outline of the vehicle; merging the outline of the vehicle by taking the initial outline of the vehicle as the basis, thus ensuring the outline of the vehicle which runs into the monitoring area to be more complete; and selecting a large outline from the residual body outline to serve as an initial outline of a new vehicle, and merging the body outline of the new vehicle, thus timely detecting the vehicle which newly runs into the monitoring area. The method solves the problems of camera shake, image interference on the two sides of a road, disconnected vehicle foreground and adhesion of outlines of adjacent vehicles.

The invention discloses a convolutional neural network training method and apparatus for face recognition and belongs to the face recognition field. The method includes the following steps that: a sample training library is constructed; the sample training library is adopted to train a convolutional neural network; the trained convolutional neural network is adopted to extract the feature vectors of all samples in the sample training library; distances between every two feature vectors are calculated; a sample pair training library is constructed; the sample pair training library is composed of sample pair sets of all face image samples, wherein the sample pair sets include heterogeneous sample pairs and homogeneous sample pairs, wherein the heterogeneous sample pairs are composed of face image samples and face image samples which are separated from the face image samples by distances which are smaller than a certain value, and the homogeneous sample pairs are composed of face image samples and face image samples which are separated from the face image samples by distances which are larger than a certain value; and the sample pair training library is adopted to train a convolutional neural network. With the method adopted, recognition errors caused by make-up and external environment can be effectively avoided.

The invention discloses an 'internet+' package bottle intelligent recovery system and method. The system comprises an intelligent recovery device, user terminal equipment and a cloud service which are connected through internet communication; the intelligent recovery device comprises a human-computer interactive system, an electromechanical control device, a package bottle transmitting and rotating device, a package bottle identifying device, a package bottle compressing and crushing device, and a machine cabinet. A user selects to start throwing a bottle through the human-computer interactive system or the user terminal equipment; the intelligent recovery device has the functions of identifying the bar code, the weight, the image and the material of the package bottle. If the intelligent recovery device fails to identify, the package bottle is rejected. If the package bottle is identified successfully, the package bottle is compressed and crushed, and is recovered and stored; meanwhile, the user gets rebate. The 'internet+' package bottle intelligent recovery system is convenient to operate and use; the interaction and data sharing of the user, the intelligent recovery device, internet cloud and a user terminal are realized by utilizing the internet; the popularization of an 'internet+' resource recycling development is strongly promoted.

The invention provides a road speed limit sign identification device, which belongs to the field of automotive electronic technology related to safe driving of vehicles. It includes: a GPS module. The GPS module includes a GPS positioning unit and a storage unit. The GPS positioning unit is used to determine The current location of the vehicle, the storage unit stores information about the road; the camera module is used to collect the speed limit signs on the road where the vehicle is traveling; the processing module is used to combine the speed limit sign information provided by the camera module with the The current vehicle road information provided by the GPS module is judged and screened to determine the effective speed limit of the current vehicle. The invention provides a road speed limit sign identification device that can identify ramp speed limit signs with high accuracy and effectively avoid misidentification of ramp speed limit signs as main road speed limit signs.

This invention discloses a certificate certification system and method based on hardware character including; a certification server uses a hardware certificate ciphering digital certificate containing customer end hardware character to form ciphered file sent to the user end which uses the hareware certificate to decipher the ciphered file to get a digital certificate provided on an applied server providing the digital certificate to a certification server for check to finish the certification. The system includes a user end hardware character collector used in generating hardware centrification according to the collected hardware character, a certification server, a customer end and an applied server.

The invention provides a lightweight license plate detection and recognition method based on a multi-scale attention mechanism. Construction of a license plate detection and recognition network comprises the following steps: S1, obtaining pictures as an original data set; S2, processing the original data set to obtain a data set A used for training a model for detecting the license plate and a data set B used for training a model for recognizing the license plate; S3, constructing a deep neural network for detecting the license plate; S4, inputting the original image P1 of the data set A intothe network constructed in the S3 to obtain a license plate detection area P2 and four corners of the license plate; and S5, performing perspective transformation on the P2 according to the angular points of the license plate to obtain a corrected image P3. S6, constructing a deep neural network for recognizing the license plate; S7, inputting P3 into the network constructed in the S6 to obtain alicense plate number corresponding to the detected license plate. According to the invention, a relatively low network parameter quantity and a relatively low calculated quantity can be obtained simultaneously under the condition of ensuring the network accuracy.

The invention discloses a financial reimbursement all-invoice picture recognition and processing method. According to the method, a specific scene of invoice recognition is optimized to some extent, invoice recognition types are expanded, invoices of all types can be recognized, and recognition is more accurate and higher in efficiency. The method is mainly used for performing recognition and processing after the invoices of all types are scanned into pictures. The method comprises the specific steps that the invoice pictures obtained after scanning are subjected to color preprocessing, and input data is provided for picture contour preprocessing; the pictures obtained after color preprocessing are subjected to contour detection, and pixel interference outside an invoice paper range is eliminated; the pictures obtained after contour detection are subjected to text preprocessing, characters on the invoices are recognized; and a character set is formed and output; the output character set is subjected to picture recognition and processing, a recognition and processing result is organized into a result object with semantics according to semantics of invoice recognition, and the result object is used as a final recognition result.

The invention provides an authentication method for a client certificate, a server and a client. The authentication method includes the steps that the server receives a certificate chain sent by the client, the certificate chain comprises a second-level CA certificate and a client temporary certificate, the second-level CA certificate includes a first MD5 value corresponding to a hardware feature code of the client, and the client temporary certificate includes a hardware feature code; the server verifies whether the certificate chain is legal or not, if the certificate chain is legal, a corresponding second MD5 value is generated according to the hardware feature code included in the client temporary certificate, the first MD5 value and the second MD5 value are compared whether to be same or not, and if yes, the situation that the identification of the client is effective is determined. Due to the uniqueness of the MD5 values, if the client temporary certificate is stolen, the second MD5 value is bound to be different from the first MD5 value. Therefore, the client can not be counterfeited, and the situation that in the prior art, a digital certificate is stolen and causes identification mistakes is avoided.

The invention relates to a laser-based amphibious three-dimensional visual detection device and a detection method, and belongs to the technical field of three-dimensional visual detection devices. The invention is an amphibious device capable of measuring a three-dimensional object and obtaining the position and attitude of the object by matching dot-line lasers to provide active features and combining land binocular stereo vision measurement with underwater multi-feature structured light measurement. According to the method, 25 pieces of line laser and 1 piece of dot laser are successfully taken as features, the technical problem of binocular stereo vision passive measurement can be solved, and meanwhile, the dot laser is taken as a marker to match the remaining light bars, the misidentification of the light bars caused by the underwater complex environment can be avoided, and the matching accuracy can be improved. Each picture can obtain 25 times more data than traditional structured light measurement, so that the underwater clear object feature data can be obtained, and the three-dimensional position and attitude under various complex conditions such as complexity, high occlusion, point cloud sparseness and the like can be solved with high accuracy.

The invention provides RFID (Radio Frequency Identification) self-help access equipment, which comprises a vertical column; at least one cylindrical storage box which is superposed up and down and penetrated on the vertical column, wherein each storage box comprises a cylindrical rotating cover which rotates around the vertical column and the side wall of the rotating cover is transparent; a plurality of access cases positioned in the rotating cover, wherein the access cases are fixed relative to the vertical column and are radial by using the vertical column as a center; an access mouth arranged on the side wall of the rotating cover; antennas distributed in the plurality of access cases or fixed on the inner wall of the rotating cover near the access mouth; and a control part which is connected with the antennas and used for detecting articles stored in or removed from the access cases, wherein the articles are bound with a RFID electronic label. The self-help access equipment provided by the invention has the advantage of simple operation and can sufficiently show the articles displayed in the storage box.

Disclosed herein is a voice book device. The voice book device includes voice book and a book support. The voice book contains various pieces of information. The book support includes a printed circuit board and a housing. The printed circuit board has a storage unit, an optical sensor unit, a decoder unit, a voice output unit, and a control unit. The housing includes the printed circuit board. Each page of the voice book consists of a transparent part and a contents part. An optical reflector is formed on the transparent part and one or more optical sensors are disposed in the book support, and the optical reflectors and the optical sensors are arranged in a one-to-one mapping relationship so that the pages of the voice book are automatically recognized by cooperation operation between the optical reflectors and the optical sensors.

The invention provides a pressure touch sensor, a display device and a drive method for the same and relates to the technical field of display, wherein wrong recognition of pressure sensing can be prevented when the display device is bent. The pressure touch sensor comprises a drive electrode, a sensing electrode as well as a piezoelectric material layer and a piezo-resistance material layers disposed between the drive electrode and the sensing electrode.

The invention relates to a text direction correction method and device, a computer device and a storage medium. The method comprises the steps of obtaining a to-be-recognized text image; inputting theto-be-recognized text image into a text direction positioning detection model based on deep learning to obtain coordinate information corresponding to each text positioning box in the to-be-recognized text image; determining the direction of the to-be-recognized text image according to the coordinate information corresponding to each text positioning box; and if the direction of the to-be-recognized text image is not the standard direction, converting the coordinate information corresponding to each text positioning box in the to-be-recognized text image according to the standard direction toobtain the text image converted into the standard direction and the coordinate information corresponding to each converted text positioning box. By adopting the method, the problem of machine error recognition caused by the direction error of the text image to be recognized can be avoided, and the accuracy of machine recognition is improved.