161 results about "Graphic recognition" patented technology

The method and apparatus for displaying speech recognition results includes a recognition filter (102) that receives a recognition result list (106) which includes a plurality of speech recognized terms (122), wherein each speech recognized term (122) has a term-specific recognition confidence value (124). The recognition filter (102) generates a modified recognition result list (108) that includes one or more speech recognized terms having term-specific recognition confidence values. The method and apparatus also includes a display generator (104) that receives the modified recognition result list (108) and generates a graphical recognition result list (110). The graphical recognition result list (110) includes speech recognized terms and a non-alphanumeric symbol as a graphical representation (274) of the term-specific recognition confidence value (128) and a speech recognized term (126).

Systems and methods are provided for identifying and recommending electronic content to consumers. In accordance with an implementation, one or more elements of electronic content are identified based on video graph data. In an exemplary method, information associated with a first element of video content is received, and corresponding video graph data is obtained. One or more second elements of video content that are similar to the first element of video content are identified based on the obtained video graph data. A subset the first and second elements of video content is subsequently identified for delivery to the user.

A graphic recognition device, method, and recognition program recognize graphics without being influenced by an image shadow area. Image input unit acquires the image of the outside environment of a vehicle using a vehicle mounted camera. A light source location information acquiring unit calculates location of a light source such as the sun using the acquired image. User vehicle shape acquiring unit and other vehicle shape acquiring unit generate shape information for the vehicles indicating the location of points forming vehicle contours. Shadow area calculating unit calculates, on the basis of both vehicles' shape information, the object shape information and the light source location information, the location coordinates of the shadow area, and converts the location coordinates into two-dimensional coordinates to the shadow / non-shadow area emphasis flag recognizing unit, which recognizes the flag in the image by judging the presence / absence of the recognition object in each shadow and non-shadow area specified.

The present invention relates to a figure recognition system and method for automatic detection, tracking and recognition of a human face image. 2D image data in the surveillance zone are remotely collected by using an optical sensor, the faces of all persons in the surveillance zone are detected, and corresponding positions are determined. The face is detected, the detected face's feature coordinate is estimated, and the detected face and the feature are tracked in the next frame while processing the video sequence. Image quality of each detected face is determined according to parameters of focus, brightness, contrast, and the presence of glasses. Recognition methods stored in the repository for each detected face are adjusted by considering the face image quality computation value, and a biometric feature set is generated by using the recognition method selected for each detected face. The figure is recognized according to the watch list by using the biometric feature generated by comparing each detected face and a template set stored in the database. A new user registration process is performed and the recognition method is adapted automatically by considering the watch list.

The invention discloses a handwritten text and graphic recognition system based on a paper medium. The handwritten text and graphic recognition system comprises a digital handwriting pen and a nano gridded touchpad, wherein the digital handwriting pen consists of a pen tip, a pressure sensor, a distance-measuring sensor, a data acquisition module, a storage, a battery, a color selection switch, a time-interval selection switch and a stroke-width selection switch; the gridded touchpad is formed by nano gridded microholes in a nano interval, and a pressure sensor is arranged under the microholes of the touchpad; the amounts of water and ink in the microholes are measured by the pressure sensor; and by the obtained storage amounts of the ink and the water added on each coordinate point, Chinese characters are recognized, and the profile of an ink painting is calculated to obtain accurate characters or the ink painting. The handwritten text and graphic recognition system disclosed by the invention has the advantages that direct connection with a computer is not needed, and an electronic document with Chinese characters or pictures can be formed on plain paper by handwriting.

The invention provides a normalizing method of hand drawing geometric figures. The method comprises following steps of (1) collecting drawing track information between a drawing start point and a terminal point on a screen; (2) extracting geometric feature parameters of drawn tracks; (3) according to the geometric feature parameters of the drawn tracks, calculating eight feature values used for classification, comparing the eight feature values with feature ratio value regions corresponding to all kinds of geometric figure types, and according to comparison results, judging the geometric figure type of the drawn tracks; (4) extracting feature points and feature parameters on the drawn track in the determined geometric figure type according to features of different figures, and fishing drawing; and (5) using the feature points as hot points for future figure correction of users. The invention also provides a method for achieving the above method. According to the invention, while users can still personally draw geometric figures, re-drawing accuracy of the geometric figures is effectively improved; and a problem of a failure to meet classroom teaching requirements of hand drawing figures caused by inaccuracy of the hand drawing figures in classroom teaching is solved.

The invention provides a mobile phone temperature and power consumption detection experimental system and a detection method thereof. A robot manual operation module is used for simulating the operation of the fingers of a user on a mobile phone screen, and is controlled to finish a whole set of operation processes via graphics recognition; an operation box is used for setting the robot manual operation module, a mobile phone bracket, a high-definition high-speed video camera and a detection module; the mobile phone bracket is used for fixing a mobile phone to be tested in the operation box; an infrared imaging instrument can be used for accurately capturing the small change of the temperature of the mobile phone to be tested, and performing analysis and processing; and the detection module is used for controlling the robot manual operation module, and giving a mobile phone temperature rising comfort evaluation report specific to the temperature rising comfort of the mobile phone to be tested. The temperature rising situation of each side of the mobile phone under various operation instances are detected at different environmental temperatures, and a temperature profile of mobile phone temperature stabilization time, a highest temperature and highest temperature time and a temperature comfort evaluation report are given.

The invention provides an intelligent automatic door as well as a graph recognition unlocking method and an automatic control method of the intelligent automatic door, and relates to the field of safety doors. With the adoption of the intelligent automatic door as well as the graph recognition unlocking method and the automatic control method of the intelligent automatic door, the problem that an intelligent door is unsafe to be locked and unlocked with a chip card is solved. A microprocessor is adopted to intelligently control the electrically-control automatic door, a graphic code is drawn through a graph recognition code recognizer, and accordingly, the problem that the chip card is prone to be stolen or the safety is low if a digital code is adopted is solved. A graph recognition code is adopted, a user can set the graph recognition code according to requirements of the user and can draw the graph recognition code during unlocking, the drawn code can be sent to the microprocessor, the microprocessor compares the received graph code with the set graph recognition code, and when the similarity is up to 90% or higher, the microprocessor sends an unlocking drive signal to the electrically-control automatic door. The user can also set a new graph recognition code before going out or set several graph recognition codes simultaneously, so that the graph recognition code is not prone to be revealed stolen, and the safety is high. The intelligent automatic door is applied to a safety door.

The present invention provides intelligent test robot system, which operation platform of intelligent robot body connected storage module for storing test script, operation platform respectively connected signal output unit and image input unit, further connected network communication module linked remote console computer. When operation platform automatically performs tests accordance test script, e.g., power switches, string inputs through keyboard, mouse cursor movements, clicks etc., it is possible to send instructions contained test script to test object via signal output unit for action controls, image input unit receives images outputted by test object and returns them to operation platform, then automatic graphic recognitions can be performed on captured images according to image recognition instructions in test script. Moreover, remote console computer may control plural intelligent robot bodies through Internet for synchronously executing automatic test flows so as to facilitate shortened test time and reduced costs thus further elevating the integral production efficiency.

Software testing techniques based on image recognition are disclosed. In various embodiments, a programmatically implemented image classifier is trained to recognize a screen shot image as being associated with a transaction end condition of a transaction. A test script configured to initiate an iteration of the transaction is run. A start time of the iteration of the transaction is recorded. Screen shot images are generated during performance of the iteration of the transaction to capture a series of screen shot images of at least a portion of a user interface display associated with the iteration of the transaction. The image classifier is used to find an earliest-captured image that matches the transaction end condition. A time associated with the matched image is used as a transaction end time to compute an end-to-end time to perform the iteration of the transaction.

The invention discloses a graphic recognition-based interaction method and electronic equipment. The method comprises the following steps of: obtaining a first to-be-analyzed image; recognizing the first to-be-analyzed image to obtain a recognition result; playing a reading audio file associated with the recognition result; after the reading audio file is completely played, playing a question audio file associated with interaction content of the first to-be-analyzed image according to the recognition result; obtaining a second to-be-analyzed image; determining whether a feature graphic existsin the second to-be-analyzed image or not; if the feature graphic exists in the second to-be-analyzed image, determining whether the feature graphic is overlapped with an interaction area or not, wherein the interaction area is an area corresponding to an answer of a question in the question audio file; if the feature graphic is overlapped with the interaction area, playing a correct audio file; and if the feature graphic is not overlapped with the interaction area, playing a wrong audio file. The graphic recognition-based interaction method is capable of improving the interactivity.

The present invention proposes one new kind of graphic recognition mark specially for testing the film thickness in semiconductor device, and the graphic recognition mark is one good comparison graph set on chip for graph recognition. The graphic recognition mark has two polygons or circles in the same geometric shape and different areas and superposed in centroid superposing mode. The polygons or circles are divided with diagonals or diameter line into several areas, of which the adjacent two are made of different materials and have different. For example, one of two adjacent areas is made of metal material, such as Al, Cu or Ag, while the other of other material, such as dielectric, oxide, nitride, etc. The two adjacent areas are constituted in different film layers and have different heights counted from the chip bottom layer.

The invention discloses a three-dimensional graph recognition method, device and apparatus and a storage medium. The method comprises: obtaining point cloud of a target three-dimensional model, preprocessing the point cloud of the target three-dimensional model to obtain a target two-dimensional array and a mapping relationship between points in the target three-dimensional model and two-dimensional pixels, obtaining a target two-dimensional image corresponding to the target three-dimensional model based on the target two-dimensional array and the feature data of each point in the point cloudof the target three-dimensional model, performing image recognition on the target two-dimensional image based on a two-dimensional image recognition network, and mapping the target two-dimensional image recognition result to a target three-dimensional model to obtain a target three-dimensional graph recognition result. By utilizing the technical scheme provided by the invention, a three-dimensional graph processing problem can be converted into a two-dimensional image processing problem. By utilizing the characteristics of more mature two-dimensional image recognition, high efficiency and accurate recognition, a more reliable three-dimensional graph recognition result is obtained, less training data is needed, and the cost and time are saved.

The invention relates to a fire-fighting component numbering method and system for an automatic fire alarm planar graph, an intelligent terminal and a storage medium, and relates to the technical field of automatic fire alarm, and the method comprises the steps: inputting a CAD drawing of the automatic fire alarm planar graph; obtaining divided fireproof partitions based on identification of partition multi-segment lines of a preset partition layer in the CAD drawing; performing graphic recognition based on component graphic symbols pre-entered in a component database to obtain fire-fighting components in the fire-fighting partitions; screening to obtain an electric connecting wire connected between the fire-fighting components; acquiring a fire-fighting loop formed by connecting the electric connecting wires, and identifying and acquiring an end point of the fire-fighting loop; and sequentially generating numbers by taking the end points of the electric connecting wires as starting points and taking the electric connecting wires as fire-fighting components, and corresponding generating fire-fighting component information of the generated numbers. The method has the effect of improving the numbering efficiency of the fire-fighting components in the automatic fire alarm plane graph.

The invention discloses character input method, device and a mobile phone terminal based on a pattern recognition technology, applied to the fields of computer software and application terminals. The device comprises an input module, a recognition module and a display module, wherein the input module is used for receiving, temporarily storing and inputting a pattern corresponding to a character to be expressed, and storing a pre-established pattern and character corresponding table; the recognition module is used for recognizing the input pattern and searching the pre-established pattern and character corresponding table according to the result of the recognition so as to obtain the character information corresponding to the input pattern; and the display module is used for displaying the character information. Through the pre-established pattern and character corresponding table, the pattern is input to carry out character input so that a user can input a corresponding character according to the cognition to the things without simply relying on the pronunciation or the spelling of the character and remembering the input rules, and convenience is brought to the use of all the people.

The invention discloses a polarized infrared detector structure. The polarized infrared detector structure includes a micro-bridge structure and a first metal grating structure stacked on a substrate;the micro-bridge structure is provided with a micro-bridge surface, supports and electrical connection holes; the micro-bridge surface is used for detecting infrared rays; the supports and electricalconnection holes are used for supporting the micro-bridge surface and conducting electrical signals generated by the micro-bridge surface to the substrate; the first metal grating structure is suspended above the micro-bridge surface, including a first metal grating composed of a plurality of first metal grid bars arranged in parallel; and the first metal grating is electrically connected to thesupport at the lower part and the electrical connection hole through a first metal support post. According to the invention, polarized light of a certain direction is selectively transmitted to the micro-bridge surface of the infrared detector; therefore, functions such as graphic recognition can be realized in an auxiliary manner; and the performance is better, the cost is lower, and the use is more flexible.

The invention relates to a pattern recognition-based interaction method and system. The method comprises the following steps of: respectively establishing a three-dimensional interaction model in a plurality of clients; seamlessly fusing the three-dimensional interaction models in the plurality of clients by a server and projecting the three-dimensional interaction models to a same screen so as toform a virtual AR three-dimensional interaction scene; putting an entitative pattern card on the screen, and recognizing a coordinate position and shape information of the pattern card by the clientsthrough a pattern recognition technology; and generating virtual interaction elements on a coordinate position corresponding to the AR three-dimensional interaction scene by the server according to the coordinate position and shape information of the pattern card, and controlling interaction behaviors of the interactions in the AR three-dimensional interaction scene according to a preset interaction rule. The pattern recognition-based interaction method is on the basis of the pattern recognition technology, so that new playing methods can be provided for users, so that the users can experience new interaction manners and then the user experience is improved.

The invention provides a method and device for displaying accessible resources and a resource access system, and relates to the technical field of communication. In the present application, the clientcan identify a preset graphic identification code to obtain a domain name address, then an IP address of a target sinking node is obtained according to the domain name address, a query request of accessible resources is sent to the target sinking node according to the IP address, and the target sinking node is a sinking node belonging to the same local area network as the client in the sinking nodes. The target sinking node can acquire locally stored description information of accessible resources and then send feedback information to the client, the feedback information comprises the description information of the accessible resources, and the client displays the description information of the accessible resources. By adopting the method and the device, the problem of low access efficiency caused by CDN traceability in the process of accessing accessible resources through an external network can be solved.

The invention discloses a method for displaying an article, which is implemented in a mobile terminal. The mobile terminal includes a camera. The method includes scanning a graphic identification codeassociated with the article with the camera to obtain presentation information associated with the article based on the graphic identification code, the presentation information including at least anidentification pattern and a virtual element Photographing an image of a predetermined position of an article by a camera, and recognizing an identification pattern in the photographed image; calculating a relative position of the identification pattern and the camera by using a predetermined algorithm; and superimposing and displaying a virtual element in the captured image based on the calculated relative position. This scheme can make the goods carry more information and enhance the user experience.

The invention provides display equipment and a geometric figure recognition method. According to the invention, the display equipment is internally or externally connected with an input device, so that a user can execute interaction through the input device to input a hand-drawn figure track; the controller of the display equipment can determine a first feature direction by traversing the left side of each hand-drawn point in a hand-drawn graph track, rotate a hand-drawn graph according to an included angle between the first feature direction and a preset judgment direction so as to determinea second feature direction, draws a standard geometric figure according to the first feature direction and the second feature direction, and finally enables a standard geometric figure to adapt to thehand-drawn figure in position through rotation; and the display equipment can eliminate the interference of the inclined state of the hand-drawn graph on graph parameters by rotating the hand-drawn graph track, facilitates the matching of a graph recognition template, improves the accuracy of graph recognition, and solves a problem that a conventional geometric graph recognition method is low inaccuracy.

Systems for transmitting and receiving signals of video digital images for links of the “LVDS” type comprise a transmit module, a transmission link and a receive module. The “RGB” video signal comprises the colour and synchronization signals and a clock signal. The “LVDS” video signal transmitted via the transmission link comprises several primary signals, the first primary signal dedicated to the clock signal, the second primary signal comprising the synchronization information, the other primary signals comprising only the colour encoding information. The function of the “LVDS” transmit module is to encode the “RGB” video signal into an “LVDS” video signal and the function of the receive module is to decode the “LVDS” signal into an “RGB” signal. The system comprises the following particular arrangements: the transmission system having a means making it possible to inlay a graphic recognition pattern in the “RGB” video signal; the receive means operating in oversampling and having a test means capable of identifying the synchronization information and the graphic recognition pattern.

The present invention especially relates to a system and method for tower crane collision prevention based on a graphics recognition technology, and relates to the tower crane technology field. The system comprises: an image obtaining device configured to obtain image information; a first image processor configured to binaryzation, filtering, edge detection and interest region extraction and collision object extraction processing of an obtained image to complete distance measurement and send a distance measurement result to a control processor; a second image processor configured to perform feature point detection and stereo matching processing of the obtained image to complete distance measurement and send a distance measurement result to a control processor; a sensor group configured to obtain tower crane motion information; the control processor configured to determine whether the collision happens or not according to the distance measurement result and tower crane motion information and emit an alarm instruction in the condition that it is determined that the collision happens; and an alarm device configured to emit alarm information according to the alarm instruction sent by the control processor. The intelligence degree is high, precision is high, and the applicability is wide, etc.

A method creates an honesty and credibility rating for a user. The method utilizes an algorithm to rate the user based on the information in any user data and / or records. The algorithm assigns an initial rating and subsequently subtracts from or adds to the initial rating a predetermined number of points for each negative and / or positive occurrence in the data and / or records. The method then creates and provides to the user an obfuscated identity that combines the rating with a variety of physical and / or digital identification means such as a wearable badge, a graphical identification, a QR (Quick Response) code, a webpage link, etc. Additionally, the method may remove some or all personally identifiable information for the protection of the user's sensitive information. Thus, the method provides a safe and secure honesty and credibility rating to be used by users to wear and display through physical appearance, digitally, online and social media postings.

The invention relates to the field of artificial intelligence, and provides a vibration damper fault detection method and system based on intelligent pattern recognition, and the method and system employ a pattern recognition method for defect recognition, and comprise the steps: obtaining a surface gray image of a vibration damper; obtaining the uniformity of each pixel point on the surface gray level image of the shockproof hammer; obtaining a plurality of connected domains on the surface grayscale image of the shockproof hammer; calculating a reconstructed gray value of a pixel point in the connected domain to obtain a reconstructed gray image; segmenting the reconstructed grayscale image to obtain an in-contour image; if the texture exists in the image in the contour, judging that the stockbridge damper has defects; if no texture exists in the image in the contour, judging that the shockproof hammer is a qualified product; and classifying the defects of the shockproof hammer according to the texture shape in the image in the contour. Therefore, according to the damper fault detection method and system based on intelligent pattern recognition, defect detection and recognition can be achieved, and the detection efficiency is high.

The invention discloses an application control method and related device. The method is applied to the electronic equipment which comprises a display screen and an under-screen fingerprint module arranged relative to a preset area of the display screen. The method comprises the steps that: when an unlocking request for a target application is detected, a target area of the display screen is determined, and the target area is lightened to prompt a user to carry out fingerprint identification, and the preset area comprises the target area; collect fingerprint data of a user through the under-screen fingerprint module, and perform fingerprint identification according to the fingerprint data; if it is detected that the fingerprint recognition result is matching and the user finger and the display screen are kept in a contact state, a preset pattern is displayed on the display screen, and a sliding track of the user finger is detected, and graphic recognition is conducted according to the sliding track; and if the pattern recognition result is matching, unlocking the target application. The invention is beneficial to improve the safety of unlocking the application by the electronic equipment.

The invention discloses a method and a system for judging the consistency of a metering device based on pattern recognition. The method comprises: collecting images of different parts of an inspectedammeter by an industrial microscope; conveying the collected images to a determination system for image processing; acquiring and storing feature signals of binary images and the images of the different parts of the inspected ammeter into a database as standard feature signals of ammeters of the inspected batch; obtaining feature signals of images of different parts of a delivered ammeter or an onsite ammeter of the same batch as the inspected ammeter; and comparing the feature signals of the delivered ammeter or the onsite ammeter with the standard feature signals stored in the database to obtain the similarity, and determining the delivered ammeter or the onsite ammeter is an ammeter as same as the inspected ammeter according to the similarity. The method provided by the invention can automatically identify that whether the ammeter delivered by the ammeter supplier and the inspected ammeter are in the same batch and whether the onsite ammeter installed on the user site is artificially replaced, thereby reduce the manual workload, and improving the working efficiency.

The embodiment of the invention provides a voice synthesis method and device, and a computer storage medium, and the method comprises the steps: obtaining a to-be-synthesized mixed sequence which comprises a to-be-synthesized text and a to-be-synthesized graph, wherein the to-be-synthesized graph comprises at least one of a graph text and a graph formula; separating the to-be-synthesized text and the to-be-synthesized graph included in the mixed sequence; inputting the to-be-synthesized graph into the graph recognition model, recognizing a recognition text included in the graph text, and recognizing a graph formula as a LaTeX character; combining the to-be-synthesized text, the recognition text and the LaTeX character according to the positions of the graphic text and the graphic formula in the mixed sequence to obtain a text sequence; and inputting the text sequence into a speech synthesis model, and converting the text sequence into audio through the speech synthesis model. According to the scheme, the accuracy of speech synthesis of the mixed sequence can be improved.