96 results about "Texture recognition" patented technology

The invention discloses a panoramic image real-time splicing algorithm and system based on multi-sensor fusion, and particularly relates to the technical field of panoramic image real-time splicing, and the algorithm comprises the following steps: constructing a structured fusion sequence based on multi-source images, postures and position information, optimizing a matching effect through high-density feature extraction and repeated texture recognition, and obtaining a multi-source image fusion sequence; a dynamic foreground and a static background are distinguished by using sparse optical flow so as to improve the visual angle estimation precision, pose fusion optimization is realized in combination with a multi-mode residual error, and the continuity and stability of a spliced image are improved through edge smoothing, brightness tuning and color correction; according to the method, the structured fusion sequence is constructed through multi-source data alignment, so that the data synchronization and splicing stability is improved; identifying repeated regions based on texture direction features, and optimizing feature matching accuracy; and through edge smoothing, brightness harmonizing and color consistency processing, the visual coherence and output quality of the panoramic image are enhanced.

The invention relates to the technical field of intelligent identification, in particular to a highway pavement damage intelligent identification and evaluation method, which comprises the following steps: detecting a structure continuity and texture density region based on a pavement image, extracting crack, pit slot and track contour marks, grouping crack, pit slot and track texture to generate an identification graph, and evaluating the pavement damage. And extracting a crack area texture and gradient change to generate a difference layer, judging trend offset to generate an evolution label, and adjusting a classification boundary to evaluate a damage level. According to the method, the structure continuity and the texture density area are detected, the positioning precision is improved, misrecognition is reduced, direction gradient and texture changes are collected under multiple scales, the crack directions are clustered and grouped, the texture recognition stability is enhanced, the difference of the crack area and the periphery is analyzed, boundary jump is recognized, difference perception is enhanced, and the dynamic recognition depth is improved. Evaluation fuzzy errors are reduced, the overall process improves morphological representation precision and trend tracking and classification boundary stability, and the method adapts to various road condition changes.

The invention discloses an aviation equipment detection and maintenance method and equipment based on target detection and a medium, and relates to the technical field of aviation equipment detection, and the method comprises the steps: inputting a correction image set into a pre-trained target detection network, carrying out the multi-scale feature analysis and edge texture recognition, and generating a part detection result; establishing a component topological relation according to a component detection result, and comparing the component topological relation with a standard configuration by using a graph structure analysis method to generate topological consistency information; performing defect positioning and quantitative analysis on the topological consistency information, extracting a defect position, a defect type and a defect quantitative index, tracking an extension track of the defect quantitative index along with time through continuous time frame difference, and generating a defect parameter; and performing risk assessment on the defect parameters, generating and executing a maintenance scheme, verifying the maintenance effect through real-time image detection, and forming a detection and maintenance closed loop. According to the invention, the accuracy and integrity of aviation equipment detection are finally improved.

The invention relates to the technical field of beef muscle texture recognition, and discloses a multi-modal image AI recognition method and system for beef muscle textures, and the method comprises the steps: collecting a beef image and spectral data; carrying out denoising, enhancement and normalization processing; using a variational auto-encoder to extract fusion features; optimizing a modal fusion strategy through reinforcement learning; reconstructing and enhancing a texture image by using the generative model; the key texture features are subjected to self-adaptive weighted reinforcement; the input classifier outputs a texture recognition result; the system comprises an image acquisition module, a spectrum acquisition module, a data preprocessing module, a multi-modal feature extraction module, a feature fusion module, an image generation module, a texture feature analysis module and an identification decision module. According to the invention, a bimodal joint modeling mechanism of image and spectral information is introduced, deep feature mapping is carried out on two types of modals by means of a variational auto-encoder, a cross-modal expression relationship is established through a submerged space, and the texture expression integrity and resolution are enhanced.

The invention discloses a visual tactile sensor fused with an optical waveguide and a preparation method thereof, and belongs to the technical field of intelligent tactile sensing. The visual tactile sensor comprises a fixed shell, and the top end of the fixed shell is open; the composite tactile sensing layer is arranged at the opening position of the fixed shell, and the composite tactile sensing layer is sequentially composed of a shading layer, a reflecting layer, a red-green spaced fluorescent layer, an elastic deformation layer and a supporting layer from top to bottom; and the optical lighting and sensing component comprises a blue LED light bar, an array light intensity sensor and a camera, the blue LED light bar and the array light intensity sensor are arranged on the two corresponding sides of the composite touch sensing layer respectively, and the camera is arranged at the bottom in the fixed shell. Through fusion of rapid and stable light intensity detection characteristics of optical waveguide sensing and pressure distribution detection capability of the visual tactile sensor, high-resolution space and texture identification and high-sensitivity mechanical response detection are simultaneously realized in a single sensor architecture.

The invention discloses an agricultural product distribution automatic identification system and a distribution method thereof, and relates to the technical field of agricultural product identification and distribution, and the system comprises a basic information module which is used for obtaining basic identification features of agricultural products; the information screening module is used for obtaining visual data, spectral data and texture data; the visual identification module is used for performing first identification on the agricultural products according to the difference quantity to obtain a first identification result; the spectrum identification module is used for carrying out second identification on the agricultural product according to the internal quality and the maturity to obtain a second identification result; the texture recognition module is used for performing third recognition on the agricultural products according to the product texture data and the packaging texture data to obtain a third recognition result; and the general management distribution module is used for distributing the agricultural products according to the final identification result. The method has the effects of improving the accuracy in the automatic identification process of the agricultural products and reducing the adverse effects caused by conditions such as time, stains and damage.

The invention discloses a surface texture recognition system based on a fabric tactile sensor and a construction method of the surface texture recognition system, and relates to the field of recognition precision regulation and control. The prepared interdigital electrode and the sensing electrode are laminated and assembled into the fabric tactile sensor with the bionic microstructure; the constructed microstructure sensing electrode can realize efficient sensing of static force and mechanical vibration at the same time through microstructure multi-dimensional deformation so as to realize efficient identification of surface fine texture textures; the constructed sensing electrode microstructure is adjustable and controllable, so that the performance is adjustable and controllable, the problems of device flexibility, air and moisture permeability, wearing comfort, recognition accuracy reduction and the like caused by a commonly used template microstructure preparation method are solved, and the problems of difficult signal collection and signal crosstalk caused by a multi-mechanism mixed mode are solved.

A method for texture identification and process parameter generation of stone materials is performed as follows. An image of a to-be-identified stone is obtained.The image is input into a texture recognition model to generate a texture recognition result and a mask; and a central position along a texture direction of the to-be-identified stone and processing parameters corresponding to a texture of the to-be-identified stone are extracted from the texture recognition result and the mask.The texture recognition result includes a recognition information of the processing parameters; and the mask is an indicative information of location and shape of individual texture regions in the image.

The application discloses a flexible tactile sensing and feedback system and method based on texture recognition, which comprises an electrostatic flexible tactile sensor, a feedback actuator and a tactile feedback control circuit, the electrostatic flexible tactile sensor comprises a tactile interaction film for acquiring texture features and a pressure sensor for texture feature conversion; the feedback actuator completes tactile feedback of the texture feature signal acquired by the flexible sensor in the form of vibration; the tactile control system is mainly connected with the electrostatic flexible tactile sensor and the tactile feedback actuator through the feedback control circuit; the tactile feedback actuator has a stimulation reinforcement structure on the contact surface with the human body, which can further enhance the fine feedback of the tactile feeling. The application can effectively identify the texture features and complete the feedback of the fine tactile feeling in the form of vibration, provides effective assistance for the tactile recovery of the disabled, and has important application value in the game industry, especially in the development of virtual reality technology.

A texture recognition module. The texture recognition module includes: a substrate (1); a driving circuit layer (9) located on one side of the substrate, including a plurality of arrayed driving transistors (12); a first insulating layer (5) located on the side of the driving circuit layer away from the substrate, including a plurality of first vias (13) penetrating the thickness of the first insulating layer; a plurality of photoelectric conversion units (15) located on the side of the first insulating layer away from the driving circuit layer, which are in one-to-one contact with the first electrode of the driving transistor through the first vias; a second insulating layer (16) located on the side of the first insulating layer away from the substrate, including a plurality of second vias (17) corresponding to the photoelectric conversion units; the distance between the edge of the second via and the edge of the surface of the photoelectric conversion unit away from the substrate is less than or equal to a first preset value; a plurality of first electrodes (18) located on the side of the photoelectric conversion unit away from the driving circuit layer; each first electrode covers the photoelectric conversion unit in the second via.

This invention discloses a method and system for detecting coating defects on the surface of rollers based on image generation, belonging to the field of industrial product quality inspection technology. The method includes the following steps: acquiring continuous image data of the roller during a stable rotational speed phase and a sudden increase in rotational speed, recording the start time of the speed change, and generating rotational speed change identification information; organizing the continuous images in chronological order based on the rotational speed change identification information, comparing the brightness distribution of the images before and after the speed change, extracting areas of sudden brightness increase, and generating a set of bright areas. This invention achieves precise correspondence between image acquisition and roller operating state by introducing rotational speed change identification information, eliminating interference from sudden changes in illumination on texture recognition; and through dynamic backtracking of the texture real image set and peeling risk information, it achieves continuous tracking and adaptive detection of coating defects, improving recognition stability and detection reliability.

The invention relates to the technical field of computer vision and artificial intelligence, and particularly discloses a bird's nest texture AI identification verification system and method, and the system comprises an image collection module, an AI processing module, a database module, and a verification interaction module. The image acquisition module acquires a texture image by using high-precision equipment; the AI processing module extracts features, trains a model and matches the features; the database module stores data in a cloud distributed manner; and the verification interaction module supports multi-terminal verification. The method comprises the steps of production end collection and filing, AI model training optimization and terminal verification operation. The system takes the natural texture of the cubilose as an identifier, avoids counterfeiting, does not need a paper label, is high in verification accuracy, is simple to operate by consumers, and is suitable for multiple scenes.

The application provides a large-scale satellite image automatic registration and enhancement method based on adaptive multi-source fusion, comprising: performing orthorectification and multi-resolution unified projection on a multi-source original data set obtained to obtain a coarse registration image set; calculating a local tensor structure of the coarse registration image set, performing repeated texture recognition, generating a final structure representation and a structure reliability; performing regional registration to obtain a full-image dense deformation field, then performing image transformation to be aligned and registration uncertainty estimation to obtain a high-precision registration image and structure registration uncertainty estimation; combining a pseudo-change probability of the high-precision registration image and the structure registration uncertainty estimation to obtain a change reliability weight; under the constraint of the change reliability weight, performing consistency enhancement on the high-precision registration image to output a quantitative and reliable enhanced image. The application realizes high-precision, low-false alarm and quantifiable and reliable automatic registration and enhancement of multi-source large-scale satellite images.

The invention relates to the technical field of fresh or chilled livestock and poultry meat type image analysis, and particularly discloses a livestock and poultry meat texture recognition and cutting method based on deep learning, which is characterized in that an improved YOLOv8 model is adopted to complete livestock and poultry meat type and part classification and texture direction detection at the same time, a multi-condition judgment mechanism and a region segmentation strategy are designed, and the recognition and cutting efficiency is improved. The accuracy of texture recognition is ensured; the cutting path is automatically planned according to the recognition result, the cutting mode is optimized for different meat types and parts, the cutting efficiency and the meat integrity are remarkably improved, manual intervention is reduced, and the method is suitable for large-scale livestock and poultry meat type processing.

The invention discloses a texture recognition method and system, a medium, equipment and a tactile sensor in the technical field of tactile perception, and aims to solve the technical problems existing when a robot perceives fine textures. The method comprises the following steps: acquiring change data of magnetic field intensity; performing data preprocessing on the change data of the magnetic field intensity, inputting the data into a pre-trained texture recognition model, and performing texture recognition to obtain a recognition result; the training of texture recognition comprises the steps of inputting a model input sample into a texture recognition model, performing random cutting on the input sample by using a Dropout layer, performing feature and attention weighted fusion by using an LSTM network layer and an attention module, learning a nonlinear relationship between features by using a KAN linear layer, and finally performing label prediction through a SoftMax layer to obtain a prediction result; and calculating the loss between the prediction result and the actual label, and optimizing the texture recognition model parameters by minimizing the loss. According to the invention, a fine texture sensing capability is provided for the robot.

A texture recognition device and a display device are provided. The texture recognition device includes a backlight element, configured to provide first backlight; a light constraint element, configured to perform a light divergence angle constraint process on the first backlight to obtain second backlight with a divergence angle within a preset angle range, the second backlight being transmitted to a detection object; and a photosensitive element, configured to detect the second backlight reflected by a texture of the detection object to recognize a texture image of the texture of the detection object.

The present application relates to the field of electronics. Provided in the embodiments of the present application are a detection assembly, a touch display screen, an electronic device and a control method therefor, which are used for providing a detection assembly integrating functions of bioelectric signal detection and identity recognition signal detection. The detection assembly comprises a texture recognition module, a first conductive layer and a bioelectric signal acquisition module. The first conductive layer is arranged on an acquisition side of the texture recognition module and serves as a biological sampling electrode. Fusing the texture recognition module and the first conductive layer serving as a biological sampling electrode with each other allows one detection assembly to have both functions of identity recognition and bioelectric signal acquisition. Thus, when users place parts to be tested such as hands on detection assemblies, identity recognition signals and bioelectric signals can be obtained.

The invention relates to the field of textile production recognition, in particular to a textile production positioning recognition system based on visual inspection, which comprises a texture recognition end, an image detection end, a cutting position generation end, a first execution end and a knitting positioning end. The method comprises the following steps: processing lines for detecting a target detection image to obtain an image texture value of a unit element, then combining the image texture value with an image with a standard line to obtain a target cutting position, then identifying a cutting piece, generating a region image, marking a standard stitching point in the region image to obtain a region marking image, and finally marking the region marking image to obtain the target cutting position. And overlapping and processing all the area marking images to obtain a target distance value, and obtaining a sewing positioning point according to the target distance value, so that the overall spinning point of the textile is determined according to sewing positioning identification, and the production quality of the textile in the production process is kept consistent.

A texture recognition device and its manufacturing method, a color filter substrate and its manufacturing method. The texture recognition device has a touch side and includes a light source array, a light valve structure, and an image sensor array. The light valve structure is disposed on a side of the light source array close to the touch side and includes a first substrate, a second substrate, and a light adjustment layer between the first substrate and the second substrate, configured to be able to respond to a control signal to control a first area to be in a light-transmitting state, so as to allow the light emitted by the light source array to pass through the first area in the light-transmitting state to form a first photosensitive light source. The second substrate of the light valve structure is closer to the touch side than the first substrate, and the image sensor array is disposed on the second substrate. The texture recognition device can form a photosensitive light source in a corresponding area through the light valve structure to achieve the function of under-screen texture recognition.

The present application relates to the technical field of fabric texture detection, and particularly relates to a fabric defect detection method, comprising: collecting a fabric image; inputting spatial domain maps into spatial domain encoders of a ViT-S model respectively; inputting frequency domain maps into frequency domain encoders of the ViT-S model respectively; inputting a spatial domain first layer block vector, a spatial domain second layer block vector and a spatial domain third layer block vector into a TPP module; inputting a frequency domain first layer block vector, a frequency domain second layer block vector and a frequency domain third layer block vector into the TPP module; performing Concat operation on a fusion first layer feature, a fusion second layer feature, the spatial domain third layer block vector, the frequency domain first layer block vector, the frequency domain second layer block vector and the frequency domain third layer block vector, and then inputting the result into a classifier to output a classification result. The present application overcomes the problem that the recognition accuracy of traditional methods for complex fabric texture needs to be further improved.

The application discloses a control system of a six-degree-of-freedom hydraulic mechanical arm for dismounting and mounting a cylinder, relates to the technical field of cylinder dismounting and mounting, and is characterized in that a multi-angle polarized light source is configured at a light jump area on the surface of the cylinder, a brightness gradient sequence is established, a multi-exposure time chain is constructed, the light intensity is controlled in time, the reflection area is formed into a continuous light level, spot energy diffusion is performed to form a continuous texture transition zone, a pose feature track is extracted, a motion edge is generated by combining light intensity variation to identify an optical flow clue, a visual guide channel is constructed according to the clue, a hydraulic actuator is driven to perform pose fine adjustment, and synchronous compensation and pressure regulation of the alignment process are realized. The application realizes the continuous transition of the light on the surface of the cylinder through the multi-angle polarized light and the multi-exposure time chain, improves the imaging accuracy and the texture recognition stability, and realizes the pose fine adjustment and the pressure balance control by combining the optical flow guide, so that the hydraulic mechanical arm can complete adaptive assembly in a reflection interference environment, and the dismounting and mounting accuracy and safety are significantly improved.

The invention discloses an article texture recognition and analysis system based on an AR technology, and relates to the field of texture recognition, and the system comprises a texture recognition platform which comprises a data collection module, a data classification module, a data decomposition module, a data recognition module, a virtual interaction module and a texture visualization module; the data acquisition module acquires historical article texture identification information and article acquisition information; the data classification module obtains texture feature information corresponding to the texture identification information of the historical articles and stores the texture feature information; the data decomposition module analyzes the article collection information to obtain a dimension image data subset of each plane dimension; the data identification module retrieves corresponding texture feature information according to the dimension image data subset; the virtual interaction module generates virtual texture data according to the retrieval result; the texture visualization module constructs a three-dimensional article texture visualization image according to the virtual texture data; according to the invention, the efficiency in the article texture identification process is improved.

A texture recognition module (100) includes: a substrate (1); an optical sensing structure (2) located above the substrate (1) and within a texture recognition area (A); an optical path structure (3) located on a side of the optical sensing structure (2) away from the substrate (1), at least within the texture recognition area (A) and not covering a bonding area (C), the optical path structure (3) being configured to have a plurality of light-transmitting channels (Q) and light rays incident on the optical path structure (3) being able to pass only through the light-transmitting channels (Q); the optical path structure (3) includes: at least two light-shielding layers (31, 31a, 31b, 31c) arranged in layers and light-transmitting layers (32, 32a, 32b) located between every two adjacent light-shielding layers (31, 31a, 31b, 31c), a first light-transmitting hole (311a) arranged in an array is provided on the light-shielding layer (31a) closest to the optical sensing structure (2), a second light-transmitting hole (311b) corresponding to the first light-transmitting hole (311a) one by one is provided on the light-shielding layer (31b) farthest from the optical sensing structure (2), the first light-transmitting hole (311a) and the second light-transmitting hole (311b) corresponding thereto define the light-transmitting channel (Q), and the orthographic projections of the first light-transmitting hole (311a) and the second light-transmitting hole (311b) corresponding thereto on the substrate (1) do not overlap. A preparation method of a texture recognition module (100) and a display device.

The invention belongs to the technical field of image processing, and particularly relates to an image recognition system and an image recognition sensor applied to a camera, and the system comprises an image recognition module, a preprocessing module, a texture recognition module, an optical flow track module and a camera tracking module which are in communication connection in sequence. FPGA hardware acceleration is combined with redundancy reduction of particle screening, so that an image recognition system can stably perform full-link processing on a high-speed camera, and the non-delay tracking requirement of a high-speed moving target is met; through a texture channel fused by multiple edge channels, the edge integrity rate in a high-speed motion fuzzy scene is improved, and the tracking loss rate of light field particles is reduced; through a designed double-constraint optical flow mechanism, the optical flow estimation error of a high-speed moving target is reduced, the inter-frame position deviation of camera tracking is reduced, and accurate positioning of the high-speed target is realized, so that the problems of image precision reduction and tracking breakage caused by high-speed movement of the target in high-speed camera image recognition are solved.

The invention discloses a GPU context awareness-based code editor dynamic text rendering acceleration method, which comprises the following steps of: establishing a multi-dimensional semantic tag system comprising variables, functions, errors and structures, extracting semantic sub-dimensions of characters, generating character semantic tags through operation, caching the character semantic tags to a semantic tag SSBO, constructing a mapping rule of the semantic tags and rendering styles, and carrying out text rendering on the rendering styles according to the mapping rule. The CPU encodes the semantic rules into semantic rule textures; identifying structural units and layout attributes thereof, encoding the structural units into structural textures by the CPU, and uploading the structural textures to a structural layout SSBO of the GPU; the calculation shader reads two types of SSBO, respectively allocates four types of weights of semantics, interaction, structure and effect for characters, and generates a pattern weight texture after determining a fusion coefficient; the vertex shader calculates the final screen position of the character in parallel according to the structure unit to which the character belongs; and the fragment shader reads the two types of SSBO, each texture and the final screen position output by the vertex shader, hierarchical fusion is carried out according to a weight sequence, and character pixel-level rendering is completed.

The present application provides a method and apparatus for repetitive texture recognition. The method horizontally stitches two images corresponding to an image pair and calculates the slope of the line connecting the matching feature point pairs in the two images. Further, it statistically counts the proportion of the lines whose deviation between the slope and the standard value of the slope is greater than or equal to a set value. If this proportion is greater than the corresponding preset value, it indicates that there are small areas of repetitive textures in the image pair in the non-primary direction of feature matching, that is, it determines that the matching relationship of the image pair is incorrect and deletes the matching relationship of the image pair. It can be seen that this method does not need to analyze the content information of the feature points in the image pair, and only recognizes the repetitive textures not in the primary direction of feature matching through the slope of the feature point connection line. Therefore, this method is not sensitive to the input image and improves the robustness of this method.

The invention discloses a bronze ware texture recognition method based on multi-principle data annotation and deep learning, and the method comprises the steps: S1, obtaining an image containing bronze ware texture, and constructing an original image data set; s2, according to a preset multi-principle data labeling strategy, labeling textures in the original image data set, and generating a high-quality labeling data set; s3, inputting the high-quality annotation data set into a preset deep learning target detection network model for training and evaluation to obtain a mature model capable of identifying the texture of the bronze ware; and S4, processing the new bronze ware image by using the mature model, and outputting types and position information of textures contained in the image. According to the method, the recognition accuracy can be remarkably improved, the multi-scale and detail problems are effectively solved, the model generalization ability can be enhanced, and meanwhile, the method has universality.

The present invention relates to the field of medical data processing technology, specifically to a radiology image data analysis system, the system comprising: a self-matching texture recognition module to collect image data, analyze the texture type in the image, adjust the size and shape of the search window, calculate the structural fit of the area in the window according to the texture features, and aggregate the data of similar areas. In the present invention, by adjusting the size and shape of the search window, the structural fit of the area is accurately calculated according to the texture features, and a more refined data analysis is achieved. By aggregating similar area data and updating the fit weight, the target of data analysis is optimized, and the iterative soft threshold algorithm is applied to effectively process texture features and edges, reduce the complexity of data, and improve the processing speed. In addition, the topological structure analysis strengthens the intuitive understanding of complex pathological structures, and the global pattern features are analyzed through the graph network, which enhances the accuracy of diagnosis and provides data support for disease prediction.

A texture recognition assembly (100) includes: a substrate (1); an optical sensing structure (2) on the substrate; and a light path structure (3) on a side of the optical sensing structure distal to the substrate and including an inclined light transmitting channel (Q) such that light incident on the light path structure can only pass through the light transmitting channel. The light path structure includes at least two light shielding layers (31, 31a, 31b, 31c) and a light transmitting layer (32, 32a, 32b) located between any adjacent two of the at least two light shielding layers, the light shielding layer (31a) closest to the optical sensing structure includes a first light transmitting hole (311a), the light shielding layer (31b) farthest away from the optical sensing structure includes a second light transmitting hole (322b), the first light transmitting hole and the second light transmitting hole define the light transmitting channel.

This invention discloses a GPU-based context-aware code editor dynamic text rendering acceleration method. It establishes a multi-dimensional semantic tagging system including variables, functions, errors, and structures. Semantic sub-dimensions of characters are extracted and processed to generate character semantic tags, which are then cached in semantic tag SSBOs. A mapping rule between semantic tags and rendering styles is constructed, and the CPU encodes the semantic rules into semantic rule textures. Structural units and their layout attributes are identified, and the CPU encodes them into structural textures and uploads them to the GPU's structural layout SSBOs. The compute shader reads two types of SSBOs and assigns four weights—semantic, interactive, structural, and effect—to the characters. After determining the fusion coefficients, it generates style-weighted textures. The vertex shader calculates the final screen position of the character in parallel based on the structural unit to which the character belongs. The fragment shader reads the two types of SSBOs, each texture, and the final screen position output by the vertex shader, and fuses them layer by layer according to the weight order to complete pixel-level character rendering.