118 results about "Texture feature" patented technology

This invention discloses a method for generating art images for the creation of traditional Chinese style content. The method first constructs a multimodal atlas of traditional Chinese style art based on independent copyright. Next, a parallel dual-stream perceptual feature extraction network is constructed to extract the topological geometric features (such as paper-cutting connectivity) and texture features (such as mural pigment texture) of the image. During the generation stage, the feature fusion weights are dynamically adjusted through a physically-aware cue word adapter and an adaptive gated cross-attention mechanism. A LoRA strategy and ControlNet are combined for joint fine-tuning, and a topological consistency loss function and a traditional Chinese style aesthetics scoring loss function are introduced to strongly constrain the generation process, effectively solving physical defects such as broken lines and structural inconsistencies. Finally, physically-rendered (PBR) technology is used for post-processing to reshape the microscopic material texture and historical weathering feel, generating professional traditional Chinese style art images with museum-level visual realism and copyright protection.

The application discloses a partition method of an image, a defect detection method and a defect detection device, and relates to the technical field of semiconductor manufacturing. The method comprises the following steps: segmenting an original image to be partitioned by using an image segmentation model to generate a plurality of initial masks; determining a plurality of target masks based on the initial masks, each target mask corresponding to a target region in the original image; determining effective texture features based on texture feature values of the target regions; obtaining a characteristic vector of each target region, wherein a vector composed of the feature values of the effective texture features of each target region constitutes a characteristic vector of the corresponding target region; and performing clustering processing on the target regions based on the characteristic vectors of the target regions to obtain target sub-images of a plurality of feature types corresponding to the original image. The technical scheme provided by the application can realize automatic and accurate image partition processing of the original image, and improves the working efficiency and accuracy of image partition.

The application relates to a method for detecting an obstacle in a parking space and a storage medium, the method comprising: collecting a parking space image; splitting the parking space image into a plurality of sub-images; determining texture features and color features of each of the plurality of sub-images; determining texture similarity of adjacent two of the plurality of sub-images with respect to the texture features and color similarity with respect to the color features; forming a difference coefficient of the parking space image according to statistical information of the texture similarity and the color similarity; and judging whether an obstacle exists in the parking space according to the difference coefficient. The method can determine whether an obstacle exists in the parking space according to an image algorithm, so as to guarantee parking safety.

This disclosure belongs to the field of image detection technology and provides an oil leak detection method and device. The method includes: acquiring multiple image frames at different acquisition times of the oil production equipment; obtaining multiple regions of interest (ROI) frames corresponding to the target location from the image frames; extracting interface environment features through a texture feature extraction branch and predicting the oil leak penetration stage based on these features; extracting jet morphology features through a geometric feature extraction branch and predicting the oil leak piercing stage based on these features; and extracting flow reflection features through a physical feature extraction branch and predicting the oil leak flow stage based on these features. Then, the oil leak detection result of the target location is obtained based on the prediction results. By utilizing the different changes in different features of the same oil production equipment image at different oil leak stages, the oil leak stage of the oil production equipment can be identified accordingly, enabling timely and accurate identification of the oil leak situation.

This invention relates to the field of automated inspection technology, providing a method, apparatus, and system for textile inspection. The method includes: acquiring a texture sample of a defect-free textile; acquiring a defect detection model; extracting texture features from the texture sample to obtain a batch reference feature library; inputting an image of the textile to be inspected into the defect detection model to obtain fused features; and inputting the fused features into the defect detection head to obtain a defect detection result. The advantage of this application lies in that, while maintaining stable general defect detection capabilities, it introduces a batch reference feature library constructed from batches of defect-free texture samples. Furthermore, through a cross-branch detection module, it achieves deep fusion of general representations and batch-specific texture features at the feature layer. This allows the same defect detection head to simultaneously utilize general defect morphology information and deviation information relative to the normal texture pattern of the current batch in a single output, thereby improving detection accuracy.

Provided are a method and device for tuning an image signal processor. The method for tuning the image signal processor comprises: obtaining an adjusted image of an image by adjusting the size of the image, and obtaining a plurality of image blocks of the image by performing a tiling process on the image, wherein the image is an output image of the image signal processor obtained in response to an input image being input into the image signal processor; extracting a brightness feature and a contrast feature of the image based on the adjusted image; extracting a noise feature and a texture feature of the image based on the plurality of image blocks; obtaining a feature extraction result of the image by fusing the brightness feature, the contrast feature, the noise feature and the texture feature; and tuning the image signal processor based on the feature extraction result and a current parameter of the image signal processor, so as to improve the tuning effect of the image signal processor by improving the accuracy and effectiveness of feature extraction.

Embodiments of the present disclosure provide a video texture migration method and device, electronic equipment and storage medium, which obtain an original video, perform feature extraction on a target frame in the original video to generate first feature information of the target frame, wherein the target frame is a video frame after an Nth video frame in the original video, and the first feature information represents an image structure contour of the target frame; perform feature fusion on the first feature information of the target frame and reference feature information to obtain second feature information of the target frame, wherein the reference feature information is used to represent an image structure contour of a reference frame, the reference frame is a video frame before the target frame, and the second feature information is the first feature information without random noise; and generate a texture migration video according to the second feature information of the target frame and corresponding texture feature information, wherein the texture feature information represents image texture details of a reference image, thereby avoiding frame flickering and improving the display effect of the texture migration video.

This invention discloses a gravity field orientation adaptability analysis method based on image texture features. This method can select adaptability regions rich in gravity information, providing directional guidance for gravity field trajectory planning and effectively improving the accuracy of multi-directional gravity field matching. This invention comprehensively considers both gravity field statistical feature parameters and image texture feature parameters, fusing these two features to determine the adaptability region, making the selected adaptability region more continuous and the texture features more obvious. During dataset training, a parallel convolutional neural network is used, simultaneously training statistical feature parameters reflecting gravity field statistical features and gray-level gradient co-occurrence matrix parameters reflecting image texture features. These features are mapped to the output layer for classification, and the gravity field adaptability region is determined based on the classification results, thus achieving the evaluation of the orientation adaptability of the gravity field adaptability region.

This invention discloses a method and system for identifying apparent damage to bridge concrete based on texture analysis, belonging to the interdisciplinary field of bridge engineering inspection and computer vision technology. The method includes: acquiring surface images of bridge components using a drone and generating orthophotos; extracting contrast, correlation, and entropy features based on the gray-level co-occurrence matrix; extracting histogram features based on local binary patterns; detecting corrosion and seepage areas based on the HSV color space; fusing multi-dimensional features and inputting them into a multi-label classifier, simultaneously outputting pixel-level segmentation masks for multiple types of damage such as cracks, spalling, exposed rebar corrosion, and seepage; generating a damage level score and maintenance recommendation report according to bridge technical condition assessment standards. This invention integrates complementary texture features to achieve simultaneous identification of multiple types of damage, outputs pixel-level segmentation results, and automatically generates an assessment report that conforms to engineering specifications.

This invention belongs to the field of metallographic inspection technology, specifically relating to an optimization method for a metallographic structure recognition model, comprising: acquiring image data of different categories of metallographic structures; constructing a sample dataset based on the image data of various metallographic structures, and using it to perform end-to-end training of the metallographic structure recognition model, so as to classify and identify metallographic structures through the optimized metallographic structure recognition model; wherein, the metallographic structure recognition model includes: an input layer, a backbone network, a feature fusion layer, and an output layer, and the backbone network includes a Stem layer and multiple Stage layers; the Stem is used to perform downsampling and basic feature extraction on the processed image data to generate an initial feature map with shallow features; the Stage layers are used to perform progressive feature enhancement and downsampling on the initial feature map to generate a final feature map with deep features; and at least one Stage layer embeds a feature extraction module for deep extraction of directional texture features in the image data of metallographic structures.

The application discloses a kind of carbonate rock flake identification method and system, belong to image processing technical field, will take the carbonate rock flake image of different geological scene respectively input pre-trained network model and identify, output attribute identification result.Network model includes classification module, segmentation module, feature fusion module and classifier, after classification module extracts mineral texture feature of carbonate rock flake image by mineral texture attention module, respectively input classification head and the regression head of embedding dynamic scaling constraint regression mechanism and carry out detection;Segmentation module carries out regional segmentation to carbonate rock flake image, outputs the pixel proportion of real mask corresponding to the prediction mask of different segmentation region respectively;Feature fusion module carries out fusion to detection result and pixel proportion;Classifier carries out coordinated inference to fusion feature, and outputs attribute identification result.The method is identified by cooperation and dynamic constraint, ensure the scientificity and reliability of identification result.

This invention relates to the field of image recognition, specifically to an automated tunnel construction monitoring system based on image data. The system includes an edge computing node that acquires the original tunnel image and constructs an atmospheric scattering physical model using measured data from an optical dust concentration sensor. The edge computing node transforms the original image to the frequency domain, extracts low-frequency brightness features and high-frequency texture features using discrete cosine transform, and adaptively compensates the high-frequency texture features with weights based on the transmittance matrix calculated by the physical model to suppress diffuse light interference. The compensated features are then input into a lightweight convolutional neural network via inverse transform. This scheme introduces dust physical parameters as prior constraints into the frequency domain feature weight calculation, reducing the probability of image edge artifacts and color distortion under conditions of localized strong light and high dust, ensuring the physical authenticity of target edge features in the reconstructed image, and improving the accuracy of feature extraction under harsh conditions.

This invention relates to a comprehensive diagnostic method for aeration tank operation based on continuous image recognition, comprising: acquiring water samples from the aeration tank; continuously acquiring multiple microscopic images of the samples within a fixed observation area, and obtaining a sequence of sample images after preprocessing; dividing the sequence into moving and stationary regions based on pixel differences between the sample images, identifying the trajectory of an object and calculating its length; extracting images of the moving object and extracting its contour and texture features; determining the microbial species of the moving object based on its contour, texture, and trajectory length; analyzing the morphological characteristics of flocs in the stationary region, and comprehensively diagnosing the aeration tank's operational status in conjunction with the microbial species. This invention can accurately determine the dominant microbial species in the aeration tank. Based on this, and combined with the characteristics of the flocs, through the coupling of multiple factors and various feature values, it can directly reflect the sludge activity and treatment effect in the aeration tank, improving the accuracy of operational status assessment.

This invention provides a method, apparatus, electronic device, and storage medium for detecting in-mold foreign objects, belonging to the field of intelligent manufacturing technology. The method includes: acquiring an image of the mold to be detected in response to a detection trigger signal; extracting an image of the region of interest and comparing it with a template image to obtain a difference region; acquiring image texture feature parameters of the difference region; determining, based on the parameters, whether the difference region is a false difference caused by ambient light interference or a real difference caused by a physical foreign object; if it is a false difference, updating the image to the template image set as a comparison benchmark; if it is a real difference, outputting an abnormal signal. This invention analyzes image texture features to deeply determine the physical attributes of the difference, effectively distinguishing between light interference and real foreign objects, achieving adaptive template updates under changing ambient light, overcoming the shortcomings of traditional visual detection that is easily affected by lighting, significantly reducing false alarm rates and manual maintenance costs, and improving the detection accuracy of the system.

This invention relates to the field of intelligent inspection and 3D visual reconstruction technology for automotive parts, specifically a method for 3D image reconstruction of lightweight internal high-pressure molded parts for automobiles. The method includes: acquiring a sequence of structured light images, multispectral reflectance texture images, and a priori simulation model of the target object, and completing spatial coordinate registration; dynamically allocating edge extraction weights based on the local curvature gradient of the 2D image to generate a non-uniform density 3D point cloud; constructing a surface reconstruction energy function using surface reflectance variation data as a penalty term, fitting the point cloud to the 3D surface, and generating a target 3D mesh model; fusing 3D geometric features, 2D texture features, and the priori simulation model, and outputting the wall thickness reduction rate and residual stress distribution via a graph neural network; generating and overlaying a risk heat map, and outputting the evaluation decision results. This invention extends from geometric reconstruction to risk semantic reconstruction, improving the comprehensiveness and reliability of online inspection of internal high-pressure molded parts.

The application discloses a crop disease and pest stress abnormal area segmentation method based on color texture fusion, relates to the technical field of agricultural remote sensing and intelligent image processing, and comprises the following steps: acquiring a farmland remote sensing image and performing pretreatment to eliminate noise and distortion; converting the pretreated image into an HSV color space to extract color features, extracting a gray level co-occurrence matrix and a local binary pattern texture feature, splicing the color features and the texture features in a channel dimension to form a multi-channel fusion input; feeding the multi-channel fusion input into a semantic segmentation network for training; after the training is completed, applying a model to segment a new image, and performing fusion and post-processing on a segmentation result to generate a disease and pest stress abnormal area distribution map. The application improves the precision and robustness of disease and pest stress abnormal area segmentation, realizes automatic full-field distribution mapping, and reduces the use cost and threshold.

This application provides a method, apparatus, electronic device, storage medium, and computer program product for changing the clothing of a target object. The method includes: acquiring an image to be changed into and a clothing image; the image to be changed into includes a target object; determining a semantic segmentation map of the image to be changed into and a pose feature map of the target object; performing masking processing on the image to be changed into based on the pose feature map and the semantic segmentation map to obtain a masked image to be changed into; extracting texture features from the clothing image to obtain the texture features of the target clothing in the clothing image; determining a changing image based on the pose feature map, the masked image to be changed into, and the texture features of the target clothing; the changing image includes the target object wearing the target clothing. This application generates a changing image by extracting the texture features of the target clothing and combining them with the texture features of the clothing features, so that the clothing in the changing image retains the real texture of the clothing, thereby improving the fidelity and realism of the changing image.

The application belongs to the technical field of image processing, and particularly relates to a UV ink curing degree detection method and system based on texture analysis, which comprises the following steps: collecting an original gray-scale image of a UV ink surface, constructing a local illumination saturation index positioning mirror reflection dominant area, and combining a texture optical masking coefficient to obtain an adaptive texture recovery gain; performing weighted processing on the gray-scale value and high-frequency component of the original gray-scale image by using the local illumination saturation index and the adaptive texture recovery gain respectively, extracting macroscopic statistics and microscopic structure features of a reconstructed image to construct a multi-dimensional texture feature vector; inputting the multi-dimensional texture feature vector into a support vector machine classifier to obtain a curing state, and generating a control signal according to the curing state. The application improves the extraction effect of weak texture features under strong light interference, and provides technical support for closed-loop control of the curing process.

This invention relates to the field of image steganalysis defense technology, and particularly to an active image steganalysis defense method and system based on signal enhancement. The method involves adding interference noise to the image to be processed based on signal texture features to enhance the stegana signal. The enhanced image is then input into a pre-trained active image steganalysis defense network. This network restores the stegana signal features and recovers the original carrier image from the processed image through an inverse difference operation. The active image steganalysis defense network employs a dual-channel parallel network model to reconstruct the stegana signal distribution by mining the correlation and spatial relationships between the stegana signals. This invention does not require knowledge of the steganalysis algorithm type and embedding rate. Through image noise addition and neural network modeling, it achieves dual destruction of secret information in the image under a heterogeneous balance state, while simultaneously restoring the quality of the original image.

The application discloses a geometric self-attention semantic segmentation method and device and a storage medium, and comprises the following steps: acquiring a color texture image and a depth topography image in a multi-modal image; obtaining a color texture feature map and a depth topography feature map according to the color texture image and the depth topography image; guiding the depth topography feature map to perform geometric correction through the color texture feature map to obtain a corrected geometric feature; performing depth uncertainty evaluation according to the depth topography image to obtain an uncertainty mask; dynamically fusing the color texture feature map and the corrected geometric feature according to the uncertainty mask to obtain a fusion feature map of n scales; and inputting the fusion feature map into a classification module to obtain a semantic segmentation result. The geometric correction of the depth topography feature map is used to eliminate the cross-modal boundary misplacement; the reliability evaluation of the depth data is used to dynamically adjust the weight of the geometric information in the attention calculation, so that the dynamic fusion between different modalities is realized, and the segmentation accuracy of the semantic segmentation result is ensured.

An image recognition device and method. The device performs a feature extraction operation based on an image to generate a feature map. The device performs a texture feature extraction operation based on the feature map to generate a texture feature map. The device performs a classification operation based on the texture feature map to recognize an object in the image. The image recognition technique provided by the present application enhances the texture feature extraction of the image, thereby improving the accuracy of object recognition of the image.

The application discloses a kind of based on deep learning's side slope crack detection method and system, it is related to side slope detection technical field, including, acquisition side slope multi-source inspection image data and through pre-processing, obtain side slope image data to be identified;According to side slope image data to be identified, slope surface structure constraint model is constructed using geometric texture feature layer and thermal anomaly feature layer, and based on slope surface structure constraint model, structure constraint analysis is carried out to side slope crack, and slope surface feature constraint atlas is formed;Band target pattern recognition algorithm is used to match and identify crack candidate area from slope surface feature constraint atlas, and crack candidate band is formed;Crack candidate band is guided to crack continuity, obtains crack continuous guide band, and performs deep learning identification to crack continuous guide band, generates initial crack identification area.The application constrains deep learning identification process by crack continuity guide band, and enhances the continuous extraction capacity of slender crack.

This invention relates to the field of industrial visual intelligent inspection technology, and in particular to an intelligent visual inspection system for surface defects of label paper. The system continuously acquires multiple frames of images of the same label area during roll-to-roll feeding, establishes spatial correspondence between adjacent frames, and calculates the time-series changes in grayscale distribution, edge position, and texture features of the divided structural regions. Through continuous discrimination, progressively changing areas are identified as process evolution areas. Areas that do not meet the continuous change pattern are anomaly screened and defect identification signals are generated. This solution changes the processing method based on single-frame matching tolerance for defect judgment, maintaining anomaly identification stability under tension fluctuations or local deformation conditions, and is suitable for detecting surface defects of various types of labels.

This invention discloses a method for detecting the appearance of planar objects. First, a set of detection parameters, including imaging parameters, acquisition strategies, and threshold rules, is obtained based on the object information. Then, camera imaging calibration and pixel-to-actual-size ratio calibration are performed, establishing a coordinate mapping between pixels and the stage. Initial images are acquired to obtain object pose parameters and perform rotational alignment. Multi-view or rotational scanning is performed for synchronous image acquisition according to the imaging parameters and acquisition strategy. Image quality is evaluated frame by frame; if unqualified, parameters are adjusted and images are re-acquired. For qualified images, illumination normalization and standardization preprocessing are performed to extract the final region of interest, generate defect candidate regions, and extract grayscale, shape, and texture features for identification and classification. The defect category, confidence level, and actual size are output. Finally, a qualified or unqualified result is determined based on preset threshold rules. This invention eliminates misjudgments caused by low-quality images at the source, significantly enhances detection robustness, and has good adaptability to various objects.

This invention provides a method, medium, and system for enhancing the features of cracks on infrastructure surfaces, belonging to the field of crack detection technology. The invention uses a structured light sensor and an inertial navigation device to scan the infrastructure surface and acquire a corrected three-dimensional depth image. An incremental encoder synchronously triggers a high-speed camera to acquire the corresponding two-dimensional grayscale image. A stereo calibration model is established, and a sub-pixel-level phase correlation algorithm is used to achieve pixel-level precise alignment between the two-dimensional grayscale image and the three-dimensional depth image. Crack contour features and crack centerlines are extracted and superimposed and fused into the three-dimensional depth image to generate an enhanced crack feature image. This image is then input into a multi-scale crack recognition model for identification and classification. This invention solves the technical problem of poor enhancement effect of crack features on infrastructure surfaces due to the difficulty in achieving pixel-level precise fusion of two-dimensional image texture features and three-dimensional depth data.

The present application relates to the technical field of image processing, more particularly, the present application relates to a kind of based on texture feature extraction's forged piece oxide skin residual identification method and system, comprising: obtaining the gray image of the surface of forged piece;The gray image is carried out superpixel segmentation, obtain multiple superpixel blocks;The edge flow direction disorder degree of each superpixel block is calculated.The present application is characterized in that by constructing edge flow direction disorder degree, local texture autocorrelation discrete index and superpixel neighborhood collaborative evolution degree and the like index, the oxide skin residual is comprehensively characterized from the edge irregularity of defect, internal multi-scale texture complexity and spatial group gathering characteristics and the like multiple dimensions.This multi-feature fusion method can overcome the limitation of single feature in complex scene, so that different morphologies, different size oxide skin residual can be accurately and robustly identified, and the miss rate and false detection rate are significantly reduced.

This invention discloses a machine learning-based bearing quality identification method and system. The method includes acquiring the local geometric entropy and weighted deviation field of sample bearing points, identifying defect regions and extracting geometric modal defects based on the weighted deviation field, performing image recognition to obtain visual modal defects, texture features, and color features, calculating texture and color deviations, inputting the raw material characteristics and process parameters of the bearing to be identified into a standard bearing quality prediction model to obtain a standard bearing quality prediction index, inputting the apparent defects and the standard bearing quality prediction index into a bearing quality propagation map to obtain a bearing quality correction index, calculating a quality index, and performing quality identification based on the quality index of the bearing to be identified. This method not only improves the efficiency and accuracy of automotive bearing quality identification but also has good interpretability and can be directly applied to automotive bearing quality identification systems.

The present application relates to the technical field of calcification point segmentation, and particularly relates to a breast molybdenum target image micro-calcification point identification and detection method based on deep learning. The present application performs image segmentation on a breast molybdenum target image based on each segmentation threshold, and determines a suspected micro-calcification point region under each segmentation threshold. Based on the morphological features, light and dark features and texture features of the suspected micro-calcification point region, a feature vector is determined, and a trained neural network is used to determine the confidence score of the suspected micro-calcification point region. The confidence scores of each pixel point in the suspected micro-calcification point region under different segmentation thresholds are corrected and fused to determine a final score and determine a final micro-calcification point region. Through the cooperative verification and fusion of multiple thresholds, the present application eliminates local tissue interference when the global threshold is determined, and improves the detection sensitivity of micro-calcification point identification and the accuracy of boundary extraction.

The application provides a lung nodule CT image processing method and system, computer equipment and a storage medium, and belongs to the field of image processing. The method comprises the following steps: collecting a lung nodule CT image; segmenting the lung nodule CT image to obtain a nodule segmentation mask; extracting nodule structure semantic features from the nodule segmentation mask; extracting lung nodule texture features from the nodule segmentation mask based on a gray level co-occurrence matrix; extracting lung nodule shape features from the nodule segmentation mask by a Fourier descriptor; splicing the lung nodule texture features and the lung nodule shape features to obtain hand-crafted features; fusing the nodule structure semantic features and the hand-crafted features based on kernel canonical analysis to obtain fused features; and determining the nodule structure complexity corresponding to the lung nodule CT image according to the fused features. The method retains the powerful pattern recognition capability of the nodule structure semantic features, and also integrates the stable discrimination information of the hand-crafted features in a small sample scene, thereby improving the accuracy and stability of classification.

This invention discloses an intelligent fire detection method based on artificial intelligence video analysis, belonging to the field of artificial intelligence video analysis technology. This method targets multiple video streams deployed on an edge computing gateway. It utilizes an asynchronous decoupled buffer queue to bind video frames and timestamps into frame units to be processed. An incremental sequence identifier is assigned to each frame unit to be processed via a hardware resource scheduler, and the frame units are then distributed to a first processing pipeline and a second processing pipeline based on the sequence identifier. In the first processing pipeline, background removal and dynamic texture extraction are performed to generate a thermal activation map. In the second processing pipeline, frequency domain transformation and multi-scale local binary mode decomposition are performed to generate a flame frequency domain texture feature map. The thermal activation map and the flame frequency domain texture feature map are then pixel-level weighted fusion at the same time reference to generate a fusion confidence tensor. Finally, non-maximum suppression and spatial connectivity analysis are performed to output the bounding box of the flame target and the initial fire intensity level.