70 results about "Normalization (image processing)" patented technology

The application discloses a kind of single frame unmanned plane image pixel positioning method and system based on elevation map, it is related to unmanned plane image processing and geographic positioning technical field, obtain the single frame original image of unmanned plane shooting and the digital elevation map of the shooting area when unmanned plane attitude information, camera internal and external parameters, shooting;According to camera internal parameter, the pixel coordinates of target pixel in original image are converted to camera normalization plane coordinate system, and target pixel back projection point coordinates are obtained after coordinate distortion correction;According to camera external parameter and unmanned plane attitude information, camera-unmanned plane body coordinate system, body-geographic inertial reference coordinate system conversion is carried out, and the normalized ray direction vector corresponding to target pixel is obtained;Based on digital elevation map, construct ground height constraint, by iterative approximation to space point along ray direction, determine the intersection of ray and ground.The application can realize the fast and accurate conversion of single frame unmanned plane image pixel to geographic coordinate.

This invention provides a novel raw domain denoising method and system, belonging to the field of digital image processing technology. The method includes: obtaining normalized raw image data and corresponding noise intensity parameters; determining the filter kernel size parameters corresponding to each pixel position, and simultaneously performing multi-directional structural analysis on the normalized raw image data to generate direction parameters and direction confidence parameters; constructing a direction-adaptive filter kernel, and performing filtering processing on the normalized raw image data to generate low-frequency denoised image data; calculating high-frequency residual information and determining high-frequency compensation parameters; performing high-frequency component compensation on the low-frequency denoised image data to generate denoised raw image data, and performing inverse normalization to output the raw domain denoising result. This invention achieves adaptive adjustment of the noise suppression process by combining noise intensity modeling and multi-directional structural perception within the raw domain, maintaining the stability of image structural information while ensuring effective noise suppression.

The application provides a medical image segmentation method and system based on concept guidance and cross-modal alignment, and belongs to the field of medical image processing. The method comprises the following steps: obtaining a medical image to be segmented and its corresponding clinical text description; generating clinical knowledge concepts related to the target disease by using a large language model, and constructing a concept set through clinical review; inputting the medical image, the clinical text description and the concept set into a trained concept-guided segmentation model to extract visual features, text features and concept labels; generating concept features aligned with the visual features through a concept-visual alignment module; dynamically adjusting the normalization process of the visual features through a concept modulation decoder, combining the features through multi-head cross attention, and outputting the final image segmentation result by using a segmentation head. The application effectively solves the problems of lack of effective clinical prior guidance in existing medical image segmentation, poor cross-modal feature alignment, and insufficient lesion segmentation accuracy.

The embodiment of the application relates to the image processing technical field, discloses a kind of method for training fitting model, the method for generating fitting image and related device, by designing the structure of the above-mentioned fitting network, decoding network is constructed using multiple cascaded, interval setting normalization layer and decoding layer, and there is cross-layer connection between the normalization layer, the first encoding layer and the second encoding layer of the same level, so that, by normalization layer, the first clothes feature map, the second clothes feature map and the up-sampling feature map of the same level are fused, so that identity feature map can be fused clothes features from different scales in decoding process, avoid the loss of clothes texture problem, so that high-resolution fitting image can be generated, and the high-resolution fitting image can have real and natural fitting effect. With the continuous iterative training of fitting network, the pretest fitting image fused and generated will be constantly close to real fitting image, that is, accurate fitting model is obtained.

The application provides an intelligent image processing system and method for a car based on a perception algorithm model, and the method comprises the following steps: S1. spatio-temporal reference double anchoring and dynamic intrinsic extrinsic parameter calibration of a vehicle-mounted image acquisition node; S2. multi-node image heterogeneous domain normalization and adaptive preprocessing based on a self-adaptive kernel regression non-local mean denoising algorithm; S3. hierarchical image feature extraction and semantic anchoring based on a graph neural network dynamic feature interaction network; S4. cross-node and cross-frame feature mutual checking and pseudo-feature elimination; S5. full-scene semantic completion and dynamic target trajectory prediction based on a variational autoencoder trajectory prediction model; S6. dynamic lightweight adaptation and algorithm power adaptive scheduling of the perception algorithm model; and S7. risk scene grading identification and image targeted enhancement output based on semantics and trajectories. The application provides stable, accurate and efficient vehicle-mounted image perception support for intelligent driving of a car, and improves the safety and adaptability of environmental perception of intelligent driving.

This invention discloses a lightweight image restoration method, relating to the fields of computer vision and image processing technology, comprising: S1, input preprocessing: inputting a damaged image and a size-matched binary mask, concatenating the two along the channel dimension to obtain an input tensor; S2, encoder feature extraction: configuring an encoder network composed of multiple downsampling blocks to extract multi-scale features; the downsampling block includes an LSConv module with improved LSNet convolution, convolutional layers, normalization layers, and activation functions. The LSConv module, with its separable convolutional structure based on multi-branch depth, simultaneously captures global structure and local detail features. Feature correction and fusion are completed through feature concatenation and channel adjustment combined with the SE attention mechanism. This invention innovatively designs a novel LSConv feature extraction module, employing a multi-branch parallel structure combined with multi-scale feature mining, breaking through the limitations of traditional single convolution, simultaneously capturing global and local features, and enhancing feature expression through channel optimization, thereby improving image restoration capabilities.

This invention provides a video image contrast enhancement method for warehouse monitoring scenarios, relating to the fields of image processing and video surveillance technology. It aims to solve problems such as insufficient contrast, unclear details in dark areas, amplified noise, and distorted edge structures in warehouse monitoring videos. The method preprocesses the video frames by performing grayscale normalization, constructing a variational energy function that includes a relative error fidelity term, an auxiliary variable consistency constraint term, a sparsity constraint term, and an adaptive regularization term. It then employs an iterative update method, alternating between the enhanced image and auxiliary variables, to achieve image contrast enhancement, noise suppression, and edge preservation. Finally, the enhanced video frames are reconstructed based on the original temporal information to obtain an enhanced video stream. This invention can improve the clarity and recognizability of video images in complex warehouse monitoring environments, enhancing the reliability of subsequent intelligent monitoring and analysis.

The application belongs to the technical field of image processing, and particularly relates to an image missing area repairing method and system based on multi-scale mixed feature modeling. The original image to be repaired and a missing area mask are spliced in the channel dimension, multi-layer normalization and convolution operations are performed on initial features, feature extraction is performed on a content channel branch and a gate channel branch, multi-layer convolution and linearization operations are performed to obtain channel gate features of each layer; the channel gate features of the last layer are split into spatial detail component features and long-range correlation component features, spatial detail components and long-range spatial components are obtained through linear mapping, and fusion output features of each layer are obtained through processing; and the fusion output features of the first layer are used as a repaired complete image. The scheme can guarantee the structural continuity of a large-area missing area, and effectively reduce blurring, artifacts and boundary fracture phenomena.

This invention discloses a multi-label classification method for medical images based on spatiotemporal integration and adaptive normalization, belonging to the field of medical image processing and computer-aided diagnosis technology. The invention proposes an improved scheme. Firstly, it constructs a dynamically balanced data input stream through frequency inverse sampling and cosine annealing strategies. Secondly, it introduces group normalization to replace batch normalization in the feature extraction network, solving the training convergence problem under limited GPU memory. During training, it employs a focal loss function to mine hard-to-classify samples. In the inference stage, the invention constructs a spatiotemporal integration mechanism based on multi-view space transformation and multi-stage model weight fusion, combined with an adaptive threshold decision algorithm based on maximizing F1 scores to output diagnostic results. This invention effectively improves the recognition accuracy of key pathological features such as cardiac hypertrophy and edema, while significantly improving the recall rate of small lesions, exhibiting high robustness and clinical auxiliary value.

The application relates to the technical fields of multimedia image processing, GPU computing power scheduling and soft power-on resource optimization, and discloses a resource occupation prediction method in a video special effect processing process, which is executed by a terminal built-in processor and comprises the following steps: collecting a video special effect frame time interval, a GPU rendering pipeline thread occupation ratio and a video memory fragment distribution ratio; performing dimensionless normalization processing on the video special effect frame time interval to obtain a special effect frame time normalization factor; counting a special effect superposition level; and calculating a special effect time coupling factor, a pipeline blocking loss factor and a total resource occupation prediction value and outputting the total resource occupation prediction value. The application solves the problem of large prediction deviation in the prior art, realizes accurate prediction through a core innovation point, guarantees reasonable allocation of video special effect rendering resources, and improves rendering stability.

The application belongs to the technical field of image processing, and particularly relates to an underwater image restoration method based on an adaptive multi-scale large kernel attention module. An obtained underwater image is decomposed into a low-frequency component and three directional high-frequency components through Haar discrete wavelet transform; a mixed domain attention module is introduced at a highest resolution stage of the underwater image decomposed through the Haar discrete wavelet transform; a composite shape convolution module is added at a bottleneck position of a high-frequency branch; a PolyKernel main body is used as a large kernel encoder-decoder in a low-frequency path, and an adaptive multi-scale large kernel attention module is introduced at a bottleneck stage; after independent processing of each frequency branch, the network re-fuses high-frequency and low-frequency features into a spatial domain through inverse wavelet transform; and a light-weight unified output refining-adjusting head is used to perform structural refining and tone normalization on the fusion result.

The application relates to the field of medical image processing and discloses a lens and a software system which can be used for shooting an anterior segment of an eye by a mobile phone, the lens comprising: a lens barrel which is used as a bearing body of an optical instrument and is used for protecting the precise optical instrument; a clamping plate one which is fixed on one side of the lens barrel and is used for clamping the mobile phone; a clamping plate two which is installed at the bottom of the clamping plate one and is used for assisting the clamping plate one to be installed on a smart terminal; and a rubber strip which is arranged on one side of the clamping plate two and is used for increasing the friction of the clamping plate two on the screen of the mobile phone; and the software system comprises an image acquisition module, an image preprocessing module, an AI disease recognition module, a time sequence progress analysis module, a data and report management module and a man-machine interaction module. Through simplification of the lens, digital image anti-shake processing and illumination normalization correction, the problems of inconvenient carrying of the equipment and unstable imaging of the portable equipment are solved, and the technical effects of improving the imaging quality and consistency of the anterior segment image are achieved.

The application discloses a seawater aging microplastic identification method based on a multimodal deep learning, relates to the technical field of environmental monitoring and artificial intelligence, and comprises the following steps: preparing a plurality of seawater microplastic samples, performing an aging experiment on the microplastic samples, regularly collecting spectrum data and microscopic images of the samples during the aging process, and constructing a data set; performing noise reduction, baseline correction, normalization and dimension reduction processing on the collected spectrum data, and processing the microscopic images by using an image processing algorithm; constructing a double-branch deep learning model, adopting a light-weight improved convolutional neural network architecture for a visual branch, adopting a sparse principal component analysis dimension reduction combined with a full-connection neural network architecture for a spectrum branch, fusing the features of the two branches by using a feature fusion module, and outputting an identification result by using a classifier; and dividing the data set into a training set, a verification set and a test set, training the model, and obtaining a final model. The application has high identification precision, strong robustness, high automation and strong practicability.

This invention discloses a boundary recognition method based on medical images of ovarian masses, relating to the field of medical image processing. The method includes: acquiring a tomographic image of the ovarian mass to be processed; performing voxel grayscale normalization and spatial interlayer registration on the image to generate a single-channel grayscale image sequence with unified spatial dimensions and standardized grayscale distribution; performing gradient direction feature encoding on the standardized single-channel grayscale image sequence at multiple scales to construct feature response matrices corresponding to different voxel neighborhood ranges; correcting coordinate deviations and completing discontinuous segments through sub-pixel contour fitting, and then optimizing the contour through closure verification and ovarian anatomical morphology constraints, ensuring that the recognition boundary conforms to the true morphology of the lesion, while simultaneously outputting the recognition confidence level, thus improving the overall accuracy and anti-interference capability of boundary recognition.

The invention relates to the technical field of computer vision and artificial intelligence, in particular to a YOLO automatic labeling tool and method based on SAM2 segmentation. Comprising an SAM2 automatic segmentation module, a mask image processing module, a morphological corrosion processing and target separation module, a connected domain analysis and bounding box generation module, an interactive label correction module and a YOLO format conversion and data set generation module. The SAM2 automatic segmentation module segments an input video and generates a binary mask image, and supports target tracking; the mask image processing module completes format conversion and preprocessing; the morphological corrosion treatment and target separation module is used for separating an adhered target; the connected domain analysis and bounding box generation module generates an initial bounding box; the interactive label correction module supports visual correction and batch adjustment; and the YOLO format conversion and data set generation module outputs a YOLO label and completes normalization, category coding and training / verification set division.

This disclosure relates to an image processing method, apparatus, electronic device, and storage medium. The image processing method includes: extracting initial sub-image features corresponding to each feature channel from an image to be processed through multiple feature channels of a feature extraction layer; inputting the initial sub-image features into an attention layer to obtain feature weights corresponding to the initial sub-image features; normalizing the initial sub-image features using a normalization layer to obtain intermediate sub-image features corresponding to the initial sub-image features; weighting the intermediate sub-image features corresponding to the initial sub-image features based on the feature weights corresponding to the initial sub-image features to obtain weighted sub-image features; and inputting each weighted sub-image feature into a feature processing layer for feature processing to obtain the image processing result of the image to be processed. This disclosure can improve the accuracy of a target image processing network and enhance the image processing effect using the target image processing network.

The application discloses a uterus tumor differential diagnosis method and system based on multi-parameter MRI imaging and belongs to the technical field of medical image processing and artificial intelligence diagnosis. The method aims at the problems existing in the current uterus tumor MRI diagnosis, such as strong subjective dependence, insufficient utilization of multi-parameter information, unreasonable feature screening and model construction. The method comprises the following steps: collecting T1WI, T2WI, T2 fat suppression sequence and DWI multi-parameter images; after format standardization, deartifacting and Z-score normalization, a model combining U-Net and attention mechanism is used to realize automatic segmentation of the lesions; multi-dimensional features are extracted and the optimal subset is screened by ANOVA filtering-RFE-SVM packaging method; a stacking integrated model is constructed for training, and the output includes the differential results and confidence of ordinary uterine fibroids, special type uterine fibroids and uterine sarcoma; the application integrates multi-parameter complementary information, improves the segmentation efficiency and feature quality, has strong model generalization ability and accurate diagnosis, is suitable for the actual situation of the scarcity of uterine sarcoma cases, and provides an objective diagnosis tool for clinical use.

The present application relates to the technical field of medical image processing, and discloses a deep learning driven sputum smear pathogen image recognition method and system, which comprises five steps of dye normalization preprocessing, adaptive contrast enhancement, U-Net-based semantic segmentation, morphological feature analysis, and classification recognition and quantitative statistics. Color deconvolution is used to eliminate dye batch differences, and multi-scale adaptive contrast enhancement is used to improve the distinction between pathogens and background, so as to realize pixel-level accurate segmentation of gram-positive bacteria and gram-negative bacteria and automatic classification and recognition of coccus, bacillus and fungal spores, and the method is suitable for auxiliary diagnosis of respiratory infection etiology in a clinical microbiology laboratory.

The application discloses an image processing method and system and a storage medium, which comprises the following steps: pre-processing an input image to obtain a high-frequency information image; performing first spatial conversion processing on the input image, and then calculating a brightness normalization histogram of the input image to obtain corresponding components p i ; calculating the probability P l (k) of each pixel being assigned to each category l; calculating the average brightness value m l (k) of the pixels in each category l and the global brightness average value m G ; calculating the inter-class variance and taking the brightness value corresponding to the maximum inter-class variance as the optimal brightness threshold k * ; performing light and shadow flattening processing and second spatial conversion processing on a to-be-processed mask region, adding the high-frequency information image, and obtaining a fourth image. The application does not need training cost, has a simple algorithm and fast processing speed, improves the clothes wrinkle removal efficiency in the image, and has a more natural and real effect.

This invention relates to the fields of image processing and pattern recognition technology, specifically disclosing a method and system for detecting residual stains on tableware after disinfection based on deep learning. The invention first performs format conversion and size normalization on the initial image of the disinfected tableware, followed by illumination correction and filtering to enhance image quality. Next, it utilizes convolution and pooling operations combined with an attention mechanism to extract multi-level features, improving the model's ability to represent complex stains. A pre-trained deep learning model is used for forward propagation and threshold segmentation to generate stain detection results, and a visual report is generated based on transparency blending rendering technology. It also features an automatic alarm function; when the stain area exceeds a preset threshold, an alarm signal is immediately triggered and an alarm notification is generated. This invention effectively solves the problems of poor environmental adaptability and insufficient feature extraction in traditional detection methods, achieving unmanned, high-throughput, and standardized operation for tableware cleanliness detection.

This invention relates to the fields of image processing and intelligent vehicle recognition technology, and discloses a license plate recognition method based on image processing. The scheme establishes a unified pixel coordinate system, records width and height indices, performs grayscale and normalization, locates the center, and sets abnormal degradation output; it sets the maximum scanning angle and step size to generate a symmetrical angle sequence; it performs centering translation, inverse rotation, and bilinear interpolation on the output pixels angle by angle to obtain a rotated image; it calculates the vertical grayscale difference, and generates a binary mask based on the mean and standard deviation adaptive threshold; it accumulates the values ​​in the row direction and takes the peak value, first determining the angle by maximizing the peak value and then minimizing the absolute angle; based on this, it performs inverse mapping and interpolation to generate a correction image; it recalculates the ratio of the index to the original peak value, and if it improves, it outputs the angle, image, and index; otherwise, it backs down. The process covers input, preprocessing, scanning, mapping, statistics, filtering, and correction, avoiding missed detections, reducing subjective thresholds and interpolation artifacts, and using self-judgment backoff to suppress invalid corrections, improving stability and adaptability.

This invention discloses a method, system, and medium for target detection and recognition in images, belonging to the field of image processing. The method includes: calculating the gradient G in the horizontal direction of the image. x and the gradient G in the vertical direction y ; For G x The values ​​at each position are squared and normalized to obtain the second-order normalized gradient in the horizontal direction for G. y The values ​​at each location are squared and normalized to obtain the sum of the absolute values ​​of the calculated second-order normalized gradient in the vertical direction and the absolute values ​​of the gradients, which serves as the second-order normalization operator for the image. This second-order normalization operator is then used to perform gradient detection on the image to identify target edges and suppress noise-induced interference edges. Based on these edges, targets present in the image are identified, thus improving the accuracy of mine detection and identification in sonar images.

The application discloses a forearm shallow blood vessel segmentation method and device based on an NSVA-Net deep learning network, and relates to the technical field of medical image processing. The method comprises the following steps: collecting near-infrared images of the forearm shallow blood vessels of a subject by using a near-infrared light source and a near-infrared camera; performing denoising, contrast enhancement, cutting of the forearm region and normalization on the near-infrared images to obtain preprocessed images; performing two-stage image enhancement of RCAE and CLAHE on the preprocessed images to obtain enhanced images; inputting the enhanced images into a pre-trained NSVA-Net deep learning network to obtain a segmentation probability map of the forearm shallow blood vessels; performing threshold segmentation, connected domain analysis and skeletonization processing on the segmentation probability map to remove artifacts and isolated noise, and obtaining a blood vessel segmentation result and a center line; and superimposing and displaying the blood vessel segmentation result and the center line on the near-infrared images to output a final segmentation image. By using the application, the segmentation recall rate and the structural continuity of the forearm shallow small blood vessels of dialysis patients can be significantly improved.

This invention relates to the fields of fluorescence image inpainting and deep learning, and particularly to a fluorescence image denoising and super-resolution method; comprising the following steps: S1, acquiring an image to be processed; S2, constructing a fluorescence image processing model, the fluorescence image processing model being used to perform denoising or super-resolution processing on the image, including an encoder, a decoder, and a convolutional unit, the output of the encoder being connected to the input of the decoder, the output of the decoder being connected to the convolutional unit, and the convolutional unit being processed using the ReLU activation function; the encoder includes multiple encoding sub-blocks, each encoding sub-block including multiple residual blocks, each residual block including an instance normalization layer, a ReLU activation layer, and a convolutional layer; S3, inputting the image to be processed acquired in step S1 into the fluorescence image processing model constructed in step S2 to obtain a denoised and super-resolution image; thereby optimizing the performance of the denoising or super-resolution task.

This invention discloses a lightweight multi-task context control image processing system, including a first image encoder, a second image encoder, a multi-scale fusion module, and an output feature processing module. The multi-scale fusion module includes N multi-scale fusion units connected sequentially from high to low spatial resolution. The first and second image encoders are used to extract features and downsample images from sample paths and control paths. The multi-scale fusion units are used to fuse query sample features and task control features at different spatial resolutions. Each multi-scale fusion unit includes a residual convolution module, a sliding window cross-attention module, a feature linear modulation module, a refinement module, and a downsampling module. This invention uses lightweight modules such as depthwise separable convolution and group normalization, significantly reducing the number of parameters compared to traditional control networks. The output feature channel is compatible with downstream diffusion models and can be plugged into existing diffusion models without extensive modifications to the original model architecture.

The application discloses a single image defogging method based on adaptive pixel selection and saturation line prior, and belongs to the technical field of image processing. Firstly, a foggy image is acquired and atmospheric light normalization is performed, and a saturation line prior linear relationship between the saturation component and the brightness component reciprocal of the pixels in a local image block is constructed in the normalized foggy image. Then, an adaptive pixel selection strategy is executed, reference pixels are selected, the slopes of the reference pixels and other pixels are calculated, the proportion of the pixels whose slopes fall within a preset interval is counted, and reliable pixels are dynamically selected in combination with local contrast. Finally, a saturation line is constructed based on the reliable pixels, a transmission rate estimation value is calculated according to the slope and intercept of the saturation line, and a fog-free image is restored based on the transmission rate estimation value and the estimated atmospheric light. Through the establishment of the saturation line prior and the adaptive pixel selection mechanism, the accuracy and robustness of the transmission rate estimation are significantly improved, and high-quality defogging effects can be obtained in complex scenes.

The application discloses a kind of SAR data active integration's remote sensing data timing seamless reconstruction method and device, belong to remote sensing image processing and space-time information analysis technical field.Sentinel-2 waveband and Sentinel-1 dual polarization data are screened and time-space alignment, radiation normalization and cloud mask construction are completed;Parallel operation dual-branch deep network optical branch extracts multi-scale space-time characteristics, SAR branch uses deformable convolution+texture self-attention to mine multi-scale directional texture;Then optical characteristics are used as Query, in cloud mask marked area active search SAR Key-Value complementary information, realize deep fusion by cross-modal multi-head attention;Fusion result is jointly corrected by relative time distance coding, time attenuation factor and cloud perception mask, and long-time sequence attention drift is inhibited;Final level fusion multi-level feature and adaptive weighting are outputted, and full-time seamless image is outputted.

The application discloses a tire mold character automatic detection method based on image processing and concretely relates to the technical field of image processing and mold detection; under fixed illumination conditions, a mold image is collected by an industrial camera; the image is preprocessed and regionally segmented, and a candidate character region is generated based on a deep convolution feature extraction network; edge density analysis and minimum circumscribed rectangle fitting are performed on the candidate region, the character arrangement direction is judged, and image direction normalization is completed; the processed character image is input into a pre-trained character recognition model for recognition and compared with a mold character template in a production planning; if the recognition result is inconsistent with the template or the confidence degree is lower than a set threshold, the abnormal region is marked and an alarm information is generated; the application has the advantages of high recognition precision, accurate direction judgment, fast feedback response and the like, can realize automatic recognition and intelligent verification of mold characters and is suitable for mold installation quality control in a tire manufacturing site.