103 results about "Contrast enhancement" patented technology

This invention discloses a sub-mesoscale process detection method based on prior structural feature embedding. The method first performs outlier removal, contrast enhancement, and normalization on acquired chlorophyll concentration remote sensing data to construct an image dataset suitable for network input. Then, the images are input into the sub-mesoscale process detection network EPSFNet, which uses a multi-stage feature extraction module composed of EPSF blocks to extract multi-scale features, and combines this with a feature pyramid network for feature fusion. The fused features are then processed by a localization-refinement decoupled detection head, which outputs a center prediction heatmap and a boundary distance feature map, respectively, and decodes the results to obtain the detection outcome. Finally, the network is optimized using a joint loss function including Gaussian focus loss, GIoU loss, and hard sample width-height balance loss. This invention significantly improves the detection accuracy and localization stability of sub-mesoscale targets in complex backgrounds by introducing a parallel multi-scale feature fusion module PMF and a bidirectional strip attention module BSA, utilizing the rotational structure prior of sub-mesoscale processes to enhance feature representation and filter background noise.

The application provides an image analysis-based eye plastic surgery evaluation method and system. The method comprises the following steps: preprocessing an image to be evaluated for eye plastic surgery to obtain a pretreated image; simulating real degradation of the pretreated image to obtain a degraded simulated image; performing contrast enhancement and denoising processing on the degraded simulated image to obtain a denoised image; extracting features from the denoised image to obtain an eye feature image, and performing guided reconstruction on the eye feature image to obtain an eye reconstructed image; and inputting the eye reconstructed image into a trained preset evaluation model for evaluation to output an evaluation result. The application not only significantly improves the visual quality of the eye plastic surgery image itself, but also provides a powerful technical tool for precise, objective and efficient evaluation of the surgical effect through the characteristics of certainty, efficiency and quantifiability.

An image processing method, an electronic device, and a readable storage medium are provided. The method includes: obtaining an original image; denoising the original image using an image filtering algorithm to form a preprocessed image S; performing contrast enhancement in the preprocessed image S to form a contrast-enhanced image J; adjusting saturation of the contrast-enhanced image J to form an enhanced display image M; sharpening the enhanced display image M to form a sharpened image N; and performing dynamic range enhancement on the sharpened image N using a dynamic range image enhancement algorithm to form an output image. The image processing method, electronic device, and readable storage medium enable multi-level processing on the original image and improve the display accuracy of the output image.

This disclosure relates to image enhancement methods, apparatus, electronic devices, storage media, and computer program products, including: acquiring an original image to be enhanced; performing global enhancement operations and local enhancement operations on the original image to obtain a global enhancement result and a local enhancement result of the original image; performing a fusion operation on the global enhancement result and the local enhancement result to obtain an enhanced image of the original image; wherein, the global enhancement operation includes: performing global contrast enhancement on the original image based on a first histogram and a second histogram to obtain a global enhancement result, wherein the first histogram is a gray-level histogram of the original image, and the second histogram is a gray-level histogram of the inverse image of the original image; wherein, the local enhancement operation includes: for each image block among multiple image blocks contained in the original image, performing local contrast enhancement on the image block based on the average value of the entropy and pixel value variance of the image block, thereby obtaining the enhancement results of multiple image blocks as the local enhancement result.

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.

This invention discloses a method for estimating sea state levels based on visual information. The method includes acquiring image and video data of a target sea area through an image acquisition module; using a combination of median filtering and Gaussian filtering for noise reduction, and histogram equalization to enhance data contrast; performing image geometric correction using radial distortion correction and tangential distortion correction models; extracting wave texture features, motion features, and wave height features from the preprocessed data; inputting the extracted features into a trained sea state level classification model for training, and outputting the sea state level estimation result. During training, multi-model fusion and dynamic model updating methods are used to improve the accuracy and reliability of the estimation. This invention uses a camera to collect wave information within a certain distance and range, and automatically estimates the sea state level based on this information, thus solving the problems of high cost, limited measurement range, significant environmental influence, and low accuracy in existing sea state level estimation methods.

This invention discloses a method and system for quantitatively assessing the degree of fibrosis in kidney pathological sections, belonging to the field of medical image processing technology. The method includes: performing color normalization and adaptive contrast enhancement preprocessing on Masson stained section images; classifying pixel-level tissue components using a multi-component semantic segmentation network containing a channel-space dual-path attention module; calculating the fibrosis area ratio and outputting a CI score based on the Banff grading standard; generating a fibrosis spatial distribution heatmap; and calculating the annual fibrosis progression rate through longitudinal follow-up comparison.

The application relates to a sludge sedimentation ratio detection method, system, device, computer equipment and medium. The method comprises the following steps: obtaining a brightness image of an image of sludge in a transparent container after sedimentation in an HSV color space; performing contrast enhancement on the brightness image to obtain an enhanced image; screening out brightness mutation pixel points on each longitudinal pixel line based on the brightness value of each pixel point on the longitudinal pixel line in the enhanced image; each longitudinal pixel line is perpendicular to the horizontal direction of the enhanced image, and the multiple longitudinal pixel lines divide the enhanced image into at least three parts; determining the sludge layer height based on the height information of the brightness mutation pixel points on all the longitudinal pixel lines; and determining the sludge sedimentation ratio based on the sludge layer height and the initial height of the sludge in the transparent container. The method can improve the accuracy of the sludge sedimentation ratio detection result.

The application belongs to the technical field of image recognition, and discloses a tailing dry discharge dynamic control method based on visual detection. The method is characterized in that a linear array light source and a high-speed industrial camera are arranged at the outlet side of the filter guide groove of the filter press to obtain the filter liquid outflow image; the image is subjected to grayscale and local contrast enhancement, the grayscale mean value and the grayscale co-occurrence matrix contrast parameter of the liquid region are calculated, the liquid flow edge contour is extracted in combination with edge detection, and the time sequence change rate of the liquid flow width is calculated; when the grayscale mean value is greater than a preset clear threshold, the contrast parameter is less than a preset uniform threshold, and the time sequence change rate absolute value is less than a preset stable threshold, the number of consecutive frames meeting the standard is counted, and a filter press termination signal is generated when the preset continuous frame number threshold is reached. The scheme takes the apparent optical and morphological changes of the filter liquid as the physical representation of the filter cake moisture extrusion limit, overcomes the defect that the fixed time or pressure cannot perceive the water permeation state, and realizes the dynamic determination of the filter press end point based on the actual physical state of the filter liquid.

The application discloses an oval foramen automatic detection and fine segmentation method based on an anatomic landmark gravity field and a tubular topology enhancement, and specifically relates to the technical field of medical image processing. Firstly, the head CT or MRI image to be processed is subjected to multi-modal space alignment and adaptive contrast enhancement; subsequently, the image is input into an anatomic landmark gravity field network, macroscopic landmarks of a skull base are extracted, a spatial gravity field matrix is constructed, and the model attention is adaptively focused on a small oval foramen high probability area; then, a multi-view tubular structure enhancement encoder is used to extract features of a three-dimensional hole track of the oval foramen, and the interference of non-penetrating bone depressions is inhibited; finally, a three-dimensional penetrating topology constraint mechanism is introduced in the decoding stage, so that the generated three-dimensional model of the oval foramen has correct anatomic connectivity. The application can effectively solve the detection problem of the oval foramen caused by the large individual variation, the small volume and the easy confusion with surrounding holes and fissures, and significantly improves the preoperative planning accuracy of trigeminal neuralgia puncture and other surgeries.

The application discloses a kind of self-adapting low-light image enhancement method, system, terminal equipment and medium, it is related to image processing technical field.The method includes: obtaining to be enhanced image, determines each pixel brightness value;Brightness value is handled by parameterization processing function, generates complementary information;Complementary information and brightness value are used to construct intuitionistic fuzzy image to express the uncertainty of pixel value;Based on the global statistical characteristics of image, contrast enhancement is carried out to intuitionistic fuzzy image, and preliminary enhanced image is obtained;With the optimization target of maximizing the information content or perceived quality of enhanced image, the adjustable parameter of parameterization processing function is iteratively optimized, and the optimal parameter enhanced image is obtained;It is converted from fuzzy domain back to spatial domain, and the final enhanced image is obtained.The application can improve the contrast of low-light image while retaining structural details, enhance visual quality, and has strong adaptability and high computational efficiency, and can be widely applied to imaging system under complex lighting conditions.

The present invention provides a curable composition which can suppress thermal deterioration of a tetraazaporphyrin compound, and realize a lens excellent in visual confirmation, anti-glare effect, and contrast enhancement effect. The curable composition of the present disclosure contains: a silsesquioxane having an epoxy cyclohexyl group; and a tetraazaporphyrin compound having an absorption peak in a wavelength region of 570 to 605 nm, the content of the tetraazaporphyrin compound being 1000 to 10000 parts by weight per million parts by weight of the silsesquioxane.

The present application relates to the technical field of image enhancement, in particular to a contrast enhancement method for nylon thread surface microscopic image, comprising the following steps: obtaining a nylon thread surface microscopic gray image, calculating the horizontal and vertical gradient values of the pixel points of the nylon thread surface microscopic gray image, constructing a pixel-level structure tensor matrix, performing eigenvalue decomposition operation on the pixel-level structure tensor matrix, and generating a nylon thread texture coherence distribution factor. In the present application, the nylon thread roughness gain mapping points are multiplied by the detail component and reconstructed with the background component to output a high-contrast enhanced image of the nylon thread surface, so that the contrast enhancement is concentrated on the real texture details and the risk of pseudo-texture caused by background gray drift and excessive enhancement is reduced, while the texture direction consistency enhancement, local roughness difference enhancement, and visual readability improvement after the separation of details and background are realized.

The present application relates to the technical field of image processing, and discloses a light staining sperm microscopic image light-weight style consistency preprocessing method and system, comprising: acquiring a light staining sperm microscopic image, performing color normalization on the light staining sperm microscopic image according to a deep staining sperm microscopic image, performing local contrast enhancement on the normalized light staining sperm microscopic image according to local contrast of a sperm head, a tail and a boundary region, performing brightness correction on the enhanced light staining sperm microscopic image according to the definition of the sperm head, the middle section and the tail structure and the background stability, and obtaining a light staining sperm microscopic image after light-weight style consistency preprocessing. The present application can solve the problems of staining difference, uneven brightness and boundary blur through image preprocessing without increasing the number of samples and additional training burden, improve the overall quality of the light staining sperm microscopic image, and improve the detection performance of the subsequent model.

There is provided an image acquisition apparatus. The apparatus comprises a memory configured to store instructions; and a processor configured to: obtain distribution information representing distribution of an original visual information of at least one region of interest including an object under observation; determine an illumination pattern of a light source based on the distribution information so that a range of the original visual information of at least one region of interest including the object under observation falls within a pre-determined range; control the light source to illuminate the determined illumination pattern on the object under observation; obtain images of the object under observation illuminated by the light source with the determined illumination pattern; and estimate the original visual information for at least one region of interest including the object under observation by tracking back information on the obtained images based on the information on the illumination pattern.

This invention relates to the field of image analysis technology, specifically to a machine vision-based method for detecting surface defects in weld seams of battery pack enclosures. The method includes: performing adaptive contrast enhancement and noise suppression preprocessing on original images of weld seams of battery pack enclosures of different specifications; extracting defect and heat-affected zone features using a contour reconstruction network and enhancing these features through a multi-dimensional collaborative attention mechanism; reconstructing a defect topology dataset and constructing a quantitative characterization set of sealing mechanisms using a dual-domain feature cross-layer anchoring fusion mechanism; and finally outputting an airtightness index through a regression mapping process to generate a quantitatively correlated judgment result. This invention utilizes image features to quantitatively correlate the airtightness index, reducing reliance on manual visual inspection and high-cost physical leak testing. Furthermore, the online diagnosis of failure mechanisms provides real-time closed-loop guidance for optimizing welding process parameters.

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.

This invention proposes an image processing method, apparatus, device, and medium based on a racing drone mode. Specifically, it includes: acquiring raw infrared image data based on the racing drone mode in real time, performing dual-layer spatial filtering denoising to generate an edge-preserving denoised image; performing high-intensity dynamic detail enhancement processing on the edge-preserving denoised image to generate a detail layer image; fusing the detail layer image with a grayscale-converted base layer image to generate an enhanced image; and performing block-based local contrast enhancement processing on the enhanced image to obtain a final high-resolution output image. This invention, through an innovative strategy combining dual-layer spatial filtering and block-based local contrast enhancement, significantly improves the clarity, contrast, and key target recognition of infrared images while ensuring real-time image processing.

The application discloses an enhanced target detection method for a complex beach scene, comprising: acquiring an original beach scene image, and performing defogging and contrast enhancement processing on the original beach scene image to output a defogging image; performing semantic segmentation processing on the defogging image to obtain a semantic segmentation result of a beach target; performing channel dimension splicing on the defogging image and the semantic segmentation result to form a multi-channel input tensor; inputting the input tensor into a target detection network to complete target detection and complete enhanced detection of the target under the complex beach scene. The application can effectively improve the problem of blurred and low-contrast beach images, overcome the defect that the traditional segmentation method is sensitive to the direction of the target, improve the accuracy, robustness and environmental adaptability of target detection under the complex beach scene, and solve the problem of performance decline of the existing method under the conditions of strong noise interference, large scale change and variable target direction.

The application discloses a kind of foam space distribution measurement method for high-strength recycled aggregate concrete, it is related to building material detection technical field, for solving the problem that foam distribution measurement is not accurate;The application constructs the three-dimensional image acquisition and foam space distribution feature extraction process based on CT scanning, realizes the high-precision reconstruction of foam structure in high-strength recycled aggregate concrete, that is, by noise filtering, gray scale normalization and contrast enhancement to generate standardized image, combined with boundary detection, gray scale aliasing feature modeling and multi-feature determination rule, and using adaptive multi-threshold segmentation and connected domain marking to generate two-dimensional foam label image, and according to the layer spacing stacking construction three-dimensional foam voxel model, calculate overall volume ratio, distribution density and interlayer aggregation trend and other parameters, form the spatial distribution feature set, and input performance evaluation model combined with three-dimensional structure atlas, output air-tightness and other prediction indexes, to realize automatic, standardized measurement and reliable evaluation.

The application discloses a polaroid defective product identification method and system based on machine vision, and relates to the fields of polaroid detection and machine vision technology; the application collects polaroid multi-band images through multi-spectral imaging and corrects registration, completes background separation through gray scale normalization, filtering, morphological operation and inflation corrosion reconstruction, adopts a partition adaptive contrast enhancement strategy to strengthen low-contrast defects and fuse multi-band images, extracts multi-dimensional feature vectors in multiple scales, matches and grades defects according to a preset defect type feature library, and generates a defective product identification report containing defect information; the application effectively solves the problem of low recognition rate of polaroid morphological changes and low-contrast defects, and significantly improves the accuracy, stability and detection efficiency of defect identification.

The application provides a speech recognition method based on bimodal mixed contrast enhancement, an electronic device, a chip, a storage medium and a program product; the method comprises the following steps: acquiring multi-modal speech training data; a bimodal mixed contrast learning model is constructed and trained, wherein samples with the same emotional label under the same mode are taken as positive sample pairs, samples with different emotional labels are taken as negative sample pairs, intra-modal contrast loss is calculated to enhance the ability of the bimodal mixed contrast learning model to distinguish intra-modal fine-grained emotional features; samples with the same emotional label under different modes are taken as positive sample pairs, samples with different emotional labels under different modes are taken as negative sample pairs, inter-modal contrast loss is calculated to realize the alignment and complementarity of different modal feature spaces; the intra-modal contrast loss and the inter-modal contrast loss are fused to obtain multi-modal mixed contrast loss, and the model parameters of the bimodal mixed contrast learning model are optimized; based on the features extracted by the bimodal mixed contrast learning model, a downstream speech recognition task is trained.

The application provides a cervical cell nucleus segmentation method based on HSV channel and multi-dimensional feature screening, comprising the following steps: converting a cell image from RGB to HSV, and extracting a V channel brightness component; performing threshold segmentation and morphological operation on the V channel to obtain a cytoplasm mask; meanwhile, performing contrast enhancement, threshold segmentation and morphological operation on the V channel to obtain a binary mask; extracting a contour and sequentially performing area primary screening and shape feature screening; creating a single nucleus mask for the contour meeting the requirements, inflating the single nucleus mask, and then calculating the number of overlapping pixels between the inflated single nucleus mask and the cytoplasm mask; if the number of overlapping pixels exceeds a dynamic threshold, the single nucleus mask is determined as a qualified cell nucleus; and finally, drawing the contour to obtain a segmentation result. The application fully utilizes the low brightness feature of the cell nucleus, enhances the distinguishability between the cell nucleus and the background, and through multi-dimensional screening and cytoplasm environment verification, obtains a cell nucleus contour meeting biological characteristics, is not required to be deep learning, has strong interpretability, and can accurately segment different sizes and shapes of cell nuclei in a full field image.

This invention belongs to the technical field of 3D modeling for engineering construction. It discloses a method and system for modeling bulldozer operation maps in mining areas based on 5D Gaussian geometry. The method includes: S1 acquiring RGB images and depth data of the earthmoving operation area using an RGB-D camera; applying a contrast enhancement algorithm to the RGB data and vibration compensation to the depth data; and performing semantic recognition of the category of each pixel location; S2 back-projecting the depth data to generate a 3D point cloud; constructing 3D Gaussian units at the sampling points of the point cloud; and converting them into 5D Gaussian implicit units covering spatial, temporal, and semantic dimensions after fusing semantic category and timestamp information; generating a 3D implicit base map; S3 filtering the 5D Gaussian implicit units; and projecting to obtain a 2D rendered image. This invention provides 3D visualization support for bulldozer operation in mining areas, is applicable to scenarios such as mining, and solves modeling problems such as weak texture in earthmoving and equipment vibration interference.

The application discloses a shield tunnel segment apparent defect image intelligent detection method and system, and belongs to the technical field of tunnel engineering detection. The method comprises the following steps: acquiring a tunnel inner wall ring scanning image in an image acquisition step; performing illumination correction and contrast enhancement in an image preprocessing step; synchronously identifying four types of defects, i.e. cracks, damages, misalignments and water seepage, through a deep learning network in a multi-class defect synchronous detection step; extracting a crack skeleton line and measuring the length, width and trend of the crack in a crack geometric parameter measurement step; calculating the misalignment amount based on gray gradient analysis in a misalignment quantitative analysis step; and performing threat degree scoring and generating a detection report in a defect evaluation and report generation step, while feeding back optimized detection parameters. The application realizes synchronous detection of multiple types of defects, the detection accuracy is above 95%, and the crack width detection precision reaches 0.2 mm.

The application discloses a high-precision two-dimensional code recognition method, through the synergistic processing of light compensation and contrast enhancement, the image details under extreme light difference are effectively balanced, and the feature recognition degree of a low-quality two-dimensional code area is greatly improved; the region segmentation link fuses adaptive threshold binarization, morphological open operation and geometric feature screening logic, accurately separates the two-dimensional code from complex background elements such as dense lines and pads, and greatly reduces the misjudgment and omission rate caused by background interference; the generative adversarial network model based on the improved U-Net architecture realizes the accurate completion of multiple types of damage such as positioning angle defects and data module missing, solves the pain point that the traditional algorithm has insufficient processing capacity for a multiple-defect concurrent scene; through the accurate sampling and grid division strategy of a high-resolution industrial camera, the integrity of the data matrix in the code is ensured, and the recognition success rate is greatly improved.

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.

The application relates to a SAR image water body submergence range change detection method and device for a flood scene. The method comprises the following steps: acquiring a training sample set containing pre-disaster and post-disaster SAR sample images and water body mask data, performing coherent speckle noise suppression and contrast enhancement preprocessing on the sample images, inputting the preprocessed images into a backbone double-branch twin network, extracting and interacting multi-scale features to generate double-time multi-scale feature maps, performing upsampling, splicing and channel space attention enhancement on the multi-scale feature fusion unit to obtain an optimized fusion feature map, generating a prediction result by a detection head, generating an intermediate heat map by a deep supervision unit, training a model to convergence by combining mask data to calculate a loss, inputting a to-be-detected image into the model after preprocessing to obtain a water body submergence range change detection result. The method can accurately extract the water body submergence range of a complex flood scene SAR image, effectively suppress noise, strengthen feature fusion, and improve the detection precision of the model to adapt to the real-time demand of flood emergency monitoring.

The present invention relates to lesion detection. To improve lesion detection, it is proposed to combine deep learning techniques with a contouring strategy, i.e. a subtraction between a contrast-enhanced image and a non-contrast-enhanced image, in order to reflect only the differences between the two images related to the lesion.