116 results about "Image denoising" patented technology

The application discloses a kind of semi-structured orchard field ridge area detection method, this method is by picking robot along field ridge with stereo vision camera Real-time acquisition field ridge area image, utilize field ridge shadow area and the different of non-shadow area color and gradient field feature, combined with Gaussian mixture model can realize the detection of shadow area, again through the shadow color weighting compensation algorithm proposed in this paper to remove shadow area, finally through to image denoising filtering, by to image secondary segmentation, again after morphological processing, finally get complete field ridge area;Finally, through edge detection operator to the image after segmentation Edge detection, again to edge point optimization fitting, based on least squares method is carried out edge point fitting, obtains the edge line of field ridge area.This method can be under any illumination conditions 100% detection field ridge area.

The present application relates to the technical field of image denoising, in particular to a self-supervised optical remote sensing image blind denoising method and system, wherein the method comprises: obtaining a remote sensing image to be denoised; performing non-local similar sampling on the remote sensing image to be denoised to obtain a first noise space-independent similar image; performing neighborhood Bernoulli sampling on the first noise space-independent similar image to obtain a first image pair set; and inputting the first image pair set into a trained denoising model to obtain a denoised remote sensing image. The present application has good processing effect on spatially correlated noise.

This invention provides a region-based noise reduction method, comprising: S1: Image region labeling: converting a color image into a grayscale image, obtaining a grayscale gradient image, and binarizing it; S2: Image dimension segmentation: dividing the image into different feature regions and labeling them using connected component labeling and edge detection algorithms, and dividing the image into different dimension images according to the labels; S3: Image denoising: denoising using different denoising methods according to the features of each dimension image; S4: Image fusion: obtaining a high-quality image based on the image region features, performing alpha fusion processing between the high-quality image and the corresponding dimension image; finally, superimposing and fusing all dimension-fused denoised images to obtain a denoised grayscale image, which is then converted into a color image for output. The method proposed in this application can achieve better noise suppression while sacrificing less sharpness. It can distinguish different regions of the image by block and perform targeted denoising processing according to the characteristics of different regions.

This invention relates to an optical frequency domain reflectance distributed magnetic field sensing method based on image denoising, comprising the following steps: acquiring and processing Rayleigh scattering signals under no magnetic field and with magnetic field conditions using an OFDR system; performing Fast Fourier Transform on the reference signal under no magnetic field and the measurement signal under magnetic field conditions to obtain the distance domain signals at various positions of the corresponding optical fiber under the two magnetic field conditions; performing windowing and zero-padding operations; obtaining the local reference Rayleigh scattering spectrum and the local measurement Rayleigh scattering spectrum, and removing the DC component; performing cross-correlation calculation, arranging the grouped normalized cross-correlation results along the corresponding positions of the optical fiber to obtain the three-dimensional cross-correlation map at various positions of the optical fiber, and then projecting it onto a two-dimensional plane to obtain the original two-dimensional cross-correlation intensity map, and cutting it into blocks; denoising a certain block as the original block to obtain the integral image; obtaining the final denoised two-dimensional cross-correlation intensity map; and obtaining the frequency shift distribution of the magnetic field intensity spectrum.

The application discloses an image denoising method and device, electronic equipment and storage medium, and relates to the technical field of artificial intelligence, wherein the image denoising method comprises the following steps: receiving a document image to be processed, and preprocessing the document image; removing first frequency noise in the preprocessed document image by using a preset deep learning network, extracting image features after noise removal processing to obtain a first image feature set, extracting image features conforming to second frequency noise in the document image by using a preset deep residual network to obtain a second image feature set, fusing the first image feature set and the second image feature set, inputting a feature map obtained after fusion into a target convolutional neural network, and outputting a target document image. The application solves the technical problem that image blurring is easily caused when a document image is denoised in the related art.

The present application belongs to the field of image denoising, and in particular to a three-dimensional point cloud denoising method. The device and method are based on Laplace regularization subspace non-local low rank learning, and extend the previously proposed low-dimensional flow model of pixel blocks to surface blocks in point clouds. The graph Laplace regularizer of the surface is used to obtain the manifold dimension of the 3D point cloud image. Then, based on the principle that the high-dimensional information of the image point cloud is located in a low-dimensional subspace, the subspace non-local low rank factor is used to study the non-local self-similarity of the subspace, estimate the three-dimensional tensor generated by the non-local similar three-dimensional surface, and finally use the three-dimensional tensor to construct a denoising model to obtain a denoised image with better visual and quantitative indicators. The denoised image point cloud obtained by the method can better preserve the visually significant structural features, and the quantitative indicators are also good.

This invention belongs to the field of power monitoring technology and discloses a brightness balancing and regional smoothing fusion algorithm for power monitoring images. The method includes: image denoising, using mean filtering and median filtering to smooth the image; image registration, performing optimal matching on two or more images obtained from different sensors, at different times, or from different angles; and image region fusion, smoothly fusing images with different angles and brightness contrasts. This method is applicable to panoramic video monitoring systems. Designed specifically for the complex lighting and high electromagnetic interference characteristics of power operation sites, this invention effectively eliminates on-site noise through adaptive preprocessing, and achieves a balance between global brightness uniformity and local detail preservation through layered brightness balancing, solving the problems of incomplete brightness balancing and detail loss in power scenarios encountered by general algorithms.

Disclosed in the present invention are a self-supervised image denoising method and system. The method comprises: by means of an input interface, acquiring a noise image and transmitting same to a memory; configuring, in the memory, a search space based on a U-Net framework; a graphics processing unit reading configuration information, executing coarse-grained population initialization on the basis of a decimal modular encoding strategy, and writing population data into the memory as a contiguous memory block; the graphics processing unit executing distance-guided parent selection and modular crossover and mutation operations in parallel; decoding offspring individuals into network structures, then executing self-supervised denoising processing in parallel, and calculating PSNR values; and a central processing unit executing environment selection and controlling an iteration process, finally selecting an optimal network structure, and outputting a denoised image. By means of the optimization of search space design and the collaboration of heterogeneous computing architectures, the present invention simultaneously realizes high-quality image detail restoration and efficient denoising processing, without requiring paired data.

The application discloses a kind of distributed image denoising methods based on edge computing, it is related to edge computing technical field;Effectively improve image denoising;The application is by setting edge node model, based on edge node model acquisition target image target pre-processing image;And target pre-processing image is classified to obtain distributed morphological image by image form;Distributed morphological image is extracted to obtain the denoising intensity coefficient of distributed morphological image;Further, according to the denoising intensity coefficient, distributed morphological image is denoised to obtain distributed denoising image;Further, the image feature set of distributed denoising image is obtained, and distributed denoising image is spliced to generate target restoration image according to image feature set;Obtain the denoising coefficient of target restoration image;Judge the eligibility of denoising coefficient, if not qualified, then target restoration image is denoised to obtain qualified target restoration image and corresponding denoising times.

This disclosure relates to the field of image processing technology, and in particular to providing an image processing method, apparatus, device, medium, and product. In this disclosure, in response to a motion capture function, multiple frames of first images are acquired; these multiple first images are consecutive frames of original images acquired based on a first exposure time, where the first exposure time is much shorter than the first duration; image denoising processing is performed on the multiple first images to obtain a second image; stripe detection is performed on the second image to obtain an image detection result; when the image detection result indicates the presence of stroboscopic stripes, stripe removal processing is performed on the second image to obtain a target image. By denoising the consecutive frames, the image quality of the original image can be improved. Then, stripe detection is performed on the second image, and if stripes are present, they can be removed. This avoids the large amount of noise present in short-exposure images, while also satisfying the stripe phenomenon that appears under a stroboscopic light source for moving targets. Therefore, the image quality is improved.

The application relates to a laser speckle image denoising method and device, which combines the complementary advantages of a laser intensity image and a laser phase image, extracts and fuses a contour feature map of a laser speckle image and a curvature feature map and a normal vector feature map of a laser phase image, provides a neural network with abundant geometric context, and further adds geometric feature constraints in the neural network to form a hierarchical system. The synergistic effect of the geometric constraints enables the denoising model to accurately maintain the edge contour, local surface morphology, surface orientation and overall topological structure of the image when removing speckle noise, significantly improves the geometric structure integrity of the denoised image, and effectively solves the problem that denoising and structure preservation are difficult to balance and diagnostic information is lost in the background technology. The application provides a more reliable and accurate solution for medical imaging application scenarios, and has significant technical progress and application value.

The application relates to the technical field of medical ultrasonic imaging and digital image processing, in particular to an ultrasonic elasticity image denoising and enhancing method, which comprises the following steps: acquiring original ultrasonic elasticity imaging data to be processed, and constructing a structure tensor matrix reflecting local texture directions; solving the anisotropic coherence degree of each pixel point, obtaining a structure attribute discrimination result, and constructing a structure confidence atlas; collecting the point spread function characteristics of an ultrasonic imaging system, establishing a speckle noise statistical model; obtaining a local smoothing coefficient of the first iteration, and performing anisotropic diffusion correction on an initial elasticity distribution matrix to obtain a first modified elasticity image matrix, and updating the structure confidence atlas to obtain a final denoised and enhanced target elasticity image; the application effectively suppresses multiplicative granular speckles, eliminates the ladder effect or artifacts easily generated by conventional methods, and significantly improves the image signal-to-noise ratio.

The application provides a RAW domain non-local mean image denoising method, comprising the following steps: S1, collecting a RAW image by a sensor; S2, dividing the image into N channels, such as R, Gr, Gb and B channels according to an actual Bayer format; S3, performing non-local mean filtering on each channel; further comprising: S301, calculating the similarity between each channel pixel point and the center pixel point of a neighborhood window; S302, calculating the weight according to the similarity information; S303, calculating the filtering result of each pixel point in each channel according to the weight; S4, merging the results of each channel after filtering into a RAW image, and outputting the result. The application utilizes the original characteristics of noise to perform image filtering in the RAW domain, reduces the difficulty of noise suppression, and has smaller side effects under the premise of achieving the same filtering effect; the non-local mean filtering is adopted, so that the problems of pattern noise after filtering, and false color and color cast caused by unbalanced channel filtering results are avoided.

The application discloses a kind of training method of image denoising model, image denoising method, device and equipment, it is related to artificial intelligence technical field.Method includes: obtaining the training sample of image denoising model;Through encoder, the characteristic information of noisy sample image is extracted;Through first decoder, the characteristic information of noisy sample image is processed, and the predicted noise image corresponding to noisy sample image is obtained;According to predicted noise image and noisy sample image, the first predicted denoising image corresponding to noisy sample image is generated;Through second decoder, the characteristic information of noisy sample image is processed, and the second predicted denoising image corresponding to noisy sample image is obtained;According to first predicted denoising image, second predicted denoising image and noiseless sample image, the training loss of image denoising model is determined, and the parameter of image denoising model is adjusted based on training loss.The application scheme can be applied in the scene of image shadow removal of document, PPT (slide) etc..

The application discloses an image processing method and device and electronic equipment, and relates to the field of information technology, to solve the problem of poor denoising effect of the existing model. The method comprises the following steps: performing encoding processing on a first image to obtain a feature map of the first image; determining the feature points corresponding to each pixel point in the first image according to the position information of each pixel point in the first image and the position information of each feature point in the feature map; and performing decoding processing on the feature map according to the relative positions of each pixel point and the corresponding feature point in the first image to obtain a denoised first image. By introducing the position information of the input image, the spatial structure of the input feature map can be better understood, and thus a better image denoising effect can be obtained.

Embodiments of the present application provide a denoising method and device for images, electronic equipment, storage medium and program product. The method comprises: generating a first denoised image by denoising an original input image through a convolutional neural network; determining a noise residual image based on the original input image and the first denoised image; obtaining a second denoised image by adjusting the contrast of the first denoised image; and generating a target denoised image by combining the second denoised image with the noise residual image and the attribute features of the original input image. The method of the present application breaks through the limitation of fixed mapping relationship in related technologies, and no longer relies on fixed mapping of the model for denoising. The method not only retains the advantages of efficient denoising of the convolutional neural network, but also designs noise addition by combining the noise residual image with the attribute features of the image, so that the denoising process has flexible adaptation ability. The method can adjust the image denoising by regulating the noise addition according to actual needs, so that the quality of the denoised image matches the actual needs.

The application is suitable for the terminal technical field, and provides a shooting method, an electronic device, a storage medium and a chip system. The method comprises the following steps: in the case that a shooting instruction is received and a to-be-shot scene in a shooting preview frame is a target scene, shooting at least one group of images; the target scene comprises a fireworks scene; each group of images comprises multiple images with the same exposure time and different exposure amounts which are shot at the same time; an image with a smaller exposure amount in each group of images is shot by a camera with better photosensitive performance, and an image with a larger exposure amount is shot by a camera with poorer photosensitive performance; the shooting time of different groups of images is different; performing first processing on each group of images, so that the field of view, size and resolution of all images in each group of images are all the same; inputting multiple to-be-fused image groups with adjacent shooting time into a trained image denoising fusion model for processing to obtain a fused image, so that the overall quality of a shot fireworks image can be improved.

This application relates to an image denoising method, apparatus, device, and medium based on a CLIP image encoder and a Fourier structure encoder. The method includes: uniformly dividing a fused feature map into multiple sub-feature groups along the channel dimension; for each sub-feature group, concatenating all other sub-feature groups along the channel dimension to form complementary context features; predicting affine parameters from the complementary context features using an affine transformation module; performing affine modulation on the current sub-feature group; recombining all affine-modulated sub-feature groups; smoothing the result using a 3×3 convolutional layer to output a refined feature map; calling a preset decoder to restore the original image resolution of the RGB image to be denoised layer by layer, obtaining high-dimensional feature data matching the original image resolution; and mapping the high-dimensional feature data to the denoised RGB image using a 3×3 convolutional layer. This application solves the problems of incomplete single-domain feature representation and semantic-detail imbalance in traditional image denoising methods.

This invention relates to the field of computer and image filtering technology, and discloses an image denoising and restoration method based on adaptive kernel estimation. The method includes: acquiring a noisy or missing image; generating a multi-scale gradient response map; constructing a local directional covariance matrix to determine the principal direction and degree of anisotropy; constructing a spatially varying elliptical adaptive kernel function; performing weighted filtering by combining nonlocal similar blocks; and restoring the missing region layer by layer using a structure-guided iterative filling strategy. This invention achieves high-fidelity image restoration by dynamically adjusting the kernel shape and scale and incorporating nonlocal priors, preserving details, and suppressing noise, thereby improving objective indicators and visual quality.

This invention disclosed a full-space intelligent detection method and system for underground drainage networks, as well as storage media, including the following steps: image acquisition, intelligent image denoising, internal pipe defect segmentation, concealed defect detection around the pipe, 3D reconstruction with volume quantification, and pipeline life prediction. This invention introduced a bionic four-wheel-drive, all-terrain detection robot that can effectively navigate through mud and flowing water-challenges that hinder traditional detection devices. By leveraging deep learning algorithms as well as various techniques of computing vision, 3D reconstruction, and point cloud processing, the system thoroughly analyzed collected data to determine defect types and precise locations. Utilizing this analysis, precise location of different defect type and quantitative measurement of their dimensions can be realized. Based on the data analysis results, a deep-learning driven model was developed for predicting pipeline longevity to support maintenance staff with timely information on pipe defects and operational lifespan.

This invention discloses a method for monitoring the particle size of ultrafine, high-fiber, fast-dissolving broccoli pollen based on image recognition, belonging to the field of immunoassay system technology. The method includes: constructing an image acquisition system; selecting an appropriate imaging module and shooting parameters based on whether the sample is broccoli pollen paste or dried powder; acquiring microscopic images of the sample; preprocessing the acquired microscopic images by sequentially performing image denoising, grayscale conversion, binarization, and edge enhancement to eliminate recognition errors caused by background interference and particle adhesion; using a contour extraction algorithm to identify particle contours in the preprocessed images, combining area, roundness, and pixel thresholds for feature filtering to remove impurities and pseudo-particle contours, obtaining a dataset of valid broccoli pollen particle contours; this invention achieves simultaneous analysis of particle size, particle size distribution range, and specific surface area, without requiring additional detection equipment, and can output multiple indicators directly related to broccoli pollen quality and process optimization from a single image acquisition.

This invention relates to an automatic grading and sorting method and device for preserved flowers based on machine vision, belonging to the field of preserved flower processing and inspection technology. The invention acquires original RGB images of preserved flowers in a darkroom, performs image denoising, foreground segmentation, ROI (Region of Interest) extraction and coordinate matching, followed by HSV color space conversion and brightness normalization. Based on the flower head diameter, flower shape scoring and pre-removal of defective products are completed. Then, dual-dimensional defect detection of color difference and creases is performed, and a comprehensive score is calculated according to preset weights to determine the grade of the preserved flowers. Finally, automated grading and sorting are completed by an automatic sorting unit. This invention achieves fully automated operation of the preserved flower grading and sorting process, with unified grading standards, high detection accuracy, and non-destructive sorting. It effectively solves the industry pain points of low efficiency, large subjective errors, and poor product consistency in manual grading, and is suitable for industrial-scale mass production of preserved flowers.

This invention relates to the field of image processing, specifically to an image compressed sensing reconstruction method based on a hypergradient denoising network. Building upon traditional block-by-block image sampling and initial reconstruction, this invention maps the compressed sensing iterative denoising reconstruction model into an end-to-end denoising network using the concept of depth unfolding. Residual dense blocks are introduced into the denoising network as denoising operators to improve the quality of image denoising and reconstruction. Furthermore, a hypergradient strategy is used to optimize the iterative denoising model, accelerating network convergence. This invention overcomes the limitations of manually setting regularization terms by learning noise information through denoising operators during the iterative denoising process, flexibly representing the prior information of the image, and accurately and efficiently reconstructing the original image.

This application discloses an image denoising method and a radiotherapy system, relating to the field of medical technology, for optimizing the denoising effect of projected images and improving the quality of image reconstruction. The method includes: acquiring an original projected image; performing a logarithmic transformation on the pixel values ​​of the original projected image to obtain a logarithmic projected image; denoising the human tissue pixel region in the logarithmic projected image to obtain an initial denoised image; and denoising the low photon number pixel region in the initial denoised image to obtain a target denoised image.

The present application belongs to the technical field of remote sensing image processing, and provides a SAR image denoising method and device based on a logarithmic domain diffusion model. The denoising method comprises: preprocessing: converting an original SAR amplitude image to a logarithmic domain to obtain a starting input image for a diffusion process; forward diffusion: constructing a forward diffusion path based on a non-central Gaussian distribution, simulating a noise injection process, and generating a noisy image sequence; neural network model noise prediction: performing feature extraction and fusion on the noisy image and physical metadata through a pre-constructed neural network model, and outputting a noise residual prediction result; backward sampling reconstruction: iteratively sampling using the noise residual prediction result to reconstruct a denoised SAR image. The denoising method solves the distribution mismatch problem of traditional diffusion models for SAR multiplicative noise, improves the denoising precision, and preserves the image texture and structure information.

This paper describes an apparatus (901) for image denoising, comprising a processor (904) for: receiving (701) an input image captured by an image sensor (902); executing a trained artificial intelligence model to: form (702) an estimate of a noise pattern in the input image; form (703) an estimate of at least one noise statistic of the image sensor that captured the input image; refine (704) the noise pattern estimate based on the estimate of the at least one noise statistic; and form (705) an output image by subtracting the refined noise pattern estimate from the input image. A method (800) for training the model is also disclosed herein. Taking into account the noise statistics of the sensor that captured the input image can improve the quality of the denoised image.

The present disclosure relates to the technical field of biological microscopic imaging. Disclosed are a deconvolution-based super-resolution imaging method and apparatus by means of deep learning-based denoising, and a medium. The method comprises: acquiring an image to be denoised having a target imaging structure thereof marked by a fluorescent molecule; using a preset image denoising neural network to denoise the image to be denoised to obtain a denoised image, wherein a training data set for training the network is generated by using the photoswitching characteristic of a photoswitchable fluorescent molecule, the photoswitchable fluorescent molecule is used for marking the target imaging structure of each sample in the training data set, and an emission spectrum of the fluorescent molecule overlaps an emission spectrum of the photoswitchable fluorescent molecule; and performing deconvolution processing on the denoised image to obtain a super-resolution image. According to the present disclosure, a large-scale and high-quality ground truth image is obtained by using the photoswitching characteristic of the photoswitchable fluorescent molecule, thereby enhancing the denoising effect of the image denoising neural network; the image is denoised by using the network, and then deconvolution is performed on the denoised image, thereby achieving single-frame super-resolution imaging for live cells over a large field of view.

The application relates to an image denoising method and device, an air conditioner and a storage medium. The method comprises the following steps: inputting a noisy image sample into a generator, extracting human behavior features in the noisy image sample through a behavior feature representation network, and obtaining a denoised image output by the generator; inputting samples of the denoised image and preset training samples into an identifier, wherein the training samples comprise noisy image samples and non-noisy image samples; calculating an error between an identification result and a true label of the noisy image sample through the identifier, optimizing network parameters of a generative adversarial network by using a back propagation algorithm, obtaining a trained generator, and taking the trained generator as a denoising model; and inputting a target noisy image into the denoising model to obtain a target denoised image. The application improves the accuracy of personnel detection results.