194results about How to "Reduce artifacts" patented technology

The invention relates to a Mama-based seismic image super-resolution reconstruction method, which comprises the step of constructing a local feature extraction module, a global feature extraction module and a high-quality seismic section reconstruction module so as to solve the problem of insufficient resolution caused by high-frequency attenuation and sparse acquisition. According to the invention, a Mama model is introduced, and a novel super-resolution reconstruction network is constructed. The local feature extraction module extracts shallow feature information through a convolutional layer; the global feature extraction module obtains global features through the multi-stage residual state space block; and the high-quality seismic image reconstruction module realizes reconstruction of a high-resolution seismic image through pixel recombination and convolution operation. In addition, a Charbonnier loss function is adopted, the gradient disappearance problem is effectively avoided, and the loss function of traditional Mamba is improved. According to the method, the seismic image resolution can be improved, and meanwhile, the calculation complexity and the time cost are remarkably reduced.

The invention relates to the field of image enhancement, in particular to an image enhancement method and system of a vehicle-mounted image sensor. The method comprises the following steps: acquiring driving record images of a vehicle at multiple angles; dynamic scene self-adaptive exposure adjustment is carried out on the driving record images of the vehicle at the multiple angles, so that multiple self-adaptive exposure driving images are obtained; carrying out deep network noise identification on the plurality of adaptive exposure driving images, and carrying out dynamic filtering and noise reduction on sub-images one by one so as to generate a plurality of filtering and noise reduction optimized images; carrying out image texture analysis on the plurality of exposure sub-images, and carrying out texture distortion reconstruction to construct a plurality of texture reconstruction images; and road object visual identification is carried out on the plurality of texture reconstruction images, and adaptive contrast enhancement processing is carried out, so that a plurality of detail contrast enhancement images are constructed. According to the invention, a high-definition and stable panoramic vehicle-mounted image is realized.

The invention provides a multi-degraded image restoration method based on self-adaptive prompt. The method comprises a two-stage hidden space diffusion model, and various degraded images can be flexibly processed. Specifically, the model generates a degradation cue by learning the difference between a degraded image and a clean image, and encodes the cue information in a hidden space. In the first stage, a degradation prompt is obtained through a degradation adaptive prompt learning mechanism as a key feature for guiding the diffusion model in the second stage to carry out image restoration. Finally, prompt information is integrated into a Fourier transform restoration network, and accurate restoration of different types of degraded images can be realized. The method not only improves the accuracy of image restoration, but also significantly reduces the calculation complexity, and is suitable for image restoration tasks in various real world scenes, including denoising, deblurring, defogging, rain removing, snow removing, raindrop removing and low illumination enhancement.

The invention discloses a DBT reconstruction method based on three-dimensional coordinate displacement, a medium and electronic equipment, and the method comprises the steps: firstly obtaining multi-angle X-ray projection data, and carrying out the preprocessing of the X-ray projection data; then, the preprocessed projection data is corrected in a three-dimensional coordinate system; after interpolation processing is conducted on the projection data, an autoregressive source moving average separation method is adopted for processing, and a cross-sectional image of any depth is obtained; and finally, carrying out image enhancement on the cross-sectional image. According to the method, DBT reconstruction is carried out through three-dimensional displacement by utilizing multi-angle X-ray projection, and the structure in the reconstruction layer is effectively focused through multi-angle projection displacement correction and magnification standardization, so that the structure in the reconstruction layer is clearer, artifacts in the reconstruction layer are reduced, the contrast of the image of the reconstruction layer is improved, and observation of breast lesions is more facilitated.

The invention discloses a road and bridge deck disease identification method based on deep learning. The method comprises the following steps: acquiring a road and bridge deck disease image data set; constructing a road and bridge deck disease recognition model, and training the road and bridge deck disease recognition model based on the road and bridge deck disease image data set to obtain a trained road and bridge deck disease recognition model; the road and bridge floor disease identification model is constructed and obtained on the basis of a YOLOv9 network framework in combination with a CARAFE up-sampling module and a Triplet Attention mechanism; and obtaining a to-be-identified road and bridge surface image, and inputting the to-be-identified road and bridge surface image into the trained road and bridge surface disease identification model to obtain a disease identification result of the to-be-identified road and bridge surface image. According to the method provided by the invention, the problem of low recognition precision of an existing algorithm in different application scenes is effectively solved, and multiple disease types in road surface and bridge environments can be effectively and accurately recognized.

The invention discloses a stylized image guided three-dimensional model texture generation method, computer equipment, a storage medium and a program product. The stylized image guided three-dimensional model texture generation method is a pipeline based on a diffusion model, style textures are generated under the guidance of a single image, style information is extracted from a reference image, and meanwhile content information is ignored. The method comprises the following steps: firstly, obtaining a grid model of a three-dimensional object and a stylized image for guiding, obtaining text embedding characteristics and style characteristics, and completing style injection in a diffusion model cross attention mechanism in a layering manner; and optimizing texture parameters of the texture representation model by utilizing interval score matching loss and style guide loss, and finally, sampling the texture representation model to obtain the final stylized texture of the high-quality three-dimensional object.

The invention discloses an intelligent coal gangue sorting method and system based on image deep learning, and belongs to the technical field of coal rock recognition. Global images and local images of coal gangue are obtained; preprocessing the global image and the local image to obtain a preprocessed global image and a preprocessed local image; fusing the preprocessed local image to the global image to obtain a fused image; and inputting the fused image into a target detection model based on a color feature attention mechanism, and carrying out detection and identification on coal and gangue to obtain an identification result. An image fusion technology is adopted to fuse a global image and a local image of coal gangue, so that coal gangue image information with rich details can be provided, a deep learning target detection model based on a color feature attention mechanism is adopted, coal and gangue can be accurately recognized, the recognition accuracy is improved by using color features, and the recognition efficiency is improved. And it is ensured that the sorting process is more accurate.

The present invention discloses a super-resolution reconstruction method for industrial CT images based on deep learning, and its application relates to the field of industrial CT image technology, in order to solve the problem of low image resolution caused by equipment limitations. The steps include data acquisition and preprocessing, data enhancement, edge enhancement module construction, convolution downsampling module construction, RRDB residual module construction, upsampling and reconstruction, model training and optimization, and splicing trace processing. By using the present invention, super-resolution reconstruction of multi-material CT images can be achieved, and the resolution and clarity of the images can be improved.

The invention discloses an image fusion method based on raindrop layer interference reduction and background detail information enhancement, and relates to the technical field of new-generation information. According to the fusion method disclosed by the invention, the enhanced feature map including the direction weight, the reconstructed infrared image feature map including the direction weight and enhanced thermal radiation information, and the raindrop layer feature map including the direction weight and having rich raindrop edge information and texture details can be obtained; subtracting the enhanced feature map from the raindrop layer feature map to obtain a background detail feature map with reduced raindrop layer interference and enhanced background detail information; and the cross-modal complementary feature fusion of the background detail feature map and the reconstructed infrared image feature map can be realized by using a cross-modal complementary feature fusion network to obtain a Y-channel fusion image. The obtained color fusion image contains richer edge information, background detail information and heat radiation information in more source images, and artifacts in the color fusion image are fewer.

The invention belongs to the field of CT image processing, and particularly relates to a CT image reconstruction method and device for improving 3D Gaussian splashing and a CT system. The method comprises the following steps: acquiring multiple frames of two-dimensional X-ray images; performing three-dimensional reconstruction on each frame of two-dimensional X-ray image to generate three-dimensional point cloud data and camera position information; according to the three-dimensional point cloud data of each frame of two-dimensional X-ray image and the camera position information, generating a two-dimensional plane of each frame of two-dimensional X-ray image by using 3D Gaussian splashing; performing adaptive rasterization processing on the data projected to the two-dimensional plane to generate two-dimensional image data; and performing adaptive rendering processing on the rasterized two-dimensional image data to generate a CT reconstructed image. The method does not need to carry out depth sorting, does not need to depend on a large-scale annotation data set, can effectively suppress noise, reduce artifacts and maintain the edge and detail definition of the image, has efficient reconstruction performance, and is suitable for rapid and high-quality reconstruction of low-dose CT imaging.

The invention discloses a high-quality image reconstruction method, and the method comprises the steps: firstly constructing a convolutional neural network model which comprises an input layer, a convolutional layer, a pooling layer, a full connection layer, an output layer, a brightness enhancement module, a saturation adjustment module, and a color cast correction module; acquiring night vision image data, performing normalization and noise reduction processing on the night vision image data, dividing the night vision image data into a training set and a test set, training the convolutional neural network model by adopting the training set, and taking a mean square error (MSE) as a loss function; a test set is adopted to test and analyze the trained convolutional neural network model, and PSNR (peak signal-to-noise ratio) and structural similarity (SSIM) are adopted to evaluate the quality of the restored image, so that an optimal convolutional neural network model is obtained; and performing high-quality image reconstruction processing on the CIS image data by using the obtained optimal convolutional neural network model to obtain a high-quality image, and transmitting the high-quality image to a display device.

The invention relates to the technical field of machine vision, in particular to an image segmentation method and system for liquid crystal screen display. The method comprises the following steps: acquiring basic data of the liquid crystal screen; performing screen response characteristic analysis according to the basic data of the liquid crystal screen to obtain screen response characteristic data; performing multi-scale image acquisition according to the basic data of the liquid crystal screen to generate multi-scale image data; performing characteristic classification on the liquid crystal display according to the screen response characteristic data, and performing edge compensation analysis on the multi-scale image data to obtain edge characteristic compensation data; acquiring real-time data of the touch screen; and performing touch interference identification analysis on the real-time data of the touch screen according to the edge feature compensation data to generate touch interference mask data. By analyzing the screen response characteristics and performing edge compensation analysis, the phenomenon of edge blurring caused by liquid crystal response time limitation is reduced, and the accuracy of edge detection is improved.

The invention discloses a minimum and maximum concave high-order total variation constraint seismic wave impedance inversion method and system, and the method comprises the steps: constructing an inversion objective function containing minimum and maximum concave high-order total variation constraint through preprocessing seismic data and logging data, and carrying out the iteration updating of a natural logarithm of wave impedance through an alternating direction multiplier method, therefore, high-precision seismic wave impedance inversion is realized. High-frequency sparse information is described by utilizing minimum and maximum concave, and transverse and longitudinal differential information is described by adopting high-order total variation, so that the inversion precision of a structure complex region is effectively improved, and artifacts of a boundary region are inhibited. The seismic wave impedance inversion method has the advantages that the resolution in an impedance structure complex region is remarkably improved, the error of an inversion result is low, and the resolution and the accuracy of seismic wave impedance inversion are further improved.

The invention provides a pulse wave time-frequency feature extraction method based on an improved Gabor atom dictionary, and belongs to the technical field of human physiological signal processing analysis and health monitoring. Firstly, an original pulse wave signal is subjected to center moving average and wavelet transform to remove high-frequency noise; then baseline drift removal operation is carried out to eliminate low-frequency noise, and a pulse wave signal without noise is obtained; performing period segmentation and normalization processing on the denoised pulse wave signal to obtain an average period signal; an over-complete Gabor atom dictionary is constructed, sparse representation is conducted on the average pulse wave period signals through an OMP orthogonal matching pursuit algorithm, and time-frequency characteristic components are obtained; the method has the advantages that the pulse wave signals can be effectively denoised, the time-frequency features with certain physiological significance can be extracted, and the method can play an important role in the aspects of human health monitoring, disease prevention and the like.

The present invention relates to the field of image defogging, and specifically discloses a 4K image defogging method, device and storage medium based on weakly supervised contrast learning, including S1, obtaining a dark channel prior image #imgabs1# after dark channel prior processing of a foggy image #imgabs0#; weighted fusion of the foggy image #imgabs2# and the processed image #imgabs3#, and finally obtaining a fused image #imgabs4#; S2, inputting the fused image #imgabs5# into a U-net convolutional neural network structure for processing, and inserting a residual block and introducing an SC attention mechanism during processing; S3, using PatchGAN as a discriminator, which divides the restored image #imgabs6# into many small overlapping areas, judging whether each small area is part of the real image, using the least squares GAN loss to train the network, and finally discriminating and obtaining the restored fog-free image #imgabs7#; S4, contrast learning loss function. The beneficial effects achieved by the present invention are: the high-resolution image defogging algorithm is short in time and can maintain a high-precision defogging effect.

The invention relates to the technical field of biomedical ultrasonic imaging, and discloses a Doppler imaging method and system based on multi-angle plane wave Hadamard coding, and the method comprises the steps: transmitting N groups of ultrasonic waves which are subjected to phase coding through Hadamard coding into a blood flow imaging region, each group of ultrasonic waves comprises N continuous plane waves which are different in angle and are separated by a preset time delay, N groups of ultrasonic echo signals are collected and decoded to obtain ultrasonic echo signals, and the step is repeatedly executed to obtain continuous multi-angle ultrasonic echo signals; moreover, according to the continuous multi-angle ultrasonic echo signals, an instantaneous blood flow image signal corresponding to the time window is obtained; a matrix equation set is constructed and solved to obtain the blood flow vectorization speed, a blood flow vector speed field transient image is generated, and / or a blood flow vector speed field dynamic change image is displayed. According to the method, the signal-to-noise ratio of plane wave imaging and the imaging sensitivity to weak blood flow signals can be remarkably improved.

The invention provides a three-dimensional real-time passive acoustic imaging method, device and equipment based on a row-column addressing ultrasonic transducer and a medium. The method comprises the following steps: passively receiving an ultrasonic signal for monitoring microbubble acoustic cavitation activity in a three-dimensional manner through the row-column addressing ultrasonic transducer; the row-column addressing ultrasonic transducer is composed of a row array and a column array, and the ultrasonic signals comprise row array signals and column array signals; respectively reconstructing a three-dimensional sound field according to the row array signal and the column array signal to obtain a row array three-dimensional sound field and a column array three-dimensional sound field; and selecting a target frequency band from the frequency bands, and performing cross-correlation superposition on the row array three-dimensional sound fields and the column array three-dimensional sound fields on the frequencies in the target frequency band to obtain a three-dimensional passive cavitation image of the row array and the column array. According to the invention, artifacts can be effectively reduced, and more accurate positioning and monitoring are realized.

The invention discloses a defocusing and deblurring method based on a hierarchical model, and relates to a defocusing and deblurring method. The invention aims to solve the problem of incompatibility between a high-level visual demand and an image recovery task. The method comprises the following steps of: 1, segmenting a blurred image x belonging to RC * H * W into h belonging to RN * D by using a basic feature encoder; step 2, a context encoder uses # imgabs0 # to learn a clearer and abstract representation hs; and step 3, using the # imgabs1 # and the hs as input by the decoder, and reconstructing an image # imgabs2 # after the blurring is removed. The invention belongs to the technical field of image processing.

The invention relates to the technical field of nuclear magnetic resonance, in particular to a method and device suitable for compressed sensing rapid nuclear magnetic resonance spectrum reconstruction. The method comprises the following steps: step 1, acquiring an under-sampling nuclear magnetic resonance spectrum; and step 2, inputting the undersampled nuclear magnetic resonance spectrum into a trained coding-decoding neural network based on an attention mechanism for processing to obtain a high-quality reconstructed nuclear magnetic resonance spectrum. According to the invention, the constructed coding-decoding neural network based on the attention mechanism is adopted to process the under-sampling nuclear magnetic resonance spectrum, key features, especially weak peak signals, of signals are gradually enhanced from the under-sampling nuclear magnetic resonance spectrum through multiple times of feature extraction and fitting processes, artifacts are effectively reduced, and the detection accuracy is improved. Finally, high-precision reconstruction output is realized, and a high-quality reconstructed nuclear magnetic resonance spectrum is obtained. According to the method, the problems of poor reconstruction quality and difficulty in weak peak recovery in some existing spectrogram reconstruction algorithms are solved.

The invention provides a lens-free dynamic imaging system and a lens-free dynamic imaging method with distinguishable motion. The system comprises a laser light source, a binary optical mask, an image sensor and image processing equipment, coherent light emitted by the laser light source is coded and modulated by the binary optical mask and then propagated to the image sensor, the image sensor collects multiple frames of diffraction images of a moving sample and transmits the collected images to the image processing device, and the image processing device reconstructs the images through a neural network method. According to the image reconstruction method, physical priori knowledge of a lensless diffraction propagation model is fused into implicit neural representation, and a space-time priori loss and bidirectional memory training method is designed for network training, so that artifacts and blur generated by moving target imaging can be effectively reduced, and a high-resolution and high-quality imaging result can be obtained.

The embodiment of the invention provides a three-dimensional image generation method and device, a storage medium and a program product. In the embodiment of the invention, based on binocular parallax, a first monocular view with a cavity area and a second monocular view without a cavity area corresponding to a two-dimensional image are generated; according to the method, the first monocular view is taken as a global constraint, the hole area in the first monocular view is subjected to block repair, image details can be accurately restored, the image quality is remarkably improved, important image details are kept, the second monocular view without the hole area is further taken as the global constraint, and the third monocular view obtained after hole area repair is subjected to global repair, so that the image quality is improved. And the generated content is ensured to be controllable during repairing, the consistency of stereoscopic vision is maintained, and the repairing definition is higher.

The invention belongs to the field of seismic exploration, and particularly relates to a microseism reverse time positioning method based on an improved imaging condition, which comprises the following steps: constructing a speed model, and carrying out gridding processing; loading the wave field data to corresponding grid points in a speed model according to the position of a detector to form a detection point; wave detection points are divided into N groups, the number of the wave detection points in each group is consistent, reverse time continuation is carried out on the wave field data in each group at the same time, in the reverse time continuation process, the squares of wave field amplitude values obtained through reverse time continuation are superposed along a time axis, and an initial positioning section is obtained; performing grouping cross-correlation operation on the wave field of each group of initial positioning profiles; and carrying out self-correlation processing on the wave field after grouping cross-correlation operation to obtain an accurate positioning profile for seismic source positioning. The problems of low positioning accuracy, poor imaging quality and high calculation cost existing in conventional imaging conditions in existing seismic source reverse time positioning are solved, more accurate seismic source positioning is realized, and meanwhile, the risk of errors and illusions is reduced.

The invention discloses a subject image editing and generating method based on a multi-party collaborative attention mechanism, and the method comprises the steps: inputting a multi-mode instruction to a subject positioning module, positioning an action region, and extracting a subject image and a target image in the action region; inputting the subject image and the target image into a pre-trained deep learning model, and executing self-attention local query in a self-attention layer to integrate the background of the source image and the foreground of the subject image; and executing self-attention global injection to realize detail enhancement of the target image. And outputting an edited and generated target image in combination with results of the self-attention local query and the self-attention global injection. According to the method, the time required for generating the consistent image by the theme model is greatly shortened, and the practical application of the theme model in a wider range is promoted.

The invention discloses a structure-guided multi-priori input image enhancement method and device. The method comprises the following steps: step 1, collecting low-quality images and corresponding high-quality images to form a data set; dividing the data set into a training set, a verification set and a test set; 2, constructing a multi-view-angle input enhancement network, wherein the multi-view-angle input enhancement network is used for preliminarily enhancing the low-quality image; designing a multi-view-angle enhanced joint loss function Lmve, specifying a training round, training and optimizing the multi-view-angle input enhanced network model, and storing the weight of the optimal model; step 3, constructing a structure guidance enhancement network, wherein the structure guidance enhancement network performs secondary enhancement on the image data based on the structure information extracted by the structure extraction module; and designing a structure guidance enhancement joint loss function Lsge, specifying a training round, training and optimizing the structure guidance enhancement network model, and storing the weight of the optimal model.

The invention provides a medical image fusion method and system based on a big kernel attention mechanism, and belongs to the technical field of medical image fusion. A big kernel attention mechanism and frequency domain transformation processing are introduced, and a multi-scale convolution operation, channel attention and a space attention mechanism are combined, so that the fusion image achieves a higher balance in the retention of global information and local details. Meanwhile, through separation processing of amplitude and phase information in a frequency domain, accurate fusion of image details and structures is realized, and common artifact and fuzzy problems in a traditional method are avoided. Besides, a densely connected decoder module is designed, the detail retention capability during image reconstruction is enhanced, and processing of different modal image features is more intelligent and accurate through a self-adaptive feature fusion mechanism.

The invention belongs to the technical field of medical imaging, and particularly relates to an MRI (Magnetic Resonance Imaging) condition reconstruction method based on coil calibration image control, which comprises the following steps of: acquiring a coil calibration image and undersampled MRI image data; inputting the coil calibration image into a condition control module to estimate a coil sensitivity distribution map; taking the coil calibration image as condition input, and reconstructing undersampled MRI image data in combination with a diffusion model; wherein the diffusion model comprises a forward diffusion process and a reverse diffusion process, image reconstruction is realized by gradually adding and removing noise, and detail reduction and definition of a reconstructed image are remarkably improved by combining the forward and reverse noise removal processes of the diffusion model with a condition control mechanism of a coil calibration image; the condition control module dynamically adjusts the influence of the coil calibration image on the reconstructed image, thereby effectively reducing the noise and artifacts in the image, and enabling the reconstructed image to be clearer and more accurate.

The invention discloses a photoacoustic imaging reflection artifact elimination method based on a neural network and spatial filtering, which comprises the following steps of: firstly, eliminating internal artifacts of optical signals by adopting singular filtering, and then eliminating boundary artifacts of the optical signals by adopting the neural network. The imaging definition and accuracy are improved, the contrast ratio and the resolution ratio of the image are enhanced by reducing artifacts and noise, so that the imaging result is closer to the real situation, the clearer image is beneficial to more accurate diagnosis of doctors, and the reliability of medical diagnosis is improved. The method is compatible with an existing photoacoustic imaging system and can be applied to various imaging platforms, the deep learning technology is utilized, the data processing efficiency is improved, the requirement for computing resources is reduced, the deep learning model can stably work under different conditions after being fully trained, and dependence on prior information is reduced. Compared with some traditional photoacoustic imaging algorithms, the deep learning method may reduce the demand for computing resources, so that the imaging process is more efficient.

The invention discloses an assembling method of a membrane switch. The assembling method comprises the following steps: S1, preparing a base material; s2, primary printing of waterproof glue; s3, assembling a semi-finished product; s4, printing the waterproof glue for the second time; and S5, assembling a finished product. The device has the advantages that through an automatic production mode, automatic printing of waterproof glue and upper-layer materials as well as waterproof glue and middle-layer materials, automatic assembly of the upper-layer materials printed with the waterproof glue and the middle-layer materials, and automatic printing of conductive glue on lower-layer materials are realized; and the lower-layer semi-finished product and the second semi-finished product are automatically assembled in the corresponding direction of the conductive adhesive and the waterproof adhesive printed on the middle-layer material, so that the precision of the product can be effectively ensured, the breakage rate and the pollution rate in the product assembling process are reduced, manual finished products are saved, and the production efficiency is improved.

The invention discloses a binocular video stitching method based on suture line search, and the method comprises the following steps: S1, video collection and preprocessing: obtaining a video stream through employing a binocular camera, and carrying out the preprocessing of each frame of image; s2, a calibration stage: carrying out feature point extraction and grid construction on each video frame by adopting an improved grid optimization algorithm, and generating calibration data; s3, generating a lookup table: generating the lookup table according to the calibration data, and mapping each pixel to a new position; s4, suture line searching: performing suture line searching by using a suture line searching algorithm based on dynamic programming; s5, motion detection and suture line updating: calculating a gradient difference of a suture line area, judging whether a moving object passes through a seam or not, and if the moving object passes through the seam, updating the suture line; and S6, image fusion: carrying out average fusion on the seam region. According to the method, the improved grid optimization and dynamic programming algorithm is adopted, high-precision binocular video stitching is realized, and motion artifacts and ghosting phenomena are effectively eliminated.

The invention discloses a rapid magnetic resonance imaging reconstruction and segmentation method and system, a medium and a product, and relates to the technical field of image processing. The method comprises the following steps: decomposing original three-dimensional magnetic resonance data into a plurality of independent two-dimensional magnetic resonance data slices along a slice sequence; image reconstruction is carried out on the two-dimensional magnetic resonance data slices through a pre-trained forward generator in the frequency domain Schrodinger bridge diffusion model so as to generate a two-dimensional magnetic resonance image, and the forward generator integrates a Fourier convolution module and is used for carrying out frequency domain transformation and feature enhancement processing on feature mapping in the image reconstruction process; inputting each two-dimensional magnetic resonance image into a pre-trained segmentation model in sequence, performing segmentation of a target region and a preset dangerous organ, and generating a corresponding two-dimensional segmentation mask; all the two-dimensional segmentation masks are rearranged and stacked according to the slicing sequence, and a three-dimensional segmentation result is generated through three-dimensional fusion operation. By implementing the technical scheme, magnetic resonance imaging reconstruction and segmentation can be quickly and accurately carried out.