207 results about "Image recovery" patented technology

The invention discloses an image deblurring system and method based on Transform and multi-scale feature fusion, and relates to the technical field of image processing, the system comprises an input layer, a processing layer and an output layer, the processing layer comprises a multi-input multi-output encoder-decoder module, the multi-input multi-output encoder-decoder module is used for extracting features from blurred images of different scales through an encoder, and outputting the features to the output layer; a clear image is gradually restored based on the extracted features through a decoder; the multi-feature multi-scale fusion module is used for integrating local and global feature information and enhancing the learning ability of the system to global features; according to the improved Transform module, a self-adaptive window mechanism and a cross-channel attention mechanism are introduced, so that the system can better adapt to different types of blurred images, and the effects of feature extraction and image restoration are improved; and the attention fusion module dynamically learns and integrates useful feature information by introducing a channel attention mechanism. The image deblurring method is suitable for various image deblurring application scenes, and image detail features can be effectively recovered.

The invention relates to the field of image processing, in particular to a multi-modal guided progressive image generation method, which comprises the following steps of: generating multi-modal features for received data; generating a final layer layout for each main object by using a layout denoising network through a noise sampling and multi-modal feature fusion method; extracting potential codes of a reference image through an inversion algorithm, combining layer text codes, performing iteration denoising through a stable diffusion model, and extracting a reference key value matrix; the initial noise, the final layer layout, the multi-modal features and the reference key value matrix are input into a layered diffusion model, and after multi-step denoising, a main body transparent image layer is generated through decoding; and after all the main body transparent layers are superposed to form a mixed image, driving the image recovery network to generate a target image based on global text coding. According to the method, the defects of an existing method in processing a complex scene are overcome; and the generated image is ensured to be consistent with the text description globally and locally.

The present application provides a cardiac fibrosis diagnosis model based on multi-task attentional feature fusion. The cardiac fibrosis diagnosis model is established by the following steps: S01: image collection and labeling: obtaining cardiac magnetic resonance (MR) images as sample data, and performing manual labeling to obtain heart labels corresponding to the MR images; S02: image preprocessing, including normalization processing, data enhancement, and data clipping; S03: model establishment, including establishment of an image recovery network and establishment of an image segmentation and classification network, and executing an image recovery task; S04: model pre-training: training the image recovery network such that the encoder of the image recovery network fully learns the feature of the cardiac fibrosis image; and S05: model training. An objective of the present application is to improve the segmentation precision and diagnosis accuracy of a network model for a cardiac fibrosis image.

The invention discloses a single-bit image recovery method and device, a terminal and a medium, and relates to the field of image processing. The method comprises the following steps: performing single-bit quantization on a to-be-recovered image by adopting a non-zero quantization threshold, and determining an initial image quantization model; replacing a sign function in the initial image quantization model with a smooth hyperbolic tangent function, performing low-rank matrix decomposition on the to-be-recovered image, and determining a target image quantization model; determining an initial optimization model according to the truncated least square function and the target image quantization model; a semi-quadratic minimization method is adopted to convert the initial optimization model, and a target optimization model is determined; solving the target optimization model by adopting a near-end block coordinate descent algorithm to obtain each low-dimension sub-matrix and a noise matrix; and determining a reconstructed image by using each low-dimensional sub-matrix. The problem that in the prior art, quantization noise cannot be effectively restrained, and therefore image restoration precision is affected is effectively solved.

The invention discloses a semantic intelligent enhanced DNA storage method for the Internet of Things, and belongs to the crossing field of artificial intelligence and biological information storage, the compression efficiency and robustness of DNA image storage are effectively improved through introduced semantic extraction and a multi-read screening mechanism of design, key information areas in images are extracted through semantic extraction, and the compression efficiency and robustness of DNA image storage are improved. The method has the advantages that redundant backgrounds are eliminated, coding lengths are reduced, high-quality sequences are selected from sequencing copies by the aid of scoring and sequence analysis through a multi-read screening mechanism, fault tolerance is enhanced, the method is applicable to efficient semantic storage in scenes of the internet of things, the problem of low storage efficiency due to excessive redundant information in original images in existing DNA image storage methods is solved, and the method is applicable to high-efficiency semantic storage in scenes of the internet of things. And a high bit error rate exists in the DNA synthesis and sequencing process, so that the image recovery quality is influenced.

The invention discloses a medical image reconstruction method and device, and belongs to the technical field of image processing, and the method can achieve the cooperative work of an overall model through a fine-tuning visual language model, a feature adapter module and an image restoration generator, and achieves the reconstruction of a single-channel to-be-processed medical image and corresponding modal text prompt information. A complete process from feature extraction, fusion to reconstruction is formed, so that the image quality of the reconstructed medical image can be improved, and the pertinence and effectiveness of medical image reconstruction are improved.

The invention provides an image shadow removing method and system based on image filling enhancement, and relates to the field of image processing, and the method comprises the following steps: constructing an image restoration model; according to a real image of the shadow-removed data set, constructing an image filling task training data set by using a random mask, training an image restoration model by using the image filling task training data set, and storing a model weight file; based on the model weight file, training the trained image recovery model again, optimizing the image recovery model in the training process, and determining and storing a model optimization weight file according to the optimized image recovery model; and carrying out initialization processing on the image restoration model, and carrying out shadow removal processing on the to-be-processed image with the shadow by using the initialized image restoration model to obtain the image with the shadow removed. According to the method, the dynamic adaptation of the task is realized, and the processing capability of the model to cope with a complex degraded scene is remarkably improved.

The invention discloses a step refractive index fiber endoscopic bending microscopic imaging loss recovery method and device. The method comprises the following steps: s1, searching and removing an image loss part in a step refractive index fiber endoscope scanning image; s2, image restoration: carrying out feature matching on the two displacement pictures processed in the step s1 to calculate x-direction and y-direction displacements of the two images, and then aligning and fusing the two images in a Poisson fusion mode to repair image loss parts; and s3, background denoising: estimating transmissivity by calculating a dark channel and a background illumination value, and denoising the image according to the transmissivity to obtain a denoised image. According to the method, through frequency domain low-pass filtering and feature matching fusion, lost image center information is successfully recovered, image center details are effectively recovered, and image recovery can be realized through processing of an imaged image.

The invention belongs to the technical field of multi-modal driving video analysis methods, and particularly relates to an image-enhanced multi-modal driving video analysis method, which comprises the following steps of: pre-training an image, converting a clear image and a degraded image into potential space representation, adding noise to the clear image by using a diffusion probability model, and guiding a recovery task through task prompt. Meanwhile, the model is finely adjusted by using Contro Net, alignment of potential space representation and task prompt is ensured in cooperation with a self-attention and text cross attention mechanism, the difference between an image and a target image is recovered through L2 loss minimization, training of an image recovery model is completed, key frame extraction, target detection and three-dimensional positioning are performed on an enhanced video, and the image recovery efficiency is improved. The method comprises the following steps: constructing semantic text description, carrying out multi-modal coding through a visual language model, generating structured perception representation, carrying out structured spatial reasoning by utilizing a small-scale language model, and training the model by adopting a strategy optimization algorithm, so that the model generates a reasoning process and an accurate answer under the condition of inputting scene description and questions.

The invention discloses an ultra-high-definition image recovery method based on a frequency-enhanced variational auto-encoder, which is characterized in that a Fourier-based lightweight frequency learning module is designed to improve parameter efficiency, a wavelet-based adapter is introduced to extract multi-scale image information, a bridging domain gap is adaptively modulated through frequency perception, and the ultra-high-definition image is recovered. And injecting the high frequency information into a VAE decoder to enhance details of the restored image. The invention aims to solve the problem of consistency caused by down-sampling in the existing UHD image restoration method, overcomes challenges of VAE (variational auto-encoder) in UHD image restoration by introducing frequency priori by utilizing strong potential space representation and reconstruction capabilities of the VAE, including the problems of large parameter quantity, domain gap, high-frequency information loss and the like, and improves the UHD image restoration efficiency. Therefore, the image restoration effect with higher quality is realized.

The invention relates to a BMC firmware mirror image recovery method and device and terminal device.The method comprises the steps that a storage area of a preset storage chip is divided into multiple areas, and the multiple areas comprise a first area and a second area; a first file in the firmware mirror image file is coded through a forward error correction algorithm, redundant recovery data is obtained, backup files of second files except the first file in the firmware mirror image file are obtained, and the first file comprises a root file system; the first file and the redundancy recovery data are stored in the first area, and the second file and a backup file of the second file are stored in the second area; when it is detected that the first file is abnormal, the first file is recovered based on the redundant recovery data through a forward error correction algorithm; and when detecting that the second file is abnormal, recovering the second file through the backup file of the second file. According to the method and the device, the problem that the reliability of recovering the firmware mirror image file through out-of-band network transmission is relatively low is solved.

The invention discloses a remote sensing image super-resolution reconstruction method based on a diffusion bridge model. The method comprises the following steps: firstly, constructing a diffusion bridge model, and connecting low-resolution and high-resolution image endpoints; secondly, explicitly aligning states of an image recovery bridge process and a pre-training generation diffusion process by designing a state alignment mechanism so as to multiplex powerful generation prior of a pre-training model; meanwhile, a lightweight feature adapter is introduced into a decoding end of the pre-training model, and high-frequency detail features reserved by an encoder are injected into a decoding path through a gating residual mechanism so as to suppress an over-smoothing phenomenon caused by VAE decoding. According to the method, the problems of insufficient prior utilization and high-frequency detail loss of a traditional diffusion model in remote sensing image super-resolution reconstruction are effectively solved, the structural integrity and visual fidelity of the image are ensured while the reconstruction efficiency is remarkably improved, and the method is suitable for a multi-scene remote sensing image super-resolution task.

The invention belongs to the technical field of digital image processing, and discloses an image restoration method, system and device based on multi-modal large model driving. The method comprises the following steps: receiving a to-be-recovered degraded image, inputting the degraded image and a preset multi-task text cue word into a multi-modal large model, analyzing and processing the degraded image, and generating an operation instruction and a visual description prompt of the degraded image; encoding the operation instruction and the visual description prompt to respectively obtain a corresponding task intention vector and a content guide vector; and fusing the task intention vector and the content guide vector through an image restoration model, reconstructing the degraded image, and outputting a restored image. According to the method, the image problem can be automatically and accurately diagnosed, rich guidance information is provided from the two dimensions of operation and content, and intelligent, automatic and high-fidelity image recovery is realized.

The invention relates to the technical field of computer vision and digital image processing, and discloses a two-stage damaged face image restoration method based on a generative adversarial network, and the method comprises the following steps: inputting a damaged face image into a reconstruction network, the input feature map is processed through at least one self-adaptive harmonic purification convolution module built in the reconstruction network, and a purified feature map is generated; based on the purified feature map, the reconstruction network outputs a low-frequency basic image and a final degradation feature map; inputting the low-frequency basic image and the final degradation feature map into a detail generator to generate a high-frequency detail map; and fusing the low-frequency basic image and the high-frequency detail image to obtain a final restored image. According to the method, the adaptive harmonic purification convolution module is arranged in the reconstruction network, frequency domain analysis can be carried out on local image features in the initial stage of feature extraction, and the harmonic attention mask is adaptively generated according to the content.

The invention discloses a two-stage multi-task image restoration method based on an RDM-CS framework (see figure 1), which can process various image restoration tasks such as low illumination, rain removal, snow removal, defogging and the like at the same time. Comprising the following steps: 1) processing and dividing a data set; and 2) carrying out feature extraction by using a VQGAN encoder and completing forward diffusion on the feature zt. And 3) training the prediction noise network and the prediction residual network to obtain residual and noise, and then completing reverse generation. And (4) training a CS (Channel-Spatial Transform) network (Channel-Spatial Transform). And 5) testing in the test set of each data set, and evaluating the image restoration effect. According to the method, through the multi-stage feature extraction and diffusion process, the model can effectively process various image degradation problems, and the image restoration quality and efficiency are improved. The system has a unified model architecture, can adapt to different image recovery tasks, and has relatively high practicability and popularization value.

The invention discloses a face image restoration method and system based on a mask auto-encoder, and belongs to the technical field of deep forgery detection, and the method comprises the steps: employing a RetinaFace model to cut a forgery face image, and obtaining a source face image and a target face image corresponding to the forgery face image; extracting features of the source face image, performing up-sampling on high-level semantic features, then splicing the high-level semantic features with shading features, and obtaining a segmentation probability graph based on a spliced feature graph; multiplying the segmentation probability graph by the source face image to obtain source face information, and restoring and reconstructing the source face based on the source face information to obtain a reconstructed source face; partitioning the segmentation probability graph, calculating the mean value of each segmentation probability graph, calculating the weight based on the mean value, and performing masking based on the weight to obtain a covered image; and inputting the potential target face features in the reconstructed source face and the covering image into a mask auto-encoder to obtain a face image recovery image of the forged face image.

The invention provides a target identification method and system for a severe working condition environment, and the method comprises the steps: firstly obtaining sequence image data, which are collected in a natural gas purification plant inspection region under the conditions of dust interference, smoke shielding and illumination variation, and comprise equipment, pipeline and instrument region images; analyzing the interference type and degree through a working condition interference sensing module, generating interference sensing parameters, inputting the interference sensing parameters into an image recovery parameter generation module, generating an image recovery parameter set, and performing layered recovery on the sequence image data according to the parameter set by utilizing an image recovery module, so as to eliminate various interference influences; and finally, performing feature extraction and classification identification on the recovered image data through a target identification and state judgment module, and generating an inspection target identification result containing a target area equipment type, an operation state identifier and a spatial position coordinate, thereby effectively coping with severe working conditions and improving the target identification accuracy.

The invention discloses a generative adversarial network (GAN)-based recoverable watermarking resisting method, which not only can ensure that an image is protected by privacy and copyright, but also can only allow an authorized party to safely use. Specifically, an encoder-decoder-restorer architecture based on a GAN (Generic Area Network) is innovatively designed, and watermarking-resistant embedding and extraction and image restoration are established as a unified task. And a dual optimization strategy is designed to resist loss and a dynamic joint training strategy, so as to achieve ideal balance among image quality, copyright protection, privacy protection and image recovery capability. Experimental results show that the method provided by the invention can ensure that the authorized DNN classifier recovers the protected image to perform accurate classification and identification when needed, and meanwhile, excellent privacy and copyright protection capability is also provided.

The invention discloses an end-to-end image recovery method and system based on image-text feature mapping and a medium, and relates to the technical field of image processing.The method comprises the steps that a sample set comprising degraded and clean images is called, and a four-layer feature space is established through an image-text feature mapping mechanism; analyzing the degradation features by adopting an isometric tight frame, constructing a prompt vector set, and guiding a feature space to carry out adaptive dynamic prompt fusion to form a dynamic prompt vector set; a first model is established through image recovery loss function iterative training, then an AdamW optimizer is used for gradient descent optimization to obtain a second model, and finally image recovery processing is executed. The technical problem that an existing image restoration method is unstable in restoration effect and poor in adaptability in the multi-degradation scene is solved, and the technical effect that the image restoration precision and adaptability in the multi-degradation scene are improved by introducing a dynamic prompt generation and hierarchical fusion mechanism is achieved.

The invention provides an underwater optical image real-time enhancement method, system and device and a storage medium, and relates to the technical field of image processing and recognition. An isomorphic multi-stage image enhancement network is constructed, the image enhancement network comprises four stages, four branches with different feature scales are obtained through down-sampling operation in each stage, and after each branch is connected with a corresponding star convolution module for feature extraction, the features are input into a multi-scale fusion module; after fusion, after extraction of a pixel attention mechanism module, a convolutional layer is spliced to output an enhanced image, progressive enhancement is realized through a cross-stage feature feedback mechanism, the enhanced image and features output by the later stage and the previous stage are used as input, underwater image recovery is performed, and multi-scale feature extraction is adopted to obtain an underwater image. The calculation complexity is remarkably reduced, the network degradation phenomenon caused by multi-stage training is avoided, and the reliability of efficient detection and maintenance of the hydropower station is improved.

The invention discloses a deep learning model remote sensing image fusion method based on dense residual errors, and belongs to the field of image fusion, and the method comprises the steps: obtaining a Gaofen-6 remote sensing image training data set, carrying out the preprocessing of the Gaofen-6 remote sensing image training data set, obtaining a Transform-based basic module, and obtaining a dense residual error-based image fusion module. Performing model training by using the preprocessed training data set; the method comprises the following steps: acquiring a Gaofen-6 remote sensing image test data set, constructing an image recovery module, constructing a loss function optimization generation process, and finally testing and evaluating a generated high-resolution multispectral image based on a trained deep learning model; compared with results of different fusion methods, the deep learning model remote sensing image fusion method based on the dense residual has excellent comprehensive performance on a high-resolution No.6 test data set, and the generated fusion image presents stronger richness in the aspects of spatial details and texture features; and a remarkable advantage is obtained on the retention of the spectral information.

The invention relates to the technical field of image processing, and discloses an H.265 coded video packet loss image recovery method based on machine learning, which comprises the following steps: acquiring packet loss characteristics of a receiving end at the current moment, inputting a packet loss prediction model pre-constructed based on characteristic dimension expansion, and outputting a packet loss characteristic prediction value at the next moment; determining whether the receiving end sends key frame request information to the sending end or not based on a comparison strategy of different thresholds and packet loss feature predicted values under different network data, so as to obtain the key frame at the current moment for continuing decoding; and if recovery cannot be realized through the key frame request, introducing a packet loss recovery mechanism of intra-frame and inter-frame prediction for different lost image frame types, and performing image recovery of the lost area by using different packet loss image recovery strategies. According to the method, a complete technical chain from prediction, decision making to repairing is constructed, and the modern video coding standard and an intelligent learning mechanism are deeply combined, so that active sensing and accurate repairing of the video packet loss are realized.

The invention belongs to the field of image recovery of computer vision, and discloses a high-resolution image moire removing method, system and device and a medium, the method adopts a U-shaped multi-stage encoder-decoder structure, and aims at solving the problem of moire multi-band distribution; according to the method, feature pyramids of the same semantic level are constructed, cavity residual dense modules are integrated on scale branches of all layers of the feature pyramids, so that multi-scale feature extraction and moire texture removal of the same semantic level are achieved, and multi-level residual dense connection and cavity convolution are combined; performing dynamic fusion on the extracted different scale features of the same semantic level through an enhanced attention gate, and enhancing feature fusion by replacing common convolution with grouped convolution and introducing an efficient channel attention module; a joint loss function of pixel loss, perception loss and color loss is constructed to optimize model training, and a depth supervision strategy is introduced to enhance the training stability.

The invention discloses a ground penetrating radar high-quality imaging method based on an image recovery diffusion model, and the method comprises the steps: constructing a simulation image through an open source simulation tool gprMax based on a finite difference time domain method (FDTD), and constructing a contrast high-frequency clutter-free and low-frequency clutter data set through preprocessing and fusing actual measurement clutter simulation; a double-layer routing attention mechanism is introduced on a basic model to enhance association between features, conditional information is fully utilized, discrete wavelet transform is used to effectively separate low-frequency and high-frequency information, information loss is reduced, and the high-frequency information is enhanced through an adaptive wavelet transform high-frequency enhancement module. According to the method, good improvement is achieved on a synthetic data set, acceptable effects are achieved on multiple evaluation indexes including root mean square error (MSE), peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), perceptual image similarity (LPIPS) and depth image structure and texture similarity (DISTS), and a certain underground target structure can also be recovered in actual measurement data.

The invention belongs to the technical field of image processing, and particularly relates to an efficient compressed image artifact removal method based on multi-feature fusion, which comprises the following steps of: preparing data; constructing a shallow feature extraction module; constructing a multi-scale feature extraction module; constructing an image restoration module; constructing a loss function L; and moving the constructed network model to a GPU for training, optimizing the image recovery network by adopting an Adam optimizer, calculating a loss function and then reversely propagating the loss function to the network for optimization, stopping training when the loss function converges, and after the training is completed, storing a model.pth weight file for subsequent test use. The multi-scale feature extraction module can capture artifact features of different scales through cascade design of a recursive residual unit (RRU) in combination with residual connection and multi-scale feature multiplexing, and the characterization capability of the model for complex artifacts is enhanced. In addition, the recursive structure reduces the calculation complexity through parameter sharing, and improves the model efficiency.

According to the degraded image restoration processing method applied to liquid crystal display, on one hand, an integrated image restoration model, namely a Smart-IR model, is provided, and compared with an existing method, the calculation efficiency is remarkably improved on the aspect of achieving multiple tasks of integrated image restoration; and on the other hand, by designing a novel hybrid expert layer, expert models with different complexities can be dynamically activated to process the image through a complexity sensing router according to the requirement of the input content, and fusion of extracting global features and local features at the same time is realized in a unified architecture for the first time.

The application discloses an image snow removal method based on a Transformer modeling and multi-scale dynamic filtering, and comprises the following steps: a data set containing a snow scene image and a corresponding snow-free image is established; an image snow removal network fusing global Transformer modeling and multi-scale dynamic filtering is constructed, and the image snow removal network is denoted as TranFusionNet; the TranFusionNet is trained by using the data set until a preset loss function converges; and a to-be-removed snow image is processed by using the trained image snow removal network to obtain a snow removal result. The application realizes deep fusion of global dependence modeling and local detail enhancement, achieves a good balance between structure consistency maintenance and detail recovery, can effectively remove complex snow particle interference, and reconstructs a clear and natural visual image, thereby providing an efficient solution for the image recovery field.

The invention discloses an image correction and paper identification method and system, and the method comprises the steps: obtaining at least two frames of original images with adjacent shooting time, carrying out the preprocessing of the original images, and obtaining a preprocessed image; wherein the original image is a reflection imaging image; the initial correction module is used for performing initial correction on the preprocessed image to obtain a first corrected image; the linkage correction module is used for linking the space information and the time information of the first correction image and adaptively performing secondary correction on the first correction image to obtain a second correction image; and the image restoration module is used for performing perspective restoration on the original image based on the second corrected image to obtain a restored paper image. According to the method, the defects in the prior art are comprehensively overcome from the four dimensions of function integration, environment adaptability, terminal adaptability and precision guarantee, a technical scheme which is efficient, low in cost and easy to fall to the ground is provided for image processing of intelligent learning equipment, and the method has remarkable technical value and application prospects.

The invention belongs to the technical field of file repair and protection, and relates to a mildew spot masking and image recovery method and application for a mildewed black-and-white photographic negative film, and the method comprises the following steps: S1, carrying out dust blowing, cleaning and airing pretreatment on the mildewed black-and-white photographic negative film; s2, laying the pretreated mildewed black-and-white photographic film on a glass plate, and then dripping methyl silicone oil on the surface of one side of the mildewed black-and-white photographic film; turning over the mildewed black-and-white photographic film, and dripping methyl silicone oil on the surface of the other side of the mildewed black-and-white photographic film; and covering a layer of glass plate on the mildewed black-and-white photographic film, and standing to complete mildewed spot masking and image recovery. According to the method, the mildewed black-and-white photographic negative film is preprocessed, then the methyl silicone oil is dropwise added to the mildewed black-and-white photographic negative film, the biocompatibility is good, the excellent masking effect on mildew spots is achieved, the image definition is ensured, and the image is recovered; and the safety is good.

The invention is suitable for the technical field of computer application, and provides a one-dimensional code image correction method and device, electronic equipment and a computer readable storage medium, and the method comprises the steps: inputting a to-be-corrected initial one-dimensional code image into an encoder of a preset self-correction neural network, and generating an initial feature map corresponding to the initial one-dimensional code image; inputting the initial feature map into an attitude prediction module of a preset self-correcting neural network, and generating a transformation parameter corresponding to the initial one-dimensional code image; and inputting the initial feature map and the transformation parameters into a decoder of a preset self-correction neural network, and generating a corrected target one-dimensional code image corresponding to the initial one-dimensional code image. Therefore, the initial feature map and the transformation parameters of the one-dimensional code image to be corrected are generated through the preset self-correction neural network, then the one-dimensional code image is corrected according to the initial feature map and the transformation parameters, and the image quality and geometric deformation of the one-dimensional code image are recovered, so that the efficiency and accuracy of one-dimensional code image recovery are improved.