131 results about "Image recovery" patented technology

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 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 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 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 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.

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.

The application discloses a global polarization image recovery method without background prior, comprising the following steps: S1, different angle polarization images are obtained by rotating a polarization mirror in front of a camera; S2, a polarization imaging proxy model is established by fusing backscattering polarization degree and a polarization angle; S3, under the constraint of EME, an original image is segmented and sampled, and local parameter optimal values of the model are solved; S4, a robust polynomial curved surface fitting method is designed based on a least square method, and global parameters of variables in the model are obtained; S5, according to the relationship between model parameters and backscattering, a method for solving an infinite far atmospheric light value based on model parameters is proposed; and S6, based on the polarization imaging proxy model, the global model parameters obtained in S4 and the infinite far atmospheric light value solved in S6 are substituted into the proxy model in S2, and a clear non-fog image is inversed.

The application discloses a kind of generation binary space constraint X-ray coherent diffraction image recovery method.This application is used to realize from the coherent X-ray diffraction image of acquisition recovery out sample image to be measured, using the method of deep learning with good predictive ability to generate corresponding space constraint support to X-ray coherent diffraction image, then it is carried out HIO phase iteration, the application can make up the condition that space constraint is not accurate in traditional HIO iterative method, and then can be more quickly converged, higher quality is recovered;Compared with directly using deep learning image recovery method, the result of the application is more accurate, there is no pixel error situation, can realize through small amount of iteration recovery better result, improve the robustness of X-ray diffraction image recovery.

The application discloses an image denoising method based on a cooperative non-local context network, and steps are as follows: 1, pre-processing the data set to construct input sample data; 2, constructing a cooperative non-local context network model, including a shallow feature extraction module, a deep feature extraction module and an image reconstruction module; 3, training the network, adjusting the network parameters and obtaining an optimal model. The application fully excavates the global dependence relationship in the image by combining the pixel-level non-local feature and the image block-level non-local feature, improves the quality of image recovery, solves the problem that the existing convolutional neural network cannot capture the non-local context dependence relationship and the effect is poor in actual application, so that the image denoising task can be used, and the texture detail information of the image is well recovered.

The invention discloses a phase difference wavefront-image estimation method based on depth image prior. The method comprises the following steps: firstly, constructing a forward physical model of an incoherent imaging system, and generating an observation image with out-of-focus aberration by introducing phase difference; and then using a depth image prior network to jointly optimize image domain loss and wavefront domain loss under the condition of no external training data by taking the consistency of an observation image and a model generation image as a constraint so as to simultaneously obtain a high-quality recovered image and accurate wavefront estimation. The method provided by the invention can realize accurate wavefront estimation and high-quality image recovery under the condition of large aberration under the condition of only needing a small number of acquired images, and has the advantages of strong anti-noise capability, no need of an additional wavefront sensor and low system complexity. The method can be widely applied to fluorescence microscopic imaging and other high-resolution microscopic imaging technologies, and the imaging resolution and the image quality are improved.

The invention discloses an industrial machine vision-oriented strong backlight environment imaging sharpening system and method. The method comprises the following steps: S10, performing optical coding imaging; s20, carrying out improved L-R iterative recovery and first-stage wavelet denoising; s30, carrying out secondary wavelet denoising and fine recovery; and S40, carrying out iterative convergence and output. According to the invention, a specific wavefront coding optical imaging module and an improved L-R image restoration algorithm module are integrated into a complete visual detection system for solving the problem of industrial strong backlight imaging. In the L-R iteration process, a staged denoising step based on wavelet transformation is introduced, and before each iteration, first-level high-threshold wavelet denoising is carried out on a residual error; and in a specific stage in the iteration process, carrying out secondary middle threshold wavelet denoising on the current estimation image.

The invention discloses an image compressed sensing recovery method based on iterative error compensation, and belongs to the field of deep learning. According to the method, on the basis of a sampling and recovery unit of a traditional image compressed sensing method, an adder, a multiplier and a delayer are added, a closed-loop negative feedback structure is formed, image recovery error iterative compensation is carried out, and the image recovery quality is improved. Compared with ten latest image compression sensing algorithms based on deep learning on three standard data sets, the image restoration quality is obviously improved for different sampling rates from 0.01 to 0.50. The maximum increment of the peak signal to noise ratio (PSNR) can reach 4dB, and the maximum increment of the structural similarity (SSIM) can reach 0.03. The method can be applied to any existing image compressed sensing method, and the reconstruction capability is enhanced.

The application discloses a kind of image tampering detection and self-recovery method, device, equipment and storage medium, belong to image detection technical field.The present application obtains image to be detected, and image to be detected is detected and preprocessed, and image to be detected information is obtained;Image to be detected information is detected, and image detection result is obtained;If image detection result is abnormal, image detection result is analyzed, and image tampering information is obtained;According to image tampering information, data processing is carried out, corresponding image restoration data is obtained, and image recovery is automatically carried out according to image restoration data, and tamper-proof image is obtained.The present application detects tampering by image to be detected, to obtain image tampering information, then according to image tampering information and corresponding data processing operation, image restoration data is obtained, and finally restored to not be tampered with image, realizes accurate detection to image tampering, and makes tampered image can be restored to not be tampered with state.

The invention belongs to the field of synthetic aperture radio array imaging detection, and relates to a deep learning-based synthetic aperture radio array rapid imaging method, which comprises the following steps of: processing observation data based on optimization parameter combination and matrix mapping to generate a brightness temperature image training set with frequency domain relevance and high image quality; an imaging neural network model composed of a pre-imaging network and an image recovery network is constructed, and high-dimensional nonlinear mapping among the visibility function, the projection baseline and the brightness temperature image is realized; through preprocessing, data preprocessing and real-time imaging operation, rapid and high-quality imaging of observation data is realized. According to the method, a sun brightness temperature image data set consistent with an actual observation scene is constructed based on the observation data of a circular array solar radio imaging telescope of meridian engineering; an imaging neural network model adapted to different sun brightness temperature characteristics and projection baselines is designed; the imaging speed of the synthetic aperture radio telescope can be obviously improved while high-quality imaging is realized.

The embodiment of the invention discloses an image restoration method and electronic equipment. The method comprises the steps that a target image and a trained image restoration model are acquired, and the target image comprises a first holmium laser exposure area of tissue details to be restored; the target image is input into the image restoration model, a target restoration image including a target restoration area is obtained according to an output result of the image restoration model, and the target restoration area is the first holmium laser exposure area with restored tissue details. According to the technical scheme provided by the embodiment of the invention, the tissue details of the holmium laser exposure area in the image can be recovered.

The invention provides a bimodal image restoration method based on a diffusion model. The bimodal image restoration method comprises the following steps: S1, acquiring a bimodal fuzzy data set; s2, encoding and fusing the multi-modal data; s3, decoding processing is carried out; and S4, submerged space diffusion recovery. The invention aims to solve the problems of low efficiency, poor reconstruction quality and single data source of the existing image reconstruction technology in a complex scene.

The application provides a semantic-based remote sensing image transmission and reconstruction system, method and product, comprising a satellite end and a ground end; the satellite end is configured to process a first remote sensing image collected based on a first processing model, obtain a second remote sensing image and a semantic text used for describing the first remote sensing image, and send the second remote sensing image and the semantic text to the ground end; and the ground end is configured to perform multi-modal fusion reconstruction on the received second remote sensing image and the semantic text based on a second processing model to obtain a third remote sensing image. The application transmits a low-resolution image and its compact text description instead of complete high-resolution data transmission, thereby greatly compressing the transmission data volume, greatly reducing the transmission bandwidth occupation and communication cost, and cooperating with the multi-modal fusion reconstruction of the ground end to realize high-fidelity image recovery, so that the transmission efficiency and reconstruction quality are considered in the bandwidth-limited scene.

The invention discloses an image restoration and enhancement method for ancient tower monitoring. The method comprises the following steps of: 1, selecting an image acquired by field video monitoring of an ancient tower, inputting a degraded image by selecting a public data set containing a typical degradation type image as a training sample of the degraded image, and preliminarily extracting image features through convolution; step 2, inputting the preliminarily extracted image features into an encoder + bottleneck layer to carry out feature extraction at a deeper level, and obtaining deep features; 3, inputting the deep features extracted by the encoder into a decoder for gradual image recovery; and 4, adding a dynamic prompt mechanism to each level of the decoder to realize image recovery. According to the method, various image degradation types can be processed at the same time, and high adaptability is achieved; global and local feature modeling is fused, and the image restoration quality is improved; a lightweight structure is adopted, and the calculation efficiency is high; the image structure is restored to be complete, and subsequent ancient tower inclination analysis is facilitated.

This invention discloses a terahertz SAR imaging method based on total variational and Cauchy combined regularization: The data obtained after range compression and azimuth deskewing of the echo data received by terahertz SAR is used as the observation matrix, the Fourier transform matrix is ​​the coefficient matrix, and the image is the matrix to be recovered. Image recovery is modeled as an inverse problem, introducing Cauchy regularization to represent sparse features and total variational regularization to recover target structural features. An alternating minimization framework is used to solve the problem, obtaining an image estimate. The image estimate is combined with the original echo data to solve for the platform phase error estimate, which is then compensated into the observation matrix. The above steps are repeated to iteratively estimate the desired image and phase error to obtain a high-precision imaging result. This invention also provides a terahertz SAR imaging device based on total variational and Cauchy combined regularization. This invention can obtain high-quality focused images and has good compensation effects for both low-frequency motion errors and high-frequency vibration errors.

The invention relates to the technical field of low-light image processing, and discloses a controllable low-light image recovery system based on multi-modal large language model guidance, which comprises a multi-modal adaptive semantic projector, an encoder, an uncertainty head module and a decoder, the encoder is used for receiving an input image and outputting the input image to the decoder; the multi-modal adaptive semantic projector is used for receiving an input image, a JSON format text blueprint generated by a large language model and output of the encoder, and guiding the decoder to generate a final image; the encoder and the decoder form a U-net framework, the decoder outputs an image restoration result, and an uncertainty head module used for receiving the output of the encoder is arranged between the encoder and the decoder. According to the system, advanced semantic priori generated by a multi-modal large model is introduced, so that the model can obtain the most reasonable and rich-detail content according to the global context in an area where pixel information is completely lost, and the upper limit of image restoration is greatly improved.

The invention provides a defogging and destreaking advanced method and device for an optical remote sensing image, and provides an optimization processing strategy of firstly removing thin cloud and then removing stripes for the common problems of stripe noise and thin cloud shielding in the remote sensing image, and is matched with an improved algorithm. Designing a segmented adaptive window moment matching fringe removal method based on an automatic sliding window, automatically dividing regions through cloud detection, dynamically determining a gray segmentation threshold value and the size of the sliding window, and effectively eliminating non-periodic fringes; and on the other hand, a shallow U-Net structure thin cloud and mist removing network with multi-scale cloud and mist feature fusion is constructed, an on-chip color balance loss function is introduced, and image splicing chromatic aberration is inhibited. According to the method, the image definition and the visual consistency can be remarkably improved, the problem of cloud and mist residue caused by'firstly removing stripes' or the problem of noise amplification caused by'firstly removing cloud and mist 'is avoided, high-efficiency and high-quality remote sensing image restoration is realized while texture details are kept, and the method is suitable for automatic processing of large-size high-resolution remote sensing data.