346 results about "Image domain" patented technology

The invention discloses a deep forgery detection method based on a visual language model, and relates to the field of image forensics. The deep forgery detection method based on the visual language model aims to combine multi-source information to improve the discrimination capability of the model on a real image and a generated image. The method comprises the following steps: firstly, extracting image features through an image encoder of a pre-trained CLIP model; meanwhile, a frequency domain enhanced counterfeit perception adapter is embedded in the image encoder to mine potential anomalies of counterfeit images in the image domain and the frequency domain. Secondly, a manual feature extraction module is provided, discriminative low-dimensional features are extracted from the four aspects of the edge, the texture, the frequency and the symmetry of the image, and the discriminative low-dimensional features are used as auxiliary information input in the forgery detection process, so that the robustness and the interpretability of the model are improved; meanwhile, the text cue words are converted into feature vectors through a text encoder of a pre-training CLIP model; and finally, the model predicts a forgery score by calculating the cosine similarity between the image features and the text features so as to realize the discrimination of the authenticity of the image. According to the method, the problem that the detection capability of the model on the cross-dataset is insufficient is effectively improved.

The invention relates to an underwater image enhancement method based on wavelet Mama, which aims at the problems of color shift, low contrast ratio and fuzzy details of an underwater image, extracts shallow layer features of an underwater low-quality image, inputs the shallow layer features into a multi-scale coding network, and performs joint enhancement on low-frequency color information and high-frequency detail features by using a wavelet Mama unit. Global semantic features are obtained by combining down-sampling layer-by-layer compression, and global modeling of color offset correction and contrast enhancement is completed; the spatial resolution is recovered through up-sampling, and reconstruction and enhancement of texture details and color information are realized in combination with jump connection and a wavelet Mama unit; and finally, the features are mapped to an image domain and fused with input image residual errors, and an enhanced underwater image with natural color, clear texture and balanced contrast is generated. According to the method, frequency domain-space domain joint feature modeling is realized through the wavelet Mama unit, and the color authenticity, the structural definition and the detail perceptibility of the underwater image are remarkably improved.

The invention relates to the technical field of constructional engineering, and discloses a concrete crack intelligent identification and analysis platform based on image and point cloud fusion, the platform operates a concrete crack intelligent identification and analysis method, and the method comprises the following steps: S1, synchronously collecting image data and point cloud data of a concrete structure in the same scene; s2, establishing a unified world coordinate system and generating a depth map corresponding to the image; s3, generating image domain crack candidates; s4, generating a depth domain crack candidate; s5, performing weighted fusion on the image domain crack candidate and the depth domain crack candidate to generate a fusion crack response; s6, extracting a crack skeleton; s7, obtaining a crack three-dimensional model; and S8, selecting an optimal view angle to trigger re-acquisition of the crack area. Through a closed-loop feedback mechanism, an optimal view angle is selected for re-acquisition by calculating a comprehensive utility value after preliminary acquisition, so that information insufficiency caused by illumination, angle or sparse data is effectively made up.

The invention relates to the technical field of computer vision and artificial intelligence, and discloses a computer vision-based hundred-million-pixel panoramic situation awareness method and system, and the method comprises the steps: synchronously collecting original local field-of-view images through multiple cameras; independently executing target detection and semantic segmentation in an original image domain; constructing local-to-global coordinate mapping based on the calibration parameters; projecting the target features to a global coordinate system and detecting a cross-view-field target; extracting multi-view-field texture, edge and color features, and performing weighted fusion according to a visible area; according to the method, through identification preposition and semantic level feature fusion, geometric splicing distortion is avoided, the cross-boundary identification precision is improved, the calculation load is reduced, target continuous tracking and situation real-time output in a high-density scene are realized, and the method has high engineering suitability and industrial popularization value.

The invention relates to the technical field of image classification, and discloses a hyperspectral image domain generalization classification method, system and device and a medium. The method comprises the following steps: acquiring a plurality of hyperspectral images of different ground feature types; obtaining a mean value and a variance of each hyperspectral image in a channel dimension, performing random disruption, and determining a spectral variation parameter of the hyperspectral image according to the mean value and the variance before and after random disruption so as to generate a corresponding spectral variation image; separating the center and the background of each hyperspectral image to obtain respective center image and background image, randomly disorganizing the center image and the background image, and generating a corresponding spatial variation image by combining the disorganized center image and background image of each hyperspectral image; a hyperspectral image classification model is obtained by training an enhanced hyperspectral image obtained by fusing a plurality of corresponding spectral variation images and spatial variation images, so that ground feature classification is performed on a to-be-classified hyperspectral image, and the domain generalization performance of the hyperspectral image classification model is improved.

The invention provides a spectrum self-attention and cloud mask guided remote sensing image cross-modal cloud detection method. According to the method, the spectral self-attention sub-network in the remote sensing image cross-modal cloud detection network is constructed, and the dependency relationship between different spectral bands of the remote sensing image is effectively mined and utilized, so that the recognition accuracy of cloud region features is improved. According to the method, cross-modal migration from the source domain image to the target domain image is realized by using the migration sub-network of the unsupervised image domain in the remote sensing image cross-modal cloud detection network, and the multi-spectral image with the target domain features is generated, so that the defect of the source domain image in spectral information is overcome, the false detection and omission ratio is effectively reduced, and the detection efficiency is improved. And the robustness of cloud detection of the model in a complex scene is enhanced.

The invention discloses a sparse view angle 3D-DSA reconstruction method based on a three-dimensional Poisson generative model. The method comprises the following steps: obtaining pairing data of a sparse view angle 2D-DSA projection drawing and a 3D-DSA reconstruction image; extracting features of a projection image by using a projection domain encoder, then converting features of two-dimensional projection into a three-dimensional image domain according to a geometrical relationship of the cone beam CT, and then obtaining a prior image by using an image decoder; the method comprises the following steps: constructing a three-dimensional Poisson generation model, adding noise to a three-dimensional image patch in a training stage to obtain a disturbance image, outputting a network reconstruction image by taking a prior image as a condition and the three-dimensional image patch before noise addition as a target image, and calculating loss of the output image and the target image to update network parameters; the mean square error loss and the mean square error loss of the maximum intensity projection images of the three orthogonal planes are used during loss calculation; in the sampling stage, random noise is used as input, a prior image is used as a condition, noise of a noise image is continuously denoised within a limited step length, and finally a reconstructed 3D-DSA image is obtained.

The invention provides a PCB surface defect detection method and system based on double-layer SAM model collaboration. The method comprises the steps that industrial image domain features and image block features of a to-be-detected PCB image are acquired; performing global semantic segmentation on the PCB image to be detected by adopting an upstream SAM model, extracting a plurality of semantic masks, and representing the semantic masks as weighted semantic mask features; on the basis of the image block features and the weighted semantic mask features, calculating the Euclidean distance between the to-be-detected PCB image and a core memory bank constructed on the basis of the normal PCB image, and obtaining a multi-level anomaly score; fusing the multi-level anomaly scores to obtain a rough anomaly score graph; a downstream SAM model is adopted, the rough anomaly score graph is used as a prompt, and an effective segmentation area mask is obtained in combination with a normal PCB structure learned by the upstream SAM model; and based on the effective segmentation region mask, pixel-level abnormal region refinement is performed on the rough abnormal score map to obtain a fine abnormal score map for category judgment and positioning of defect detection. According to the invention, high-precision defect detection in a small sample scene is realized.

The invention discloses an absolute quantitative correction method and device for medical imaging equipment, and relates to the technical field of nuclear medical imaging equipment correction. When the method is executed, the actual activity concentration of the calibration die body injected with the first known tracer activity serves as the first activity concentration; then, the calibration die body injected with the first known tracer activity is collected in medical imaging equipment, and the activity concentration in a first image domain obtained through calculation serves as second activity concentration; and finally, calculating a correction factor based on the first activity concentration and the second activity concentration, wherein the correction factor is used for correcting absolute quantification of the medical imaging equipment. Therefore, the correction factor is calculated by comparing the activity concentration calculated by the medical imaging equipment with the actual activity concentration of the calibration die body, so that the medical imaging equipment can accurately adjust the measurement result according to the correction factor during subsequent absolute quantitative analysis; the effect of improving the absolute quantification accuracy of the medical imaging equipment is achieved.

The invention discloses a medical MRI image denoising method, device, system and equipment, a medium and a product, and relates to the technical field of image enhancement. The method comprises the following steps: firstly, converting a medical MRI image signal into an image domain to obtain three-dimensional image data, then selecting three-dimensional image sub-blocks, searching M three-dimensional image similar sub-blocks which are most similar in a predefined neighborhood, and then carrying out vectorization straightening processing and superposition on the sub-blocks to obtain an original matrix Y; then assuming that an original matrix Y is equal to X + N + S and solving the minimization objective function to obtain a de-noising matrix X, reconstructing according to the de-noising matrix X to obtain new sub-blocks corresponding to the sub-blocks, and replacing the new and old sub-blocks to obtain new three-dimensional image data subjected to image de-noising. Therefore, the problem that the denoised image is blurred when the prior art is applied to MRI denoising can be solved, the quality of the medical MRI image is improved, and subsequent image analysis is facilitated.

The invention discloses a multi-contrast magnetic resonance image reconstruction method and device based on detail contour feature perception. The method comprises the following steps: acquiring a target modal initial image and an auxiliary modal initial image; constructing an iterative network formed by alternately cascading image domain reconstruction units and data consistency layers, wherein each image domain reconstruction unit comprises an encoder and a decoder; in the first iteration, target modal initial images and auxiliary modal initial images are spliced and then input, an encoder extracts shared features firstly, then global contour features and high-frequency detail features are separated in parallel, and potential features are obtained through collaborative fusion; the decoder takes the potential features as input and outputs an image domain preliminary reconstruction result; the data consistency layer transforms the preliminary result into a k space, performs consistency correction on the preliminary result and a target modal sampling point, and then inversely transforms the preliminary result back to an image domain to complete one iteration; and splicing the current output and the auxiliary modal initial image again, inputting the spliced image into a next round of iteration, and repeating the process until a preset number of times to obtain a final target modal magnetic resonance image.

The invention relates to a cone beam CT imaging scanning parameter determination method and imaging equipment, and the method comprises the steps: designing an optimization model for a microgravity environment, carrying out the optimization processing of the cone beam CT imaging scanning parameters based on a pre-constructed optimization model with the maximum imaging performance as a target, and obtaining the optimal parameters of the cone beam CT imaging. Wherein optimization problem modeling and solving are sequentially carried out in a projection domain and an image domain so as to obtain target scanning parameters meeting constraint conditions, and according to the technical scheme of the invention, aiming at factors such as scanning space and energy consumption in space, requirements of high spatial resolution, compact physical size of equipment, high image quality and low scanning dose are met, and the method and the device have the advantages of being high in efficiency and high in reliability. The method is applied to cone beam CT imaging in the space microgravity environment, and the comprehensive requirements of scientific research, health guarantee and medical service in the space environment are met.

The invention discloses a low-dose CT reconstruction method and device, and relates to the technical field of image processing, and the method comprises the steps: obtaining a low-dose CT image; the trained deep learning network is adopted to process the low-dose CT image in a projection domain, a chordal graph domain and an image domain; in the projection domain, processing the low-dose CT image to obtain updated projection data, in the chordal graph domain, processing the updated projection data to obtain updated chordal graph data, and in the image domain, processing the updated chordal graph data to obtain a reconstructed low-dose CT image; wherein the trained deep learning network takes data of a preset category as a training data set, the initial deep learning network is trained, intermediate supervision is performed in the training process, and the trained deep learning network is finely adjusted to obtain the deep learning network. According to the invention, good reconstruction of the low-dose CT image can be realized.

The invention discloses an unsupervised image conversion imaging method based on the Schrodinger bridge theory, and the method comprises the following steps: 1, constructing an image domain-domain conversion frame based on the Schrodinger bridge theory, simulating a smooth evolution path from a source domain image to a target domain image through a time condition generator, and forming antagonism training in combination with a discriminator; 2, integrating a saliency content guide constraint, a global feature consistency constraint and a contrast learning constraint in the conversion framework so as to enhance semantic content retention and detail generation capability; 3, establishing a composite loss function, and carrying out weighted combination on Schrodinger bridge path loss, adversarial loss and each auxiliary constraint loss for guiding model optimization; and 4, training a time condition generator and a discriminator through an optimization algorithm, and carrying out stable and high-fidelity target domain conversion on the source domain image by utilizing the generator after training is completed. According to the method, the stability of model training and the quality and fidelity of the generated image are remarkably improved.

The invention discloses an HDR video reconstruction method based on brightness alignment, and the method comprises the steps: carrying out the gamma correction of continuous frames of an input LDR video, generating an HDR image domain, and splicing the HDR image domain with an original frame to form an input tensor; constructing a brightness alignment network model, and generating brightness alignment features through a brightness attention module; generating detail features through a detail synthesis module; performing dynamic weighted fusion on the brightness alignment features and the detail features through an adaptive mixing layer, and performing up-sampling to obtain final alignment features; and finally, generating an HDR video frame by fusing the final alignment features. Through collaborative optimization of the brightness attention mechanism and the time domain alignment module, the problem of brightness inconsistency in a motion scene is effectively solved, and the HDR reconstruction quality is remarkably improved.

The invention provides a medical magnetic resonance image reconstruction method and system, and belongs to the technical field of image reconstruction, and the method comprises the steps: obtaining sampling coding and under-sampling k space data; processing the under-sampled k space data through inverse Fourier transform, and converting the k space data into an image domain to obtain under-sampled image data with blurring or artifacts; carrying out preliminary restoration on the undersampled image data based on sampling coding, further applying data consistency operation on the image to obtain a rough image, and taking the rough image as an image condition vector after underspace coding; acquiring a text serving as a cue word, inputting the text into a text encoder, and encoding the text into a high-dimensional semantic embedding vector by the text encoder; and inputting the high-dimensional semantic embedding vector and the image condition vector into a reconstruction model based on the correction flow to predict a full-sampling MRI image, and generating a final reconstructed MRI image.

The invention discloses a composite material defect modeling method based on physical modeling generation and meta-learning migration, which comprises the following steps: S10, starting from a forming mechanism of a fatigue crack of a composite material, establishing a morphological function of a crack morphological simulation model based on a mechanical principle for simulating a spatial evolution process of a defect; s20, embedding the morphological function as a regular term into a generator loss function of a generative adversarial network, and generating a high-simulation pseudo-defect image; s30, introducing a transfer learning mechanism, constructing a model-irrelevant meta learning training strategy, and realizing rapid learning of the model on a new task through a two-layer nested optimization strategy; s40, introducing a domain adaptive residual module in the model training process to enhance the feature alignment capability of a cross-batch image domain; and S50, training the model by using a real sample and a synthetic defect sample in a mixed manner.

Techniques are disclosed relating to exchange of images in networked computing applications. In particular, the disclosure relates to exchange of gain curves that are used to represent imaging and / or video in such applications. A gain curve may define a mathematical transformation that relates values from a source image domain to a destination image domain. The image and its associated gain curve(s) may be published to destination devices for consumption. When a destination device consumes the image, the destination device may apply a transform to source image content according to the gain curve(s) published with the image. For example, the destination device may apply a gain curve to an associated image directly, or it may derive another transform from the gain curve and additional information known to the destination device.

Disclosed are methods, systems, and other implementations, including a unified complex-valued deep learning framework (AFT-Net), which determines the k-space domain to image domain mapping for MRI reconstruction and allows incorporation of existing deep learning models. Embodiments include a computer-implemented method for reconstructing images that includes obtaining resonance (MR) k-space data resulting from a scan performed by an MRI scanner on tissue of a patient, with the MR k-space data including complex-valued data, and processing, by a complex-valued machine learning image reconstruction system, the complex-valued data of the MR k-space data to generate image data representing features of the MR k-space data. The processing may include performing data filtering operations, by one or more machine learning filter blocks implemented according to a CU-Net architecture realized using one or more convolutional neural networks (CNN) configured for complex data processing, on data that is based on the k-space data.

The invention discloses a method for detecting the surface roughness of a perspective optical lens, and relates to the technical field of optical detection, and the method comprises the following steps: constructing an optical-image cross-domain feature migration model, so as to establish a mapping relation between the optical characteristics of the surface of the lens and the noise characteristics of an image domain; analyzing the adaptive chaotic mapping characteristics of noise associated with the roughness in the image domain, and extracting chaotic characteristic parameters reflecting the roughness; according to the method, by constructing an optical-image cross-domain feature migration model and combining a surface microdefect correction factor and a lens material constraint layer, noise modeling and an actual optical physical process are closely combined; the roughness correlation noise is analyzed through adaptive chaotic mapping and is converted into effective features, the noise feature utilization rate is increased, and information loss caused by blind denoising is avoided; by means of a double-closed-loop optimization mechanism, precision feedback is achieved, the detection precision is improved, nanoscale roughness changes can be recognized, the self-calibration capability is achieved, and the anti-interference performance is high.

The invention discloses a brain MRI super-resolution reconstruction method based on a learnable weight linear accumulation strategy, and relates to the technical field of magnetic resonance imaging image super-resolution reconstruction. According to the method, the Swin-WKV model is built, the model is based on a Swin Transform and RWKV architecture Transform-like model, high-quality reconstruction of the brain MRI image can be achieved with quite low memory consumption, a mixed loss function is provided, image domain difference and frequency domain difference are combined, and the model is guided to restore frequency spectrum and pixel-level features of a reference image as much as possible.

The invention belongs to the technical field of cross-seasonal remote sensing image change detection, and particularly relates to a cross-seasonal remote sensing image domain adaptive change detection method based on an improved CycleGAN. According to the method, through segmentation of all models and boundary constraint multi-scale super-pixel segmentation, the source domain image and the target domain image are kept consistent in object-level structure, the problems of ground feature breakage, texture dislocation and sample alignment irregularity caused by seasonal differences are effectively reduced, pre-training ViT-B high-dimensional semantic features and a density clustering algorithm are introduced, and the accuracy and the robustness of the method are improved. Noise samples such as mixed ground features, shadows and illumination anomalies in a complex remote sensing scene can be automatically recognized, a source domain training set is made to be purer, the stability of CycleGAN style migration training is improved, a generator fuses a multi-scale residual block and a self-attention module, a migrated image is made to be close to a target domain in the aspects of color, texture and seasonal features, and the image migration efficiency is improved. And meanwhile, the boundary and the structure of the ground object are kept not to be damaged through semantic consistency constraint, so that the problem of false change in cross-seasonal change detection is fundamentally solved.

The invention discloses a tactile image domain migration method and device based on a multi-scale generative adversarial network, and the method comprises the steps: constructing the multi-scale generative adversarial network, and achieving the domain migration between a simulation tactile image and a real tactile image. The generator takes U-Net as a trunk, introduces a multi-scale stacking module, a multi-stage attention gate mechanism and a channel-space attention module, and improves the reconstruction capability of simulation image textures, illumination and contact areas. And the discriminator adopts a multi-scale discrimination structure to realize the discrimination of image authenticity and detail consistency. Through joint training of joint adversarial loss, loop consistency loss, contact area consistency loss, illumination balance loss and frequency domain loss functions, it is ensured that an output image is consistent with a real image in visual and semantic levels. The method can be widely applied to a robot vision-touch fusion perception task, and the migration performance and robustness of the perception model are remarkably improved under the condition of non-paired data.

The invention belongs to the technical field of CT images, and particularly relates to a double-domain CT metal artifact removal method based on deep learning. Comprising the following steps: 1) acquiring CT images of different scanning parts, and processing the CT images to obtain simulated CT images containing metal artifacts; 2) correcting and simulating the CT image containing the metal artifact through a traditional nonlinear interpolation algorithm to obtain an image after nonlinear interpolation correction, and preprocessing the image; 3) constructing a metal artifact removal model based on a deep convolutional neural network, and training the metal artifact removal model; 4) reasoning the preprocessed image by using the trained model to obtain a metal artifact-removed image, and counting the training precision; and 5) carrying out post-processing on the metal artifact-removed image, and carrying out reverse normalization to an original CT magnitude. The method not only performs metal artifact correction in the projection domain, but also performs metal artifact correction in the image domain, so that the metal artifact removal precision is ensured, and the model convergence can be accelerated.

The invention provides an SAR two-dimensional deception jamming resisting jammer positioning method and device, and belongs to the field of electronic support system synthetic aperture radar countermeasure, and the method comprises the steps: building a single-baseline interference SAR deception jamming resisting geometric model; carrying out primary observation imaging by using a single-baseline interference SAR; positioning a false target by using the particularity of the interference phase of the interference signal, and inverting the distance direction position of the jammer; establishing a mathematical relationship between the false target position deviation and the jammer azimuth position; the position deviation of a false target in the two SAR images is obtained through image domain comparison and measurement, and the azimuth position of the jammer is inverted in combination with the obtained range position of the jammer and other information, so that the two-dimensional position of the jammer is determined. According to the invention, jammer positioning can be carried out on all types of deception jamming including range deception jamming, azimuth deception jamming and two-dimensional deception jamming only through two signal channels and one-time observation imaging.

The invention provides a low-count PET image quality enhancement method and system based on a fusion multi-input loop consistent generative adversarial network. The method comprises the steps that a PET image set is acquired, the PET image set comprises a plurality of training sample pairs, and each training sample pair comprises an SCPET image sample and a corresponding LCPET image sample; constructing a fusion multi-input loop consistent generative adversarial network, including expanding inputs of a generator and a discriminator of an LCPET image domain into a plurality of input channels, expanding outputs of a generator of an SCPET image domain into a plurality of output channels, one input channel or output channel corresponding to one PET image, and counting proportions of the plurality of PET images being different; a total loss function is designed, wherein the total loss function comprises perception loss, adversarial loss and period consistency loss; based on the total loss function, training the network by using the image set to obtain a trained image quality enhancement model; and inputting the low count PET image to be enhanced into the trained generator of the LCPET image domain to obtain an enhanced PET image.

The application discloses a vocal cord leukoplakia pathological detection method and system based on a laryngeal endoscope image, a device and a medium, and belongs to the field of data management. The method is as follows: inputting the acquired laryngeal endoscope image into a preset pathological semantic field model, performing feature extraction on the laryngeal endoscope image through the pathological semantic field model to obtain a feature map; performing coordinate mapping on coordinate points of the feature map through the pathological semantic field model, generating a pathological semantic vector corresponding to each coordinate point, and constructing a continuous pathological semantic field according to the pathological semantic vector; deploying a perception particle swarm in the feature image domain, and performing particle iterative motion according to the pathological semantic vector of the deployment position until a lesion contour is generated by meeting a convergence condition, and outputting a vocal cord leukoplakia pathological detection result according to the lesion contour. Therefore, by implementing the application, accurate detection of vocal cord leukoplakia pathology can be realized, and the accuracy and reliability of laryngeal precancerous lesion diagnosis can be improved.

The invention discloses a CBCT (cone beam computed tomography) metal artifact removal method and system based on projection domain metal identification, which skip the traditional image domain segmentation and orthographic projection process, directly extract key geometric features of a metal area in an original projection image, and match with a pre-established metal model library to obtain a metal artifact removal result. The high-precision identification and spatial attitude estimation of the metal object are realized, the processing flow is obviously simplified, and the identification stability and the artifact repair effect are improved. In order to solve the problems of shielding and overlapping possibly occurring in a multi-metal structure, a step-by-step stripping type recognition mechanism is provided, multi-target interference is effectively avoided through round-by-round recognition, fitting and image updating, and the accuracy and integrity of model matching are ensured.

In implementation of techniques for translating images based on semantic information, a computing device implements a translation system to receive an input image in a first format, encoded semantic information describing a domain of the input image, and a selection of a second format. The translation system decodes the encoded semantic information using a machine learning model. The translation system then generates an output image in the second format by translating the input image from the first format to the second format using the machine learning model, the machine learning model guided by the decoded semantic information. The translation system then displays the output image in the second format in a user interface.