665 results about "Image prediction" patented technology

SOLUTION: A semi-supervised medical image segmentation method based on a visual language model includes the steps of: obtaining a medical image; inputting an unlabeled image and a text description into a visual language model, and obtaining a text-guided mask based on obtained dense image embedding and text embedding; inputting a labeled image into a student model, and calculating supervised loss by using obtained labeled image prediction; respectively inputting the unlabeled image into the student model and a teacher model to obtain unlabeled image prediction and a pseudo label, merging the text-guided mask with the pseudo label, and calculating semi-supervised loss by using the merged pseudo label and unlabeled image prediction; and performing medical image segmentation by using a trained student model on the basis of the supervised loss and the semi-supervised loss.EFFECT: A target segmentation region can be accurately identified by using advantages of text descriptions.SELECTED DRAWING: Figure 1

Devices and techniques are described for augmented reality virtual makeup try-on. In some examples, first image data representing at least a portion of a human face may be received. A selection of a first virtual makeup asset from a first catalog entry may be received. A first color value and a first finish type of the first virtual makeup asset may be determined. The first color value may be predicted from an image of the first virtual makeup asset in the first catalog entry. The first finish type may be predicted from first text data included in the first catalog entry. A first 3D model of an application of the first virtual makeup asset may be generated based on a 3D mesh of at least the portion of the human face. Second image data may be generated based on the first 3D model and the first image data.

A method and apparatus for training a text-graph model, a device, and a storage medium, relating to the artificial intelligence. The method comprises: on the basis of a training set of graph-text sample pairs, performing iterative training on a model to be trained, to obtain a text-graph model; in a training process: selecting a graph-text sample pair from the training set of graph-text sample pairs, the graph-text sample pair comprising a sample image and a description text, and the sample image comprising at least two objects; obtaining mask images corresponding to the at least two objects and associated object class names, the mask images being used for distinguishing position regions of the objects in the sample image; inputting the sample image and the description text to a model to be trained, to obtain an image prediction noise of the sample image, and inputting at least two mask images and the associated object class names to the model to be trained to obtain object prediction noises respectively associated with the at least two mask images; and constructing a loss function on the basis of the image prediction noise and the object prediction noises, and by using the loss function, adjusting a parameter for the model to be trained.

The invention provides a single particle diffusion quantitative feature prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a target input image corresponding to a target single particle; based on a pre-trained particle trajectory prediction model, according to the target input image, predicting to obtain a particle pseudo trajectory image; on the basis of the particle pseudo-trajectory image, diffusion quantitative characteristics of the target single particle are calculated; wherein the particle trajectory prediction model is obtained by performing training optimization according to a first training sample set formed by the single-particle motion blurred image and the corresponding particle motion trajectory image. According to the method, the actual movement path of the target single particle is predicted from the target input image through the particle trajectory prediction model, and the diffusion quantitative characteristic of the target single particle is calculated based on the actual movement path, so that the diffusion coefficient of a large number of single particles can be rapidly and accurately predicted in a high-mark-density environment, and the phototoxicity is remarkably reduced; diffusion characteristics of different biological particles can be effectively distinguished, and a powerful tool is provided for dynamic research of particles in a diffusion system and living cells.

The invention discloses a soil heavy metal inversion method and system integrating satellite remote sensing and near-end sensing, and the method comprises the steps: collecting a soil sample, and measuring the soil heavy metal content and a soil visible light-near infrared spectrum; obtaining a time sequence multispectral image of a research area, calculating a spectral index, and selecting and screening bare soil pixels through a threshold value to obtain a bare soil image; performing spectrum correction on the bare soil image; obtaining a joint dictionary and a sparse coefficient through sparse representation and dictionary learning, and reconstructing a hyperspectral image of the bare soil image; converting the one-dimensional spectral data into a two-dimensional spectrogram by using continuous wavelet transform, extracting spectral features in combination with a 2D-CNN algorithm, and constructing a soil heavy metal inversion model; and using the trained inversion model to predict the soil heavy metal content of the research area based on the reconstructed hyperspectral image. According to the method, satellite remote sensing and near-end sensing are integrated to obtain a large-scale accurate soil heavy metal content distribution map, deep features are extracted in combination with a 2D-CNN algorithm, and the inversion model precision and model efficiency are improved.

The invention provides an automatic defect labeling method and device, electronic equipment and a readable storage medium, and the method comprises the steps: segmenting a specified defect for a target image based on a first model for an input reference image and an example of a reference image mask, and obtaining a target image prediction mask; and judging whether the prediction mask of the target image belongs to a real defect or not through a multi-layer perceptron, and reserving the part belonging to the real defect, thereby realizing automatic marking of the defect in the target image. Wherein the first model is obtained by adding a feature encoder in a context reference segmentation algorithm DINOV model, and the feature encoder is used for extracting the similarity of defects in the reference image and the target image. According to the method, the defects of the target image can be labeled in different industrial scenes, the problem of background over-killing in defect labeling is reduced, and meanwhile, the time required for subsequent manual defect labeling inspection is shortened.

The invention relates to the technical field of image prediction, and discloses an emotion prediction method and system based on a KAN network, and a storage medium, and the method comprises the steps: collecting a data set, and carrying out the preprocessing of the data set; constructing an emotion prediction model based on a KAN network, training the emotion prediction model by using the training set, and adjusting parameters of the emotion prediction model by using a cross entropy loss function in the training process to obtain a trained emotion prediction model; evaluating the performance of the trained emotion prediction model by using the verification set; and inputting a to-be-predicted image into the trained emotion prediction model, and outputting an emotion prediction result. According to the method, the Kolmogorov-Arnold network is used for replacing a traditional multi-layer perceptron for image sentiment analysis, the KAN network has remarkable advantages in the aspects of complex relation processing and logical reasoning, the sentiment prediction accuracy can be improved, training data are obtained by combining network data collection and a text generation picture model, and the method is high in practicability and high in practicability. And the workload of manual labeling is effectively reduced.

The invention discloses a cancer grading prediction method and device, equipment and a storage medium, and the method comprises the steps: collecting a pathological image of a patient and corresponding grading labeling information, carrying out the preprocessing, and dividing the image into a plurality of image blocks; training a self-supervised learning model by using the image block of each pathological image; clustering the image block coding vectors by using a clustering algorithm, and clustering the image block coding vectors of each pathological image into a plurality of category areas; carrying out feature sampling on the image block coding vectors of each category region, and carrying out feature fusion on the sampled image block coding vectors to obtain image fusion features of each pathological image; training a cancer grading model by using the image fusion features with the category region information of each pathological image, wherein the cancer grading model is used for predicting cancer grading; and applying the trained model to a to-be-analyzed pathological image, and predicting cancer classification. According to the method, cancers can be accurately graded, diseases can be found in time, and a treatment scheme can be formulated.

The invention relates to a multi-mode ultra-short-term photovoltaic power generation power prediction system and method, through setting an image sequence prediction module, historical image features are extracted step by step based on a gating loop algorithm, and compared with other methods, the method is more suitable for processing sequence data, so that more accurate historical motion features can be obtained. In addition, the image sequence prediction module also adopts a method based on a diffusion model to predict a future sky image, and the diffusion model has the characteristics of accurate predicted image and clear generated image compared with other sky image prediction models. Moreover, by arranging a multi-modal prediction module, feature fusion is carried out through a self-attention coding and decoding algorithm, features from different modals can be better fused in a self-attention mode, and meanwhile, a cross-attention layer can integrate historical features and predicted sky image features to obtain a more accurate generated power prediction result.

The invention discloses a distributed photovoltaic cluster power prediction method and device based on multi-modal fusion. The method comprises the following steps: acquiring historical photovoltaic data and historical photovoltaic images of a photovoltaic region to be predicted; analyzing a time sequence relationship in the historical photovoltaic data, extracting photovoltaic time sequence characteristics, and giving a first prediction result in combination with the data time sequence prediction model; extracting spatial features in the historical photovoltaic image, reconstructing the historical photovoltaic image, and giving a second prediction result in combination with the image prediction model; and in combination with a preset fusion weight, fusing the first prediction result and the second prediction result to obtain a target prediction power, and completing power prediction of the distributed photovoltaic cluster, thereby effectively capturing the influence of sudden weather events on photovoltaic power generation, improving the accuracy of conventional cloud picture data when coping with complex and changeable cloud layer motion, and improving the prediction efficiency of the distributed photovoltaic cluster. Therefore, the accuracy of power prediction is improved.

The invention relates to a textile product defect identification method based on improved YOLOv11. The method comprises the following steps: acquiring a textile product defect image data set; performing pretreatment; dividing into a training set and a verification set; the method comprises the following steps: introducing MConv into a YOLOv11 backbone network, adding a CCIAP module behind a C2PSA module, and applying BiFPN in a path aggregation network; performing prediction through YOLO Head to obtain N prediction feature maps; the overall loss of the network is calculated, and network parameters are optimized through back propagation; predicting the verification set image through a network to output AP values of various categories; repeating the above steps to obtain a trained YOLOv11 network; and detecting the test image or video by using the trained detector to obtain a detection result. According to the method, the MConv is introduced into the YOLOv11 network to enlarge the receptive field, the CCIAP module is added behind the C2PSA to improve the feature extraction capability, and the BiFPN is applied to the Neck layer to enhance the feature fusion capability, so that the target detection precision is improved and the real-time detection of textile product flaws is realized under the condition that the reasoning speed is not influenced.

The invention relates to a coastal zone remote sensing observation-oriented Landsat image prediction synthesis method, which comprises the following steps of: acquiring a real image of an adjacent year of a to-be-predicted synthesis image, preprocessing the real image, and constructing time sequence observation; screening time sequence observation according to seasons and cloud cover; removing abnormal observation values for time sequence observation pixel by pixel; dividing an image water body pixel and a land pixel; respectively fitting available observations of the water body pixels and the land pixels through a functional equation, and respectively constructing surface reflectance time sequence observation curves of the water body pixels and the land pixels; solving an undetermined coefficient of the functional equation; and predicting and synthesizing a Landsat image at the corresponding time according to the fitted time sequence observation curve. The method has the beneficial effects that the Landsat images with high confidence in different time periods in the growth period can be synthesized, so that the requirements of large-range, long-time and high-precision coastal zone monitoring caused by rapid change of land utilization can be met.

The invention discloses a cross-view image geographic positioning method based on dynamic threshold pseudo tag self-training learning, and the method specifically comprises the following steps: introducing a difficult sample feature mining method, dynamically adjusting the loss weight of a sample according to the change of similarity, and building a dynamic difficult sample triple loss model; the method comprises the following steps: dynamically adjusting a confidence threshold value of a sample by adopting an index moving average weighting method, iteratively training and screening an unlabeled sample, namely a pseudo label, establishing a pseudo label self-training mechanism of a dynamic threshold value, mining and utilizing non-paired data, and solving the problem of high manual labeling cost; a reference image most similar to a query image is found through image retrieval, and the offset of a query position is predicted. Experiments on CVUSA and CVACT data sets show that as the distance threshold increases, the accuracy of the cross-view image geographic positioning method based on dynamic threshold pseudo tag self-training learning presents a stable rising trend, and the cross-view image geographic positioning method based on dynamic threshold pseudo tag self-training learning is superior to other methods under the same threshold condition.

One embodiment of the present invention sets forth a technique for simplifying a trained machine learning model. The technique includes determining a first set of images associated with a first output class predicted by the trained machine learning model. The technique also includes generating a first aggregated representation of the first set of images, wherein the first aggregated representation includes a first plurality of representative pixel values for a plurality of pixel locations included in the first set of images. The technique further includes generating a simplified representation of the trained machine learning model that includes a first mapping of the first aggregated representation to the first output class, wherein the first mapping indicates that the trained machine learning model predicts the first output class for one or more input images.

The invention relates to the technical field of five-wheel continuous casting low-oxygen copper, in particular to a copper rod continuous casting process parameter optimization-based microstructure prediction method, which comprises the following steps of: formulating an adjusting factor set based on a comparison result of a crystallization line position of a copper casting blank and a standard crystallization line position; obtaining a microstructure image and inputting the microstructure image into the feature comparison model to obtain an anomaly set; inputting the production elements and the abnormal set into a parameter optimization model, and screening out a plurality of adjustment schemes; setting a reference factor to perform serialized adjustment on the adjustment scheme, and casting a copper casting blank according to the previous adjustment scheme; various passive data of the cast wheel are obtained, and a real-time matrix is obtained; the production elements and the real-time matrix are input into a microscopic image prediction model, and microstructure prediction is carried out; through construction of a feature comparison model and a parameter optimization model and application of a real-time matrix and a microscopic image prediction model, the automation level of the production process is improved, and a scientific basis is provided for standardization of process parameters.

A text-to-image model training method, apparatus, and computer-readable storage medium for enhancing text-to-image generation through object-aware training. The method trains a text-to-image model using cyclic iterative training with sample image and text pairs. Training involves selecting image-text sample pairs containing multiple objects, obtaining corresponding mask images and object class names that distinguish location regions of the objects, and inputting both the sample image with description text and the mask images with object class names into the model. The method obtains image predicted noise and object predicted noises, constructs a loss function based on these predictions, and performs parameter adjustment accordingly. This approach enables improved object-level understanding in text-to-image generation models.

The invention relates to the technical field of aviation composite material detection, and discloses an aviation composite material terrace multi-dimensional flatness digital imaging acceptance system. The system comprises a feature acquisition module, an imaging parameter calibration module, an environment adaptation adjustment module, a deviation threshold setting module, an imaging prediction module and an acceptance feedback control module. The feature acquisition module analyzes the multi-dimensional flatness difference to obtain a feature distribution state value; the imaging parameter calibration module screens an optimal angle and resolution combination to obtain an imaging calibration parameter set; the environment adaptation adjustment module matches the environment factors and the imaging combination to obtain an environment adaptation parameter set; the deviation threshold value setting module sets a threshold value to obtain a deviation load threshold value; the imaging prediction module deduces an imaging change trend to obtain an imaging distribution prediction value; the acceptance feedback control module analyzes errors and adjusts parameters to obtain an acceptance regulation and control scheme. According to the system, through cooperation of multiple modules, the accuracy and adaptability of aviation composite floor flatness acceptance inspection are improved, and many problems existing in traditional detection are solved.

The embodiment of the invention provides a training method of an image denoising model, an image processing method and an image processing system. The training method of the image denoising model comprises the following steps: acquiring a sample standard image and a sample noise-added image; generating a sample reference image according to the sample standard image, inputting the sample noise-added image and the sample reference image into an initial image denoising model to obtain an initial prediction image, and determining noise mode information by the initial image denoising model according to coding feature information of the sample noise-added image and the sample reference image; denoising the sample noise-added image according to the noise mode information; adjusting model parameters according to the initial prediction image and the sample standard image to obtain a reference image denoising model; the sample noise-added image is input into a reference image denoising model, a target prediction image is obtained, and the reference image denoising model predicts noise mode information according to the sample noise-added image; and adjusting model parameters according to the target prediction image and the sample standard image to obtain an image denoising model.

The invention discloses a multispectral satellite cloud picture prediction method based on motion stripe decoupling. The method comprises the following steps: carrying out normalization preprocessing on multi-channel satellite observation data; utilizing a motion branch model to extract motion features based on a displacement field, iteratively updating a prediction frame in an autoregressive distortion-correction pipeline, and keeping physical consistency in combination with atmospheric dynamics and smoothness constraint; a texture branch model is utilized to sequentially pass through a high-fidelity encoder, long memory state space modeling and a high-fidelity decoder, time sequence texture features are extracted, and cloud picture details are kept; the motion features output by the motion branches and the texture features output by the texture branches are input into a gating fusion module, adaptive weighting of the features is achieved through convolution and a gating mechanism, and fusion features are output; and carrying out reverse normalization processing on the fusion features to obtain satellite cloud picture prediction results at a plurality of moments in the future. According to the method, the spatial texture fidelity of cloud picture prediction can be improved while the physical interpretability is ensured, and high-precision satellite cloud picture prediction is realized.

The invention discloses an object surface defect segmentation method based on small samples, and the method specifically comprises the steps: collecting images of different types of object surface defects and corresponding segmentation masks, constructing a small sample data set, and dividing the small sample data set into a training set and a test set; constructing training and testing tasks, and respectively extracting a corresponding support set and a query set for each task; constructing and training a defect segmentation network, wherein the defect segmentation network comprises a query prior mask generator, a prior-guided bidirectional feature interaction module, a prototype-loss compensation module and a context-aware attention-guided feature aggregation decoding module; and after training is completed, inputting the support set and the to-be-tested query image into the converged defect segmentation network, and outputting a query image prediction result. Experiments prove that the method realizes remarkable performance improvement on an FSSD-12 data set, and shows that the method has obvious advantages in a small sample defect segmentation task.

The embodiment of the invention provides a blind image restoration method and system, electronic equipment and a storage medium. The method comprises the following steps: acquiring a to-be-restored image; inputting the to-be-restored image into a pre-established blind image restoration model, and outputting to obtain a restored image; wherein the blind image restoration model is pre-established based on a vector quantization variational auto-encoder, a multi-layer perceptron and a continuous diffusion generation model. According to the embodiment of the invention, by utilizing the superiority of the continuous diffusion generation model in learning data manifold distribution, the vector quantization variational automatic encoder is used as a codec between the image space and the submerged space, and the generation process in the submerged space of image encoding is constructed, so that a low-quality image under complex degradation is repaired, and the image quality is improved. And a good image restoration effect is achieved. A continuous diffusion generation mode is introduced, and a preprocessed guide embedding mode is constructed, so that guide conditions in a high-quality image prediction process are more reasonable and interpretable.

The invention belongs to the technical field of medical image processing, and particularly relates to a glioma segmentation method based on a multimodal fusion network guided by anatomical symmetry, which comprises the following steps of: jointly inputting an FLAIR image, a T2 image, a T1 image and a T1c image of the same glioma into a trained image segmentation model, and outputting a predicted segmentation image by the trained image segmentation model, the prediction segmentation image is a glioma MRI image with three segmentation areas obtained through prediction, and the three segmentation areas are an edema area, an enhanced tumor area and a necrosis area respectively; the image segmentation model comprises an encoder, a jump connection part and a decoder; the encoder comprises an ASG module, the jump connection part comprises an IMP module, and the decoder comprises a CMF module. Through a three-module cooperation mechanism, the performance of tumor localization, cross-modal fusion, subregion segmentation and the like is improved, and a reliable image basis is provided for glioma operation plan formulation, prognosis evaluation and personalized treatment decision.

The invention discloses a satellite cloud picture sequence prediction method combining deformable convolution and pyramid pooling, and relates to the field of deep learning. The method comprises the following specific steps: (1) preprocessing satellite cloud picture sequence data and dividing into a training set and a test set; (2) building a satellite cloud picture sequence prediction model of a basic encoder-translator-decoder structure; (3) combining a motion perception loss function and an L2 loss function to supervise the model for training; and (4) predicting a satellite cloud picture sequence image. According to the method, a deformable volume operator based on dynamic sparseness is used in an encoder and a decoder to replace the traditional convolution operation, so that the network can adaptively select proper parameters according to the space structure of a cloud picture, softmax normalization in deformable convolution space aggregation is removed, and the robustness of the network is improved. The memory access is optimized to accelerate the running speed; a pyramid pooling structure is used in the translator, so that the calculation process can be simplified, and spatial-temporal characteristics of different scales in the cloud picture sequence can be captured; meanwhile, a motion perception loss function and a traditional L2 loss function are combined to supervise model training, and motion information between adjacent frames of a satellite cloud picture sequence can be further obtained. The method is not only suitable for all satellite cloud picture sequence images, but also can be applied to sequence image prediction in other complex scenes.

The invention discloses a knowledge distillation-based model training method and electronic equipment. The method comprises the following steps: performing feature extraction on a first sample image through a plurality of teacher models to obtain foreground supervision sub-features and background supervision sub-features of N local category objects; performing feature extraction on the first sample image through a first student model to obtain first foreground features and first background features of the N local category objects; performing foreground knowledge distillation on the first student model according to the foreground supervision sub-feature and the first foreground feature, and performing background knowledge distillation on the first student model according to the background supervision sub-feature and the first background feature; the first student model after foreground knowledge distillation and background knowledge distillation is a second student model; and performing image prediction on the second sample image through the second student model, and adjusting model parameters of the second student model according to a prediction result of image prediction. According to the invention, on the premise of a limited number of samples, the student model with high concurrency capability and high precision can be distilled based on a plurality of teacher models.

An image prediction method, apparatus, and system, a device, and a storage medium are provided. The method includes: (401) obtaining a split mode of a current node, where the current node is an image block in a coding tree unit in a current image; (402) determining, based on the split mode of the current node and a size of the current node, whether the current node satisfies a first condition; and (403) when it is determined that the current node satisfies the first condition, performing intra prediction on all coding blocks belonging to the current node, to obtain predictors of all the coding blocks belonging to the current node.

The invention discloses an actinide alloy corrosion behavior prediction method and device based on machine learning and a storage medium, and the method comprises the steps: obtaining a corrosion morphology recognition model and a corrosion behavior prediction model based on machine learning, inputting to-be-recognized actinide alloy corrosion images into the corrosion morphology recognition model for recognition processing, and determining corrosion morphology identification time sequence data according to the processing result, inputting the corrosion morphology identification time sequence data into the corrosion behavior prediction model for prediction processing, and determining actinide alloy corrosion behavior prediction data according to the processing result. According to the method, the corrosion behavior of the actinide alloy can be predicted according to the to-be-identified image of the actinide alloy, a more comprehensive and reliable tool and technical means are provided for solving the problem that the corrosion behavior of the actinide alloy is difficult to research and analyzing the corrosion characteristics and rules of the actinide alloy, and the method is worthy of popularization and application. The defect that the accuracy is not high when the corrosion behavior of the actinide alloy is researched in the prior art is overcome. The method is widely applied to the technical field of metal corrosion behavior prediction.

The invention discloses a component defect detection method and device, electronic equipment and a storage medium. The method comprises the following steps: constructing a three-dimensional model of a component; collecting laser ultrasonic data of the three-dimensional model, and collecting a thermal imaging image and a polarized light image of the assembly; based on the laser ultrasonic data, the thermal imaging image and the polarized light image, predicting to obtain a first defect category and a first defect position corresponding to a defect area of the assembly; based on the defect category and the defect position of the defect area, reconstructing three-dimensional defect data of the component; and on the basis of the three-dimensional defect data, predicting to obtain an expansion direction and an expansion range of the defect area.

The invention relates to a colorectal cancer space transcriptome prediction method and device based on deep learning and a storage medium. The prediction method comprises the following steps: collecting paired digital pathological images and spatial transcriptome data to form a data set; preprocessing the spatial transcriptome data; the method comprises the following steps of: constructing an STFormer model; the Style-Aug module is used for performing feature space conversion on an input digital pathological image; the dense connection convolutional network DenseNet module is used for constructing a deep mapping relation between a pathological image and a spatial transcriptome; the inter-batch full-image crossing Transform module is used for effectively avoiding overfitting of the model due to data volume limitation through an inter-batch attention mechanism; and performing spatial transcriptome prediction on the input digital pathological image by using the trained STFormer model to obtain a prediction result. Under the condition of a small sample, the performance and the general stability of a pathological image prediction space transcriptome are remarkably improved, and an efficient and reliable deep learning tool is provided for analyzing a tumor microenvironment.

The invention discloses a multi-modal false information detection method, system and device and a storage medium, and belongs to the technical field of false information detection.The method comprises the steps that a text of multi-modal information is input into a text representation network to obtain text representation, and an image of the multi-modal information is input into an image representation network to obtain image representation; and inputting the text representation and the image representation into a shared classifier to obtain a text prediction information label, an image prediction information label, a text weight and an image weight, and weighting the text prediction information label and the image prediction information label based on the text weight and the image weight to obtain a prediction information label. According to the method, the text and image modal information is combined, and an adaptive weight distribution mechanism is adopted, so that efficient and accurate multi-modal information processing is realized, the prediction performance is remarkably improved, and the application range is widened.

The invention discloses an image reconstruction method and system based on a hybrid network framework, a terminal and a storage medium, and the method comprises the steps: carrying out the prediction of an original image, obtaining the prediction data, obtaining the quality loss and the physical loss of momentum conservation in a prediction process, comparing the prediction data with the original data, and obtaining a prediction result; obtaining a matching value between the two to construct a total loss function; and introducing an NTK matrix to draw up a proper learning rate, training a hybrid network framework by using the learning rate and a total loss function, and finally obtaining a DeepONet-NTK hybrid network. According to the method, DeepONet is used for learning a nonlinear mapping relation in a multi-dimensional function space, and the NTK theory is combined to optimize the training process and improve the convergence speed and stability, so that the signal-to-noise ratio of a reconstructed image is reduced, and high-dimensional semantic features are reserved.