117 results about "Image properties" patented technology

The present disclosure relates to systems, methods, and non-transitory computer-readable media that generates text and image attributions and provides for display in a digital document the image attribution of an image element and the text attribution of text in the digital document. In particular, the disclosed systems receive a prompt relative to a digital document, and in response, generates an answer to the prompt using a multimodal large language model. Furthermore, the disclosed systems generating an image attribution and a text attribution in response to a selection of at least a portion of the answer to the prompt. Specifically, the image attribution and the text attribution indicate portions of the digital document that provide support for the at least a portion of the answer. Moreover, the disclosed systems provide for display in the digital document of a client device, the image attribution and the text attribution.

The application discloses a garbage classification model training method, device and equipment. A set proportion of garbage images is selected from garbage images, and image properties of regions where each target is located in the selected garbage images are adjusted to obtain a first data set. The first data set includes garbage images whose image properties are adjusted and garbage images whose image properties are not adjusted in original garbage images. The garbage images have been labeled with categories of the targets and regions where the targets are located. Garbage images including multiple targets that overlap with each other in the first data set are copied, and the copied garbage images are added to the first data set to obtain a second data set. The copied garbage images are labeled with one of the multiple targets that overlap with each other. A target detection model is trained based on the second data set. The application not only improves the efficiency of garbage classification model training, but also further improves the accuracy and detection speed of garbage classification performed by the garbage classification model.

The present application relates to the technical field of image processing, and particularly relates to a scenic spot image processing method and device, equipment and a storage medium, the method comprising obtaining a to-be-processed scenic spot image, determining a target region in the to-be-processed scenic spot image, removing the target region in the to-be-processed scenic spot image to obtain a removed image; obtaining image attribute information of the to-be-processed scenic spot image, obtaining a similar image corresponding to the removed image according to the image attribute information; determining a target region in the similar image, completing the removed image according to the target region in the similar image to obtain a completed image; inputting the completed image and the image attribute information into a preset image inpainting neural network model to perform image inpainting on the completed image, and obtaining an inpainted image of the to-be-processed scenic spot image, which realizes the elimination of sundries and inpainting of the to-be-processed scenic spot image, and meets the image processing requirements of users.

A system and method performed by an electronic device for generating a high-resolution image from an input low-resolution image are provided. The method includes determining one or more feature vectors for each of attributes associated with an input low-resolution image based on one or more image attributes, determining a degradation representation map of the input low-resolution image based on at least one of the input low-resolution image and the one or more feature vectors of the one or more image attributes, generating one or more personalization parameters based on at least one of the input low-resolution image and a user input, obtaining a first output image based on degradation information, a first process, and the one or more personalization parameters, obtaining a second output image based on the degradation information, a second process, and the one or more personalization parameters, and generating the high-resolution image by upsampling at least one of the first output image and the second output image.

The application provides an image encryption method and device, equipment, storage medium and program product, and relates to the technical field of privacy calculation. The method obtains an original image, generates a chaotic sequence corresponding to the original image, generates a secure thumbnail image and a chaotic compressed ciphertext image that reserve visual features of the original image based on the chaotic sequence and the original image, and embeds the chaotic compressed ciphertext image in the least significant bit of the secure thumbnail image to obtain a visually perceptible image. The method solves the contradiction between security and recognizability of the traditional encryption method through the fusion of multi-level encryption and visual perception technology, significantly improves the security and user recognizability of image transmission, reduces the possibility of identification by attackers, and ensures that users can quickly identify image attributes through visual preview.

Embodiments of the present application disclose an image generation method and device, computer equipment and a storage medium; an image generation instruction can be received, the image generation instruction including image attribute information of a target image to be generated, environment information is obtained, the environment information is collected through a display device displaying the target image, data mapping is performed on the environment information through a preset image generation model, a content image corresponding to the environment information is generated, style features are extracted from at least one preset style reference image, content features are extracted from the content image, and the target image is obtained based on the fusion of the content features and the style features; in the embodiments of the present application, the image generation model can map the environment information to obtain the content image, the content features in the content image can be fused with the style features in the style reference image, and finally the target image is generated, so that a wallpaper image with rich content and various styles can be generated, and the visual experience of a user is improved.

The embodiment of the present disclosure discloses an object information determination method, device, equipment and storage medium, the method comprises: acquiring a panoramic image and image attribute information of the panoramic image; determining pixel point matrix information of the panoramic image according to the image attribute information of the panoramic image, the pixel point matrix information includes depth direction information of each pixel point in the panoramic image relative to the image capture position point; identifying the panoramic image, determining a target object in the panoramic image and object region information of the target object; and determining region attribute information of the target object according to the pixel point matrix information and the object region information. By using the method, the region attribute information of the object in the real scene can be effectively determined through the analysis of the panoramic image, the determined region attribute information of the scene object can be used as data support to participate in the actual business operation, and the cost investment of introducing the region attribute information from the data information provider is reduced.

The invention relates to the technical field of gastric cancer image recognition, and discloses a gastric cancer early lesion image recognition method based on deep learning. The method comprises the steps of obtaining a to-be-analyzed gastric cancer medical image set, and screening an adaptive deep learning model group according to image attributes and recognition requirements; efficiency indexes such as model memory occupancy, single-frame processing delay and throughput rate are continuously tracked, priorities are evaluated for candidate models according to tracking data, and a model activation sequence list is formed. Selecting models one by one according to the list, and checking whether all the assigned images can be completed within a specified time limit or not: if the checking is passed, allocating computing resources to initialize a single model copy, and if the checking is not passed, deducing the number of the required model copies. Checking available computing resources, if the available computing resources are sufficient, starting corresponding copies, and if the available computing resources are insufficient, recovering low-priority activated model resources and then checking again; finally, whether all the active models are located at the top of the list or not is verified, if yes, scheduling is terminated, and if not, remaining models of the list continue to be processed.

The application provides an image rendering method, device and equipment, which can be applied to the technical field of image processing. The method comprises the following steps: performing feature fusion on a plurality of initial images to obtain image fusion features, wherein the plurality of initial images represent a target object based on different initial shooting angles; generating a voxel grid representing the target object according to the image fusion features, wherein a center point of the voxel grid is used as an anchor point feature; performing attention fusion on a specified pose of the plurality of initial images, the image fusion features and the anchor point feature based on an attention mechanism to obtain a target feature; performing image attribute detection on the target feature to obtain a target attribute; and performing image rendering by using the target attribute to obtain a target image representing the target object based on a target shooting angle.

The application discloses a test system and method for an unmanned device controller, which comprises an image acquisition device configured to acquire first image data, and send the first image data to a video injection core board, wherein the first image data comprises at least first image attributes and first image content; an image storage device configured to send second image data to the video injection core board, wherein the second image data comprises second image content; and the video injection core board configured to analyze the first image attributes to obtain analyzed first image attributes, replace the first image content with the second image content to obtain target image data, and send the target image data to the unmanned device controller, wherein the target image data comprises at least the analyzed first image attributes and the second image content; and the unmanned device controller configured to output a control instruction based on the received target image data, thereby improving the test accuracy.

The application belongs to the technical field of image processing, and discloses a cloud networking video AI image enhancement method, system, device, medium and terminal. The cloud networking video AI image enhancement method comprises the following steps: performing image analysis on a road material database composed of roads, vehicles and geological structures, combing image attributes, and classifying and collating, cooperating with an image enhancement algorithm, and obtaining a clear picture through material replacement, picture repair, contrast enhancement and intelligent deployment. The application enhances the definition of standard definition and below images, so that it meets the requirements of high-definition video. The application changes the original unclear image into a high-definition image through the algorithm of material replacement. Since the highway video is relatively single compared with the public security monitoring image content, the picture improvement effect is relatively obvious, thereby improving the accuracy of the intelligent analysis and event detection functions in the later stage, and the application effect is obvious. The application reduces the construction cost of the monitoring device. The application has good compatibility.

This invention provides a determination device, determination method, program, and recording medium that improve the accuracy of determining whether a person's eyes are open or closed based on an image. [Solution] The determination device includes an image acquisition unit that acquires a person's face image sent from an imaging device connected via a network, an attribute acquisition unit that acquires attribute information of the person based on the face image acquired by the image acquisition unit, and a determination unit that determines whether the person's eyes are open or closed based on the attribute information of the person acquired by the attribute acquisition unit and the face image.

A method for analyzing an image, called “analysis image”, of a dental arch of a patient. The method in which the analysis image is submitted to a neural network, in order to determine at least one value of an image attribute relating to the analysis image. The analysis image is a photograph or an image taken from a film. The image attribute relates to a position or an orientation or a calibration of an acquisition apparatus used to acquire the analysis image or a combination thereof, or a quality of the analysis image, and in particular relating to the brightness, to the contrast or to the sharpness of the analysis image, or a combination thereof.

The application discloses a kind of X-ray flat panel detector timing synchronization and correction method and system, image is acquired by flat panel detector;By timing control module, the main synchronization pulse is sent to the synchronization interface of flat panel detector on one hand, the working frequency of flat panel detector is controlled;On the other hand, the exposure window pulse returned by flat panel detector is frequency-division;After frequency-division, the secondary synchronization pulse is given to high voltage generator interface to control X-ray beam exposure;Image property is marked according to the pulse controlled by timing control module and the setting of frequency-division in the image acquired by flat panel detector in the above step 1;According to the strategy set, dark-field image multi-frame average or recursive average is carried out, and real-time offset correction data is generated.The offset correction data of the application is updated in real time, and does not need to be generated in advance, which greatly simplifies the generation mode of other correction files, solves the contradiction between the real-time application and the image quality of the equipment, and also provides a solution for variable frequency acquisition.

The invention provides a mammary gland ultrasonic focus interpretable diagnosis system, a storage medium and electronic equipment, and relates to the technical field of medical image artificial intelligence auxiliary diagnosis. According to the method, image attribute feature tags are mapped to corresponding nodes of a knowledge graph. Then, the graph neural network model carries out multi-hop reasoning on a graph structure through a message passing mechanism; according to the method, not only can information from related attribute nodes be aggregated, but also the reasoning result of the graph neural network model can be calibrated and explained by utilizing clinical expert rules extracted from the knowledge graph, so that a clear and traceable reasoning path is attached to each prediction of the graph neural network model. The technical problem that image information is separated from the knowledge reasoning process in an existing knowledge graph fusion ultrasonic focus diagnosis method is solved, the visual perception ability of the image and the symbol reasoning ability of the knowledge graph are combined, and therefore an intelligent diagnosis system which is accurate in prediction and clear in explanation is provided.

A system includes a projection device configured to project images onto a receiver surface of a viewing device. The viewing device includes a screen having the receiver surface and a viewing surface opposite the receiver surface. The screen is configured to permit transmission of the images through the screen, from the receiver surface, to the viewing surface such that the images are viewable on the viewing surface. The viewing device also includes a focusing lens configured to focus the images for a user when wearing the viewing device. Further, the system includes a tracking system configured to determine a location and orientation of the receiver surface of the viewing device. The projection device is configured to adjust image properties of the images based at least in part on the determined location and orientation of the receiver surface.

The invention provides an image processing method, electronic equipment and a storage medium, and the method comprises the steps: obtaining a first image in response to a shooting operation; obtaining an image attribute parameter of the first image, wherein the image attribute parameter is related to the first scene mode; determining a first processing model from a plurality of image processing models according to the image attribute parameters; and performing image enhancement on the first image through the first processing model to obtain a second image. On the basis of an image obtained in an original shooting process, according to a corresponding scene mode, a first processing model matched with the image is selected to carry out further image enhancement processing on the image, so that the image quality is improved.

Embodiments of the present application provide a denoising method and device for images, electronic equipment, storage medium and program product. The method comprises: generating a first denoised image by denoising an original input image through a convolutional neural network; determining a noise residual image based on the original input image and the first denoised image; obtaining a second denoised image by adjusting the contrast of the first denoised image; and generating a target denoised image by combining the second denoised image with the noise residual image and the attribute features of the original input image. The method of the present application breaks through the limitation of fixed mapping relationship in related technologies, and no longer relies on fixed mapping of the model for denoising. The method not only retains the advantages of efficient denoising of the convolutional neural network, but also designs noise addition by combining the noise residual image with the attribute features of the image, so that the denoising process has flexible adaptation ability. The method can adjust the image denoising by regulating the noise addition according to actual needs, so that the quality of the denoised image matches the actual needs.

The application provides a multimedia content search method and device. After receiving a search sentence input by a user, the application identifies image attribute features contained in the search sentence based on a pre-constructed pattern tree and slot tree. For example, for multimedia content containing a person object, the application can identify a person title and a person quantity. Further, the application searches for a matched picture from an index library based on the identified image attribute features and a text vector corresponding to the search sentence. The method accurately identifies image attribute features (such as a person title and a person quantity) in the search sentence by using a pattern tree and a slot tree corresponding to attribute information of the search sentence, thereby improving the accuracy of a semantic understanding result of the search sentence and finally improving the accuracy of a search result.

The application discloses a salt-underground seismic image quality evaluation method and device, equipment and a storage medium. The salt-underground seismic image quality evaluation method comprises the following steps: acquiring a salt-underground seismic image to be evaluated, and uniformly setting at least two quality detection points in the salt-underground seismic image; determining a linear quality score relationship between an expert score result of a quality detection point and an optimal image attribute based on the expert score result of the quality detection point and an attribute value of the optimal image attribute corresponding to the quality detection point; and determining a predicted expert score result of the quality detection point based on the linear quality score relationship, and performing quality grade evaluation on the salt-underground seismic image to be evaluated. Through the technical solution, objective, rapid and accurate evaluation of a large amount of seismic images is realized.

The invention discloses an image processing method, electronic equipment and a storage medium, relates to the technical field of terminals, and can reduce the difference of images shot for multiple times in the aspects of color or exposure and the like under the condition of micro change of a scene. Specifically, when the current photographing is processed, if a photographed scene of the current photographing does not change obviously compared with a photographed scene of the previous photographing, the electronic equipment fuses image attribute adjustment data corresponding to the current photographing and the previous photographing, such as AWB data or AE data. The fused image attribute adjustment data is closer to the image attribute adjustment data corresponding to the previous photographing, that is, the change amplitude between the image attribute adjustment data of the two times of photographing is reduced, and the image of the current photographing can be generated based on the fused image attribute adjustment data subsequently, so that the photographing efficiency is improved. Therefore, under the condition that the shot scene does not change obviously, the difference between the two shot images can be reduced, for example, the color difference and / or the exposure difference can be reduced.

This disclosure provides a method and apparatus for training an action recognition model, relating to the fields of computer vision and deep learning. The specific implementation scheme includes: acquiring a pre-set sample set; acquiring a pre-established action recognition network, which includes a convolutional neural network, a recurrent neural network, and a fully connected layer connected to the convolutional neural network for classifying image attributes; performing the following training steps: calculating attribute loss values ​​based on attribute-labeled samples selected from the sample set, using a convolutional neural network and a fully connected layer; calculating action loss values ​​based on action-labeled samples selected from the sample set, using a convolutional neural network and a recurrent neural network; obtaining the action recognition network loss value from the attribute loss value and the action loss value; and using the action recognition network as the action recognition model when the training completion condition is met. This implementation improves the accuracy of action recognition.

Aspects of the present disclosure relate to zoom action based image presentation. A zoom action on a first image can be received on a user device, the zoom action defined by a set of zoom action parameters. The first image can be analyzed to determine image properties of the first image. A second image depicting a different structural level of the first image can be searched for based on the zoom action parameters of the zoom action and the image properties of the first image. The second image can be presented to the user as a response to the received zoom action.

The application discloses a pipeline leakage determination method and device, equipment and storage medium, relates to the technical field of pipeline leakage, and aims to solve the problem of low accuracy in determining whether the oil and gas pipeline leaks. Including: obtaining the first detection image, the first electromagnetic wave signal, the second detection image and the second electromagnetic wave signal obtained by detecting the pipeline to be detected; the first detection image is histogram equalization processed to determine the first gray scale mapping function, and the second detection image is histogram equalization processed to determine the second gray scale mapping function; the first attribute image is obtained based on the first electromagnetic wave signal, and the second attribute image is obtained based on the second electromagnetic wave signal, and the attribute includes at least one of the following: instantaneous amplitude, instantaneous phase, instantaneous frequency; based on the first gray scale mapping function, the second gray scale mapping function, the first attribute image and the second attribute image, it is determined whether the pipeline to be detected has a leakage event.

An image noise learning server includes an image input interface configured to receive training images, and at least one processor configured to control an image extractor to extract, from the training images, a first image including a stationary object and a second image including a moving object, a noise filter to obtain a third image by applying noise filtering with a first intensity to the second image, the third image including the moving object, a labeling unit to determine an intensity of a side effect based on a difference between the stationary object included in the first image and the moving object included in the third image, and a machine learning unit to receive, as a label, the determined intensity of the side effect and image attributes of the training images, and obtain artificial intelligence (AI) parameters by performing machine learning on the second image based on the received label.

This invention belongs to the field of image enhancement technology, specifically to a method and system for automatic optimization and reconstruction of vector graphics based on image enhancement. It includes collecting full-dimensional original feature data and partition quality index data of the image to be processed. Different abnormal scenarios are identified, and corresponding reconstruction collaborative error data is constructed by combining the current reconstruction processing stage and image attribute state. An optimized reconstruction strategy is formulated based on preset vector reconstruction quality requirements. The set of parameters to be corrected is marked in the optimized reconstruction strategy according to the reconstruction collaborative error data, and adjustments are made to obtain a refined optimized reconstruction strategy. The distribution stability index of the partition quality index data of each structural region after optimized reconstruction is collected in real time. Processing nodes that fail the evaluation in the refined optimized reconstruction strategy are defined as error nodes, and an iterative correction strategy pointing to the error nodes is generated. This invention can improve reconstruction accuracy, make reconstruction results more stable, and enhance anomaly detection and scene recognition capabilities.

A method, apparatus, non-transitory computer readable medium, and system for image generation include obtaining an input prompt comprising a pattern element and a target level of an image attribute. A guidance feature representing the pattern element is generated, using a prior model, based on the input prompt and the target level of the image attribute. The prior model is trained using reinforcement learning to generate guidance features for pattern image generation based on the target level of the image attribute. An image generation model generates a synthesized image based on the guidance feature. The synthesized image includes a set of versions of the pattern element with the target level of the image attribute.

A method for training an image generation model includes receiving training data having multiple training images, image captions corresponding to the training images, and corresponding image features, each training image associated with one image caption and one or more image features. The method further includes performing a training process to condition the image generation model using the training images, the image captions, and the image features, resulting in a trained model that generates images conditioned to the image features. The image features include image properties that are extracted from pixels or regions of each training image and camera properties that are associated with each training image.