4083 results about "Digital image" patented technology

Disclosed in the present invention are a digital image calculation method and system for deformable template-based RGB-D camera multi-view matching. The method comprises the six steps of data acquisition, point cloud data preprocessing, feature point matching, re-registration of deformable templates, calculation of a point cloud data transformation relationship between large-view images, and point cloud fusion. The size of a non-adjacent image matching template is adjusted on the basis of a registration result of adjacent views to achieve correct registration of feature points of non-adjacent view images, thereby improving the matching precision, eliminating the accumulative error of an image set, providing a relatively accurate initial value for subsequent iteration of point cloud fusion, reducing the number of iterations, and implementing three-dimensional reconstruction of images.

Implementations relate to leveraging large language model(s) (LLMs) and vision language model(s) (VLMs) to facilitate human-to-computer dialogs. In various implementations, one or more digital images may be processed using one or more VLMs to generate VLM output indicative of a state of an environment. An LLM prompt may be assembled based on the VLM output and a natural language input. The LLM prompt may be processed using one or more LLMs to generate content that is responsive to the natural language input. The content that is responsive to the natural language input may subsequently be rendered at one or more output devices.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that edit digital images using combinations of speech input and gesture interactions. For instance, in some embodiments, the disclosed systems receive speech input from a client device displaying a digital image within a graphical user interface, the digital image portraying an object. Additionally, the disclosed systems detect, via the graphical user interface, one or more gesture interactions with respect to the object of the digital image. Based on the speech input, the disclosed systems determine an edit for the object of the digital image indicated by the one or more gesture interactions. Further, the disclosed systems modify the object within the digital image using the edit indicated by the one or more gesture interactions.

A method including receiving a digital image including text arranged in a layout. The method also includes generating, by an optical character recognition model, a layout text vector that encodes at least one word in the text of the digital image and a position of the at least one word in the layout of the digital image. The method also includes generating, by a visual encoder model, a visual representation vector embedding a content of the digital image. The method also includes converting both the layout text vector and the visual representation vector into a projected text vector including a digital format suitable for input to a large language model. The method also includes combining, into a prompt, the projected text vector, a system message, and a task instruction. The method also includes generating an output including a key-value pair.

Computer-implemented techniques for multimodal content relevance prediction using neural networks involves processing multimodal content comprising a digital image and text. Initially, dense embeddings are obtained: an image embedding from a pretrained convolutional neural network, and a text embedding from a pretrained transformer network. These embeddings encapsulate the features of the image and text respectively. Two pretrained dense neural sub-networks then reduce the dimensionality of these embeddings. A third dense neural sub-network determines a numerical score for the multimodal content using the reduced embeddings and an additional feature embedding. This score reflects various aspects of the multimodal content, leading to an action taken based on this numerical evaluation, providing a comprehensive and nuanced understanding and management of multimodal digital content.

Described herein are systems, methods, devices, and other techniques for comprehensive and automated evaluation of digital images generated from artificial intelligence (AI) models in order to promote accurate representations of real-world content. Prompts are received at the system that are then passed to both a search engine and a generative AI model. Synthesized digital images are obtained from the generative AI model. The top-matching image from the search engine is used as a verification of the ground truth of the synthesized digital images. A realism score is generated for each synthesized digital image that characterizes the accuracy of the synthesized digital image with reference to the verification image. The realism score can be used to assist and expedite the image selection process, as well as serve as input to fine-tune the performance of generative models.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that implements a vision language machine learning model to generate text representations of an input digital image from localized context tokens. In particular, in some embodiments, the disclosed systems generate image patch feature representations that represent patches from an input image. Further, in some embodiments, the disclosed systems generate localized context tokens from the image patch feature representations and prompt context tokens. Moreover, in some embodiments, by utilizing the localized context tokens, the disclosed systems generate a text representation by utilizing a text encoder of the vision language machine learning model.

In implementation of techniques for three-dimensional reconstructions based on Gaussian primitives, a computing device implements a reconstruction system to receive a first digital image depicting an object from a first angle and a second digital image depicting the object from a second angle. The reconstruction system segments the first digital image and the second digital image into patches. The reconstruction system then generates, using a machine learning model, three-dimensional Gaussian primitives that predict parameters of points of the object in a three-dimensional space that correspond on a per-pixel basis to pixels of the patches. The reconstruction system then forms a three-dimensional reconstruction of the object for display in a user interface by merging the three-dimensional Gaussian primitives.

The invention discloses a reservoir bank slope crack identification method based on unmanned aerial vehicle inspection and digital images, and relates to the technical field of reservoir bank slope inspection. 2, image preprocessing: preprocessing the data by adopting processing methods of graying, gray enhancement and bilateral filtering; 3, crack identification: identifying reservoir bank slope cracks in the image by adopting methods of threshold segmentation, edge detection and supervised classification; 4, crack pixel filtering: performing filtering processing on the extracted crack image by adopting morphological closed operation, length filtering and direction filtering; and 5, model fusion: fusing the threshold segmentation model, the edge detection model and the supervised classification model together by adopting a minimum-risk Bayesian probability method. The method shows remarkable applicability and effect in large-range and multi-form crack identification and investigation, and shows high robustness when processing crack images with different scales, shapes and backgrounds, and the accuracy of the method can stably reach more than 90%.

Disclosed is a digital image calculation method and system for RGB-D camera multi-view matching based on a variable template, the method includes six steps: acquiring data, preprocessing point cloud data, performing feature point matching, re-registering a variable template, calculating point cloud data transformation relationships among large-view images, and performing point cloud fusion. A size of a non-adjacent image matching template is adjusted based on registration results of adjacent angles of view, and correct registration of feature points of images from non-adjacent angles of view is accordingly achieved, which improves matching accuracy, eliminates cumulative errors in image sets, and provides more accurate initial values for subsequent iterations of point cloud fusion, such that the number of iterations is reduced, and three-dimensional reconstruction of images is implemented.

This disclosure describes one or more implementations of systems, non-transitory computer-readable media, and methods that trains (and utilizes) an image color editing diffusion neural network to generate a color edited digital image(s) for a digital image. In particular, in one or more implementations, the disclosed systems identify a digital image depicting content in a first color style. Moreover, the disclosed systems generate, from the digital image utilizing an image color editing diffusion neural network, a color-edited digital image depicting the content in a second color style different from the first color style. Further, the disclosed systems provide, for display within a graphical user interface, the color-edited digital image.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For instance, in one or more embodiments, the disclosed systems generate utilizing a segmentation neural network, an object mask for each object of a plurality of objects of a digital image. The disclosed systems detect a first user interaction with an object in the digital image displayed via a graphical user interface. The disclosed systems surface, via the graphical user interface, the object mask for the object in response to the first user interaction. The disclosed systems perform an object-aware modification of the digital image in response to a second user interaction with the object mask for the object.

Examples assist in renovating a room, including receiving a first image of a room, being a digital image prior to a planned renovation, inputting the first image and a renovation prompt to a generative machine-learning (ML) model, being configured to generate an renovated room image from the input image and an input prompt, receiving, from the generative ML model, a second image of the room, the second image being the renovated room image, inputting the second image to a second ML model, the second ML model being configured to identify objects that appear in an input image and output a list of objects, and transmitting the second image and the list of objects to a user computing device, the list of objects being displayed as a list of items to upgrade the room to appear as shown in the second image.

The present disclosure relates to systems, non-transitory computer-readable media, and methods that implement a neural network framework for interactive multi-round image generation from natural language inputs. Specifically, the disclosed systems provide an intelligent framework (i.e., a text-based interactive image generation model) that facilitates a multi-round image generation and editing workflow that comports with arbitrary input text and synchronous interaction. In particular embodiments, the disclosed systems utilize natural language feedback for conditioning a generative neural network that performs text-to-image generation and text-guided image modification. For example, the disclosed systems utilize a trained model to inject textual features from natural language feedback into a unified joint embedding space for generating text-informed style vectors. In turn, the disclosed systems can generate an image with semantically meaningful features that map to the natural language feedback. Moreover, the disclosed systems can persist these semantically meaningful features throughout a refinement process and across generated images.

In implementations of systems for searching for images using generated images, a computing device implements a search system to receive a natural language search query for digital images included in a digital image repository. The search system generates a set of digital images using a machine learning model based on the natural language search query. The machine learning model is trained on training data to generate digital images based on natural language inputs. The search system performs an image-based search for digital images included in the digital image repository using the set of digital images. An indication of the search result is generated for display in a user interface based on performing the image-based search.

Methods, systems, and non-transitory computer readable storage media are disclosed for generating difference captions indicating detected differences in digital image pairs. The disclosed system generates a first feature map of a first digital image and a second feature map of a second digital image. The disclosed system converts, utilizing a linear projection neural network, the first feature map to a first modified feature map in a feature space corresponding to a large language machine-learning model. The disclosed system also converts, utilizing the linear projection neural network layer, the second feature map to a second modified feature map in the feature space corresponding to the large language machine-learning model. The disclosed system further generates, utilizing the large language machine-learning model, a difference caption indicating a difference between the first digital image and the second digital image from a combination of the first modified feature map and the second modified feature map.

A system, method, and computer program product for generating a digital image is disclosed. In use, a first image and a second image are received from a first image sensor, where the first image sensor detects wavelengths of a visible spectrum. A third image and a fourth image are received from a second image sensor, where the second image sensor detects wavelengths of a non-visible spectrum. Using an image processing subsystem, a resulting image is generated by combining one of the first image or the second image, with one of the third image or the fourth image.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize a text-image alignment loss to train a diffusion model to generate digital images from input text. In particular, in some embodiments, the disclosed systems generate a prompt noise representation form a text prompt with a first text concept and a second text concept using a denoising step of a diffusion neural network. Further, in some embodiments, the disclosed systems generate a first concept noise representation from the first text concept and a second concept noise representation from the second text concept. Moreover, the disclosed systems combine the first and second concept noise representation to generate a combined concept noise representation. Accordingly, in some embodiments, by comparing the combined concept noise representation and the prompt noise representation, the disclosed systems modify parameters of the diffusion neural network.

The invention discloses an image processing method applied to printed matter surface color difference detection, which relates to the technical field of image processing, and comprises the following steps: acquiring a digital image of a printed matter to be detected, performing illumination non-uniformity correction, and converting the corrected digital image into a CIELAB color space; performing region segmentation on the digital image based on double constraint conditions of color gradient and texture boundary to generate a detection region graph; feature parameters are extracted based on the detection area graph, and a feature data set is generated; establishing a dynamic reference model by utilizing process parameters and material characteristics of the printed matter; and calculating the distance between the feature data set and the dynamic reference model, identifying color difference regions and generating color difference scores, and screening and grading the color difference regions according to the color difference scores. According to the method, a multi-layer image pyramid and homomorphic filtering combined illumination correction technology is adopted, and an adaptive weight fusion mechanism based on image features is introduced, so that the illumination nonuniformity is effectively eliminated while the definition of printing details is kept.

The invention discloses a three-dimensional finite element model generation and numerical simulation method and system for a wading engineering composite material XCT digital image, and belongs to the technical field of finite element analysis. Comprising the steps of collecting a composite material XCT image in an initial state and performing preprocessing; performing statistical analysis on the two-dimensional microstructure parameters; a virtual XCT image is generated based on the Pix2PixHD style migration network; the method comprises the following steps of: accurately segmenting each component region of a real XCT (X-ray computed tomography) image based on a Swinin-Transformer network; completing contour feature extraction and smoothing of the segmented image based on a mapping relation between pixels and nodes; constructing a space coordinate system and carrying out discrete derivation on all yarn center points of each segmented image; grid division is carried out based on a multi-material moving cube algorithm in a CGAL library, and a global cohesion unit is inserted; completing material attribute and local material direction distribution; and customizing proper boundary conditions, and carrying out numerical simulation based on a finite element method.

The invention relates to the technical field of prediction analysis, and discloses a lung cancer phenotype prediction auxiliary analysis method and system based on artificial intelligence. The method comprises the following steps: carrying out adaptive preprocessing on a digital image of a lung cancer pathological section to obtain a standardized preprocessed image; carrying out hierarchical progressive tissue segmentation on the preprocessed image to obtain a lung cancer region labeled image; carrying out multi-dimensional feature cascade extraction on the lung cancer region labeled image to obtain a phenotypic feature set; performing hierarchical prediction on the phenotype feature set to obtain an immune phenotype prediction result; performing subtype mapping analysis on the immune phenotype prediction result to obtain a patient diagnosis report; and carrying out multi-dimensional data integration on the diagnosis report of the patient to obtain a personalized treatment scheme. The accuracy and interpretability of lung cancer phenotype prediction are improved through cascade extraction and hierarchical prediction modeling of multi-dimensional features.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modify digital images via scene-based editing using image understanding facilitated by artificial intelligence. For example, in one or more embodiments the disclosed systems utilize generative machine learning models to create modified digital images portraying human subjects. In particular, the disclosed systems generate modified digital images by performing infill modifications to complete a digital image or human inpainting for portions of a digital image that portrays a human. Moreover, in some embodiments, the disclosed systems perform reposing of subjects portrayed within a digital image to generate modified digital images. In addition, the disclosed systems in some embodiments perform facial expression transfer and facial expression animations to generate modified digital images or animations.

The invention relates to the technical field of intelligent file processing, and discloses an element extraction method and device of a test report, computer equipment and a storage medium, the method comprises the following steps: obtaining scanning document documents of a plurality of paper test reports, and screening out a multi-modal format document from the scanning document documents; identifying and extracting text features, picture features and table features in the multi-modal format document based on an optical character identification technology model; performing paragraph combination on the extracted text features; and extracting structured data from the text features, the picture features and the table features after paragraph combination by adopting a multi-modal element extraction model to obtain a complete electronic document corresponding to the multi-modal format document. Based on an optical character recognition technology, character features, image features and table features in various paper test reports are accurately recognized and extracted by using a number, image and character recognition and extraction technology, and the recognition and extraction accuracy and extraction efficiency are improved.

The invention belongs to the technical field of medical image processing, and discloses a wound identification and charging system based on precision medical treatment, which realizes intelligent management of wound treatment through cooperative work of multiple modules. The method comprises the following steps: firstly, collecting a multi-angle digital image of a wound surface, performing standardization processing, performing image enhancement and noise reduction, and then performing identification and segmentation by using a deep learning algorithm; and performing three-dimensional reconstruction based on the accurate contour map to form parameter feature vectors, and performing intelligent wound type discrimination and severity evaluation. And according to an evaluation result, matching an optimal dressing change type and predicting required consumables, generating a precise dressing change scheme, and further calculating personalized charges and performing transparency verification. And finally, the system automatically generates a standardized medical service file through historical data comparison and rationality analysis. According to the system, the precision, standardization and transparency of wound treatment are realized, the medical service quality is improved, and the resource allocation is optimized.

A computer-implemented method includes receiving a digital image of a document and a workflow describing an automation task. The method also include converting the digital image of the document into rich text that includes layout information in the document. The method further includes creating, based on the rich text and the workflow, a tree of thoughts that includes nodes and edges connecting the nodes and that binds at least some nodes representing the rich text with a task node representing the automation task. The method also includes converting the nodes and edges of the tree of thoughts into a natural language text. The method further includes inputting the natural language text into a language machine learning model with attention given to a token in the natural language text representing the task node. The language machine learning model, in response, outputs a result of completing the automation task.

The present disclosure relates to systems, methods, and non-transitory computer readable media for accurately, efficiently, and flexibly restoring degraded digital images utilizing a deep learning framework for repairing local defects, correcting global imperfections, and / or enhancing depicted faces. In particular, the disclosed systems can utilize a defect detection neural network to generate a segmentation map indicating locations of local defects within a digital image. In addition, the disclosed systems can utilize an inpainting algorithm to determine pixels for inpainting the local defects to reduce their appearance. In some embodiments, the disclosed systems utilize a global correction neural network to determine and repair global imperfections. Further, the disclosed systems can enhance one or more faces depicted within a digital image utilizing a face enhancement neural network as well.

The invention relates to a temperature field and deformation field synchronous measurement system and method based on laser speckle DIC and temperature field algorithm temperature measurement. The system comprises a 3CCD color camera, a lens, a three-band filter, a monochromatic light source, a mechanical support adjusting platform, a triangular support and a computer. A test piece is actively illuminated by blue laser, and a color image containing three channel sub-images of red, green and blue on the surface of a high-temperature sample before and after deformation is acquired by a 3CCD color camera. A temperature field algorithm is used for analyzing sub-images of the R channel and the G channel after deformation to calculate a temperature field of the surface of the test piece, and a digital image correlation method is used for analyzing sub-images of the B channel before and after deformation to obtain a strain field of the surface of the test piece, so that synchronous measurement of the temperature field and the deformation field of the surface of the test piece is realized. The principle is simple, the system structure is compact, temperature field measurement is not interfered by speckles, and non-contact, high-precision and synchronous measurement of a material deformation field and a temperature field under the action of force and thermal loads can be achieved.

In implementation of techniques for re-dimensioning images based on foreground objects, a computing device implements a re-dimension system to receive a digital image and an input specifying an update to a dimension of the digital image. The re-dimension system then generates, using the machine learning model, a re-dimensioned background by changing the background based on the update to the dimension specified by the input. Using the machine learning model, the re-dimension system generates a re-dimensioned digital image by positioning the foreground object over the re-dimensioned background. The re-dimension system then displays the re-dimensioned digital image in a user interface.

The present disclosure relates to systems, methods, and non-transitory computer readable media for generating and composting pixels of a digital image that depict hair of an individual using generative neural networks. In some embodiments, the disclosed systems receive a modification to a face crop enclosing a face depicted within a digital image. In some cases, the disclosed systems determine, from the modification, modified hair pixels within the face crop of the digital image and unmodified hair pixels outside of the face crop of the digital image. The disclosed systems generate, for the unmodified hair pixels outside of the face crop, replacement hair pixels that resemble the modified hair pixels utilizing a generative neural network. Additionally, the disclosed systems generate a modified digital image by replacing the unmodified hair pixels outside of the face crop with the replacement hair pixels.

The invention belongs to the field of tunnel engineering, and particularly discloses a tunnel surrounding rock multi-mode intelligent fine grading method and system, and the method comprises the steps: 1, constructing a sample library which comprises parameters while drilling of a tunnel face, a digital image and a corresponding tunnel face surrounding rock grade; 2, constructing a while-drilling parameter refined grading characteristic system; 3, constructing a surrounding rock intelligent grading model based on multi-modal data fusion; 4, dividing the rock mass in front of the tunnel face into a plurality of three-dimensional space unit bodies according to the tunnel contour and blast hole distribution characteristics; and 5, based on the surrounding rock intelligent grading model, finely and intelligently judging the grade of the tunnel face surrounding rock. According to the method, the intelligent surrounding rock grading model based on the multi-modal data fusion theory is constructed, the refined intelligent judgment of the tunnel face surrounding rock grade is realized, the precision and robustness of the refined intelligent judgment of the surrounding rock grade of the model are improved, the surrounding rock grading level in the construction stage is improved, more comprehensive reference is provided for a subsequent construction scheme, and the construction efficiency is improved. And tunnel intelligent construction is guided.