2898 results about "Digital image" patented technology

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.

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 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.

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.

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 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.

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 invention discloses an electric power design drawing identification and review method and system, and the method comprises the following steps: S1, obtaining an electric power design drawing, and constructing a primitive library and a rule library; s2, performing primitive recognition on the electric power design drawing based on an edge recognition method and a deep learning method to obtain a corresponding digital image; s3, in OCR recognition, a weak supervised learning method is used, deep learning and a computer vision processing method are combined, texts in the electric power design drawing are recognized, and text information is obtained; s4, comparing the digital image with a primitive library to obtain position and type information of each electrical primitive in the electric power design drawing; and S5, comparing the position, type information and text information of each electrical primitive with a rule base to obtain an identification result, post-processing the obtained identification result, and judging and modifying the result through priori knowledge.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for training and implementing a vision-language model using masked distillation and contrastive image-text training. In particular, in one or more embodiments, the disclosed systems generate, utilizing a vision encoder, an image embedding from a masked digital image comprising a digital image with one or more masked patches. In some embodiments, the disclosed systems generate, utilizing a text encoder, a text embedding from a masked text phrase. In one or more embodiments, the disclosed systems generate, utilizing the vision-language model from the image embedding and the text embedding, a predicted text reconstruction of the text description and a predicted image reconstruction of the digital image. In some embodiments, the disclosed systems modify parameters of the vision-language model according to a masked distillation loss between the predicted text reconstruction and a text reconstruction generated by a pretrained large language model.

A system to capture a plurality of two dimensional digital source images of a scene / event by a user, including a memory device for storing an instruction, a processor in communication with the memory and configured to execute the instruction, a digital image capture device in communication with the processor configured to capture a digital image of the scene, the processor configured to execute an instruction to generate a plurality of two dimensional digital images of the scene from said first two dimensional digital image of the scene via a camera angle rotation of between 1-180 degrees of said first two dimensional digital image of the scene for each of said plurality of two dimensional digital image of the scene as a sequence, and a display in communication with the processor, the display configured to display a multidimensional digital image sequence of an event.

The invention relates to a deformation online measurement and control method for multi-robot collaborative assembly. The method comprises the steps that multi-view surface images of workpieces in the assembly process are collected in real time through distributed robots and cameras arranged at the tail ends of the distributed robots; each view angle surface image is input into a deep learning model trained based on a digital image related technology, the optimal pixel displacement corresponding to each view angle surface image is output, and the optimal pixel displacement corresponding to each view angle surface image is converted into a spatial displacement label; the deep learning model takes an encoder-decoder as a trunk network; fusing the spatial displacement labels corresponding to the view angle surface images to obtain a fused displacement field; based on the fusion displacement field and the nominal path planning point, the tail end pose of the distributed robot is determined; the assembly error is calculated based on the reference target positioning and the tail end pose, and the PID controller adjusts the joint space of the distributed robot based on the assembly error. According to the method, the calculation overhead is remarkably reduced, and the measurement precision and robustness are improved.

The invention relates to the field of digital image detection and signal processing, and particularly discloses an unmanned aerial vehicle tracking aerial target vehicle trajectory generation method, which comprises the following steps of: constructing a moving target detection neural network model, and performing stage processing on micro, medium and fast moving optical flow features on an input image by the model through a hierarchical cascade optical flow attention mechanism to obtain a moving target detection neural network model; motion processing of video frames is improved using bidirectional timing optical flow enhancement. Inputting a target vehicle video into a model to obtain a center coordinate of a target vehicle detection frame in each frame as a position coordinate of a vehicle, and connecting the position coordinates according to a time sequence to form a preliminary track; performing decoupling compensation of the motion of the unmanned aerial vehicle on the initial track through a multi-scale adaptive dense optical flow algorithm; performing coordinate transformation to obtain a roughly estimated trajectory of the trajectory after decoupling compensation in a geodetic coordinate system; and identifying an abnormal frequency through wavelet transform, removing noise points by using Lagrange interpolation, and de-noising by applying extended Kalman filtering to generate an accurate trajectory of the target vehicle.

The invention relates to the technical field of digital image security and authentic identification, and provides an image tampering detection method and system based on mixed features and RGB features, and the method comprises the steps: obtaining a to-be-detected input image, and carrying out the preprocessing of the to-be-detected input image; respectively extracting a Haar wavelet high-frequency component, a discrete cosine transform frequency domain feature and a Bayer convolution noise feature, and carrying out matrix level fusion to obtain a mixed feature; extracting RGB (Red, Green and Blue) features for the preprocessed input image; the mixed features are connected through cross-layer residual errors, and mixed feature learning features are obtained; and integrating the mixed feature learning features and the fused RGB features by using a cross-modal feature interaction architecture to obtain a prediction probability graph. Multi-modal features are fused, high-frequency response is enhanced, and the accuracy of image tampering detection is improved by adopting a dynamic fusion mechanism. The technical problems that an existing tampering detection method is insufficient in feature characterization capacity in a complex scene, low in tampering trace detection sensitivity and the like are solved.

The invention relates to the technical field of digital image processing and digital printing control, in particular to a digital printing color calibration method and system based on real-time image processing, and the method comprises the steps: constructing a fabric surface feature point coordinate set through a mixed feature tracking technology; calculating and predicting a target deformation field of the fabric at the printing position by applying a self-adaptive time domain prediction algorithm; and performing dynamic pixel interpolation on the original digital image by combining the target deformation field and the fabric texture feature map analyzed in real time to generate final printing image data. According to the invention, by combining high-robustness tracking, high-precision adaptive prediction and high-fidelity image generation technologies, the geometric precision and visual quality of printed products are significantly improved.

A system to capture a two dimensional digital source image of a scene by a user, including a smart device having a memory device for storing an instruction, a processor in communication with the memory and configured to execute the instruction, a digital image capture device in communication with the processor, said processor configured to capture a first two dimensional digital source image of the scene, said processor configured to execute an instruction to generate a second two dimensional digital image of the scene from said first two dimensional digital image of the scene via a camera angle rotation of between 1-180 degrees of said first two dimensional digital image of the scene, and a display in communication with the processor, the display configured to display a multidimensional digital image.

The invention relates to the technical field of digital image correlation DIC measurement, in particular to a DIC displacement field dynamic correction method and system based on a lightweight convolutional network, and the method comprises the steps: 1, collecting a structure surface image sequence, and carrying out the preprocessing; 2, calculating an initial displacement field of the preprocessed image sequence through a traditional DIC algorithm, extracting key feature information, and taking the key feature information as input data for dynamic correction; 3, constructing a lightweight convolutional neural network model, transmitting the extracted input data to the lightweight convolutional neural network model for recognition, designing a mixed loss function for training, and learning a mapping relation between an initial displacement field and a real displacement field; and 4, correcting the initial displacement field through the trained lightweight convolutional neural network model, and directly outputting corrected high-precision displacement field data. By using the function fitting capability of the neural network, high-precision displacement field correction is realized under limited computing resources, and the measurement precision is improved.

The invention discloses an intelligent agent digital image interaction generation method based on multi-modal perception, which comprises the following steps: collecting multi-modal input data of a user, and respectively carrying out preprocessing and feature extraction on the multi-modal input data; inputting to an improved efficient modal cross learning network, and carrying out multi-modal feature fusion processing; constructing a semantic intention map, introducing a time index edge weight and an emotion driving edge weight, and encoding the map by using a structure perception map neural network; a modal style vector is extracted through a cross-modal style contrast learning mechanism, and a personalized style coding vector is generated through a hierarchical nested structure; inputting a personalized regulation and control gating mechanism, and regulating and controlling the middle layer representation in the interaction strategy generation process by adopting a feature channel linear modulation method; inputting the representation vector into a behavior strategy generation module to generate a multi-modal behavior output sequence; and the sequence is output to drive the digital image to perform synchronous response, and natural response generation in the user interaction process is completed.

Methods and systems are presented for classifying a digital image of a document using a machine learning model framework. The machine learning model framework is configured to provide a classification output based on a fusion of features corresponding to different modalities and extracted from the digital image. The machine learning model framework includes multiple encoders. Each encoder is configured to encode features corresponding to a distinct modality into a respective embedding. Different embeddings generated by the multiple encoders are fused together using one or more fusion techniques. The fused embedding is provided to a machine learning model for classifying the document.

A grain loss detector disposed on a combine harvester to detect grain loss within crop material being discharged by a separating or cleaning stage component of combine harvester while harvesting a crop. The grain loss detector includes at sensor generating sensor data output. A computing device receives the sensor data output for processing via software which compares the sensor data output against crop data characteristics to identify any grain kernels from among material other than grain. In one embodiment the sensor is a camera and the generated sensor data output is a digital image frame capturing the grain kernels and material other than grain passing the camera.

Methods, systems, and non-transitory computer readable storage media are disclosed for generating digital images with a diffusion-based generative neural network conditioned on background-extracted lighting features. The disclosed system determines, in response to a request to generate a digital image, a target background image for inserting a foreground object into the target background image. The disclosed system generates, from the target background image and utilizing a lighting conditioning neural network, a lighting feature representation indicating one or more lighting parameters of the target background image. Additionally, the disclosed system generates, utilizing a diffusion-based generative neural network conditioned on the lighting feature representation, the digital image including the foreground object inserted into the target background image based on a composite image comprising the foreground object and the target background image with a foreground mask corresponding to the foreground object.

The present disclosure relates to systems, methods, and non-transitory computer-readable media that modifies parameters of a fused feature extractor. In particular, the disclosed systems generate inferred masks from digital images and digital text prompts using a fused feature extractor. Furthermore, the disclosed systems identify a subset of the inferred masks that satisfy a validity threshold. Moreover, the disclosed systems generate an augmented training set by combining the subset of the inferred masks with a training set that includes the ground truth masks. Further, the disclosed systems generate object mask predictions from the augmented training set and determine ground truth and pseudo measures of loss by comparing the object mask predictions with the inferred masks and the ground truth masks. From the ground truth and pseudo measures of loss, the disclosed systems modify parameters of the fused feature extractors.

The present disclosure relates to systems, methods, and non-transitory computer readable media that generate segment labels for image segments of a digital image that have been determined via deep segmentation. For instance, in some embodiments, the disclosed systems generate, using a segment classification neural network, an image embedding for a digital image portraying a plurality of image segments. Additionally, the disclosed systems determine, using the segment classification neural network, masked segment embeddings for the plurality of image segments of the digital image based on the image embedding and a plurality of masks corresponding to the plurality of image segments. Based on the masked segment embeddings, the disclosed systems use the segment classification neural network to determine segment labels for the plurality of image segments.

The invention relates to the technical field of biomedical engineering and digital image processing, in particular to a digital image enhancement method based on cytopathology. The method comprises the following steps: eliminating noise and artifacts caused by non-uniform dyeing, section folding and dust factors; the problem of dyeing difference caused by different scanning devices is solved; key areas including cell nucleuses and cell membranes are highlighted, so that the visual effect of a low-contrast image is improved; segmenting an area, including cell nucleuses and cytoplasm, of the cells, and extracting morphological characteristics; the detail resolution of a low-resolution image, especially the definition of a small cell structure, is improved; the brightness component Y is corrected to compensate for the difference of different dyeing methods and dyeing qualities in brightness response, then the chromatic value is adjusted according to the color correction factor to make the colors of the images more consistent, and finally, the images which are acquired by different dyeing methods and dyeing qualities and subjected to brightness and chroma correction are fused to make the color of the images more consistent. And a final corrected image is obtained.

The invention relates to the technical field of torque sampling inspection, in particular to a torque sampling inspection method and system. Comprising the following steps: tool identity digitization: performing laser etching on an encrypted two-dimensional code in a tool stress concentration area, and associating and storing tool specification parameters, detection standards and use constraint conditions to a central database; intelligent task allocation: the system generates a dynamic detection plan according to a production line real-time state, an equipment service cycle and an operator skill level; multi-source data acquisition: acquiring tool identity information through a scanning device, and synchronously acquiring a physical signal of a torque detection device and a digital image of a tool identification file; grading judgment processing: performing process conformity verification on the measurement data, and generating a process stability evaluation report in combination with historical detection records; according to the closed-loop control strategy, the detection scheme is automatically adjusted according to the quality fluctuation characteristics. According to the scheme, the problem that a traditional method is seriously insufficient in the aspects of detection efficiency, abnormal traceability, process control and the like can be solved.

A high dynamic range editing system is configured to generate visualizations to aide digital image editing in both high dynamic ranges and standard dynamic ranges. In a first example, the visualization is generated as a histogram. In a second example, the visualization is generated to indicate high dynamic range capabilities. In a third example, the visualization is generated to indicate ranges of luminance values within a digital image. In a fourth example, the visualization is generated as a point curve that defines a mapping between detected luminance values from a digital image and output luminance values over both a standard dynamic range and a high dynamic range. In a fifth example, the visualization is generated as a preview to convert pixels from the digital image in a high dynamic range into a standard dynamic range.