A computing system includes a storage device and processing circuitry. The processing circuitry is configured to obtain an image frame that comprises a plurality of pixels that form a pixel array. Additionally, the processing circuitry is configured to determine that a region of the image frame belongs to a trigger content type. Based on determining that the region of the image frame belongs to the trigger content type, the processing circuitry is configured to modify the region of the image frame to adjust a luminance of pixels of the region of the image frame based on part on an ambient light level in a viewing area of the user; and output, for display by a display device in the viewing area of the user, a version of the image frame that contains the modified region.

An image of a document is received from an image capture device, the image being in a format of an image file. At least one location of a user input field is automatically detected within the image based on patterns previously detected in a set of other images that were annotated to identify locations of user input fields within the individual images of the set. Coordinates are determined for the at least one location, and an electronic document is generated based on the received image. Generation of the electronic document includes addition of a software user input component at the location within the image with use of the coordinates, the software user input component configured to receive input from a user in electronic form.

Methods and systems are presented for extracting categorizable information from an image using a graph that models data within the image. Upon receiving an image, a data extraction system identifies characters in the image. The data extraction system then generates bounding boxes that enclose adjacent characters that are related to each other in the image. The data extraction system also creates connections between the bounding boxes based on locations of the bounding boxes. A graph is generated based on the bounding boxes and the connections such that the graph can accurately represent the data in the image. The graph is provided to a graph neural network that is configured to analyze the graph and produce an output. The data extraction system may categorize the data in the image based on the output.

To extract necessary information, documents are received, converted to text, and stored in a database. A request for information is then received, and relevant documents and/or document passages are selected from the stored documents. The needed information is then extracted from the relevant documents. The various processes use one or more artificial intelligence (AI), image processing, and/or natural language processing (NLP) techniques.

According to one embodiment, a reading support system includes a processing device. The processing device includes an extractor and a type determiner. The extractor extracts a plurality of regions from a candidate region. The candidate region is a candidate of a region in which a meter is imaged. The regions respectively include a plurality of characters of the meter. The type determiner determines a type of the meter based on positions of the regions.

A computer-implemented method of preloading content includes generating a user interface; receiving a set of object models; processing the received object models; based on detecting an event: (i) receiving a document model; and (ii) rendering the document model via a viewport. A non-transitory computer readable medium contains program instructions that when executed, cause a computer to generate a user interface; receive a set of object models; process the received object models; detect an event; receive a document model; and render the document model via a viewport. A computing system includes a processor and a memory storing instructions that when executed by the process, cause the computing system to generate a user interface; receive a set of object models; process the received object models; detect an event; receive a document model; and render the document model via a viewport.

Described are techniques for font attribute detection. The techniques include receiving a document having different font attributes amongst a plurality of words respectively comprised of at least one character. The techniques further include generating a dense image document from the document by setting the plurality of words to a predefined size, removing blank spaces from the document, and altering an order of characters relative to the document. The techniques further include determining characteristics of the characters in the dense image document and aggregating the characteristics for at least one word. The techniques further include annotating the at least one word with a font attribute based on the aggregated characteristics.

Disclosed herein are systems, methods and devices for identifying, verifying, and authenticating information attained from an individual's worn uniform. The novel technology captures images of uniformed members accessing on-installation facilities, uses computer vision filter and machine learning techniques to identify valuable on-uniform information, and then matches that information with a registered database of names for proper identification, verification, and optional authentication. The rapid identification, verification, and authentication of uniformed personnel significantly reduces the need to fill out excessive paperwork, saves valuable time, and generally streamlines bureaucracy across on-installation facilities.

A system for generating digital flowcharts is provided. The system receives sketch image data comprising a plurality of shapes and text, and processes the sketch image data to generate flowchart data by applying a first model configured to generate shape data, applying a second model configured to generate text data, and generating linking data that associates shape data and text data. The system may generate and display a visualization of the flowchart data. The system may map the flowchart data to a region of a presentation slide and display a visualization of the flowchart data on the presentation slide.

According to implementations of the subject matter described herein, there is provided a solution for text recognition in an image. In this solution, a target text line area, which is expected to include a text to be recognized, is determined from an image. Probability distribution information of a character model element(s) present in the target text line area is determined using a single character model. The single character model is trained based on training text line areas and respective ground-truth texts in the training text line areas. Texts in the training text line areas are arranged in different orientations, and/or the ground-truth texts comprise texts are related to various languages (e.g., texts related to a Latin and an Eastern languages). The text in the target text line area can be determined based on the determined probability distribution information. The single character model enables more efficient and convenient text recognition.