The application is directed to the generation of training materials for optical character recognition. Generating the training materials for optical character recognition can include selecting a plurality of terms that include a string of characters. For each term, generating multiple digital term images that each includes the term with a different visual appearance. For generation of a training document, the method includes positioning the term images on a digital background and generating the digital training material.

An apparatus for identifying the state of an object includes a processor configured to input, every time obtaining an image from a camera, the image into a first classifier to detect, for each of one or more predetermined objects represented in the image, an object region including the object; determine a predicted object region in a subsequent image to be obtained from the camera for an object whose position in the subsequent image is predictable; and input characteristics into a second classifier to identify the state of an object involving time-varying changes in outward appearance. When the object has a predicted object region, the characteristics are obtained from pixel values of the predicted object region in the subsequent image. On the other hand, when the object does not have a predicted object region, the characteristics are obtained from pixel values of the object region detected from the subsequent image.

Disclosed are an artificial intelligence-based legal document analysis system and method. The present invention can provide relevant laws and detailed explanation by analyzing the legal risk in a legal document having a structure such as legal clauses, terms and conditions and contracts by automatically comprehending the meaning by means of an artificial intelligence technology, and perceiving omissions and erroneous risk elements in the contract.

Detection of typed and/or pasted text, caret tracking, and active element detection for a computing system are disclosed. The location on the screen associated with a computing system where the user has been typing or pasting text, potentially including hot keys or other keys that do not cause visible characters to appear, can be identified and the physical position on the screen where typing or pasting occurred can be provided based on the current resolution of where one or more characters appeared, where the cursor was blinking, or both. This can be done by identifying locations on the screen where changes occurred and performing text recognition and/or caret detection on these locations. The physical position of the typing or pasting activity allows determination of an active or focused element in an application displayed on the screen.

Methods, apparatus, systems and articles of manufacture are disclosed for receipt decoding. An example apparatus for processing a receipt associated with a user disclosed herein includes an optical character recognition engine to generate bounding boxes, respective ones of the bounding boxes associated with groups of characters detected in the receipt, the bounding boxes including a first bounding box, a second bounding box and a third bounding box, a word connector to connect the first bounding box to the second bounding box based on (1) an adjacency of the first bounding box to the second bounding box and (2) a difference value from a comparison of a location of the first bounding box to a location of the second bounding box, a line connector to form a line of the ones of the bounding boxes by connecting the third bounding box to the second bounding based on a relationship between the first bounding box and the second bounding box, the line of the ones of the bounding boxes indicative of related receipt fields, and a creditor to generate a report based on the line.

An electronic device for providing a corrected response message according to an utterance intention of a user by using a keyword included in an input inquiry input by the user, and an operation method of the electronic device are provided. The electronic device includes receiving the input inquiry input by the user, identifying a representative inquiry according to an utterance intention of the user by analyzing the input inquiry by using a natural language understanding (NLU) model, extracting a keyword from the input inquiry by comparing a vector value of a first embedding vector of the input inquiry changed through the NLU model with a vector value of a second embedding vector of the representative inquiry, and correcting a response message mapped to correspond to the representative inquiry, by using the extracted keyword.

An interactive system for identifying and correcting inconsistencies between a written work, an audio reading of the written work, and a resulting transcription of the audio reading. The system stores on a computing device connected to a network a manuscript, an audio version of the manuscript, and a transcription of the audio version of the manuscript. Via a transcription engine, difference and comparison engine, and a user device having a visual interface, a user is visually presented via the display the inconsistencies between the transcript and the manuscript, the user can amend the manuscript and/or the transcript to reconcile the works, the user can listen to a corresponding section of the corresponding audio file, and the user can interact with collaborators in a context aware interface. Upon the user processing, the manuscript may be read and listened to simultaneously as an enhanced e-book through a separate software tool.

Systems and apparatuses are disclosed for extracting information from document images. An example method includes segmenting a document image into multiple segments and determining formatting information for each segment. Determining formatting information for a segment includes determining one or more features of the segment and comparing the one or more features of the segment to one or more clusters of features associated with different document types. The formatting information for the segment is based on the comparison. The method also includes, for each segment, storing the formatting information in a data structure associated with the segment. The method further includes, for each segment including text to be identified during information extraction, applying OCR to the segment to generate machine-encoded text and storing the machine-encoded text in the associated data structure.

Systems, methods, and devices for data ingestion and aggregation, file analysis, and predictive modeling. A method includes ingesting an unstructured file comprising text. The method includes providing the unstructured file to a file analysis machine learning algorithm configured to execute optical character recognition processing to identify one or more textual characters in the unstructured file. The method includes assigning the one or more identified textual characters to a data bucket associated with an aggregated data form. The method includes generating a virtual file comprising information from the aggregated data form, wherein the virtual file comprises structured data and unstructured data.

An image processing device includes: an image sensor for acquiring a pixel value of each of a plurality pixels; and a controller for acquiring a pattern image including the pixel value of each of the plurality of pixels and an exposure value representing an exposure time, generating a plurality of super resolution images based on pixels having the same exposure value among the plurality of pixels included in the pattern image, generating a motion map, which represents a motion of an object based on a ratio of exposure values of pixels at a selected position among a plurality of pixels included in the plurality of super resolution images and a ratio of pixel values of the pixels at the selected position, and generating a target image according to a weighted sum of the plurality of super resolution images and the motion map.