This technology improves the readability of optical character recognition (OCR) output for low resolution (LR) scanned documents. Super resolution (SR) images are typically generated using multiple LR images. This invention, however, is a single-image super resolution (SISR) method that drastically...

This technology automatically describes and categorizes the topic of text using nouns, allowing it to serve as a foundation for semantic interfacing with a knowledgebase. It has the advantage of not needing stop lists or extensive word stemming, which enables the tool to find words regardless of...

This technology draws on lexical morphology (a branch of linguistics) to improve processing of machine-readable text. This method of morphological text processing provides all inflected forms, or any subset thereof, of an input word or group of words of a highly tone-varying language. By cross-...

This technology uses a simplified, internal algorithm to extract only those sentences from text that convey the essential meaning, providing a concise summary of the full text. The number of sentences is limited to provide a summary of the text with only enough information for a user to determine...