Articles tagged with Optical Character Recognition
A new deep learning model, ENDNet, significantly enhances subgraph matching accuracy by identifying and neutralizing extra nodes that interfere with the matching process. This improves performance in pattern recognition tasks across various fields, including drug discovery and natural language processing.
Researchers from Cornell and Tel Aviv University developed ProtoSnap to copy cuneiform characters from photos of tablets. The approach allows for accurate reproduction of characters and whole tablets, making it easier for experts to analyze and compare ancient texts.
Researchers at EPFL developed a next-generation miniaturized brain-machine interface capable of direct brain-to-text communication on tiny silicon chips. The MiBMI system can decode neural signals generated when a person imagines writing letters or words with high accuracy and low power consumption.
A Texas A&M University team, led by historian Dr. Daniel Schwartz, is working to preserve the 2,000-year-old Syriac language, deemed endangered due to conflict and persecution in the Middle East. The project, Syriaca.org, aims to safeguard cultural heritage and make it accessible to expat communities worldwide.
A portable artificial vision device improved daily living tasks for 12 legally blind participants, who performed better when using the device than with their best-corrected visual acuity alone. The device recognizes text, faces, and objects, providing an effective low-vision aid despite technical limitations.
Carnegie Mellon researchers digitize old books with reCAPTCHA, achieving industry-standard transcription accuracy. Over 100 million CAPTCHAs are solved daily, equivalent to hundreds of thousands of hours of human effort.
A new project by Carnegie Mellon University aims to boost book digitization efforts by using reCAPTCHAs to correct OCR mistakes and improve internet security. The system, developed by Luis von Ahn, uses words from troublesome passages to replace artificially distorted letters and numbers in CAPTCHAs.