MUMBAI, India, July 7 -- Intellectual Property India has published a patent application (202541000316 A) filed by Shri Madhwa Vadiraja Institute Of Technology And Management on January 02, 2025, for A System And Method For Converting Image-Based Text To Speech For Accessibility Enhancement.
Inventors include Raghavendra Gs; Rathan R Nayak; Suhas Bhat; Sherigar Pradwin Madhava; and Sriharsha Upadhya P.
The application for the patent was published on July 03, 2026, under issue no. 27/2026.
Abstract: This invention describes an overall scheme of complex ITTTS system that provides additional facilities for people with vision impairment and other people having reading issues. The proposed framework uses connected component analysis and MSER algorithms for the detection and analysis of text in various image types to improve efficiency and accuracy of text processing. It is intended for working with noisy or low-quality images, multilingual and developed for comfortable and easy usage with an adaptive interface. Verified on large databases, the system shows a great deal of potential to enhance the relevance of existing web resources, promote the learning and understanding processes, and integrate disabled people into the process of active Internet communication as consumers and producers of content, proving to be an effective realization of the idea of turning visuals in real-life applications.
Disclaimer: Curated by HT Syndication.
