MUMBAI, India, April 17 -- Intellectual Property India has published a patent application (202641043637 A) filed by Mr. K. Arjun; Mr. A. S. Jeffrey; and Dr. Sonia Jenifer Rayen, Chennai, Tamil Nadu, on April 6, for 'vision speak: ai-powered multimodal assistive vision system for the visually impaired.'
Inventor(s) include Mr. K. Arjun; Mr. A. S. Jeffrey; and Dr. Sonia Jenifer Rayen.
The application for the patent was published on April 17, under issue no. 16/2026.
According to the abstract released by the Intellectual Property India: "The invention proposes an offline, AI-powered assistive vision system designed to enhance environmental awareness for visually impaired individuals. The system integrates multiple deep learning modules including object detection (YOLOv8), scene text recognition (DBNet + TrOCR), facial emotion analysis (Vision Transformers), and scene captioning (BLIP). These modules operate on edge devices such as smartphones and Raspberry Pi to generate real-time contextual audio feedback using offline text-to-speech. The system improves mobility, safety, and social interaction without relying on cloud infrastructure."
Disclaimer: Curated by HT Syndication.
