MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122216 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 4, 2025, for 'ai-powered image captioning system for visually impaired users.'
Inventor(s) include Dr. Muchenedi Hari Kishor; Rohith Chanda; Bollimpalli Takash Chowdary; and Hardhik Madiraju.
The application for the patent was published on Jan. 2, under issue no. 01/2026.
According to the abstract released by the Intellectual Property India: "The present disclosure provides a method (100, 200, 400) for generating audio descriptions of visual content for visually impaired users. The method includes receiving a voice command from a user (202), capturing visual content in response to the voice command (206, 408), processing the captured visual content through a neural network to generate a descriptive caption (410, 412), converting the generated caption to audio output (214), and delivering the audio output to the user (216, 414). The method may involve determining if the voice command corresponds to a screenshot capture instruction (204) and capturing a current screen image when the voice command corresponds to the screenshot capture instruction (206). The processing includes extracting visual features using a convolutional neural network (106), generating a feature vector representation (108), and processing the feature vector through a long short-term memory network to generate the descriptive caption (110, 112)."
Disclaimer: Curated by HT Syndication.
