Intellectual Property India Publishes Patent Application for 'System And Method For Automated Image Caption Generation With Multilingual Neural Translation' Filed by Malla Reddy Engineering College For Women; and Malla Reddy University

MUMBAI, India, Feb. 27 -- Intellectual Property India has published a patent application (202641017985 A) filed by Malla Reddy Engineering College For Women; and Malla Reddy University, Hyderabad, Telangana, on Feb. 18, for 'system and method for automated image caption generation with multilingual neural translation.'

Inventor(s) include Y. Madhaveelatha; L Vijay Kumar; Somashekhar Sanjeevini; Contractor Gajala Akhtar; Usha Maheswari Chiranjeevi; A V Lsujith; T. Sashi Rekha; and Shaik Mazar Hussain.

The application for the patent was published on Feb. 27, under issue no. 09/2026.

According to the abstract released by the Intellectual Property India: "The invention relates to a system and method for automated image caption generation with multilingual neural translation. The system integrates three primary modules: an image feature extraction network, a caption generation model, and a multilingual translation module. The feature extraction network employs convolutional neural networks or transformer-based vision encoders to derive semantic features from input images. These features are processed by a caption generation model, which utilizes sequence-based architectures such as LSTM, GRU, or transformer models to produce coherent and context-rich textual descriptions. The generated captions are subsequently translated into multiple languages using neural machine translation frameworks, including transformer-based multilingual models such as mBART and mT5, ensuring semantic fidelity and contextual accuracy across diverse linguistic outputs. The invention is implemented as a web-based application, enabling users to upload images and select preferred output languages. Applications include digital media platforms, accessibility tools for visually impaired users, multilingual education systems, and global communication frameworks. By combining vision-language modeling with multilingual translation, the invention enhances inclusivity, accessibility, and user engagement across domains."

Disclaimer: Curated by HT Syndication.