Intellectual Property India Publishes Patent Application for 'Deep Learning Based Welding Defect Classification Using Mobilenet And Prediction Result Through Weld Classifier Bot' Filed by V. Antony Aroul Raj

MUMBAI, India, Feb. 6 -- Intellectual Property India has published a patent application (202541122423 A) filed by V. Antony Aroul Raj, Chennai, Tamil Nadu, on Dec. 5, 2025, for 'deep learning based welding defect classification using mobilenet and prediction result through weld classifier bot.'

Inventor(s) include V. Antony Aroul Raj; Praveen Kumar M; and Neeraj Kumar Boraik.

The application for the patent was published on Feb. 6, under issue no. 06/2026.

According to the abstract released by the Intellectual Property India: "The invention presents a novel Deep Learning-Based Welding Defect Classification System using the MobileNet architecture and Weld Classifier Bot for real-time defect detection. Welding images are sent to the Telegram bot, which forwards them to a deep learning model for processing and classification. This system enhances accuracy, reduces inspection time, and minimizes human intervention. Designed for manufacturing and industrial applications, it offers a cost-effective, automated solution for welding quality inspection, addressing inefficiencies in traditional manual and hardware-based defect detection methods."

Disclaimer: Curated by HT Syndication.