MUMBAI, India, Aug. 17 -- Intellectual Property India has published a patent application (202641097132 A) filed by Vellore Institute Of Technology on August 11, 2026, for System And Method For Automated Detection And Classification Of Leather Surface Defects Using Vision Transformers.
Inventors include P Balakrishnan; A Anny Leema; Denis Ashok S; S B Rishabh Poovaiah; and Chirag Garg.
The application for the patent was published on August 14, 2026, under issue no. 33/2026.
Abstract: The present disclosure proposes a system (100) and method for automated detection and classification of defects in leather materials using Vision Transformer (ViT)- based deep learning techniques. The system (100) comprises a computing device (102) having a processor (104) and a memory (106) for storing one or more instructions executable by the processor (104). The processor (104) is configured to execute plurality of functional modules (108) for automated inspection of leather surfaces for detection and classification of defects in an industrial quality control environment. The plurality of functional modules (108) comprises a data acquisition module (110), a pre-processing module (112), a first processing module (114), a second processing module (120), a control module (122), and a generation module (124). The proposed system (100) improves overall accuracy, reliability, and consistency in defect detection and classification compared to conventional methods.
Disclaimer: Curated by HT Syndication.
