MUMBAI, India, July 24 -- Intellectual Property India has published a patent application (202641085162 A) filed by Koneru Lakshmaiah Education Foundation on July 11, 2026, for Transformer-Based System For Detecting Counterfeit Brand Logos In E-Commerce Product Images.
Inventors include Preeti C. M; and Dr. T Santhi Sri.
The application for the patent was published on July 17, 2026, under issue no. 29/2026.
Abstract: The present invention discloses an artificial intelligence-based system and method for detecting counterfeit brand logos in e-commerce product images. The system receives product images, performs preprocessing, and extracts hierarchical visual features using a transformer-based feature extraction network. The extracted features are converted into discriminative embeddings using an ArcFace metric learning model and compared with authenticated logo embeddings stored in a reference database through FAISS similarity search. The system determines logo authenticity based on similarity scores and classification criteria. The invention provides robust detection against image distortions, rotation, blur, occlusion, and manipulation, enabling accurate, scalable, and efficient automated brand logo verification for e-commerce platforms, digital marketplaces, and brand protection applications.
Disclaimer: Curated by HT Syndication.
