MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122830 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'litter object detection using deep learning.'
Inventor(s) include Dr. Kalaivani. K; Buvaneshram. K; and Alwin Infant. K.
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 litter object detection system including a data collection module configured to acquire image data containing litter objects from urban environments, a preprocessing module configured to resize images to consistent dimensions and normalize pixel values for neural network processing, a model selection module including three different deep learning architectures including a Convolutional Neural Network (CNN), a You Only Look Once (YOLO) network, and a Siamese Network, a training module configured to train the CNN, YOLO network, and Siamese Network using the image data, and an evaluation module configured to assess performance of the CNN, YOLO network, and Siamese Network using accuracy metrics. The system enables automated identification and classification of waste materials in urban environments through integration of multiple complementary deep learning architectures that leverage respective strengths while compensating for individual limitations."
Disclaimer: Curated by HT Syndication.
