MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202541133604 A) filed by Nitte, Mangaluru, Karnataka, on Dec. 30, 2025, for 'a dual-model smart waste classifier system.'
Inventor(s) include Dr. Anantha Murthy; Harshitha; and Mohammad Rehan.
The application for the patent was published on Jan. 9, under issue no. 02/2026.
According to the abstract released by the Intellectual Property India: "Disclosed herein is a dual-model smart waste classifier system using CNN and MobileNetV2 with gradio integration (100) comprises an image acquisition and interface module (102) configured to receive a waste image from a user. The system also includes a modular pre-processing module (104) configured to dynamically process the received image. The system also includes a first machine-learning classification module (106) comprising a custom-built Convolutional Neural Network (CNN). The system also includes a second machine-learning classification module (108) comprising a MobileNetV2 architecture initialized with pre-trained ImageNet weights and fine-tuned on the same labeled waste dataset to provide high-accuracy prediction using transfer learning. The system also includes a dual-model inference module (110) configured to selectively route the pre-processed image to either the CNN model or the MobileNetV2 model based on the user's input. The system also includes a deployment and visualization module (112) configured to render the classification output in real time."
Disclaimer: Curated by HT Syndication.
