Intellectual Property India Publishes Patent Application for 'Lightweight Cnn With Dual-Activation Efficient Channel Attention For Tomato Leaf Disease Detection' Filed by MLR Institute of Technology; and Marri Laxman Reddy Institute Of Technology And Management

MUMBAI, India, May 1 -- Intellectual Property India has published a patent application (202641050057 A) filed by MLR Institute of Technology; and Marri Laxman Reddy Institute Of Technology And Management, Hyderabad, Telangana, on April 20, for 'lightweight cnn with dual-activation efficient channel attention for tomato leaf disease detection.'

Inventor(s) include Dr. Sivaramakrishna Yechuri; Mr. C. Akhil; Mr. D. Narsimlu; Ms. G. Bhavana; and Ms. Sree Deepika.

The application for the patent was published on May 1, under issue no. 18/2026.

According to the abstract released by the Intellectual Property India: "The invention discloses a lightweight convolutional neural network (CNN) integrated with Dual-Activation Efficient Channel Attention (DualECA) for the classification of tomato leaf diseases. The DualECA mechanism utilises dual activation functions (Sigmoid and tanh) to enhance channel feature recalibration, thereby improving disease discrimination. The lightweight CNN model is used for extracting the features effectively. The model is trained on hybrid datasets (PlantVillage and PlantDoc), ensuring robustness in both controlled and field conditions. With only 1.46M parameters (~5.6 MB), the architecture achieves 98.9% classification accuracy while maintaining computational efficiency for real-time mobile deployment. The invention addresses the limitations of existing models by providing a scalable, accurate, and cost-effective solution for sustainable tomato farming."

Disclaimer: Curated by HT Syndication.