Intellectual Property India Publishes Patent Application for 'Automated Crop Disease Detection Using Selective Layer Unfreezing' Filed by Vellore Institute Of Technology

MUMBAI, India, Jan. 2 -- Intellectual Property India has published a patent application (202541122915 A) filed by Vellore Institute Of Technology, Vellore, Tamil Nadu, on Dec. 5, 2025, for 'automated crop disease detection using selective layer unfreezing.'

Inventor(s) include Dr. Kanagaraj R; Mr. Dhruv Sharma; Mr. Ashish Chauhan; and Ms. Lingampalli Raaga Harshita.

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 computer-implemented method (100) for automated crop disease detection. The method includes receiving (102) a plant leaf image upload, preprocessing (104) the image to 224x224 pixels (224x224), normalizing (106) pixel values using ImageNet parameters, loading (108) a fine-tuned ResNet50 model (50) having layers 140-175 (140-175) unfrozen for disease-specific feature adaptation, executing inference (110) to generate disease classification predictions, and calculating (114) a confidence score from softmax output displaying (116) the disease name and confidence percentage. A web-based crop disease detection system (300) provides an interface (302) for receiving plant leaf image uploads, a backend processing system (306), an image preprocessing pipeline (308, 310) resizing images to 224x224 pixels (224x224) and applying ImageNet normalization, a ResNet50 inference engine (312) executing disease classification, and a prediction conversion module (314) transforming outputs to disease classification results returned via JSON responses (316)."

Disclaimer: Curated by HT Syndication.