MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521131042 A) filed by Symbiosis International, Pune, Maharashtra, on Dec. 23, 2025, for 'system and method for rice variety classification using convolutional neural network architecture.'
Inventor(s) include Shreyas Rajendra Hole.
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: "A computer-implemented system for classifying rice varieties from image data using convolutional neural networks is disclosed. The system comprises a memory storing executable instructions and a processor coupled to the memory configured to execute the instructions. The system comprises an image preprocessing module configured to perform pixel intensity normalization and apply data augmentation transformations comprising rotation, translation, flipping, zooming, and brightness variation. The system comprises a convolutional neural network architecture module configured to process images through three hierarchical convolutional blocks with thirty-two, sixty-four, and one hundred twenty-eight filters respectively, each block comprising convolutional layers with ReLU activation and max pooling operations. The system comprises a feature extraction module configured to generate hierarchical feature maps representing grain texture, color, shape, and edge curvature characteristics. The system comprises a classification module configured to classify extracted features using fully connected layers with softmax activation to compute probability distributions across five rice variety classes."
Disclaimer: Curated by HT Syndication.
