Intellectual Property India Publishes Patent Application for 'Lightweight Deep Learning System For Feature Extraction In Pomegranate Crop Imaging' Filed by Symbiosis International

MUMBAI, India, Jan. 9 -- Intellectual Property India has published a patent application (202521131046 A) filed by Symbiosis International, Pune, Maharashtra, on Dec. 23, 2025, for 'lightweight deep learning system for feature extraction in pomegranate crop imaging.'

Inventor(s) include Mrs. Mrunal Aware; Dr. Deepak S. Dharrao; Mrs. Madhuri Dharrao; and Dr. Anupkumar Bongale.

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: "The present invention relates to a lightweight deep learning system (100) and method (200) for feature extraction and classification in pomegranate crop imaging. The system (100) comprises an image acquisition unit (101), a preprocessing module (102) for normalization and noise removal, a custom convolutional neural network (103) with a Softmax classifier (105), and a MobileNetV2-based lightweight feature extraction module (104) coupled with a global average pooling module (106) and a support vector machine classifier (107). An output module (108) generates disease classification and fruit quality assessment results. The method (200) includes acquiring images (201), preprocessing (202), selectively extracting fruit-specific features (203), feature extraction using a custom CNN (204) and MobileNetV2 (205), pooling (206), classification (207), and generating results (208). The invention enables efficient deployment on low-power agricultural devices."

Disclaimer: Curated by HT Syndication.