MUMBAI, India, Jan. 23 -- Intellectual Property India has published a patent application (202521123379 A) filed by Dr. D. Y. Patil Institute Of Technology, Pune, Maharashtra, on Dec. 8, 2025, for 'botanica - utilizing deep learning for precise identification of medicinal plants and leaves.'
Inventor(s) include Ms. Arti Vilas Sonawane; Gayatri Bhandge; Maansi Sonawane; Vishvachaitanya Wagh; and Tejas More.
The application for the patent was published on Jan. 23, under issue no. 04/2026.
According to the abstract released by the Intellectual Property India: "Identifying medicinal plants can be a difficult job because it is time-consuming as well as tiring. In this study, an approach of classification using a Convolutional Neural Network (CNN), specifically ResNet-101 model has been developed for the identification of ayurvedic plant. ResNet-101 is a famous model for deep residual learning and has the advantage of being able to train very deep networks with reasonable training time due to an efficient way in which it makes gradients clear from vanishing as network depth increases. It offers superior accuracy and performance compared to Resnet50, SVM, VGG19 among other algorithms. Plant-specific leaf images are identified using CNNs to differentiate individual plant leaves and species. The approach is essentially relying on image processing and feature extraction, intelligent models using CNN algorithm is developed. In our study, the accuracy achieved in this method is 98.75% using Resnet101v2 architecture This automated system provides a consistent resource for botanists and researchers to aid in their efforts."
Disclaimer: Curated by HT Syndication.
