MUMBAI, India, Sept. 28 -- Intellectual Property India has published a patent application (202641112850 A) filed by Sri Eshwar College Of Engineering on September 21, 2026, for Machine Learning-Based Vector Margin Classifier For Analysis Of Sanjeevani In Marunthuvazh Malai Using Feature Extraction.
Inventors include T Sahila; and Dr. N. Muthukumaran.
The application for the patent was published on September 25, 2026, under issue no. 39/2026.
Abstract: The identification and recognition of medicinal plants through intelligent systems have become important for monitoring ecology and conserving biodiversity. The Sanjeevani plant, found in the Marunthuvazh Malai area, is particularly interesting because of its medicinal value and morphological differences. This work aims to present a Machine Learning (ML)-based classification approach to identify and distinguish Sanjeevani plant categories (Green and Dry) from other hill herbs automatically based on image-based characteristics. The proposed approach integrates a hybrid feature extraction method involving Gray-Level Co-occurrence Matrix (GLCM) for texture features and a pretrained Residual Network (ResNet) model for deep visual features. The study utilized Latent Diffusion Models (LDM) for data augmentation to strengthen model resistance with real samples. These features are selected through Recursive Feature Elimination (RFE), and plant identification is performed using a Vector Margin Classifier.
Disclaimer: Curated by HT Syndication.
