AI-Based Ayurvedic Leaf Analysis and Recommendations

DOI

10.2991/978-94-6463-858-5_85How to use a DOI?

Keywords

Leaf classification; Ayurvedic medicine; Deep learning; CNN; EfficientNet; Vision Transformer; Plant disease detection; Maturity mapping

Abstract

Ayurvedic classical medicine depends, to a greater extent, upon the accurate identification, health appraisal and ripeness estimation of medicinal leaves. Yet, all such classification through manual processes involves expertise-based discrimination, takes lot of time, and hence contributes to variations when establishing their medico-usability. The available AI-powered models of plant analyses concentrate more or less on recognizing species alone while largely overlooking essential considerations such as health evaluation and ripeness estimation, which Ayurveda stresses in importance. Traditional deep learning techniques, though efficient for classification, are poor at fine-grained detailed analysis and hence provide suboptimal recommendations.

LeafScan AI, a three-stage AI system, is proposed in this paper to improve Ayurvedic leaf classification and usability evaluation. LeafSense, the first stage, uses a CNN-based model to detect the leaf species from the image. Health- Guard, the second stage, uses EfficientNet for binary classification to check if the leaf is healthy or not. Lastly, the third phase, AyurCheck, utilizes a Vision Transformer (ViT) to examine healthy leaves for maturity and medicinal value and diagnose unhealthy leaves and mark them as unusable for medicine preparation. The organized, multi- phase methodology results in an accurate, consistent, and scalable process for Ayurvedic practitioners, researchers, and pharmaceutical companies. The suggested method reduces human subjectivity, boosts efficiency, and offers an automatic pipeline for medicinal leaf assessment.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Ambekar Tejas
AU  - Kethan Chandar Reddy
AU  - Sravan Kumar Battu
AU  - Vemula Vasuki Rohini Devi
PY  - 2025
DA  - 2025/11/04
TI  - AI-Based Ayurvedic Leaf Analysis and Recommendations
BT  - Proceedings of International Conference on Computer Science and Communication Engineering (ICCSCE 2025)
PB  - Atlantis Press
SP  - 1018
EP  - 1033
SN  - 2352-538X
UR  - https://doi.org/10.2991/978-94-6463-858-5_85
DO  - 10.2991/978-94-6463-858-5_85
ID  - Tejas2025
ER  -