MED-PLANT-XAI: An Explainable Deep Learning and Flask Information Retrieval System for Medicinal Plant Identification via CNN

DOI

10.2991/978-94-6239-654-8_64How to use a DOI?

Keywords

IoT; Health Monitoring; Artificial Intelligence; Vitals Sign Sensing; Pose Estimation; Emotion Recognition; As- tronauts; Elderly Care; Offline Systems

Abstract

Despite the question of traditional medicine, botany or pharmaceutical research, the identification of medici- nal plants is one of the primary ones because of morphological similarity, localism as well as the requirement of a complex system of botanical knowledge. In this paper, the median explainable AI project, MED- PLANTXAI, an automated medicinal plant identification project, is introduced based on the web deployment implemented in Flask, which uses convolutional neural networks (CNN). “Accu- racies (99.84) of 30 different species of medicinal plants were classified with the suggested system with depthwise separable CNNs and were trained using pre-trained architecture of VGG16, ResNet-50 and Inception V3, which was especially successful. Here, the application of Grad-CAM is added to increase trans- parency of the system and consequently trust among the users as it generates the heatmaps that visually explain the choice that the model makes. QuantifyingTensorFlow Lite can be installed on Android to be used on-the-fly and it can support multiple languages through the assistance of Google Translate API. The long medical information retrieval is able to furnish some therapy information as compared with classification only. It is also done by strict application of various data augmentation tools like rotation, shifting, zooming and adjusting of brightness to ensure high model generalization under wide imaging condition. The system architecture will enable the proper identification of the plant and stable use by the various farmers herbalists researchers and traditional medicine practitioners through the real time recognition of the plant as well as availing meaningful information that can be interpreted. Search terms: CNN, Grad-CAM, Explainable AI, Deep learning, flask, tensorflow-lite, Plant Classification, and Multilingual Support; medicinal plants.

Copyright

© 2026 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  - S. Arthika
AU  - S. Mahalakshmi
AU  - Ancy Ancy
PY  - 2026
DA  - 2026/04/24
TI  - MED-PLANT-XAI: An Explainable Deep Learning and Flask Information Retrieval System for Medicinal Plant Identification via CNN
BT  - Proceedings of the Global Conference on Sustainable Energy Systems, Smart Electronics and Intelligent Computing (GCSESEIC 2025)
PB  - Atlantis Press
SP  - 818
EP  - 833
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-654-8_64
DO  - 10.2991/978-94-6239-654-8_64
ID  - Arthika2026
ER  -