Segmentation of Potato Plants: Leveraging OpenCV and Deep CNNs for Pathogenic Degradation Analysis

DOI

10.2991/978-94-6239-723-1_24How to use a DOI?

Keywords

Potato Plant Disease; Deep CNN; UNet Segmentation; OpenCV

Abstract

There is an increasing need for improving plant health against pathogenic degradation in the potato crop and preventing morphological degradation of Potato plants. In this paper, the exploration of the integration of Deep Convolution Neural Network models for the segmentation and severity estimation of various Plant Diseases in potatoes is focused. Potato plants’ leaf surfaces have been specifically picked for this study. Potatoes are a staple food crop consumed globally. Its production is significantly threatened by various diseases, leading to substantial economic losses. Disease lesion segmentation is crucial for disease management for preserving the morphology of the biological potato plant leaf surfaces. Using OpenCV-based image segmentation and UNet segmentation, analysing the methodologies, datasets, performance metrics, and challenges is crucial. The average severity scores for Potato Early blight, late blight and healthy leaves are 0.0431, 0.0567 and 0.0427 for Plant Village and 0.0449, 0.0508, and 0.0428 for Plant Doc, respectively. Several other segmentation performance metrics for the UNet model achieved are IoU of 0.735 and a Dice Coefficient of 0.847. The testing pixel accuracy came out to be 0.98 for the Plant Village dataset and 0.89 for the Plant Doc dataset.

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  - Kajal Kaul
AU  - Amit Prakash Singh
AU  - Anuradha Chug
PY  - 2026
DA  - 2026/07/14
TI  - Segmentation of Potato Plants: Leveraging OpenCV and Deep CNNs for Pathogenic Degradation Analysis
BT  - Proceedings of the International Conference on Responsible, Risk-aware, and Regulated AI (RRRAI 2026)
PB  - Atlantis Press
SP  - 260
EP  - 266
SN  - 1951-6851
UR  - https://doi.org/10.2991/978-94-6239-723-1_24
DO  - 10.2991/978-94-6239-723-1_24
ID  - Kaul2026
ER  -