Comparative Evaluation of Classical Segmentation Methods for Cocoa Pods in Uncontrolled Field Images: Accuracy and Structural Robustness
Authors:
- Fermín Martínez-SolísFMFermín Martínez-Solís
- Mary de Los Santos Córdova-ÁlvarezMCMary de Los Santos Córdova-Álvarez
- Reymundo Ramírez-BetancourtRRReymundo Ramírez-Betancourt
- Erika V. Miranda-MandujanoEMErika V. Miranda-Mandujano
- Humberto Noverola-GamasHNHumberto Noverola-Gamas
- Jesus Lopez-GomezJesus Lopez-Gomez
Open Access
- 7 July 2026
- journal article
- research article
- Published by MDPI AG in Agriengineering
- Vol. 8 (7) , 277
Abstract
Image segmentation is a critical step in computer vision systems for phytosanitary diagnosis in cacao production. However, the reliability of classical segmentation methods remains insufficiently assessed under real field conditions, where images captured under non-standardized conditions are often affected by variable illumination, complex backgrounds, partial occlusions, and chromatic similarity between cacao pods and surrounding vegetation. This study compares global thresholding, K-means clustering, and GrabCut using 343 cocoa pod images captured in uncontrolled agricultural environments with non-standardized mobile devices; low-resolution images were retained to preserve external validity. Robustness was assessed on the full dataset using unsupervised structural metrics, including the segmented area ratio (AS), the largest component ratio (LCR), and the catastrophic failure rate (FC), while accuracy was validated on 50 manually annotated images using Intersection over Union (IoU). Wilcoxon signed-rank tests indicated statistically significant differences among methods. GrabCut achieved the best performance (IoU = 0.814), high structural coherence (LCR = 0.985), and a low catastrophic failure rate (FC = 1.7%). In contrast, K-means showed severe fragmentation and instability, whereas global thresholding was highly sensitive to illumination variability and complex backgrounds. These results indicate that GrabCut provides a robust training-free baseline for cocoa pod segmentation under uncontrolled field conditions, particularly for offline phytosanitary analysis where annotated datasets, supervised training, or GPU-based deployment are limited.Keywords
Funding Information
- Consejo de Ciencia y Tecnología del Estado de Tabasco (PRODECTI-2023-01/142)
This publication has 27 references indexed in Scilit:
- CocoaMoniliaDataSet: A cocoa pod dataset to detect and classify Monilia roreri in real conditionsData in Brief, 2026
- Automatic pixel-level annotation for plant disease severity estimationComputers and Electronics in Agriculture, 2025
- A review on automated plant disease detection: motivation, limitations, challenges, and recent advancements for future researchJournal of King Saud University Computer and Information Sciences, 2025
- Deep learning and computer vision in plant disease detection: a comprehensive review of techniques, models, and trends in precision agricultureArtificial Intelligence Review, 2025
- Deep learning implementation of image segmentation in agricultural applications: a comprehensive reviewArtificial Intelligence Review, 2024
- Sustainable practices in cocoa production. The role of certification schemes and farmer cooperativesEcological Economics, 2024
- Computer vision for plant pathology: A review with examples from cocoa agricultureApplications in Plant Sciences, 2023
- Robust plant segmentation of color images based on image contrast optimizationComputers and Electronics in Agriculture, 2022
- Artificial Neural Network: Models, Applications, and Challenges2021
- Deep learning in agriculture: A surveyComputers and Electronics in Agriculture, 2018