Interpretable ANN-Based Computer Vision System for Mangosteen Ripeness Detection for Export Markets

Simple item page
dc.contributor.authorLapcharoensuk, Ravipat
dc.contributor.authorTosribunjerd, Naphon
dc.contributor.authorPoonpakdee, Pasu
dc.date.accessioned2026-08-06T10:54:29Z
dc.date.available2026-08-06T10:54:29Z
dc.date.issued2026-01-21
dc.description.abstractMangosteen is a high-value tropical fruit widely consumed and exported from Thailand. Mangosteen ripeness classification is crucial for export quality control, but manual grading leads to inconsistency and inefficiency. This study presents a computer vision system using an Artificial neural network to classify mangosteen into ripe, semi-ripe, and unripe stages based on peel color. A dataset of 378 images was collected and processed to extract 40 color-based features across multiple color spaces. Principal Component Analysis demonstrated non-linear separability among the ripeness classes. SMOTE and Gaussian noise augmentation were used to tackle data imbalance and enhance generalizability. The model reached a 95% accuracy rate and displayed flawless precision and recall for the ripe class. Integrated Gradients analysis highlighted the importance of the red-green color component (CIELAB a*) in the classification process. The proposed method demonstrates a low-cost, interpretable, and efficient solution suitable for real-world application in the mangosteen export industry.
dc.identifier.citationAsse 2025 2025 6th Asia Service Sciences and Software Engineering Conference, 1-6, 2026
dc.identifier.doi10.1145/3775030.3775032
dc.identifier.other2-s2.0-105030339879
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/17838
dc.sourceAsse 2025 2025 6th Asia Service Sciences and Software Engineering Conference
dc.subjectArtificial neural network
dc.subjectComputer vision
dc.subjectIntegrated Gradients
dc.subjectMangosteen
dc.titleInterpretable ANN-Based Computer Vision System for Mangosteen Ripeness Detection for Export Markets
dc.typeConference Paper

Files

Collections

Research