COMPUTATIONAL IMAGE PROCESSING FOR DEFECT DETECTION AND QUALITY ASSESSMENT OF AGRICULTURAL PRODUCTS
AMA, AGRICULTURAL MECHANIZATION IN ASIA, AFRICA AND LATIN AMERICA, cilt.3, sa.57, ss.1-16, 2026 (SCI-Expanded)
- Yayın Türü: Makale / Tam Makale
- Cilt numarası: 3 Sayı: 57
- Basım Tarihi: 2026
- Dergi Adı: AMA, AGRICULTURAL MECHANIZATION IN ASIA, AFRICA AND LATIN AMERICA
- Derginin Tarandığı İndeksler: Science Citation Index Expanded (SCI-EXPANDED)
- Sayfa Sayıları: ss.1-16
- Dokuz Eylül Üniversitesi Adresli: Evet
Özet
This study investigates the application of computational image processing techniques for detecting mechanical damage and quality assessment in agricultural products, with a focus on Golden Delicious apples. Postharvest fruits are exposed to physical and chemical stresses that alter their surface properties, which can be quantitatively analyzed using computer vision. By employing MATLAB-based algorithms in the HSV (Hue, Saturation, Value) color space, color variations were segmented and morphological operations were applied to identify defect regions. A controlled imaging system was designed to minimize shadow effects from multiple light sources, ensuring reproducibility of results. The percentage of damaged areas was calculated, providing an objective metric for quality evaluation. Beyond agricultural applications, this computational approach demonstrates the potential of image-based defect quantification as a material characterization method, aligning with the broader scope of computational materials science. The integration of image segmentation, morphological analysis, and quantitative defect evaluation highlights the role of computer vision as a scalable and reliable tool for material quality assessment.