PERBANDINGAN METODE KNN DAN SVM DALAM KLASIFIKASI KEMATANGAN BUAH MANGGA BERDASARKAN CITRA HSV DAN FITUR STATISTIK

Mutmainnah Muchtar (Universitas Sembilanbelas November Kolaka)
Rafiqah Arjaliyah Muchtar (Universitas Halu Oleo Kendari)

Jurnal Informatika dan Teknik Elektro Terapan
Vol 12, No 2 (2024)

This research compares the classification methods of K-Nearest Neighbors (KNN) and Support Vector Machine (SVM) in identifying the ripeness level of mango fruit based on HSV images and statistical features. A total of 80 mango fruit images were categorized into two classes, namely "ripe" and "unripe" mango, with 40 images each. Testing was conducted using k-cross validation, revealing that KNN achieved an accuracy of 98.75%, while SVM reached 97.5%. KNN demonstrated superior and consistent performance, indicating its effectiveness in mango fruit ripeness classification. The study contributes to the advancement of automated systems for mango fruit processing, leveraging image technology and machine learning to support the agriculture and food industry.