Optimalisasi Kentang Merah dan Kentang Biasa Secara Otomatis Menggunakan Median Filter dan Segmentasi Gambar Berbasis Warna dan Analisis Tekstur: Pendekatan K-Means Clustering

Permata, Edo
Khomsi, Ahmad
Ramadhanu, Agung

Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen)
Vol 6, No 1 (2025): Edisi Januari

In this study, we propose an automated system to identify potato varieties (red and regular potatoes) using color-based image segmentation, median filter, and texture analysis. The system uses K-Means Clustering for color segmentation in Lab color space, followed by the application of median filter to reduce noise in the image, as well as texture feature extraction using Gray-Level Co-occurrence Matrix (GLCM) to distinguish potato types. Experimental results show that the proposed method achieves more than 90% accuracy in identifying potato varieties, demonstrating its potential for industrial applications in tuber processing. Our findings show that the system is robust under various lighting conditions and can significantly reduce human error in the potato sorting process.