Identifikasi Varietas Anggur Secara Otomatis Menggunakan Segmentasi Gambar Berbasis Warna dan Analisis Tekstur: Pendekatan K-Means Clustering
A Afriadi, Jefri Harnaranda, Agung Ramadhanu
Abstract
In this study, we propose an automated system for identifying grape varieties (red and green) using color-based image segmentation and texture analysis. The system employs K-Means Clustering for color segmentation in the Lab* color space, followed by Gray-Level Co-occurrence Matrix (GLCM) texture feature extraction to differentiate grape types. The experimental results show that the proposed method achieved an accuracy of over 90% in identifying grape varieties, demonstrating its potential for industrial applications in fruit processing. Our findings indicate that the system is robust under various lighting conditions and can significantly reduce human error in grape sorting processes. Automated Identification of Grape Varieties Using Color-Based Image Segmentation and Texture Analysis: A K-Means Clustering Approach