The Effects of Segmentation Techniques in Digital Image Based Identification of Ethiopian Coffee Variety

Abstract

This paper presents the effects of segmentation techniques in the identification of Ethiopian coffee variety. In Ethiopia, coffee varieties are classified based on their growing region. The most widely coffee growing regions in Ethiopia are Bale, Harar, Jimma, Limu, Sidamo and Welega. Coffee beans of these regions very in color shape and texture. We investigated various segmentation techniques for efficient coffee beans variety identification system. Images of six different coffee beans varieties in Oromia and Southern Ethiopia were acquired and analyzed. For this study Otsu, Fuzzy-C-Means (FCM) and Kmeans segmentation techniques are considered. For classification of the varieties of Ethiopian coffee beans back propagation neural network (BPNN) is used. From the experiment 94.54% accuracy is achieved when BPNN is used on FCM segmentation technique.