2014/11/28 by Birhanu Turi, Turi, Birhanu, Getachew Abebe +3
Arts and Humanities · Health Professions · #Aging, Elder Care, and Social Issues #Health, Medicine and Society #Hermeneutics and Narrative Identity
paper · doi:10.20372/eajs.v7i1.145
openalex publication_date 2014/11/28 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/01
Ethiopian coffee beans are distinct from each other in terms of quality based on their geographic origins. The quality of export coffee beans is usually determined by visual inspection, which is subjective, laborious, and prone to error. This calls for the development of an alternative method that is accurate and objective. This research was conducted with the objective of developing an appropriate computer routine algorithm that can characterize coffee beans drawn from four coffee growing regions in the country. Imaging techniques were employed to automatically classify the coffee bean samples according to provenance in Ethiopia (Hararghe, Jimma, Wollega and Yirgacheffe) which corresponds to their botanical origins. Important coffee bean features, namely, colour, morphology and texture were extracted from 160 images (40 images from each location). For the purpose of classification, altogether 29 features (11 colours, 6 morphological and 12 textural features) were extracted from images of the coffee samples from the four locations. Artificial neural network (ANN) was employed to automatically categorize the coffee beans according to their provenance. Four classification setups (1, 2, 3 and 4) were employed based on the features used for colour, morphology, texture, and combination of morphology and colour respectively. Out of 80 sample images, 70 % (56), 25% (20) and 5% (4) were used for training, testing, and validating, respectively. Classification scores of 95%, 100%, 87.5% and 100% were achieved for colour, morphology, texture and a combination of morphology and colour features, respectively. The classification results of the network indicated that morphology and a combination of morphological and colour features exhibited the highest accuracy. In conclusion, the results of this study have revealed that imaging technique could be used as the most effective method to determine coffee bean qualities for export. However, it is suggested that the repeatability of this coffee quality testing method be validated using a large data set before employing the algorithm for the purpose of classifying coffee beans as a daily routine.