Coffee Type Classification Using Gray Level Co-Occurrence Matrix Feature Extraction And The Artificial Neural Network Classifier

摘要

This paper is focused on determining the species of a coffee bean using the GLCM or the Gray Level Co-Occurrence Matrix method with the help of ANN or the Artificial Neural Network. This research is done to make a new method in determining the species of coffee bean in different parts of Cavite (Arabica, Excelsa, and Robusta). The image processing techniques that the author will use will be simulated in order the classify the species of the coffee bean that will be used. The coffee bean features based on the GLCM are the Contrast, Energy, Cluster Shade and Sum of Square Variance that will be extracted from 120 training images and 60 testing images. Using the ANN classifier, it will categorize the coffee bean based on the said parameters for GLCM. Using ANN classification, the scores of 95.31% were achieved. In conclusion, the study showed that image processing can effectively determine the quality of the coffee bean varieties.