Grading and Profiling of Coffee Beans for International Standards Using Integrated Image Processing Algorithms and Back-Propagation Neural Network

Abstract

Coffee has become one of the Philippines' main beverages in recent years, exporting quality coffee all over the world. Most specialty coffees have been sorted and processed by hand. There was a lack of integration with modern technology concerning the evaluation of coffee beans of which lead to lower yield due to little personnel as sorting of coffee beans are generally done by a trained expert. To solve the problem, recent researches about integrating image processing techniques in industrialization has become more apparent apart from only a few that focus on the different features of a coffee bean. The focus of this paper is to create a device that can evaluate the size, quality, and roast level of a batch of the coffee bean through the use of image processing techniques and Back Propagation Neural Network. BPNN would serve as the brain of the device to determine these features. This study would use different image processing techniques such as K-mean shift, Blob, and Canny Edge to extract the features of the coffee beans and use Red Green Blue Analysis, Hu's Moment, and Blob Analysis to make use of these features and feed it into the BPNN. The coffee beans used in the study are obtained and sorted from the Philippine Coffee Board Inc.