Title: CLASSIFICATION OF PIPER NIGRUM SAMPLES USING MACHINE LEARNING TECHNIQUES: A COMPARISON

Year of Publication: 2013
Page Numbers: 454-462
Authors: D.N.F Awang Iskandar, Nuraya Abdullah, Alvin W. Yeo, Shapiee Abdul Rahman, Ahmad Hadinata Fauzi, Rubiyah Baini
Conference Name: The Third International Conference on Digital Information Processing and Communications (ICDIPC2013)
- United Arab Emirates

Abstract:


Pepper is a key export of the state of Sarawak (Malaysian Borneo). At present, processed pepper berries are graded manually. This process is time consuming and error prone as it is very much dependent on the experience of the pepper grader. To overcome these weaknesses, we propose an automated Pepper Grading System which employs image processing and machine learning using image features and moisture content data of the pepper berries. In this paper, we present our findings of using twenty machine learning algorithms to classify the pepper berries into its respective grades based on image features, which is part of our research work towards an automated Pepper Grading System. We found that Rotation Forest was the best classifier.