Recognition System of Oil Palm Fruit Bunch Types Based on Texture Feature and Image Processing Techniques
Oil palm is one of the most widely planted agricultural crop in Malaysia, where different types of oil palm fruits produce varying quality levels of palm oil. These fruits, which are of different types, are purchased by oil palm fresh fruit bunches (FFB) traders from multiple plantations. These fruits are then delivered to the oil palm mill for processing. For purpose of grading and quality control, the oleifera type of oil palm FFB is rejected as it has very low oil content. Currently, the different types of FFB are differentiated by human visual inspection. This method leads to disputes at times between the buyers at the mill and the FFB traders. The motivation of this research is to create an automated method of identifying the different types of oil palm FFB so that such disputes about the types of oil palm FFB being rejected can be avoided. In this paper, the recognition system of oil palm types used the image processing methods based on the texture feature techniques and supervised machine learning. The results reveal that basic gray level aura matrix technique (BGLAM) with support vector machine (SVM) significantly exhibits high accuracy (91%) for FFB type recognition compared with gray level co-occurrence matrix (GLCM) (79%) and Gabor wavelet transform (GWT) (78%), which is as useful tools for palm oil quality production based on its types.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
Document Type: Research Article
Publication date: December 1, 2013
More about this publication?
- ADVANCED SCIENCE LETTERS is an international peer-reviewed journal with a very wide-ranging coverage, consolidates research activities in all areas of (1) Physical Sciences, (2) Biological Sciences, (3) Mathematical Sciences, (4) Engineering, (5) Computer and Information Sciences, and (6) Geosciences to publish original short communications, full research papers and timely brief (mini) reviews with authors photo and biography encompassing the basic and applied research and current developments in educational aspects of these scientific areas.
- Editorial Board
- Information for Authors
- Subscribe to this Title
- Ingenta Connect is not responsible for the content or availability of external websites