Ripeness Detection of Oil Palm Fresh Fruit Bunches Using 4-Band Sensors
Ripeness of oil palm fresh fruit bunches (FFB) has recently become a major issue since it affects processing cost as well as market price. 135 samples were randomly collected from the field. The vision system employs a computer and a 4-band sensor device, which are utilized to measure a vegetation index with images that require human analysis and interpretation. The 4-Band Sensor equipment consists of the following bands: 660 nm, 780 nm, 870 nm and 970 nm. Data analysis using the T-test method was performed to inspect three classes of oil palm fresh fruit bunches ripeness; under-ripe, ripe and over-ripe categories. This paper focuses on reflectance acquisition, which can reveal the essential information of interest using the visible and near-infrared bands of radiation. The laboratory results demonstrate that the 4-Band Sensors can distinguish ripe, under-ripe and over-ripe categories. Only the 780 nm band differed significantly when the T-test statistical method was applied to differentiate the three categories. The three best indicators have been identified, which are the 780 nm band, interaction between the 780 nm band and the 870 nm band as well as the 870 nm band. The indicators were ranked utilizing the chi-square method. The highest classification accuracy was 83% using the Support Vector Machine method. This study has greatly explored the potential of hand-held equipment using spectral technology to be utilized commercially as it is affordable, suitable and useful for the palm oil industry in general and specifically useful for palm oil mills, plantation sectors and small holders.
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