Classification of oil palm fresh fruit bunches based on their maturity using portable four-band sensor system

Published Date
Computers and Electronics in Agriculture
March 2012, Vol.82:55–60, doi:10.1016/j.compag.2011.12.010

• Author 

• Osama Mohammed Ben Saeed ^a,
• Sindhuja Sankaran ^b
• Abdul Rashid Mohamed Shariff ^a,c,,
• Helmi Zulhaidi Mohd Shafri ^d
• Reza Ehsani ^b
• Meftah Salem Alfatni ^a
• Mohd Hafiz Mohd Hazir ^a

• aSpatial and Numerical Modeling Laboratory, Institute of Advanced Technology, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia
• bCitrus Research and Education Center, IFAS, University of Florida, 700 Experiment Station Road, Lake Alfred, FL 33850, USA
• cDepartment of Biological and Agricultural Engineering, Faculty of Engineering, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia
• dDepartment of Civil Engineering, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia

Received 18 March 2011. Revised 25 November 2011. Accepted 21 December 2011. Available online 21 January 2012. 

Abstract

Classification of oil palm fresh fruit bunch (FFB) maturity is a critical factor that dictates the quality of produced palm oil. This study evaluates a multi-band portable, active optical sensor system; comprising of four spectral bands, 570, 670, 750, and 870 nm, to detect oil palm FFB maturity. The in-field spectral reflectance data were collected using the sensor system from a total of 120 fresh fruit bunches. These fruit bunches were categories into unripe, ripe, and overripe classes. Different classifiers were applied to assess the applicability of using the sensor system. Based on the classification accuracies, data analysis on the spectral features (reflectance data and other features extracted from vegetation indices) indicated that the spectral reflectance data could be valuable in predicting the maturity of the fruit bunches. The quadratic discriminant analysis and discriminant analysis with Mahalanobis distance classifiers yielded highest average overall accuracies of greater than 85% in classifying oil palm FFB maturity. Additionally, the average individual class (unripe, ripe, and overripe) classification accuracies were also higher than 80%. Thus, optical sensing using four-band sensor system could be useful for oil palm FFB maturity classification under field condition.

Highlights

► Optical sensor evaluated for maturity classification of oil palm fruit bunches. ► Oil palm fresh fruit bunches maturity determined with 80% accuracy. ► System useful for oil palm FFB maturity classification under field conditions.

Keywords

Visible-near infrared sensor

Optical sensing

Oil palm fresh fruit bunches

Fruit maturity

Classification

---

Fig. 1.

Fig. 2.

Fig. 3.

 Table 1

Table 1.

Fig. 4.

 Table 2

Table 2.

 Table 3

Table 3.

• ⁎ 
  Corresponding author at: Spatial and Numerical Modeling Lab, Institute of Advanced Technology, Universiti Putra Malaysia, 43400 Serdang, Selangor, Malaysia. Tel.: +60 1 23025723/8481141; fax: +60 3 89466425.

Copyright © 2011 Elsevier B.V. Published by Elsevier B.V. All rights reserved.

For further details log on website :
http://www.sciencedirect.com/science/article/pii/S016816991100322X