At present, fruits are graded manually by a conventional grading system of Fresh Fruit Bunches (FFB). The most difficult is to classify and sort the oil palm fruit bunches since it is labour intensive, slow and can be inconsistent due to fatigue. Different human graders classify the fruits differently and an expert grader may fail to record the grading criteria properly. The local past research focused more on the correlation of oil content with the images of the fruits captured using a CCD RGB or digital camera. They also programmed in traditional programming language to produce the algorithm which can be very time consuming and tedious.
Nevertheless, no focus was done to develop a fully integrated and automated grading system. Thus the automatic fruit grading system proposed in this study integrates a feeding section for FFB, a vision inspection chamber and a sorter mechanism to classify the fruits. The grading is done in one system autonomously. A webcam is used to capture the FFB images running under the MATLAB image processing toolbox. The MATLAB image processing toolbox is currently the most commonly and widely accepted form of computing. The fruits will be classified into ripe and unripe bunches which are reflected by red, green and blue (RGB) color information. The fruits will then be sorted accordingly. This automated grading system increases accuracy, quality and consistency of palm oil grading which can standardize the grading criteria for palm oil millers and refiners.
The system can be sold to small palm oil holders, factories, and exporters.
Contact:
