Colour Extraction of Agarwood Images for Fuzzy C-Means Classification

Colour is one of the quality features used in determining agarwood quality and grade. This research investigates the relationship of agarwood physical colour properties with its price. Colour features of agarwood images taken from Red, Green, Blue (RGB), Hue, Saturation, Intensity (HSI) and Commission Internationale de l'Eclairage standard L,*a,*b colorspace (CIELAB) has been extracted by Fuzzy C-Means (FCM) classification. The performance of these colorspaces has been determined using five cluster validity indices. One hundred and forty agarwood images consisting of seven different prices have been analyzed. From the experiment, it has been shown that CIELAB colorspace with four numbers of clusters gave more consistent and accurate results compared to the others. It also gave a significant relationship when tested using analysis of variance (ANOVA) and Duncan Multiple Range Test (DMRT). The method performs best when classifying lower price agarwood with component L for RM250 and RM800, b for RM350 and RM2500 while a for RM900. Overall, the proposed method proved that there is a significant relationship between agarwood price and its physical colour properties, which thus shows that the image processing has an enormous potential to be used in the agarwood chips grading task for the future development.