Mango ripeness classification system using hybrid technique

Abstract

Nowadays there are many systems develop for agricultural purposes and most system implemented on the use of non-destructive technique not only to classify but also to determine the fruit ripeness. However, most of the studies concentrates using single technique to assess the fruit ripeness. This paper presents the work on mango ripeness classification using hybrid technique. Hybrid stands for mix or combination between two different elements, thus this study combined two different technique that is image processing and odour sensing technique in a single system. Image processing technique are implemented using color image that is HSV image color method to determine the ripeness of fruit based on fruit peel skin through color changes upon ripening. Whereas, odour sensing technique are implemented using sensors array to determine the fruit ripeness through smell changes upon ripening. The “Harumanis” and “Sala” mango was used for sample collection based on two different harvesting condition that is unripe and ripe were evaluated using the image processing and followed by the odour sensor. Support Vector Machine (SVM) is applied as classifier for training and testing based on the data collected from both techniques. The finding shows around 94.69% correct classification using hybrid technique of image processing and odour sensing in a single system.