Pengembangan Algoritma Image Processing untuk Menduga Kemasakan Buah Manggis Segar

Abstract

One of important factor in post harvest handling is cropping at correct maturity level. Fruit maturity relates to age pluck vegetable or fruit to be harvested have old enough or not yet. Grading represent dissociation of product becomes some group quality of pursuant to maturity level, size measure, color, form, heavy, texture, aroma and freedom from foreign object or dirt. The objective of this research is to predict the maturity of fresh mangosteen by means of an image processing algorithm. In this study, four stages of maturity (120, 126, 132 and 138 days after flowering) were used as objects with 30,37,40,40 samples for each stages of maturity.The images data were collected using a CCD Camera and then processed by an image processing program to analyze the relationship between the maturity and the color, size, and shape of fruits. The result showed linear relationship between the maturity and the color index (RGB) with a coefficient determination of 0.8159 for blue, but not for red and green. As a result, the developed image processing program can be used to classify the fresh mangosteens based on their maturity using blue index with 70% precicion.