Mature and immature paddy identification using image processing technique

Maturity of paddy contributes a very high impact on the production of rice quality. Immature paddy will produce high percentage of broken rice, poor grain quality and more chances of disease attack during storage. This research focuses on the use of image processing technique for paddy maturity identification. Three types of automatic image thresholding techniques had been used during a segmentation process, i.e., Mean, Median and Otsu. The average intensity of paddy image is used as features in development of a decision rule to identify paddy maturity. All of the techniques give small value of standard deviation which is around 0.01 in mature and immature paddy. Results from the test validation had shown that, all of the techniques can identify mature paddy with the percentage of success rate of 92.31%. For immature paddy, features extracted by Median give superior result which is 100% success rate compared to the others. In overall, Median is the most reliable approached for mature and immature paddy identification. It gives the highest average percentage of success rate which is of 96.15% as compared with Mean (86.15%) and Otsu (66.15%).