Application of webcam for inspection of rice grain quality by using image processing technique

Abstract

This paper presents the image processing system for quality inspection of rice grains after sorting process by using an ordinary webcam to ensure that rice grains should meet the quality standards and impurity such as grits, dirt and stones should not be found [1]. Moreover, statistical information of rice grains from image processing could be taken into analysis to enhance the efficiency of the sorting process. Image data analysis of rice grains can be divided into 2 main arrangement conditions, non-overlapping and overlapping. In this study, the experiments to inspect rice grains were applied for 24 samples and 18 experimental designs including the complete and incomplete structures, the overlapping and non-overlapping arrangements, and the combination of rice grains from complete and incomplete structures in equal and unequal ratios. From experiments, it was found that the inspection of rice grain quality by using image processing technique and image data recorded by an ordinary webcam was reliable and efficient. The inspection errors under non-overlapping arrangement condition of complete and incomplete structures of rice grains were not observed. The inspection errors of rice grains combined from complete and incomplete structures in equal and unequal ratios were about 0.8% and 1.11%, respectively. However, under overlapping arrangement condition, it was observed that the inspection errors of image processing would be high by up to 53.82% on average.