Inspection of Rice Appearance Quality Using Machine Vision

Abstract

Characteristics of rice appearance quality are very important to evaluate rice quality and pricing. The normal method for determining rice quality is based on manual inspection which is an inefficient way and resulting in unconstant outcomes. Thus, we developed an automatic system relying on the machine vision which allowed us evaluate rice appearance quality including rice chalkiness and shape. In our system, contacting angle analysis method was used for separating the contacting rice grains. Improved multi-threshold method based on maximum entropy was used for inspecting rice chalkiness. Minimum enclosing rectangle method was used for evaluating rice shape. The outcomes of inspection for 21 rice varieties showed that our system was an objective and effective way for inspecting rice appearance quality.