Quality assessment of corn grain sample using color image analysis

Abstract

Grain quality is assessed based on different grain features like appearance, shape, color, smell, flavour, moisture content, infections, presence of impurities, etc. The main indexes for the quality of grain samples are related to the color characteristics and the shape of the grain sample elements. Most of these characteristics are assessed visually by an expert. In this paper, an approach for an objective estimation of some basic grain quality characteristics is presented. It is based on a complex analysis of color images of the investigated objects. Due to the conceptual difference in presenting the objects’ color and shape characteristics, their assessment was performed separately. After that the results form these two assessments were combined and the final decision about the object’s classification to one of the quality groups defined by the standard regulations was made. Methods and tools for feature extraction and for object description, as well as for classification of the objects into predetermined groups were proposed. Three classifiers, based on radial basis elements, which were used for grain color and shape class recognition, were analyzed. Two different approaches for fusing the results from object color and object shape analyses were investigated. The training and testing errors of the developed procedures were evaluated.