ABSTRACT
In order to investigate variety-specific characteristics reflected by peanuts from different origins, we use a scanner to capture the images of the same species (Huayu 22) from three different regions. Each variety includes one front and two side images of 100 peanuts. For each image, we have acquired 50 characteristics including shape, color, and texture. We build an artificial neural network (ANN) model for identification based on these characteristics and those optimized by principal component analysis (PCA). Result shows that for species of different origins, the maximum rate of detectability reaches 100%. The methods used in this chapter have positive significance to the distinctness, uniformity and stability (DUS) testing of peanut.
