Image Recognition of Unsound Wheat Using Artificial Neural Network

The objective of this research is to develop algorithm to recognize unsound wheat based on image processing and artificial neural network. The sample used for this study involved wheat from major producing areas of China. Images of wheat were acquired with a color machine vision system. Each image was processed to extract shape and color quantitative features. All features were analyzed with principal components analysis method. A two-layer back propagation network was created and trained using gradient descent with momentum and adaptive learning rate. Nr. of hidden nodes was tested and early stopping skill was used. The total error of the finally established net is 2.5% for the classification of normal and unsound wheat.