Image analysis of bulk grain samples using neural networks

Visen, N.S., Paliwal, J., Jayas, D.S. and White, N.D.G. 2004. Image analysis of bulk grain samples using neural networks. Canadian Biosystems Engineering/Le génie des biosystèmes au Canada 46: 7.117.15. Algorithms were developed to acquire and process color images of bulk grain samples of five grain types, namely barley, oats, rye, wheat, and durum wheat. The developed algorithms were used to extract over 150 color and textural features. A back propagation neural network-based classifier was developed to identify the unknown grain types. The color and textural features were presented to the neural network for training purposes. The trained network was then used to identify the unknown grain types. Classification accuracies of over 98% were obtained for all grain types. For example, the results can be used to identify grain types when unloading railcars at a terminal elevator (grain handling facility).