Feedforward neural networks for automated classification

We investigate an intelligent computer vision system that incorporates feedforward neural networks (NN) for recognition and classification of commercially available cork tiles. The system is capable of acquiring and processing gray images using several feature generation and analysis techniques. Its functionality includes image acquisition, feature extraction and preprocessing, and feature classification with NN. We also discuss system test and validation results from the recognition and classification tasks. The system investigation also includes statistical feature processing (features number and dimensionality reduction techniques) and classifier design and training. The NN are trained with our genetic low-discrepancy search method for global optimization (GLPτS), and demonstrate very good generalisation abilities when tested on unseen samples. In our view, the reported success rate of up to 95% is due to several factors: combination of feature generation techniques; application of Analysis of Variance (ANOVA) and Principal Component Analysis (PCA), which appeared to be very efficient for preprocessing the data; and also the use of suitable NN design and learning method.