APPLICATION OF THE CASCADE-CORRELATION NETWORK TO THE CLASSIFICATION OF CIRCULARLY SCANNED IMAGES

This paper describes an application of the Cascade-Correlation (CC) ne twork to pattern recognition. The pattern recognition task was to simu late an automatic vision inspection system that had to properly classi fy five different objects. The feature vectors were extracted from 2D images of circularly scanned images and used as inputs for a neural ne twork that was then trained to classify an unknown presented object. T he results show that the CC network is viable tool in pattern recognit ion tasks. It is able to classify partially occluded objects with high accuracy, and to considerably improve classification of noisy images based on simple histogram trimming preprocessing.