The intelligent inspection engine-a real-time real-world visual classifier system

Abstract

An intelligent inspection engine (IIE) for the classification of nonregular shaped objects from images is described and evaluated using real-world data from a waste package sorting application. The entire system is self-organizing. Principal component analysis and additional a priori knowledge on color properties are used for feature extraction. As classifiers, growing neural networks provide robustness and minimize the number of runs for parameter tuning. The authors propose a method to encompass feature extraction and classification within a bootstrap procedure. This method reduces the immense memory requirement for the computation of principal components if the number and size of training images are huge without too much loss of recognition quality.