Title :
A neural network image classification system for automatic inspection
Author_Institution :
Div. of Building, Constr. & Eng., CSIRO, Highett, Vic., Australia
Abstract :
The development of a neural network image classification system for range image automatic inspection is described. The classifier operates on regions of interest (ROIs) which have been identified in the image through segmentation and connected component labelling. The classification of ROIs is carried out by a Bayesian decision tree of feedforward neural networks operating on features derived from the region and image model. The feature set includes Fourier wedge-ring samples and image histogram moments
Keywords :
Bayes methods; decision theory; feedforward neural nets; image classification; image segmentation; trees (mathematics); Bayesian decision tree; Fourier wedge-ring samples; automatic inspection; connected component labelling; feedforward neural networks; image histogram moments; neural network image classification system; range image automatic inspection; segmentation; Bayesian methods; Classification tree analysis; Decision trees; Feedforward neural networks; Histograms; Image classification; Image segmentation; Inspection; Labeling; Neural networks;
Conference_Titel :
Neural Networks, 1995. Proceedings., IEEE International Conference on
Conference_Location :
Perth, WA
Print_ISBN :
0-7803-2768-3
DOI :
10.1109/ICNN.1995.487504
