Image algebra networks for pattern classification
Paul Gader, Yonggwan Won, Mohamed A. Khabou · Proceedings of SPIE, the International Society for Optical Engineering/Proceedings of SPIE · 1994
A neural network structure that learns feature extraction and classification operations simultaneously is described. The feature extraction operations are represented using generalized image algebra operations. Learning rules are described. Linear operations and nonlinear, hit-or-miss operations are used to perform handwritten digit recognition.