The use of associative techniques to perform shape recognition is considered. With respect to classical recognition techniques, it is shown how the pattern-completion capability and content addressability of associative memories can yield robust performance and high computational speed in shape recognition applications, especially in those domains in which promptness of ‘first-glance’ classification is more important than accurate pattern-analysis capabilities. The noise-like coding model of associative memory is adopted, specifying the basic associative classification principle. A set of different experimental domains are considered, at increasing levels of complexity, evidencing how the theoretical model can be effectively applied to image and shape recognition.
KeywordsAssociative Memory Fourier Descriptor Shape Recognition Associative Model Input Shape
Unable to display preview. Download preview PDF.
- Parodi GC, Zunino R (1990) Image classification by using associative noise-like memories. Proc. IEEE Int.Phoenix Conf.on Comp.and Comm. IPCCC’90 Phoenix AZ March 1990.Google Scholar
- Parodi GC, Zunino R (1990) Noise insensitivity of an associative image classification system. Proc. IEEE Int.Workshop on Robust Comp.Vision, Seattle WA — in press by Academic Press New York.Google Scholar
- Parodi GC, Regazzoni C, Vernazza G, Zunino R (1991) Speeding up scene recognition by using an associative noise-like coding memory. IEEE Int.Phoenix Conf. on Comp.and Comm. IPCCC’91 Phoenix AZ March 1991.Google Scholar
- Kie-Bum Eom, Juha Park (1990) A robust model based approach in shape recognition. Proc. IEEE Int.Workshop Robust Comp.Vision, Seattle Oct 1990, pp. 57–71 — in press by Academic Press, New York.Google Scholar
- Chen DS, Schunck BG (1990) Robust statistical methods for building classification procedures. Proc. IEEE Int.Workshop Robust Comp.Vision, Seattle Oct 1990, pp. 72–85 — in press by Academic Press, New York.Google Scholar
- Fukushima K, Miyake S, Ito T (1983) Neocognitron: a neural network model for a mechanism of visual pattern recognition. IEEE Trans Sys Man and Cybern Sept/Oct 1983: 826-834.Google Scholar
- Rumelhart DE, McClelland JL (1986) Parallel distributed processing — Vols. 1 and 2. MIT Press 1986.Google Scholar