The Research Of Fuzzy Morphological Scale Space Associative Memories And Its Application

Associative memory is one important function of human brain cells, and one important aspect of artificial neural network is to simulate the associative memory function of human beings. The morphological associative memories proposed by G.X.Ritter et al at the end of the 20th century is an effective way to overcome the drawbacks classical associative memories, such as the limited sample storage capacity and necessity of iterative memory. In addition, this network has adequate anti-noise capability in processing binary images with single noise, but it seems inadequate in dealing with random noise. Morphological associative memories and its improved versions cannot effectively deal with the issue of ambiguous interpretation, thus B.Kosko proposes fuzzy associative memories, which solves the issue of ambiguous interpretation but has quite poor storage capacity. Papers by combining morphology and fuzzy associative memories, propose fuzzy morphological associative memories. This new network solves the problem of poor storage capacity and also has a strong anti-noise capability against single noise, but can hardly suppress any random noise, which limits its wide use.Two things are done in this paper: firstly, it combines scale space and morphological associative memories to get a new network, with the input process going through a erosion/dilation storage matrix under a particular scale before the associative memory processing. This new network proves to have outstanding capability against dilative or erosive noise besides its robustness against random noise but also is applied to processing of grayscale image.Secondly, it combines scale space and fuzzy associative memories to produce a fuzzy associative memories based on scale space, which not only maintains the advantages of fuzzy associative memories---strong anti-noise capability against single noise and fuzzy interpretation ability---but also suppresses the random noise in processing binary image and grayscale image. A lot of simulation experiments have been conducted to verify the above conclusion.