Distributed key-generation structures for associative image-classification

Associative memories can be utilized in image classification to provide robustness and noise insensitivity. On the other hand, real-time applications demand fast performance at all steps of associative coding. In the present work, the noise-like coding model of an associative memory is adopted, and a general architecture for the key-generation process is described. The fractal property of Peano curves is exploited to define a structure which performs distributed computations; this facilitates the system´s implementation on parallel architectures, and also notably improves the associative system´s performance