Real-Time Wavelet Transform for Image Processing on the Cellular Neural Network Universal Machine
IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
| Hi-index | 0.00 |
The Cellular Neural Network (CNN) is a bidimensional array of analog dynamic processors whose cells interact directly within a finite local neighborhood [2]. The CNN provides an useful computation paradigm when the problem can be reformulated as a well-defined task where the signal values are placed on a regular 2-D grid (i.e., image processing) and direct interaction between signal values are limited within a local neighborhood. Besides, local CNN connectivity allows its implementation as VLSI chips which can perform image processing based in local operations at a very high speed [5]. In this paper, we present a general methodology to extend actual CNN operations to a large family of useful image processing operators in order to cover a very broad class of problems.