Title: Hardware implementation of new bell-shaped pulse mode neural network with on-chip learning and application to image processing

Authors: Amir Gargouri; Mohamed Krid; Dorra Sellami Masmoudi

Addresses: Computer Imaging and Electronics Systems Group at CEM Laboratory, Sfax Engineering School, University of Sfax, BP W, 3038 Sfax, Tunisia ' Computer Imaging and Electronics Systems Group at CEM Laboratory, Sfax Engineering School, University of Sfax, BP W, 3038 Sfax, Tunisia ' Computer Imaging and Electronics Systems Group at CEM Laboratory, Sfax Engineering School, University of Sfax, BP W, 3038 Sfax, Tunisia

Abstract: A key task in the hardware implementation of neural networks is the design of activation functions. We focus in this paper on hardware driven simple implementation of a bell-shaped function (BSF) avoiding complexity and reducing hardware resources with efficient on-chip learning. This implementation is done in pulse mode to take advantage of its valuable features, significantly reducing the hardware cost. The proposed design is flexible and scalable enabling several image processing potential tasks. A first application is devoted to image denoising where a comparison with some existing denoising techniques demonstrates the efficiency of the proposed approach. As a second application, we consider edge detection operation and good approximation features are accordingly obtained. The corresponding design is implemented on a Virtex-II-PRO FPGA platform. Synthesis results prove that the bell-shaped PMNN is not cumbersome, and provides higher performances versus other PMNN architectures in terms of computing speed and required hardware resources.

Keywords: pulse mode; bell-shaped function; BSF; FPGA implementation; image denoising; canny edge detector; on-chip learning; neural networks; hardware implementation; image processing; field-programmable gate arrays.

DOI: 10.1504/IJHPSA.2013.055224

International Journal of High Performance Systems Architecture, 2013 Vol.4 No.3, pp.132 - 143

Available online: 23 Jul 2013 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article