FPGA-Based Handwritten Signature Recognition System
Sami El Moukhlis11, Abdessamad Elrharras2, Abdellatif Hamdoun3
1Sami El Moukhlis, Department of Information Processing FSBM, HASSAN II University, Casablanca Morocco.
2Abdessamad Elrharras, Department of Information Processing FSBM, HASSAN II University, Casablanca Morocco.
3Abdellatif Hamdoun, Department of Information Processing FSBM, HASSAN II University, Casablanca Morocco.
Manuscript received on 6 April 2014 | Revised Manuscript received on 17 April 2014 | Manuscript Published on 30 April 2014 | PP: 23-26 | Volume-3 Issue-11, April 2014 | Retrieval Number: K15780431114/14©BEIESP
Open Access | Editorial and Publishing Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In this paper, a method of classification of handwritten signature based on neural networks, and FPGA implementation is proposed. The designed architecture is described using Very High Speed Integrated Circuits Hardware Description Language (VHDL). The proposed application consists of features extraction from handwritten digit images, and classification based on Multi Layer Perceptron (MLP). The training part of the neural network has been done by using MATLAB program; the hardware implementations have been developed and tested on an Altera DE2-70 FPGA.
Keywords: ANN, FPGA, MLP, Recognition, VHDL.
Scope of the Article: Pattern Recognition