S.Jagadeesh Babu; P.Karunakaran; S.Venkatraman; Hameem Shanavas .I; T.Kapilachander

Edge Detection System using Pulse Mode Neural Network for Image Enhancement

Full Text (PDF, 359KB), PP.42-48

Views: 0 Downloads: 0

Author(s)

S.Jagadeesh Babu ^1,* P.Karunakaran ² S.Venkatraman ³ Hameem Shanavas .I ⁴ T.Kapilachander ⁵

1. Department of ECE,Dhanalakshmi College of Engineering,Chennai,India

2. Department of ECE,K.L.N College of Information Technology,Madurai , India

3. Department of ECE, Vel Tech Chennai,India

4. Department of ECE, M.V.J College of Engineering,Bangalore-67,India

5. Department of ECE, Sudharsan college Engineering, Trichy, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijigsp.2012.03.07

Received: 23 Dec. 2011 / Revised: 7 Feb. 2012 / Accepted: 14 Mar. 2012 / Published: 8 Apr. 2012

Index Terms

Edge detection, Pulse mode, Synapse multiplier, Floating point operation

Abstract

Edge detection of an image reduces significantly the amount of data and filters out information that may be regarded as less irrelevant. Edge detection is efficient in medical imaging. Pulse mode neural networks are becoming an attractive solution for function approximation based on frequency modulation. Early pulse mode implementation suffers from some network constraints due to weight range limitations. To provide the best edge detection, the basic algorithm is modified to have pulse mode operations for effective hardware implementation. In this project a new pulse mode network architecture using floating point operations is used in the activation function. By using floating point number system for synapse weight value representation, any function can be approximated by the network. The proposed pulse mode MNN is used to detect the edges in images forming a heterogeneous data base. It shows good learning capability. In addition, four edge detection techniques have been compared. The coding is written in verilog and the final result have been simulated using Xilinx ISE simulator.

Cite This Paper

S.Jagadeesh Babu, P.Karunakaran, S.Venkatraman, I.Hameem Shanavas, T.Kapilachander,"Edge Detection System using Pulse Mode Neural Network for Image Enhancement", IJIGSP, vol.4, no.3, pp.42-48, 2012. DOI: 10.5815/ijigsp.2012.03.07

Reference

[1]Alima Damak, Mohamed Krid And Dorra Sellami Masmoudi, "Neural Network Based Edge Detection With Pulse Mode Operations And Floating Point Format Precision", International Conference On Design And Technology Of Integrate Systems In Nanoscale Era (08).

[2]James A. Freeman, David M. Skapura (2008):"Neural Networks (Algorithms, Applications And Programming Techniques)" Pearson Education Third Edition Pg 103-108.

[3]Alima Damak, Benoit Gosselin, Mohamed Sawan, Dorra Sellami Masmoudi AND Nabil Derbel (2007): "Modeling Of Cortical Neurons By Pulse Neural Networks" International CONFERENCE Ssd'07.

[4]Mohamed KRID Alima DAMAK Dorra SELLAMI MASMOUDI (2006): "FPGA Implementation Of Programmable Pulse Mode Neural Network With On Chip Learning For Signature Application" International Conference Icecs'06.

[5]Alima Damak, Mohamed Krid, Dorra Sellami Masmoudi And Nabil Derbel (2006): "FPGA Implementation Of Programmable Pulse Mode Neural Network With On Chip Learning" International Conference Dtis06.

[6]Stavros Paschalakis, Miroslaw Bober (2004): "Real-Time Face Detection and Tracking For Mobile Videoconferencing". Siancedirect Real-Time Imaging 10 (2004), Pp. 8194.

[7]H.Hikawa, "Digital Pulse Mode Neuron with Robust Nonlinear Activation Function", IEEE Tmns. On Neural Networks, Pp.2665-2670, IEEE 2004.

[8]H. Hikawa (1999): "Frequency-Based Multilayer Neural Network With On Chip Learning Enhanced Neuron Characteristics". IEEE Trans.Neural Networks, Vol. 10, No. 3, Pp. 545-553.

[9]B.Yegnanarayana (1999):"Artificial Neural Networks"Prentice Hall Of India Private Limited Pg 1-75

International Journal of Image, Graphics and Signal Processing (IJIGSP)