Share Email Print
cover

Proceedings Paper

Binary image registration using cellular simultaneous recurrent networks
Author(s): Keith Anderson; Khan Iftekharuddin; Paul Kim
Format Member Price Non-Member Price
PDF $14.40 $18.00

Paper Abstract

Cellular simultaneous recurrent networks (CSRN)s have been traditionally exploited to solve digital control and conventional maze traversing problems. In a previous work [1], we investigate the use of CSRNs for image registration under affine transformations for binary images. In Ref. [1], we attempt to register simulated binary images with in-plane rotations between ±20° using two different CSRN implementations such as with 1) a general multi-layered perceptron (GMLP) architecture; and (2) a modified MLP architecture with multi-layered feedback. Our results in Ref. 1 show that both architectures achieve moderate local registration, with our modified MLP architecture producing a best result of around 64% for cost function accuracy and 98% for image registration accuracy. In this current work, for the first time in literature, we investigate gray scale image registration using CSRNs. We exploit both types of CSRNs for registration of realistic images and perform complete evaluation of both binary and gray-scale image registration. Simulation results with both CSRN architectures show an average cost function accuracy of 40.5% and an average image accuracy of 33.2%, with a best result of 46.2% and 40.3%, respectively. Image results clearly show that the CSRN shows promise for use in registration of gray-scale images.

Paper Details

Date Published: 1 September 2009
PDF: 12 pages
Proc. SPIE 7442, Optics and Photonics for Information Processing III, 74420C (1 September 2009); doi: 10.1117/12.828473
Show Author Affiliations
Keith Anderson, Univ. of Memphis (United States)
Khan Iftekharuddin, Univ. of Memphis (United States)
Paul Kim, Univ. of Memphis (United States)


Published in SPIE Proceedings Vol. 7442:
Optics and Photonics for Information Processing III
Khan M. Iftekharuddin; Abdul Ahad Sami Awwal, Editor(s)

© SPIE. Terms of Use
Back to Top