Pushpa Publishing House

Journal Menu

Content

Volume 17 (2018)

Volume 16 (2016)

Volume 15 (2015)

Volume 14 (2015)

Volume 13 (2014)

Volume 12 (2014)

Volume 11 (2013)

Volume 10 (2013)

Volume 9 (2012)

Volume 8 (2012)

Volume 7 (2011)

Volume 6 (2011)

	Volume 6, Issue 2 Pg 105 - 204 (May 2011)
	Volume 6, Issue 1 Pg 1 - 104 (February 2011)

Volume 5 (2010)

Volume 4 (2010)

Volume 3 (2009)

Volume 2 (2008)

Volume 1 (2007)

Advances in Computer Science and Engineering

Advances in Computer Science and Engineering
Volume 6, Issue 2, Pages 129 - 157 (May 2011)

A HYBRID LEARNING NEURAL NETWORK BASED IMAGE ALIGNMENT SYSTEM USING GLOBAL FEATURE SELECTION APPROACH
Chi-Yao Hsu, Yung-Chi Hsu and Sheng-Fuu Lin

Abstract:
The need for accurate and efficient image alignment has drastically increased in industrial visual inspection application because it can provide the inspected object with precise pose. Recently, the neural networks based on image alignment approaches are very popular due to their high efficiency of aligning images. However, such methods are difficult to not only find a good global descriptor to represent images, but also identify the parameters of neural network. Thus this paper develops a novel efficient image alignment, which consists of global feature selection approach (GFSA) and hybrid learning neural network (HLNN), to not only identify a well-performed global region descriptor, but also automatically adjust the parameters of neural network. Experimental results on both synthesized and real images are shown superior performance of the proposed image alignment system over other existing systems. Such system is useful to develop efficient image alignment systems.

Keywords and phrases: efficient image alignment, global feature selection approach, hybrid learning neural network, global region descriptor.

Number of Downloads: 256 | Number of Views: 812