Chinese Journal of Computers   Full Text
Title	A Novel Image Fusion Algorithm Based on Local Contrast and Adaptive PCNN
Authors	MIAO Qi-Guang WANG Bao-Shu
Address	(School of Computer Science, Xidian University, Xi’an 710071)
Year	2008
Issue	No.5(875—880)
Abstract &   Background	Abstract This paper proposes a new fusion algorithm based on the improved pulse coupled neural network(PCNN) model, the fundamental characteristics of images and the properties of human vision system. Compared with the traditional algorithm where the linking strength of each neuron has the same value and its value is chosen through experimentation, this algorithm uses the local contrast of each pixel as its value, so that the linking strength of each pixel can be chosen adaptively. After the processing of PCNN with the adaptive linking strength, new fire mapping images are obtained for each image taking part in the fusion. The clear objects of each original image are decided by the compare-selection operator with the fire mapping images pixel by pixel and then all of them are merged into a new clear image. Furthermore, by this algorithm, other parameters, for example, Δ, the threshold adjusting constant, only have a slight effect on the new fused image. It therefore overcomes the difficulty in adjusting parameters in PCNN. Experimental results indicate that the method outperforms the traditional approaches in preserving edge information while improving texture information. Keywords image fusion; Pulse-Coupled Neural Network(PCNN); human vision system; local contrast; linking strength; fire mapping image Background This work is supported by the National Natural Science Foundation of China Under grant No.60702063, the Pre-research Foundation of China and the Youth Science Foundation of Guangxi under grant No.0640067. Image fusion is an important step in the image analysis which needs to combine various kinds of data to get the final result. The pulse coupled neural network (PCNN) has a significant biological background and was introduced by Eckhorn as a research effort to explain the synchronous pulse bursts in the visual cortex of the cat and monkey. The physiologically motivated PCNN has an extraordinary advantage in image processing over other methods scientists have ever used. It can be applied to a large variety of research fields as diverse as image denoise, image edge detection, image segmentation, image enhancement, image shadow removal, image object recognition, and so on. In the application of PCNN to image fusion, it is not in wide use because of its long running time, great difficulty in adjusting parameters, high demand on images. Its requests of a brighter object area and a primary and secondary relation also restrict the wide application. Besides, there is not sufficient literature about the application of PCNN to image fusion. In this paper, the new algorithm is based on the improved PCNN model, the fundamental characteristics of images and the properties of human vision system. The research group‘s interests include image understanding and analysis, image registration, image fusion and image recognition. The group has proposed some novel algorithms in image registration and image fusion.