Abstract—Image fusion is the process of combining information of interest in two or more images of a scene into a single highly informative image. Generally, the multi-resolution image fusion based on the wavelet transform performs better on diverse images than traditional methods. Therefore, a comparative study of wavelet-based image fusion with different wavelet families and fusion methods are far-reaching to guide people in their applications. On the other hand, in this paper, a novel fusion rule based on focus measure and local contrast measure is proposed to analyze the information in images and help selecting appropriate information from different source images to obtain a fused image. Experimental results on various wavelet functions and fusion rules demonstrate that the proposed fusion approach outperforms traditional methods in real images.
Index Terms—Fusion rule, image fusion, local contrast measure, wavelet transform.
Bo Jiang is with the Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences, Guangzhou 510530, China (e-mail: firstname.lastname@example.org).
Rui Zhang is with Sun Yat-sen University, China (e-mail: email@example.com).
Xiao Zhang is with the Guangzhou Institutes of Biomedicine and Health, Chinese Academy of Sciences, Guangzhou 510530, China (e-mail: firstname.lastname@example.org).
Cite: Bo Jiang, Rui Zhang, and Xiao Zhang, "A Comparative Study of Wavelet-Based Image Fusion with a Novel Fusion Rule," International Journal of Machine Learning and Computing vol.5, no. 6, pp. 484-492, 2015.