Feature-level image fusion is investigated with region segmentation and dual-tree complex wavelet transform (DT-CWT). The DT-CWT coefficients are preprocessed by median filtering, and the texture gradients are computed with Gaussian derivatives. The key step of the proposed algorithm is a consistent segmentation of multiple images in the same sub-band. The authors construct a two-order tensor with the gradient of each image, and take the difference between its two eigenvalues as the equivalent gradient squared norm. The watershed algorithm is applied to this norm to obtain the desired region segmentation. Many activity measures of a region are used to construct various fusion rules, and many performance metrics are computed to evaluate the performance. The proposed feature-level approach based on a selection and averaging strategy is compared with many well known approaches, including the latest sparse representation based ones. A comprehensive examination indicates its advantages over other approaches, especially for outdoor applications involving noise and complex background.
Tao Wei, Qiong Gao, Na Ma, Na Li, Juanfeng Wang, Ping Lei, Xinsheng Ji, "Feature-Level Image Fusion Through Consistent Region Segmentation and Dual-Tree Complex Wavelet Transform" in Journal of Imaging Science and Technology, 2016, https://doi.org/10.2352/J.ImagingSci.Technol.2016.60.2.020502