19 December 2017 Multi-focus image fusion algorithm based on non-subsampled shearlet transform and focus measure
Author Affiliations +
Proceedings Volume 10613, 2017 International Conference on Robotics and Machine Vision; 1061309 (2017) https://doi.org/10.1117/12.2300361
Event: Second International Conference on Robotics and Machine Vision, 2017, Kitakyushu, Japan
Abstract
novel multi-focus image fusion algorithm is proposed in the Sheartlet domain. The core idea of this paper is to utilize the focus measure to detect the focused region from the multi-focus images. The proposed algorithm can be divided into three procedures: image decomposition, sub-bands coefficients selection and image reconstruction. At first, the multi-focus images are decomposed by non-subsampled Sheartlet transform (NSST), and the low frequency sub-bands and high frequency sub-bands can be obtained. For the low frequency sub-bands, saliency detection and improved sum-modified-Laplacian are combined to detect the focused regions. A modified edge measure algorithm is utilized to guide the coefficients combination for high frequency sub-bands at different levels. Moreover, in order to avoid the erroneous results introduced by the above procedures, mathematical morphology technique is used to revise the decision maps of the low frequency sub-bands and high frequency sub-bands. The final fused image can be obtained by taken the inverse NSST. The performance of the proposed method is tested on series of multi-focus images extensively. Experimental results indicate that the proposed method outperformed some state-of-the-art fusion methods, in terms of both subjective observation and objective evaluations.
© (2017) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Hongmei Wang, Hongmei Wang, Mir Soban Ahmed, Mir Soban Ahmed, } "Multi-focus image fusion algorithm based on non-subsampled shearlet transform and focus measure", Proc. SPIE 10613, 2017 International Conference on Robotics and Machine Vision, 1061309 (19 December 2017); doi: 10.1117/12.2300361; https://doi.org/10.1117/12.2300361
PROCEEDINGS
7 PAGES


SHARE
Back to Top