Pattern selective image fusion for multi-focus image reconstruction
CAIP'05 Proceedings of the 11th international conference on Computer Analysis of Images and Patterns
Producing object-based special effects by fusing multiple differently focused images
IEEE Transactions on Circuits and Systems for Video Technology
Fusing images with different focuses using support vector machines
IEEE Transactions on Neural Networks
| Hi-index | 0.00 |
A novel depth fusion algorithm is proposed for multi-focused images based on point spread functions (PSF). In this paper, firstly, a discrete PSF model is present and functions with different parameters are prepared for the proposed algorithm. Based on the analysis of the effect of PSF, the detail process to fuse the depth of multi-focused images is described. By employing PSF to convolve each original images and comparing with its adjacent one in the image sequence, the focused and defocused region in the original images may be located. Combining the the focused region in the images according to Choose Max rules, an all-in-focus image may be got. The complexity of the algorithm for an image series with more than two original images is discussed at the end of this paper. Experimental results show that the image is distinctly segmented into multi-regions and the image edge is legible as well. The proposed algorithm based on PSF convolvetion as a focus measure has been shown to be experimentally valid. The fusion results are satisfactory with smooth transitions across region boundaries.