Multi-Focus Image Fusion by Combining PDTDFB and Wavelet Transform

To extract the salient features of the image more effectively and improve the performance of multi-focus image fusion, for the shortcomings of Curvelet which can not capture the texture information, According to the respective advantages of Pyramidal dual-tree directional filter bank and wavelet, this paper proposes multi-focus image fusion algorithm based on PDTDFB and wavelet. Firstly, the multi-focus image is decomposed into different directions of information by PDTDFB, the absolute value of largest selection of fusion rule is used for the low-frequency information .Then high-frequency information is used for further decomposition of discrete wavelet, the absolute value of the largest selection of fusion scheme is also used for the low-frequency information, while the high-frequency of decomposition is obtained by regional energy rule. Experiment and theoretical analysis show that this method is effective in improving the direction information and edge information of the image, meanwhile extract the salient features of the image. The fusion method proposed in this paper has more improvements than the method of curve let combining wavelet transform. Vision has made great improvements, and evaluation is better than the latter.