Multifocus Image Fusion Scheme Using Feature Contrast of Orientation Information Measure in Lifting Stationary Wavelet Domain

In this paper, a novel image fusion algorithm based on orientation information measure and lifting stationary wavelet transform (LSWT) is proposed, aiming at solving the fusion problem of multifocus images. In order to select the coefficients of the fused image properly, the selection principles for different subbands are discussed, respectively. For choosing the low frequency subband coefficients, a new sum-modified-Laplacian (NSML) of the orientation information measure is proposed and used as the focus measure to fuse the low frequency subband. When choosing the high frequency subband coefficients, a novel feature contrast of the orientation information measure, which can effectively restrain the influence of noise and can be used as the activity-level measurement to select coefficients from the sharpness parts of the high frequency subimages, is proposed. Experimental results indicate that the proposed fusion approach cannot only extract more important visual information from source images, but also effectively avoid the introduction of artificial information. It significantly outperforms the traditional fusion methods in fusion multifocus clean images and multifocus noisy images, in terms of both visual quality and objective evaluation.