An image fusion algorithm based on fuzzy C-means clustering

The visible light and infrared image fusion technology can effectively combine the high resolution information of visible light image with the thermal target information of infrared image, so as to achieve a more accurate and comprehensive expression of the scene. Traditional fusion methods are difficult to highlight salient objects and retain rich details. Therefore, this paper proposes a visible light and infrared image fusion algorithm based on Fuzzy C-means Clustering (FCM). The algorithm uses FCM and region projection method to extract the target region and background region of the source image, and combines Non-subsample Shear-wave Transform (NSST) to decompose each region. In addition, Spiking Cortical Model (SCM) and specific strategies are used to fuse decomposed coefficients. Experimental results show that the fusion image obtained by the proposed algorithm has prominent infrared targets and rich texture details in subjective vision. In objective evaluation, its average gradient and edge retention factor are better than the comparison method.