Multi-focus Image Fusion Based on Hess Matrix

This paper proposes a Hess (also known as Hessian) matrix-based multi-focus image fusion method. In this method, multi-scale Hess matrix is utilized to detect feature and background regions. On this basis, source images are split into two different parts, and different fusion strategies are applied to generating decision map respectively. By combining decision maps in different parts, an initial decision map is obtained, and then the initial decision map is refined with post-processing method. To improve the performance of the fusion method, a new focus measure is proposed based on multi-scale Hess matrix for both feature and background regions. Integral images are also introduced for fast computation to meet the real-time application requirements. Experimental results demonstrate that the proposed method is competitive with or even outperforms the state-of-the-art methods in terms of both subjective visual perception and objective evaluation metrics.