Multi-focus image fusion plays an important role in the field of image recognition and analysis. However, current focus evaluation operators are complex and inefficiency. In this paper, a new focus evaluation operator based on max–min filter is proposed. In new focus measure, we use max–min filter with the help of average filter and median filter (MMAM) to evaluate the focus degree of source images. This evaluation algorithm can well measure the sharpness of different regions of the image, and the selected clear region will be more useful for human visual or machine perception. The experiment proved that MMAM can perform better than sum-of-modified-Laplacian in most of cases. Later, MMAM is used to fused multi-focus image by combined structure-driven fused regions and depth information of blurred images. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art fusion algorithms on image quality and objective fusion criteria. This paper firstly proposes the concept and computational processing of MMAM, which provides a new research direction and innovative idea for multi-focus image fusion base on filter, and MMAM can embedded into state-of-the-art fusion algorithm to achieve high quality multi-focus image fusion.

中文翻译：

---

一种新的基于最大最小滤波器的焦点评价算子及其在高质量多焦点图像融合中的应用

多焦点图像融合在图像识别和分析领域发挥着重要作用。然而，当前的焦点评估算子复杂且效率低下。在本文中，提出了一种新的基于最大-最小滤波器的焦点评估算子。在新的聚焦度量中，我们使用最大-最小滤波器，并借助平均滤波器和中值滤波器（MMAM）来评估源图像的聚焦程度。这种评价算法可以很好地衡量图像不同区域的锐度，所选择的清晰区域对人类视觉或机器感知将更有用。实验证明，在大多数情况下，MMAM 的性能优于修正拉普拉斯算子之和。后来，MMAM被用于通过组合结构驱动的融合区域和模糊图像的深度信息来融合多焦点图像。实验结果表明，所提出的算法在图像质量和客观融合标准方面优于最先进的融合算法。本文首次提出了MMAM的概念和计算处理，为基于滤波器的多焦点图像融合提供了新的研究方向和创新思路，MMAM可以嵌入到最先进的融合算法中，实现高质量的多焦点图像融合。 -焦点图像融合。