Multi-focus Image Fusion Based on the Improved PCNN and Guided Filter

详细信息    查看全文

• 作者：Zhaobin Wang ; Shuai Wang ; Ying Zhu
• 关键词：Image fusion ; Multi ; focus image ; PCNN ; Guided filter ; Selection rule
• 刊名：Neural Processing Letters
• 出版年：2017
• 出版时间：February 2017
• 年：2017
• 卷：45
• 期：1
• 页码：75-94
• 全文大小：
• 刊物类别：Physics and Astronomy
• 刊物主题：Artificial Intelligence (incl. Robotics); Complex Systems; Computational Intelligence;
• 出版者：Springer US
• ISSN：1573-773X
• 卷排序：45

文摘

This paper proposes a novel multi-focus image fusion method based on pulse coupled neural networks (PCNN) and guided filter. PCNN matches human visual perception very well. And guided filter is an edge-preserving filter which is proposed in recent years. In our method, the fusion process consists of the following steps: firstly, the source images are preliminarily fused with the guided filter. Then the intermediate fused image is employed to motivate the improved PCNN to generate a fusion map. Finally, the source images are fused according to the fusion map. Six contrast methods are employed to evaluate the performance of the proposed approach in six groups of experiments. The experimental results show that the proposed method outperforms the most existing methods in both subjective visual effect and objective evaluation criteria.