CFNet: Context fusion network for multi‐focus images. Issue 2 (18th November 2021)

• Record Type: Journal Article
• Authors: Zhang, Kang; Wu, Zhiliang; Yuan, Xia; Zhao, Chunxia
• Is Part Of: IET image processing. Volume 16:Issue 2(2022)
• Page Start: 499
• Page End: 508
• Publication Date: 2021-11-18
• Subjects: Image processing -- Periodicals; 621.36705
• DOI: 10.1049/ipr2.12363
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract: Multi‐focus image fusion aims to generate a clear image by fusing multiple source images. Existing deep learning‐based fusion methods often neglect the context information resulting in the loss of detail information. To address this issue, a context fusion network to merge multi‐focus images, namely CFNet, is proposed. Specifically, a context fusion module is proposed to make full use of low‐level pixels and high‐level semantic features. Particularly, the pyramid fusion mechanism and cross‐scale transfer strategy are adopted to ensure the visual and semantic consistency of the fused image. Meanwhile, to extract salient features more effectively, a spatial attention mechanism is introduced to enhance these features. Further, the pyramid loss is used to progressively refine the fused features at each scale. Experimental results show that the proposed method is superior to some existing methods in both qualitative and quantitative evaluation.