当前位置: X-MOL 学术Mobile Netw. Appl. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Region- and Pixel-Level Multi-Focus Image Fusion through Convolutional Neural Networks
Mobile Networks and Applications ( IF 3.8 ) Pub Date : 2021-01-06 , DOI: 10.1007/s11036-020-01719-9
Wenyi Zhao , Huihua Yang , Jie Wang , Xipeng Pan , Zhiwei Cao

Capturing all-in-focus images with 3D scenes is typically a challenging task due to depth of field limitations, and various multi-focus image fusion methods have been employed to generate all-in-focus images. However, existing methods have difficulty simultaneously achieving real-time and superior fusion performance. In this paper, we propose a region- and pixel-based method that can recognize the focus and defocus regions or pixels by the neighborhood information in the source images. The proposed method can obtain satisfactory fusion results and achieve improved real-time performance. First, a convolutional neural network (CNN)-based classifier generates a coarse region-based trimap quickly, which contains focus, defocus and boundary regions. Then, precise fine-tuning is implemented at the boundary regions to address the boundary pixels that are difficult to discriminate by existing methods. Based on a public database, a high-quality dataset is constructed that provides abundant precise pixel-level labels, so that the proposed method can accurately classify the regions and pixels without artifacts. Furthermore, an image interpolation method called NEAREST_Gaussian is proposed to improve the recognition ability at the boundary. Experimental results show that the proposed method outperforms other state-of-the-art methods in visual perception and object metrics. Additionally, the proposed method has 80% improved to the conventional CNN-based methods.



中文翻译:

通过卷积神经网络的区域和像素级多焦点图像融合

由于景深的限制,使用3D场景捕获全焦点图像通常是一项艰巨的任务,并且已经采用了各种多焦点图像融合方法来生成全焦点图像。但是,现有方法难以同时获得实时和优异的融合性能。在本文中,我们提出了一种基于区域和像素的方法,该方法可以通过源图像中的邻域信息识别焦点和散焦区域或像素。所提出的方法可以获得令人满意的融合结果,并提高了实时性能。首先,基于卷积神经网络(CNN)的分类器可快速生成基于粗糙区域的三图,其中包含聚焦,散焦和边界区域。然后,在边界区域实施精确的微调,以解决现有方法难以区分的边界像素。在公共数据库的基础上,构建了高质量的数据集,该数据集提供了丰富的精确像素级标签,从而使所提出的方法可以准确地对区域和像素进行分类,而不会出现伪影。此外,一种称为提出了NEAREST_Gaussian来提高边界的识别能力。实验结果表明,该方法在视觉感知和目标度量方面优于其他最新技术。此外,所提出的方法比传统的基于CNN的方法具有80%的改进。

更新日期:2021-01-06
down
wechat
bug