Deep Direction-Context-Inspiration Network for Defocus Region Detection in Natural Images
文献类型：期刊论文
| 作者 | Zhao, Fan2; Wang, Haipeng1; Zhao, Wenda3 |
| 刊名 | IEEE ACCESS
 |
| 出版日期 | 2019 |
| 卷号 | 7页码:64737-64743 |
| 关键词 | Defocus region detection direction-context-inspiration network level-integration |
| ISSN号 | 2169-3536 |
| DOI | 10.1109/ACCESS.2019.2916332 |
| 通讯作者 | Wang, Haipeng(whp5691@163.com) |
| 英文摘要 | Defocus region detection (DRD) problem aims to assign per-pixel predictions of focus clear areas and defocus blur areas. One of the challenges in this problem is to accurately detect the boundary of the transition region between the focus and defocus regions. To address this issue, the paper proposes a direction-context-inspiration network (DCINet), which can take advantage of the directional context effectively. First, we extract directional context by recurrent neural networks initialized with the identity matrix (IRNN) to weight the feature maps and integrate them in the two-group integration method, which can produce the coarse DRD maps. Second, the maps are level-integrated with the source image guiding and the coarse maps are refined gradually. The overall DCINet can integrate low-level details and high-level semantics efficiently. The Experimental results demonstrate that the network can detect the boundary of the transition region precisely, achieving the state-of-the-art performance. |
| WOS关键词 | BLUR DETECTION |
| 资助项目 | National Natural Science Foundation of China[61801077] ; National Natural Science Foundation of China[61771088] ; China Postdoctoral Science Foundation[2017M611221] |
| WOS研究方向 | Computer Science ; Engineering ; Telecommunications |
| 语种 | 英语 |
| WOS记录号 | WOS:000470032800001 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; National Natural Science Foundation of China ; China Postdoctoral Science Foundation ; China Postdoctoral Science Foundation ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; China Postdoctoral Science Foundation ; China Postdoctoral Science Foundation ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; China Postdoctoral Science Foundation ; China Postdoctoral Science Foundation ; National Natural Science Foundation of China ; National Natural Science Foundation of China ; China Postdoctoral Science Foundation ; China Postdoctoral Science Foundation |
| 源URL | [http://cas-ir.dicp.ac.cn/handle/321008/171969]  |
| 专题 | 大连化学物理研究所_中国科学院大连化学物理研究所 |
| 通讯作者 | Wang, Haipeng |
| 作者单位 | 1.Naval Aviat Univ, Inst Informat Fus, Yantai 264001, Peoples R China 2.Chinese Acad Sci, Dalian Inst Chem Phys, Dalian 116023, Peoples R China 3.Dalian Univ Technol, Sch Informat & Commun Engn, Dalian 116024, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhao, Fan,Wang, Haipeng,Zhao, Wenda. Deep Direction-Context-Inspiration Network for Defocus Region Detection in Natural Images[J]. IEEE ACCESS,2019,7:64737-64743. |
| APA | Zhao, Fan,Wang, Haipeng,&Zhao, Wenda.(2019).Deep Direction-Context-Inspiration Network for Defocus Region Detection in Natural Images.IEEE ACCESS,7,64737-64743. |
| MLA | Zhao, Fan,et al."Deep Direction-Context-Inspiration Network for Defocus Region Detection in Natural Images".IEEE ACCESS 7(2019):64737-64743. |
入库方式： OAI收割
来源：大连化学物理研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。