Pixel-wise ordinal classification for salient object grading | |
Liu, Yanzhu1; Wang, Yanan2; Kong, Adams Wai Kin1 | |
作者部门 | 飞行器光学成像与测量技术研究室 |
2021-02-01 | |
发表期刊 | IMAGE AND VISION COMPUTING |
ISSN | 0262-8856 |
卷号 | 106页码:12 |
产权排序 | 2 |
摘要 | Driven by business intelligence applications for rating attraction of products in shops, a new problem - salient object grading is studied in this paper. In computer vision, plenty of salient object detection approaches have been proposed, while most existing studies detect objects in a binary manner: salient or not. This paper focuses on a new problem setting that requires detecting all salient objects and categorizing them into different salient levels. Based on that, a pixel-wise ordinal classification method is proposed. It consists of a multi-resolution saliency detector which detects and segments objects, an ordinal classifier which grades pixels into different salient levels, and a binary saliency enhancer which sharpens the difference between non-saliency and all other salient levels. Two new image datasets with salient level labels are constructed. Experimental results demonstrate that, on the one hand, the proposed method provides effective salient level predictions and on the other hand, offers very comparable performance with state-of-the-art salient object detection methods in the traditional problem setting. (C) 2020 Elsevier B.V. All rights reserved. |
关键词 | Ordinal classification Salient object grading Deep neural networks |
DOI | 10.1016/j.imavis.2020.104086 |
收录类别 | SCI |
语种 | 英语 |
资助项目 | Ministry of Education, Singapore[MOE2016-T2-1-042(S)] |
WOS研究方向 | Computer Science ; Engineering ; Optics |
项目资助者 | Ministry of Education, Singapore |
WOS类目 | Computer Science, Artificial Intelligence ; Computer Science, Software Engineering ; Computer Science, Theory & Methods ; Engineering, Electrical & Electronic ; Optics |
WOS记录号 | WOS:000620292700002 |
出版者 | ELSEVIER |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/94591 |
专题 | 飞行器光学成像与测量技术研究室 |
通讯作者 | Liu, Yanzhu |
作者单位 | 1.Nanyang Technol Univ, Sch Comp Sci & Engn, Singapore 639978, Singapore 2.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Xian 710119, Peoples R China |
推荐引用方式 GB/T 7714 | Liu, Yanzhu,Wang, Yanan,Kong, Adams Wai Kin. Pixel-wise ordinal classification for salient object grading[J]. IMAGE AND VISION COMPUTING,2021,106:12. |
APA | Liu, Yanzhu,Wang, Yanan,&Kong, Adams Wai Kin.(2021).Pixel-wise ordinal classification for salient object grading.IMAGE AND VISION COMPUTING,106,12. |
MLA | Liu, Yanzhu,et al."Pixel-wise ordinal classification for salient object grading".IMAGE AND VISION COMPUTING 106(2021):12. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 | ||
1-s2.0-S026288562030(3495KB) | 期刊论文 | 作者接受稿 | 限制开放 | CC BY-NC-SA | 请求全文 |
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。
修改评论