Detecting Densely Distributed Graph Patterns for Fine-Grained Image Categorization | |
Zhang, Luming1; Yang, Yang2; Wang, Meng1; Hong, Richang1; Nie, Liqiang3; Li, Xuelong4 | |
作者部门 | 光学影像学习与分析中心 |
2016-02-01 | |
发表期刊 | IEEE TRANSACTIONS ON IMAGE PROCESSING |
ISSN | 1057-7149 |
卷号 | 25期号:2页码:553-565 |
产权排序 | 4 |
摘要 | Fine-grained image categorization is a challenging task aiming at distinguishing objects belonging to the same basic-level category, e.g., leaf or mushroom. It is a useful technique that can be applied for species recognition, face verification, and so on. Most of the existing methods either have difficulties to detect discriminative object components automatically, or suffer from the limited amount of training data in each sub-category. To solve these problems, this paper proposes a new fine-grained image categorization model. The key is a dense graph mining algorithm that hierarchically localizes discriminative object parts in each image. More specifically, to mimic the human hierarchical perception mechanism, a superpixel pyramid is generated for each image. Thereby, graphlets from each layer are constructed to seamlessly capture object components. Intuitively, graphlets representative to each super-/sub-category is densely distributed in their feature space. Thus, a dense graph mining algorithm is developed to discover graphlets representative to each super-/sub-category. Finally, the discovered graphlets from pairwise images are integrated into an image kernel for fine-grained recognition. Theoretically, the learned kernel can generalize several state-of-the-art image kernels. Experiments on nine image sets demonstrate the advantage of our method. Moreover, the discovered graphlets from each sub-category accurately capture those tiny discriminative object components, e.g., bird claws, heads, and bodies. |
文章类型 | Article |
关键词 | Fine-grained Sub-category Graphlet Matching Image Kernel Dense Graph Mining |
WOS标题词 | Science & Technology ; Technology |
DOI | 10.1109/TIP.2015.2502147 |
收录类别 | SCI |
关键词[WOS] | CLASSIFICATION ; RECOGNITION |
语种 | 英语 |
WOS研究方向 | Computer Science ; Engineering |
项目资助者 | State High-Tech Development Plan(2014AA015104) ; Program for New Century Excellent Talents in University(NCET-13-0764) ; Key Research Program through the Chinese Academy of Sciences(KGZD-EW-T03) |
WOS类目 | Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic |
WOS记录号 | WOS:000383905800005 |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | http://ir.opt.ac.cn/handle/181661/28382 |
专题 | 光谱成像技术研究室 |
作者单位 | 1.Hefei Univ Technol, Dept Comp Sci & Informat Engn, Hefei 230009, Peoples R China 2.Univ Elect Sci & Technol China, Sch Comp Sci & Engn, Chengdu 610051, Peoples R China 3.Natl Univ Singapore, Sch Comp, Singapore 119077, Singapore 4.Chinese Acad Sci, Xian Inst Opt & Precis Mech, Ctr Opt IMagery Anal & Learning, State Key Lab Transient Opt & Photon, Xian 710119, Peoples R China |
推荐引用方式 GB/T 7714 | Zhang, Luming,Yang, Yang,Wang, Meng,et al. Detecting Densely Distributed Graph Patterns for Fine-Grained Image Categorization[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2016,25(2):553-565. |
APA | Zhang, Luming,Yang, Yang,Wang, Meng,Hong, Richang,Nie, Liqiang,&Li, Xuelong.(2016).Detecting Densely Distributed Graph Patterns for Fine-Grained Image Categorization.IEEE TRANSACTIONS ON IMAGE PROCESSING,25(2),553-565. |
MLA | Zhang, Luming,et al."Detecting Densely Distributed Graph Patterns for Fine-Grained Image Categorization".IEEE TRANSACTIONS ON IMAGE PROCESSING 25.2(2016):553-565. |
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 | ||
Detecting Densely Di(3427KB) | 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