中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering

文献类型:期刊论文

作者Hu, Weiming1,4; Hu, Ruiguang1; Xie, Nianhua1,4; Ling, Haibin2; Maybank, Stephen3
刊名IEEE TRANSACTIONS ON IMAGE PROCESSING
出版日期2014-04-01
卷号23期号:4页码:1513-1526
关键词Saliency detection nonlinear diffusion multiscale information fusion image classification
英文摘要In this paper, we propose saliency driven image multiscale nonlinear diffusion filtering. The resulting scale space in general preserves or even enhances semantically important structures such as edges, lines, or flow-like structures in the foreground, and inhibits and smoothes clutter in the background. The image is classified using multiscale information fusion based on the original image, the image at the final scale at which the diffusion process converges, and the image at a midscale. Our algorithm emphasizes the foreground features, which are important for image classification. The background image regions, whether considered as contexts of the foreground or noise to the foreground, can be globally handled by fusing information from different scales. Experimental tests of the effectiveness of the multiscale space for the image classification are conducted on the following publicly available datasets: 1) the PASCAL 2005 dataset; 2) the Oxford 102 flowers dataset; and 3) the Oxford 17 flowers dataset, with high classification rates.
WOS标题词Science & Technology ; Technology
类目[WOS]Computer Science, Artificial Intelligence ; Engineering, Electrical & Electronic
研究领域[WOS]Computer Science ; Engineering
关键词[WOS]REGION DETECTION ; OBJECT DETECTION ; ENHANCEMENT ; ATTENTION ; EFFICIENT ; FEATURES ; KERNEL ; SHAPE
收录类别SCI
语种英语
WOS记录号WOS:000332112400002
源URL[http://ir.ia.ac.cn/handle/173211/3265]  
专题自动化研究所_模式识别国家重点实验室_视频内容安全团队
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Temple Univ, Dept Comp & Informat Sci, Philadelphia, PA 19122 USA
3.Birkbeck Coll, Dept Comp Sci & Informat Syst, London WC1E 7HX, England
4.Chinese Acad Sci, Inst Automat, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Hu, Weiming,Hu, Ruiguang,Xie, Nianhua,et al. Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering[J]. IEEE TRANSACTIONS ON IMAGE PROCESSING,2014,23(4):1513-1526.
APA Hu, Weiming,Hu, Ruiguang,Xie, Nianhua,Ling, Haibin,&Maybank, Stephen.(2014).Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering.IEEE TRANSACTIONS ON IMAGE PROCESSING,23(4),1513-1526.
MLA Hu, Weiming,et al."Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering".IEEE TRANSACTIONS ON IMAGE PROCESSING 23.4(2014):1513-1526.

入库方式: OAI收割

来源:自动化研究所

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。