Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering

CORC > 自动化研究所 > 中国科学院自动化研究所 > 模式识别国家重点实验室 > 视频内容安全团队

	Image Classification Using Multiscale Information Fusion Based on Saliency Driven Nonlinear Diffusion Filtering
	Hu, Weiming1,4 ; Hu, Ruiguang 1; Xie, Nianhua 1,4; Ling, Haibin 2; Maybank, Stephen 3
刊名	IEEE TRANSACTIONS ON IMAGE PROCESSING
	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
内容类型	期刊论文
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.