中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
Global and local exploitation for saliency using bag-of-words

文献类型:期刊论文

作者Zheng, Zhenzhu; Zhang, Yun; Yan, Luxin
刊名IET COMPUTER VISION
出版日期2014
英文摘要The guidance of attention helps human vision system to detect objects rapidly. In this study, the authors present a new saliency detection algorithm by usingbag-of-words (BOW) representation. The authors regard salient regions as coming from globally rare features and regions locally differ from their surroundings. Our approach consists of three stages: first, calculate global rarity of visual words. A vocabulary, a group of visual words, is generated from the given image and a rarity factor for each visual word is introduced according to its occurrence. Second, calculate local contrast. Representations of local patch are achieved from the histograms of words. Then, local contrast is computed by the difference between the two BOW histograms of a patch and its surroundings. Finally,saliency is measured by the combination of global rarity and local patch contrast. We compare our model with the previous methods on natural images, and experimental results demonstrate good performance of our model and fair consistency with human eye fixations.
收录类别SCI
原文出处http://www.crossref.org/iPage?doi=10.1049%2Fiet-cvi.2013.0132
语种英语
源URL[http://ir.siat.ac.cn:8080/handle/172644/5938]  
专题深圳先进技术研究院_数字所
作者单位IET COMPUTER VISION
推荐引用方式
GB/T 7714
Zheng, Zhenzhu,Zhang, Yun,Yan, Luxin. Global and local exploitation for saliency using bag-of-words[J]. IET COMPUTER VISION,2014.
APA Zheng, Zhenzhu,Zhang, Yun,&Yan, Luxin.(2014).Global and local exploitation for saliency using bag-of-words.IET COMPUTER VISION.
MLA Zheng, Zhenzhu,et al."Global and local exploitation for saliency using bag-of-words".IET COMPUTER VISION (2014).

入库方式: OAI收割

来源:深圳先进技术研究院

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。