Locality Discriminative Coding for Image Classification

	Locality Discriminative Coding for Image Classification
	Yang, Xiaoshan; Zhang, Tianzhu; Xu, Changsheng; Xu CS(徐常胜)
	2013-08
会议名称	ACM International Conference on Internet Multimedia Computing and Service
会议录名称	ICMICS
会议日期	2013-8
会议地点	安徽黄山
摘要	The Bag-of-Words (BOW) based methods are widely used in image classification. However, huge number of visual information is omitted inevitably in the quantization step of the BOW. Recently, NBNN and its improved methods like Local NBNN were proposed to solve this problem. Nevertheless, these methods do not perform better than the stateof- the-art BOW based methods. In this paper, based on the advantages of BOW and Local NBNN, we introduce a novel locality discriminative coding (LDC) method. We convert each low level local feature, such as SIFT, into code vector using the Local Feature-to-Class distance other than by k-means quantization. Extensive experimental results on 4 challenging benchmark datasets show that our LDC method outperforms 6 state-of-the-art image classification methods (3 based on NBNN, 3 based on BOW).
关键词	Bag-of-words Feature Coding Discriminative
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/11761
专题	多模态人工智能系统全国重点实验室_多媒体计算
通讯作者	Xu CS(徐常胜)
作者单位	中科院自动化研究所
第一作者单位	中国科学院自动化研究所
推荐引用方式 GB/T 7714	Yang, Xiaoshan,Zhang, Tianzhu,Xu, Changsheng,et al. Locality Discriminative Coding for Image Classification[C],2013.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Locality Discriminat（636KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载