Robust Feature Encoding with Neighborhood Information for Image Classification

	Robust Feature Encoding with Neighborhood Information for Image Classification
	Bingyuan Liu; Jing Liu; Chunjie Zhang; Maolin Chen; Hanqing Lu
	2013
会议名称	International Conference on Image and Graphics
会议录名称	Proceedings of the Seventh International Conference on Image and Graphics
会议日期	July 26-28, 2013
会议地点	Qingdao, China
摘要	The bag of visual words (BoW) model is one of the most successful model in image classification task. However, the major problem of the BoW model lies in the determination of visual words, which consists of codebook training and feature encoding phases. The traditional K-means and hard-assignment method completely ignore the structure of the local feature space, leading to high loss of information. To alleviate the information loss, we propose to incorporate the neighborhood information of the features into the codebook training and feature encoding process. We firstly propose a model to roughly measure the influence of the distribution of the neighboring features. Then we combine the proposed model with the traditional K-means method in a probability perspective to train the visual codebook. Finally, in the feature encoding phase, both the hard-assignment and soft-assignment method are improved with the proposed neighborhood information term. We investigate our method on two popular datasets: 15-Scenes and Caltech-101. Experimental results demonstrate the effectiveness of our proposed method.
关键词	Image Classification Feature Encoding
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/13445
专题	紫东太初大模型研究中心_图像与视频分析
通讯作者	Jing Liu
推荐引用方式 GB/T 7714	Bingyuan Liu,Jing Liu,Chunjie Zhang,et al. Robust Feature Encoding with Neighborhood Information 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
06643795.pdf（606KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载