A new manifold distance measure for visual object categorization

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 机器人理论与应用

	A new manifold distance measure for visual object categorization
	Fengfu Li; Xiayuan Huang; Hong Qiao; Bo Zhang
	2016
会议名称	arXiv
会议录名称	arXiv
会议日期	none
会议地点	none
摘要	Manifold distances are very effective tools for visual object recognition. However, most of the traditionalmanifold distances between images are based on the pixel-level comparison and thus easily affected by image rotations and translations. In this paper, we propose a new manifold distance to model the dissimilarities between visual objects based on the Complex Wavelet Structural Similarity (CW-SSIM) index. The proposed distance is more robust to rotations and translations of images than the traditionalmanifold distance and the CW-SSIM index based distance. In addition, the proposed distance is combined with the k-medoids clustering method to derive a new clustering method for visual objectcategorization. Experiments on Coil-20, Coil-100 and Olivetti Face Databases show that the proposeddistance measure is better for visual object categorization than both the traditional manifold distances and the CW-SSIM index based distances.
关键词	None
文献类型	会议论文
条目标识符	http://ir.ia.ac.cn/handle/173211/12834
专题	多模态人工智能系统全国重点实验室_机器人理论与应用复杂系统管理与控制国家重点实验室
通讯作者	Fengfu Li
推荐引用方式 GB/T 7714	Fengfu Li,Xiayuan Huang,Hong Qiao,et al. A new manifold distance measure for visual object categorization[C],2016.

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
A New Manifold Dista（226KB）	会议论文		开放获取	CC BY-NC-SA	浏览下载