A new manifold distance measure for visual object categorization

CORC > 自动化研究所 > 中国科学院自动化研究所 > 复杂系统管理与控制国家重点实验室 > 机器人应用与理论组

	A new manifold distance measure for visual object categorization
	Fengfu Li; Xiayuan Huang; Hong Qiao; Bo Zhang
	2016
会议名称	arXiv
会议日期	none
会议地点	none
关键词	none
通讯作者	Fengfu Li
英文摘要	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.
会议录	arXiv
内容类型	会议论文
源URL	[http://ir.ia.ac.cn/handle/173211/12834]
专题	自动化研究所_复杂系统管理与控制国家重点实验室_机器人应用与理论组自动化研究所_复杂系统管理与控制国家重点实验室
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]. 见:arXiv. none. none.