Enhanced hierarchical model of object recognition based on a novel patch selection method in salient regions

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

	Enhanced hierarchical model of object recognition based on a novel patch selection method in salient regions
	Lu Yanfeng(吕彦锋); Kang Taekoo; Zhang Huazhen; Lim Myotaeg
刊名	IET Computer Vision
	2015
卷号	5 期号:9 页码:663-672
关键词	Hierarchical Model Object Recognition Keypoint-based Patch Selection Hmax
英文摘要	The biologically inspired hierarchical model for object recognition, Hierarchical Model and X (HMAX), has attracted considerable attention in recent years. HMAX is robust (i.e., shift-and-scale invariant), but its use of random-patch-selection makes it sensitive to rotational deformation, which heavily limits its performance in object recognition. The main reason is that numerous randomly chosen patches are often orientation selective, thereby leading to mismatch. To address this issue, we propose a novel patch selection method for HMAX called Saliency and Keypoint based Patch Selection (SKPS), which is based on a saliency (attention) mechanism and multi-scale keypoints. In contrast to the conventional random-patch-selection based HMAX model that involves huge amounts of redundant information in feature extraction, the SKPS based HMAX model (S-HMAX) extracts a very few features while offering promising distinctiveness. To show the effectiveness of S-HMAX, we apply it to object categorization and conduct experiments on the CalTech101, TU Darmstadt (TUD), ImageNet, and GRAZ01 databases. Our experimental results demonstrate that S-HMAX outperforms conventional HMAX and is very comparable to existing architectures that have a similar framework.
语种	英语
内容类型	期刊论文
源URL	[http://ir.ia.ac.cn/handle/173211/15329]
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
推荐引用方式 GB/T 7714	Lu Yanfeng,Kang Taekoo,Zhang Huazhen,et al. Enhanced hierarchical model of object recognition based on a novel patch selection method in salient regions[J]. IET Computer Vision,2015,5(9):663-672.
APA	Lu Yanfeng,Kang Taekoo,Zhang Huazhen,&Lim Myotaeg.(2015).Enhanced hierarchical model of object recognition based on a novel patch selection method in salient regions.IET Computer Vision,5(9),663-672.
MLA	Lu Yanfeng,et al."Enhanced hierarchical model of object recognition based on a novel patch selection method in salient regions".IET Computer Vision 5.9(2015):663-672.