Dominant Orientation Patch Matching for HMAX

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

	Dominant Orientation Patch Matching for HMAX
	Lu Yanfeng(吕彦锋)1 ; Zhang Huazhen 2; Kang Taekoo 3; Lim Myotaeg 2
发表期刊	Neurocomputing
	2016
期号	193 页码:155-166
摘要	The biologically inspired 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 it is sensitive to rotational deformation, which greatly limits its performance in object recognition. The main reason for this is that HMAX lacks an appropriate directional module against rotational deformation, thereby often leading to mismatch. To address this issue, we propose a novel patch-matching method for HMAX called Dominant Orientation Patch Matching (DOPM), which calculates the dominant orientation of the selected patches and implements patch-to-patch matching. In contrast to patch matching with the whole target image (second layer C1) in the conventional HMAX model, which involves huge amounts of redundant information in the feature representation, the DOPM-based HMAX model (D-HMAX) quantizes the C1 layer to patch sets with better distinctiveness, then realizes patch-to-patch matching based on the dominant orientation. To show the effectiveness of D-HMAX, we apply it to object categorization and conduct experiments on the CalTech101, CalTech05, GRAZ01, and GRAZ02 databases. Our experimental results demonstrate that D-HMAX outperforms conventional HMAX and is comparable to existing architectures that have a similar framework.
关键词	Object Recognition Classification Hmax Dominant Orientation Patch Matching
收录类别	SCI
语种	英语
WOS记录号	WOS:000375506500017
引用统计	被引频次：10[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/15330
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
作者单位	1.Institute of Automation, Chinese Academy of Sciences 2.Korea University 3.Sangmyung University
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	Lu Yanfeng,Zhang Huazhen,Kang Taekoo,et al. Dominant Orientation Patch Matching for HMAX[J]. Neurocomputing,2016(193):155-166.
APA	Lu Yanfeng,Zhang Huazhen,Kang Taekoo,&Lim Myotaeg.(2016).Dominant Orientation Patch Matching for HMAX.Neurocomputing(193),155-166.
MLA	Lu Yanfeng,et al."Dominant Orientation Patch Matching for HMAX".Neurocomputing .193(2016):155-166.

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
Dominant orientation（9039KB）	期刊论文	作者接受稿	开放获取	CC BY-NC-SA	浏览下载