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
Source PublicationIET Computer Vision
2015
Volume5Issue:9Pages:663-672
AbstractThe 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.
KeywordHierarchical Model Object Recognition Keypoint-based Patch Selection Hmax
Indexed BySCI
Language英语
Document Type期刊论文
Identifierhttp://ir.ia.ac.cn/handle/173211/15329
Collection复杂系统管理与控制国家重点实验室_机器人理论与应用
Recommended Citation
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.
Files in This Item: Download All
File Name/Size DocType Version Access License
Lu et al. - 2015 - E(1858KB)期刊论文作者接受稿开放获取CC BY-NC-SAView Download
Related Services
Recommend this item
Bookmark
Usage statistics
Export to Endnote
Google Scholar
Similar articles in Google Scholar
[Lu Yanfeng(吕彦锋)]'s Articles
[Kang Taekoo]'s Articles
[Zhang Huazhen]'s Articles
Baidu academic
Similar articles in Baidu academic
[Lu Yanfeng(吕彦锋)]'s Articles
[Kang Taekoo]'s Articles
[Zhang Huazhen]'s Articles
Bing Scholar
Similar articles in Bing Scholar
[Lu Yanfeng(吕彦锋)]'s Articles
[Kang Taekoo]'s Articles
[Zhang Huazhen]'s Articles
Terms of Use
No data!
Social Bookmark/Share
File name: Lu et al. - 2015 - Enhanced hierarchical model of object recognition based on a novel patch selection method in salient regions.pdf
Format: Adobe PDF
All comments (0)
No comment.
 

Items in the repository are protected by copyright, with all rights reserved, unless otherwise indicated.