Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Dominant orientation patch matching for HMAX

Authors
Lu, Yan-FengZhang, Hua-ZhenKang, Tae-KooLim, Myo-Taeg
Issue Date
12-6월-2016
Publisher
ELSEVIER
Keywords
Object recognition; Classification; HMAX; Dominant orientation; Patch; Matching
Citation
NEUROCOMPUTING, v.193, pp.155 - 166
Indexed
SCIE
SCOPUS
Journal Title
NEUROCOMPUTING
Volume
193
Start Page
155
End Page
166
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/88344
DOI
10.1016/j.neucom.2016.01.069
ISSN
0925-2312
Abstract
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 Cl 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. (C) 2016 Elsevier B.V. All rights reserved.
Files in This Item
There are no files associated with this item.
Appears in
Collections
College of Engineering > School of Electrical Engineering > 1. Journal Articles

qrcode

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

Related Researcher

Researcher Lim, Myo taeg photo

Lim, Myo taeg
공과대학 (전기전자공학부)
Read more

Altmetrics

Total Views & Downloads

BROWSE