A binary based HMAX model for object recognition

Tae Koo Kang; Huazhen Zhang; Dong Sung Pae; Myo Taeg Lim

doi:10.1109/ICCAS.2015.7364837

A binary based HMAX model for object recognition

Tae Koo Kang, Huazhen Zhang, Dong Sung Pae, Myo Taeg Lim

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract

In this paper, we propose a fast binary based HMAX model (B-HMAX). In our method, we detect corner based interest points after the second layer C1 to extract fewer numbers of features with better distinctiveness, and use binary string to describe the image patches extracted around detected corners, then use hamming distance for matching between two patches in the third layer S2, which is much faster than Euclidean method. Experimental results demonstrate that our proposed B-HMAX model can significantly reduce the total process time, while keeping the accuracy performance as the same with or better than standard HMAX.

Original language	English
Title of host publication	ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
Pages	1297-1301
Number of pages	5
ISBN (Print)	9788993215090
DOIs	https://doi.org/10.1109/ICCAS.2015.7364837
Publication status	Published - 2015 Dec 23
Event	15th International Conference on Control, Automation and Systems, ICCAS 2015 - Busan, Korea, Republic of Duration: 2015 Oct 13 → 2015 Oct 16

Other

Other	15th International Conference on Control, Automation and Systems, ICCAS 2015
Country/Territory	Korea, Republic of
City	Busan
Period	15/10/13 → 15/10/16

Keywords

Binary descriptor
Biologically inspired model
HMAX
Object recognition

ASJC Scopus subject areas

Control and Systems Engineering

Access to Document

10.1109/ICCAS.2015.7364837

Cite this

A binary based HMAX model for object recognition. / Kang, Tae Koo; Zhang, Huazhen; Pae, Dong Sung et al.
ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings. Institute of Electrical and Electronics Engineers Inc., 2015. p. 1297-1301 7364837.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Kang, TK, Zhang, H, Pae, DS & Lim, MT 2015, A binary based HMAX model for object recognition. in ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings., 7364837, Institute of Electrical and Electronics Engineers Inc., pp. 1297-1301, 15th International Conference on Control, Automation and Systems, ICCAS 2015, Busan, Korea, Republic of, 15/10/13. https://doi.org/10.1109/ICCAS.2015.7364837

@inproceedings{fa5f373b379549158478023166ac5dba,

title = "A binary based HMAX model for object recognition",

abstract = "In this paper, we propose a fast binary based HMAX model (B-HMAX). In our method, we detect corner based interest points after the second layer C1 to extract fewer numbers of features with better distinctiveness, and use binary string to describe the image patches extracted around detected corners, then use hamming distance for matching between two patches in the third layer S2, which is much faster than Euclidean method. Experimental results demonstrate that our proposed B-HMAX model can significantly reduce the total process time, while keeping the accuracy performance as the same with or better than standard HMAX.",

keywords = "Binary descriptor, Biologically inspired model, HMAX, Object recognition",

author = "Kang, {Tae Koo} and Huazhen Zhang and Pae, {Dong Sung} and Lim, {Myo Taeg}",

year = "2015",

month = dec,

day = "23",

doi = "10.1109/ICCAS.2015.7364837",

language = "English",

isbn = "9788993215090",

pages = "1297--1301",

booktitle = "ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

note = "15th International Conference on Control, Automation and Systems, ICCAS 2015 ; Conference date: 13-10-2015 Through 16-10-2015",

}

TY - GEN

T1 - A binary based HMAX model for object recognition

AU - Kang, Tae Koo

AU - Zhang, Huazhen

AU - Pae, Dong Sung

AU - Lim, Myo Taeg

PY - 2015/12/23

Y1 - 2015/12/23

N2 - In this paper, we propose a fast binary based HMAX model (B-HMAX). In our method, we detect corner based interest points after the second layer C1 to extract fewer numbers of features with better distinctiveness, and use binary string to describe the image patches extracted around detected corners, then use hamming distance for matching between two patches in the third layer S2, which is much faster than Euclidean method. Experimental results demonstrate that our proposed B-HMAX model can significantly reduce the total process time, while keeping the accuracy performance as the same with or better than standard HMAX.

AB - In this paper, we propose a fast binary based HMAX model (B-HMAX). In our method, we detect corner based interest points after the second layer C1 to extract fewer numbers of features with better distinctiveness, and use binary string to describe the image patches extracted around detected corners, then use hamming distance for matching between two patches in the third layer S2, which is much faster than Euclidean method. Experimental results demonstrate that our proposed B-HMAX model can significantly reduce the total process time, while keeping the accuracy performance as the same with or better than standard HMAX.

KW - Binary descriptor

KW - Biologically inspired model

KW - HMAX

KW - Object recognition

UR - http://www.scopus.com/inward/record.url?scp=84966389665&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84966389665&partnerID=8YFLogxK

U2 - 10.1109/ICCAS.2015.7364837

DO - 10.1109/ICCAS.2015.7364837

M3 - Conference contribution

AN - SCOPUS:84966389665

SN - 9788993215090

SP - 1297

EP - 1301

BT - ICCAS 2015 - 2015 15th International Conference on Control, Automation and Systems, Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 15th International Conference on Control, Automation and Systems, ICCAS 2015

Y2 - 13 October 2015 through 16 October 2015

ER -

A binary based HMAX model for object recognition

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this