Robust local feature extraction algorithm with visual cortex for object recognition

J. Lee; K. Roh; D. Wagner; H. Ko

doi:10.1049/el.2011.1832

Robust local feature extraction algorithm with visual cortex for object recognition

J. Lee, K. Roh, D. Wagner, H. Ko

Research output: Contribution to journal › Article › peer-review

6 Citations (Scopus)

Abstract

A robust local feature extraction algorithm comprised of two key steps is proposed. The first step is the extraction of feature point candidates from a multi-scale fast Hessian detector at 0° and 45° based on Gabor rotation angles and a multi-scale Harris corner detector based on the Gabor phase. The second step is a MAX operation for selecting points from the outputs of the three feature point detectors used in the previous step. Performance analysis shows that the proposed algorithm significantly enhances the recognition rate and is better than SIFT and SURF.

Original language	English
Pages (from-to)	1075-1076
Number of pages	2
Journal	Electronics Letters
Volume	47
Issue number	19
DOIs	https://doi.org/10.1049/el.2011.1832
Publication status	Published - 2011 Sept 15

ASJC Scopus subject areas

Electrical and Electronic Engineering

Access to Document

10.1049/el.2011.1832

Cite this

@article{51ab0bb89025407a8334b74eb81c8cfe,

title = "Robust local feature extraction algorithm with visual cortex for object recognition",

abstract = "A robust local feature extraction algorithm comprised of two key steps is proposed. The first step is the extraction of feature point candidates from a multi-scale fast Hessian detector at 0° and 45° based on Gabor rotation angles and a multi-scale Harris corner detector based on the Gabor phase. The second step is a MAX operation for selecting points from the outputs of the three feature point detectors used in the previous step. Performance analysis shows that the proposed algorithm significantly enhances the recognition rate and is better than SIFT and SURF.",

author = "J. Lee and K. Roh and D. Wagner and H. Ko",

year = "2011",

month = sep,

day = "15",

doi = "10.1049/el.2011.1832",

language = "English",

volume = "47",

pages = "1075--1076",

journal = "Electronics Letters",

issn = "0013-5194",

publisher = "John Wiley & Sons Inc.",

number = "19",

}

TY - JOUR

T1 - Robust local feature extraction algorithm with visual cortex for object recognition

AU - Lee, J.

AU - Roh, K.

AU - Wagner, D.

AU - Ko, H.

PY - 2011/9/15

Y1 - 2011/9/15

N2 - A robust local feature extraction algorithm comprised of two key steps is proposed. The first step is the extraction of feature point candidates from a multi-scale fast Hessian detector at 0° and 45° based on Gabor rotation angles and a multi-scale Harris corner detector based on the Gabor phase. The second step is a MAX operation for selecting points from the outputs of the three feature point detectors used in the previous step. Performance analysis shows that the proposed algorithm significantly enhances the recognition rate and is better than SIFT and SURF.

AB - A robust local feature extraction algorithm comprised of two key steps is proposed. The first step is the extraction of feature point candidates from a multi-scale fast Hessian detector at 0° and 45° based on Gabor rotation angles and a multi-scale Harris corner detector based on the Gabor phase. The second step is a MAX operation for selecting points from the outputs of the three feature point detectors used in the previous step. Performance analysis shows that the proposed algorithm significantly enhances the recognition rate and is better than SIFT and SURF.

UR - http://www.scopus.com/inward/record.url?scp=84855414235&partnerID=8YFLogxK

U2 - 10.1049/el.2011.1832

DO - 10.1049/el.2011.1832

M3 - Article

AN - SCOPUS:84855414235

SN - 0013-5194

VL - 47

SP - 1075

EP - 1076

JO - Electronics Letters

JF - Electronics Letters

IS - 19

ER -

Robust local feature extraction algorithm with visual cortex for object recognition

Abstract

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this