Fast cortical keypoints for real-time object recognition

Kasim Terzić; J. M.F. Rodrigues; J. M.H. Du Buf

doi:10.1109/ICIP.2013.6738695

Fast cortical keypoints for real-time object recognition

Kasim Terzić, J. M.F. Rodrigues, J. M.H. Du Buf

School of Computer Science

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

Abstract

Best-performing object recognition algorithms employ a large number features extracted on a dense grid, so they are too slow for real-time and active vision. In this paper we present a fast cortical keypoint detector for extracting meaningful points from images. It is competitive with state-of-the-art detectors and particularly well-suited for tasks such as object recognition. We show that by using these points we can achieve state-of-the-art categorization results in a fraction of the time required by competing algorithms.

Original language	English
Title of host publication	2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings
Pages	3372-3376
Number of pages	5
DOIs	https://doi.org/10.1109/ICIP.2013.6738695
Publication status	Published - 1 Dec 2013
Event	2013 20th IEEE International Conference on Image Processing, ICIP 2013 - Melbourne, VIC, Australia Duration: 15 Sept 2013 → 18 Sept 2013

Conference

Conference	2013 20th IEEE International Conference on Image Processing, ICIP 2013
Country/Territory	Australia
City	Melbourne, VIC
Period	15/09/13 → 18/09/13

Keywords

Computer vision
Gabor filters
Image classification
Object recognition
Real time systems

Access to Document

10.1109/ICIP.2013.6738695

Cite this

@inproceedings{7f267ffac51a4b5abbc57eb0ab0721d0,

title = "Fast cortical keypoints for real-time object recognition",

abstract = "Best-performing object recognition algorithms employ a large number features extracted on a dense grid, so they are too slow for real-time and active vision. In this paper we present a fast cortical keypoint detector for extracting meaningful points from images. It is competitive with state-of-the-art detectors and particularly well-suited for tasks such as object recognition. We show that by using these points we can achieve state-of-the-art categorization results in a fraction of the time required by competing algorithms.",

keywords = "Computer vision, Gabor filters, Image classification, Object recognition, Real time systems",

author = "Kasim Terzi{\'c} and Rodrigues, {J. M.F.} and {Du Buf}, {J. M.H.}",

year = "2013",

month = dec,

day = "1",

doi = "10.1109/ICIP.2013.6738695",

language = "English",

isbn = "9781479923410",

pages = "3372--3376",

booktitle = "2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings",

note = "2013 20th IEEE International Conference on Image Processing, ICIP 2013 ; Conference date: 15-09-2013 Through 18-09-2013",

}

TY - GEN

T1 - Fast cortical keypoints for real-time object recognition

AU - Terzić, Kasim

AU - Rodrigues, J. M.F.

AU - Du Buf, J. M.H.

PY - 2013/12/1

Y1 - 2013/12/1

N2 - Best-performing object recognition algorithms employ a large number features extracted on a dense grid, so they are too slow for real-time and active vision. In this paper we present a fast cortical keypoint detector for extracting meaningful points from images. It is competitive with state-of-the-art detectors and particularly well-suited for tasks such as object recognition. We show that by using these points we can achieve state-of-the-art categorization results in a fraction of the time required by competing algorithms.

AB - Best-performing object recognition algorithms employ a large number features extracted on a dense grid, so they are too slow for real-time and active vision. In this paper we present a fast cortical keypoint detector for extracting meaningful points from images. It is competitive with state-of-the-art detectors and particularly well-suited for tasks such as object recognition. We show that by using these points we can achieve state-of-the-art categorization results in a fraction of the time required by competing algorithms.

KW - Computer vision

KW - Gabor filters

KW - Image classification

KW - Object recognition

KW - Real time systems

UR - http://www.scopus.com/inward/record.url?scp=84897750955&partnerID=8YFLogxK

U2 - 10.1109/ICIP.2013.6738695

DO - 10.1109/ICIP.2013.6738695

M3 - Conference contribution

AN - SCOPUS:84897750955

SN - 9781479923410

SP - 3372

EP - 3376

BT - 2013 IEEE International Conference on Image Processing, ICIP 2013 - Proceedings

T2 - 2013 20th IEEE International Conference on Image Processing, ICIP 2013

Y2 - 15 September 2013 through 18 September 2013

ER -

Fast cortical keypoints for real-time object recognition

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this