Performance Evaluation of New Colour Histogram-based Interest Point Detectors

Interest point detection is an active area in computer vision due to its importance in many applications. Measuring the pixel-wise difference between image pixel intensities is the mechanism of most detectors that have been proposed in literature. Recently, interest point detectors were proposed tha...

Full description

Bibliographic Details
Main Authors:	Rassem, Taha H., Khoo, Bee Ee
Format:	Article
Published:	Springer US 2015
Subjects:	QA75 Electronic computers. Computer science
Online Access:	http://umpir.ump.edu.my/id/eprint/6910/ http://umpir.ump.edu.my/id/eprint/6910/ http://umpir.ump.edu.my/id/eprint/6910/

id	ump-6910
recordtype	eprints
spelling	ump-69102018-01-22T06:27:28Z http://umpir.ump.edu.my/id/eprint/6910/ Performance Evaluation of New Colour Histogram-based Interest Point Detectors Rassem, Taha H. Khoo, Bee Ee QA75 Electronic computers. Computer science Interest point detection is an active area in computer vision due to its importance in many applications. Measuring the pixel-wise difference between image pixel intensities is the mechanism of most detectors that have been proposed in literature. Recently, interest point detectors were proposed that incorporated the histogram representation instead of image pixel intensity. In this paper, research that extends histogram-based interest point detectors is introduced. Four colour-space representations were used to construct new detectors: HSV, Opponent, Transformed and Ohta colour spaces. Several experiments were performed to evaluate the new colour histogram-based detectors and compare them with previous detectors. First, the proposed detectors were evaluated in an image-matching task. Then, we studied and evaluated the performance of some of the local image descriptors that were extracted from the interest points and regions detected by the proposed detectors. Finally, the four top-ranked descriptors in the descriptor evaluation experiments were used to evaluate the new colour histogram-based detectors in an image-classification task using different object and scene image datasets. The experimental results demonstrate that our new detectors possess an increased ability to distinguish and more robust in regards to image matching, particularly with respect to textured scene images that involve transformations, such as illumination, viewpoint and blur changes. Furthermore, the descriptor performance may change depending on the detector and data set type. The image-classification results demonstrate that the proposed detectors exhibit higher classification accuracy for certain descriptors and data sets than the other detectors. Springer US 2015 Article PeerReviewed Rassem, Taha H. and Khoo, Bee Ee (2015) Performance Evaluation of New Colour Histogram-based Interest Point Detectors. Multimedia Tools and Applications, 74 (24). pp. 11357-11398. ISSN 1380-7501 (print); 1573-7721 (online) http://dx.doi.org/10.1007/s11042-014-2235-4 DOI: 10.1007/s11042-014-2235-4
repository_type	Digital Repository
institution_category	Local University
institution	Universiti Malaysia Pahang
building	UMP Institutional Repository
collection	Online Access
topic	QA75 Electronic computers. Computer science
spellingShingle	QA75 Electronic computers. Computer science Rassem, Taha H. Khoo, Bee Ee Performance Evaluation of New Colour Histogram-based Interest Point Detectors
description	Interest point detection is an active area in computer vision due to its importance in many applications. Measuring the pixel-wise difference between image pixel intensities is the mechanism of most detectors that have been proposed in literature. Recently, interest point detectors were proposed that incorporated the histogram representation instead of image pixel intensity. In this paper, research that extends histogram-based interest point detectors is introduced. Four colour-space representations were used to construct new detectors: HSV, Opponent, Transformed and Ohta colour spaces. Several experiments were performed to evaluate the new colour histogram-based detectors and compare them with previous detectors. First, the proposed detectors were evaluated in an image-matching task. Then, we studied and evaluated the performance of some of the local image descriptors that were extracted from the interest points and regions detected by the proposed detectors. Finally, the four top-ranked descriptors in the descriptor evaluation experiments were used to evaluate the new colour histogram-based detectors in an image-classification task using different object and scene image datasets. The experimental results demonstrate that our new detectors possess an increased ability to distinguish and more robust in regards to image matching, particularly with respect to textured scene images that involve transformations, such as illumination, viewpoint and blur changes. Furthermore, the descriptor performance may change depending on the detector and data set type. The image-classification results demonstrate that the proposed detectors exhibit higher classification accuracy for certain descriptors and data sets than the other detectors.
format	Article
author	Rassem, Taha H. Khoo, Bee Ee
author_facet	Rassem, Taha H. Khoo, Bee Ee
author_sort	Rassem, Taha H.
title	Performance Evaluation of New Colour Histogram-based Interest Point Detectors
title_short	Performance Evaluation of New Colour Histogram-based Interest Point Detectors
title_full	Performance Evaluation of New Colour Histogram-based Interest Point Detectors
title_fullStr	Performance Evaluation of New Colour Histogram-based Interest Point Detectors
title_full_unstemmed	Performance Evaluation of New Colour Histogram-based Interest Point Detectors
title_sort	performance evaluation of new colour histogram-based interest point detectors
publisher	Springer US
publishDate	2015
url	http://umpir.ump.edu.my/id/eprint/6910/ http://umpir.ump.edu.my/id/eprint/6910/ http://umpir.ump.edu.my/id/eprint/6910/
first_indexed	2023-09-18T22:03:05Z
last_indexed	2023-09-18T22:03:05Z
_version_	1777414528507576320

Performance Evaluation of New Colour Histogram-based Interest Point Detectors

Similar Items