Natural Scene Image Recognition by Fusing Weighted Colour Moments with Bag of Visual Patches on Spatial Pyramid Layout

Yousef Alqasrawi; Daniel Neagu; Peter I Cowling

doi:10.1109/ISDA.2009.134

Natural Scene Image Recognition by Fusing Weighted Colour Moments with Bag of Visual Patches on Spatial Pyramid Layout

Yousef Alqasrawi, Daniel Neagu, Peter I Cowling

Computer Science

Research output: Contribution to conference › Paper

Abstract

The problem of object/scene image classification has gained increasing attention from many researchers in computer vision. In this paper we investigate a number of early fusion methods using a novel approach to combine image colour information and the bag of visual patches (BOP) for recognizing natural scene image categories. We propose keypoints density-based weighting method (KDW) for merging colour moments and the BOP on a spatial pyramid layout. We found that the density of keypoints located in each image sub-region at specific granularity has noticeable impacts on deciding the importance of colour moments on that image sub-region. We demonstrate the validity of our approach on a six categories dataset of natural scene images. Experimental results have proved the effectiveness of our proposed approach.

Original language	English
Pages	140-145
DOIs	https://doi.org/10.1109/ISDA.2009.134
Publication status	Published - 30 Dec 2009
Event	9th International Conference on Intelligent Systems Design and Applications (ISDA 2009) - Pisa, Italy Duration: 30 Nov 2009 → 2 Dec 2009

Conference

Conference	9th International Conference on Intelligent Systems Design and Applications (ISDA 2009)
Country/Territory	Italy
City	Pisa
Period	30/11/09 → 2/12/09

Access to Document

10.1109/ISDA.2009.134

http://www.computer.org/csdl/proceedings/isda/2009/3872/00/3872a140-abs.html

Cite this

@conference{a8f5697507b14a76a1472caf6ed85336,

title = "Natural Scene Image Recognition by Fusing Weighted Colour Moments with Bag of Visual Patches on Spatial Pyramid Layout",

abstract = "The problem of object/scene image classification has gained increasing attention from many researchers in computer vision. In this paper we investigate a number of early fusion methods using a novel approach to combine image colour information and the bag of visual patches (BOP) for recognizing natural scene image categories. We propose keypoints density-based weighting method (KDW) for merging colour moments and the BOP on a spatial pyramid layout. We found that the density of keypoints located in each image sub-region at specific granularity has noticeable impacts on deciding the importance of colour moments on that image sub-region. We demonstrate the validity of our approach on a six categories dataset of natural scene images. Experimental results have proved the effectiveness of our proposed approach.",

author = "Yousef Alqasrawi and Daniel Neagu and Cowling, {Peter I}",

year = "2009",

month = dec,

day = "30",

doi = "10.1109/ISDA.2009.134",

language = "English",

pages = "140--145",

note = "9th International Conference on Intelligent Systems Design and Applications (ISDA 2009) ; Conference date: 30-11-2009 Through 02-12-2009",

}

TY - CONF

T1 - Natural Scene Image Recognition by Fusing Weighted Colour Moments with Bag of Visual Patches on Spatial Pyramid Layout

AU - Alqasrawi, Yousef

AU - Neagu, Daniel

AU - Cowling, Peter I

PY - 2009/12/30

Y1 - 2009/12/30

N2 - The problem of object/scene image classification has gained increasing attention from many researchers in computer vision. In this paper we investigate a number of early fusion methods using a novel approach to combine image colour information and the bag of visual patches (BOP) for recognizing natural scene image categories. We propose keypoints density-based weighting method (KDW) for merging colour moments and the BOP on a spatial pyramid layout. We found that the density of keypoints located in each image sub-region at specific granularity has noticeable impacts on deciding the importance of colour moments on that image sub-region. We demonstrate the validity of our approach on a six categories dataset of natural scene images. Experimental results have proved the effectiveness of our proposed approach.

AB - The problem of object/scene image classification has gained increasing attention from many researchers in computer vision. In this paper we investigate a number of early fusion methods using a novel approach to combine image colour information and the bag of visual patches (BOP) for recognizing natural scene image categories. We propose keypoints density-based weighting method (KDW) for merging colour moments and the BOP on a spatial pyramid layout. We found that the density of keypoints located in each image sub-region at specific granularity has noticeable impacts on deciding the importance of colour moments on that image sub-region. We demonstrate the validity of our approach on a six categories dataset of natural scene images. Experimental results have proved the effectiveness of our proposed approach.

U2 - 10.1109/ISDA.2009.134

DO - 10.1109/ISDA.2009.134

M3 - Paper

SP - 140

EP - 145

T2 - 9th International Conference on Intelligent Systems Design and Applications (ISDA 2009)

Y2 - 30 November 2009 through 2 December 2009

ER -