Refined gaussian weighted histogram intersection and its application in number plate categorization

UTSePress Research/Manakin Repository

Search UTSePress Research


Advanced Search

Browse

My Account

Show simple item record

dc.contributor.author Jia, Wenjing en_US
dc.contributor.author Zhang, Huaifeng en_US
dc.contributor.author Wu, Qiang en_US
dc.contributor.author He, Sean en_US
dc.contributor.editor Banissi, M; Huang, M; Qu, Q en_US
dc.date.accessioned 2009-11-09T05:36:15Z
dc.date.available 2009-11-09T05:36:15Z
dc.date.issued 2006 en_US
dc.identifier 2006005594 en_US
dc.identifier.citation Jia Wenjing et al. 2006, 'Refined gaussian weighted histogram intersection and its application in number plate categorization', IEEE Computer Society, Los Alamitos, USA, pp. 249-254. en_US
dc.identifier.issn 0-7695-2606-3 en_US
dc.identifier.other E1 en_US
dc.identifier.uri http://hdl.handle.net/10453/2709
dc.description.abstract This paper proposes a refined Gaussian weighted histogram intersection for content-based image matching and applies the method for number plate categorization. Number plate images are classified into two groups based on their colour similarities with the model image of each group. The similarities of images are measured by the matching rates between their colour histograms. Histogram intersection (HI) is used to calculate the matching rates of histograms. Since the conventional histogram intersection algorithm is strictly based on the matching between bins of identical colours, the final matching rate could easily be affected by colour variation caused by various environment changes. In our recent paper [9], a Gaussian weighted histogram intersection (GWHI) algorithm has been proposed to facilitate the histogram matching via taking into account matching of both identical colours and similar colours. The weight is determined by the distance between two colours. When applied to number plate categorization, the GWHI algorithm demonstrates to be more robust to colour variations and produces a classification with much lower intra-class distance and much higher interclass distance than previous HI algorithms. However, the processing speed of this GWHI method is still not satisfying. In this paper, the GWHI method is further refined, where a colour quantization method is utilized to reduce the number of colours without introducing apparent perceptual colour distortion. New experimental results demonstrate that using the refined GWHI method, image categorization can be done more efficiently. en_US
dc.publisher IEEE Computer Society en_US
dc.relation.hasversion Accepted manuscript version
dc.relation.isbasedon http://dx.doi.org/10.1109/CGIV.2006.76 en_US
dc.title Refined gaussian weighted histogram intersection and its application in number plate categorization en_US
dc.parent Proceedings, computer graphics, imaging and visualisation en_US
dc.journal.volume en_US
dc.journal.number en_US
dc.publocation Los Alamitos, USA en_US
dc.identifier.startpage 249 en_US
dc.identifier.endpage 254 en_US
dc.cauo.name FEIT.School of Computing and Communications en_US
dc.conference Verified OK en_US
dc.conference.location Sydney Australia en_US
dc.for 080106 en_US
dc.personcode 044299 en_US
dc.personcode 995032 en_US
dc.personcode 990421 en_US
dc.personcode 000748 en_US
dc.percentage 60 en_US
dc.classification.name Image Processing en_US
dc.classification.type FOR-08 en_US
dc.custom International Conference Computer Graphics, Imaging and Visualization en_US
dc.date.activity 20060726 en_US
dc.location.activity Sydney Australia en_US
dc.description.keywords refinedgaussian weighted histogram, number plates, colour quantisation, colour variation en_US
dc.staffid 000748 en_US


Files in this item

This item appears in the following Collection(s)

Show simple item record