Vehicle logo recognition by weighted multi‐class support vector machine ensembles based on sharpness histogram features. Issue 7 (1st July 2015)

• Record Type: Journal Article
• Authors: Xiao, Jianli; Xiang, Wenshu; Liu, Yuncai
• Is Part Of: IET image processing. Volume 9:Issue 7(2015)
• Page Start: 527
• Page End: 534
• Publication Date: 2015-07-01
• Subjects: road vehicles -- traffic engineering computing -- object recognition -- support vector machines -- image matching -- feature extraction -- image colour analysis; vehicle logo recognition -- weighted multiclass support vector machine ensembles -- sharpness histogram features -- image feature matching approaches -- SVM -- colour histogram features -- average recognition performance -- kernel function; Image processing -- Periodicals; 621.36705
• DOI: 10.1049/iet-ipr.2014.0691
• Languages: English
• ISSNs: 1751-9659

Abstract

Abstract : Classical methods recognise vehicle logos with image feature matching approaches. Different from these methods, this study proposes a novel algorithm to recognise the vehicle logos in real time by constructing the weighted multi‐class support vector machine (SVM) ensemble model to classify the vehicle logos based on sharpness histogram features. To evaluate the performance of the proposed algorithm, extensive experiments have been performed. Experimental results indicate that the sharpness histogram features proposed by the authors has better distinguishability than colour histogram features. Moreover, they show that the proposed algorithm has the best average recognition performance, and its performance is the most robust. Conveniently, the proposed algorithm can avoid the burden of choosing the appropriate kernel function and parameters comparing with multi‐class SVM model.