Vehicle logo recognition by weighted multi‐class support vector machine ensembles based on sharpness histogram features
Authors:
Open Access
- 1 July 2015
- journal article
- research article
- Published by Institution of Engineering and Technology (IET) in IET Image Processing
- Vol. 9 (7) , 527-534
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.Keywords
This publication has 23 references indexed in Scilit:
- A Gaussian mixture model and support vector machine approach to vehicle type and colour classificationIET Intelligent Transport Systems, 2014
- Performance of visual search tasks from various types of contour informationJournal of the Optical Society of America A, 2013
- Image retrieval and classification using adaptive local binary patterns based on texture featuresIET Image Processing, 2012
- Texture feature extraction method for scale and rotation invariant image retrievalElectronics Letters, 2012
- Comparison of different wavelets for automatic identification of vehicle license plateIET Intelligent Transport Systems, 2011
- Vehicle model recognition from frontal view image measurementsComputer Standards & Interfaces, 2011
- Color spatial feature-based approach for multiple-vehicle trackingApplied Optics, 2010
- Vehicle Logo Recognition Using a SIFT-Based Enhanced Matching SchemeIEEE Transactions on Intelligent Transportation Systems, 2010
- Vehicle-Classification Algorithm for Single-Loop Detectors Using Neural NetworksIEEE Transactions on Vehicular Technology, 2006
- Robust license-plate recognition method for passing vehicles under outside environmentIEEE Transactions on Vehicular Technology, 2000