Home > Archive > 2014 > Volume 4 Number 2 (Apr. 2014) >
IJMLC 2014 Vol.4(2): 142-145 ISSN: 2010-3700
DOI: 10.7763/IJMLC.2014.V4.402

Real Time Vehicle Make and Model Recognition Based on Hierarchical Classification

Hajar Emami, Mahmood Fathi, and Kaamran Raahemifar

Abstract—In recent years Intelligent Transportation Systems (ITS) have become an important research area. Vehicle make and model recognition is one of the topics in the domain of ITS for secure access and traffic monitoring applications. This paper presents an effective approach for fast recognition of vehicle make and model form back views. We use efficient hierarchical classifier that determine the class of vehicle at first and then recognize vehicle make and model in a smaller group which dramatically increases the speed and performance of the method by focusing attention on the most discriminative regions. In this method, different classes are defined based on the location of license plate and taillights of vehicle. By considering the vehicle initial class, we can select different regions and features for different classes in recognition step that improve the results. Results confirm our prediction that hierarchical classification is more powerful in vehicle model recognition. The final system is capable of recognition rates of 96% on a dataset of over 280 back view images of vehicles. The proposed algorithm is robust to illumination and weather conditions.

Index Terms—Vehicle make and model recognition, vehicle classification, hierarchical classification, intelligent transportation systems.

Hajar Emami is with Iran University of Science and Technology.
Mahmood Fathy is with the Department of Computer Engineering, Iran University of Science & Technology, Iran (e-mail: mahfathy@iust.ac.ir).
Kaamran Raahemifar is with the Department of Electrical and Computer Engineering, Ryerson University, Iran.


Cite: Hajar Emami, Mahmood Fathi, and Kaamran Raahemifar, "Real Time Vehicle Make and Model Recognition Based on Hierarchical Classification," International Journal of Machine Learning and Computing vol.4, no. 2, pp. 142-145, 2014.

General Information

  • E-ISSN: 2972-368X
  • Abbreviated Title: Int. J. Mach. Learn.
  • Frequency: Quaterly
  • DOI: 10.18178/IJML
  • Editor-in-Chief: Dr. Lin Huang
  • Executive Editor:  Ms. Cherry L. Chen
  • Abstracing/Indexing: Inspec (IET), Google Scholar, Crossref, ProQuest, Electronic Journals LibraryCNKI.
  • E-mail: ijml@ejournal.net

Article Metrics in Dimensions