A. Nazemi - Computer Vision and Pattern Recognition Lab School of Cognitive Sciences, Institute for Research in Fundamental Sciences
M. J. Shafiee - School of Electrical & Computer Engineering, Shiraz University, Shiraz, Iran
Z. Azimifar - Computer Vision and Pattern Recognition Lab School of Cognitive Sciences, Institute for Research in Fundamental Sciences

Automatic vehicle Make and Model Recognition(MMR) system offers a competent way to vehicle classificationand recognition systems. This paper proposes a real time whilerobust vehicle make and model recognition system extracting thevehicle sub-image from the background and studies some sparsefeature coding methods such as Orthogonal Matching Pursuit(OMP), some variation of Sparse Coding (SC) methods andcompares them to choose the best one. Our method employs thesparse feature coding methods on dense Scale-Invariant FeatureTransform (SIFT) features and Support Vector Machine (SVM)for classification. The proposed system is examined by an Iranianon road vehicles dataset, which its samples are in different pointof views, various weather conditions and illuminations.

make and model recognition, orthogonal matching pursuit, sparse coding, bag of words, hard vector quantization