Daubechies complex wavelet transform based approach for Multiclass object classification

Object classification is an important step in different applications such as video surveillance, content based video retrieval etc. The task of multiclass object classification has more challenges. The goal of multi class object classification is to classify objects into one of the chosen classes. In this paper we propose a new method for multiclass object classification which is based on Daubechies complex wavelet transform. Daubechies complex wavelet transform is having advantage of approximate shift invariance and better edge representation as compared to real valued discrete wavelet transform. We have used Multiclass support vector machine as a classifier for classification of object. The proposed method has been tested on our own dataset prepared by authors of this paper. Evaluation results shows that the proposed method is better than other state-of-the-art methods and gives better performance for multiclass object classification.