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.

[1]  Pietro Perona,et al.  Object class recognition by unsupervised scale-invariant learning , 2003, 2003 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2003. Proceedings..

[2]  Thomas Serre,et al.  Robust Object Recognition with Cortex-Like Mechanisms , 2007, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[3]  Manish Khare,et al.  Dual Tree Complex Wavelet Transform Based Multiclass Object Classification , 2013, 2013 12th International Conference on Machine Learning and Applications.

[4]  Sergio A. Velastin,et al.  Object classification for real-time video-surveillance applications , 2008 .

[5]  Manish Khare,et al.  Curvelet transform based moving object segmentation , 2013, 2013 IEEE International Conference on Image Processing.

[6]  Sebastian Nowozin,et al.  On feature combination for multiclass object classification , 2009, 2009 IEEE 12th International Conference on Computer Vision.

[7]  Yi Lin.  Multicategory Support Vector Machines, Theory, and Application to the Classification of . . . , 2003 .

[8]  Manish Khare,et al.  Despeckling of medical ultrasound images using Daubechies complex wavelet transform , 2010, Signal Process..

[9]  Rogério Schmidt Feris,et al.  An Integrated System for Moving Object Classification in Surveillance Videos , 2008, 2008 IEEE Fifth International Conference on Advanced Video and Signal Based Surveillance.

[10]  Tieniu Tan,et al.  Real-Time Moving Object Classification with Automatic Scene Division , 2007, 2007 IEEE International Conference on Image Processing.

[11]  Manish Khare,et al.  An approach towards wavelet transform based multiclass object classification , 2013, 2013 Sixth International Conference on Contemporary Computing (IC3).

[12]  Sebastian Nowozin,et al.  Object Classification using Local Image Features , 2006 .

[13]  Mubarak Shah,et al.  Tracking and Object Classification for Automated Surveillance , 2002, ECCV.

[14]  Dimitrios Makris,et al.  Object Classification in Visual Surveillance Using Adaboost , 2007, 2007 IEEE Conference on Computer Vision and Pattern Recognition.

[15]  Chih-Jen Lin,et al.  A comparison of methods for multiclass support vector machines , 2002, IEEE Trans. Neural Networks.

[16]  Tieniu Tan,et al.  A survey on visual surveillance of object motion and behaviors , 2004, IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews).

[17]  Nicolás García-Pedrajas,et al.  Improving multiclass pattern recognition by the combination of two strategies , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[18]  Biswajit Bose,et al.  Improving object classification in far-field video , 2004, Proceedings of the 2004 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2004. CVPR 2004..

[19]  Diego Clonda,et al.  Complex Daubechies wavelets: properties and statistical image modelling , 2004, Signal Process..

[20]  Tieniu Tan,et al.  Recent developments in human motion analysis , 2003, Pattern Recognit..