Abstract There have been a number of recent works in computer vision that had used new age multiresolution multidirectional transforms like curvelets and contourlets for face and character recognition. Although these works produced high recognition accuracies they did not provide any comparative study against more well known techniques and hence could not justify the use of these new transforms as against more traditional methods. In this work we will compare the recognition accuracies of the aforesaid two transforms against a very well known multiresolution transform viz. the wavelet transform. this study aims at showing the research community how good or how bad the aforesaid transforms are when compared against wavelets as a feature set for pattern recognition.

References

[1] Cand s E. and Donoho D., Curvelets: A Surprisingly Effective Nonadaptive A Comparative Study in Wavelets, Curvelets and Contourlets as Feature Sets for Pattern Recognition 51 Representation for Objects with Edges , Stanford University, USA, 1999.

[2] Candes E. , Demanet L., Donoho D., and Ying L., Fast Discrete Curvelet Transforms , Macromolecular Theory and Simulations , vol. 5, no .3, pp. 861-899, 2006.

[3] Candes E., Ridgelets Theory and Applications , Stanford, USA, 1998.

[4] Chaudhuri B. and Majumdar A., Curvelet B ased Multi SVM Recognizer for Offline Handwritten Bangla: A Major Indian Script, in the 7th International Conference on Document Analysis Research , pp. 647-656 , 2007.

[5] Do M. and Vetterli M., The Contourlet Transform: An Efficient Directional Multiresolution Image Representation , IEEE Transactions Image on Processing , vol. 14, no. 12, pp. 2091-2106, 2005.

[6] Computer Vision Science Research Projects , http://cswww.essex.ac.uk/mv/allfaces/faces94.ht ml , 2007 .

[7] Computer Vision Science Research Projects , http://cswww.essex.ac.uk/mv/allfaces/faces95.ht ml , 2007.

[8] Curvelet.org, http://www.curvelet.org/download/ download.html , 2007.

[9] Image Formation and Processing , http://www. ifp.uiuc.edu/~minhdo/software/contourlet_toolbo x.tar, 2003.

[10] Fedora Core Test Page , http://www-stat-class. stanford.edu/~tibs/ElemStatLearn/datasets/zip.tes t.gz, 2008.

[11] Fedora Core Test Page , http://www-stat-class. stanford.edu/~tibs/ElemStatLearn/datasets/zip.tra in.gz , 2008

[12] Majumdar A., Ray S., and Bhattac harya A., Face Recognition by Multiresolution Contourlet Transform on Bit Quantized Facial Images, Indian International Conference on Artificial Intelligence , pp. 640-641, 2005.

[13] Mandal T., Majumdar A., and Wu J., Face Recognition by Curvelet Based Feature Extraction, in Proceedings of the International Conference on Image Analysis and Recognition , pp. 806-817, 2007.

[14] Ruiz J., Acosta J., Salazar A., and Jaime R., Shift Invariant Support Vector Machines Face Recognition System , Transactions on Engineering, Computing and Technology , vol. 16, no. 2, pp. 167-171, 2006.

[15] Shutalo L., Shawe J., Fred A., Caelli T., Duin R., Campilho A., and De D., Texture Classification By Combining Wavelet and Contourlet Features, Joint IAPR International Workshops SSPR , pp. 1126-1134, 2004.

[16] Starck J. , Candes J., and Donoho L., The Curvelet Transform for Image Denoising , IEEE Transactions on Image Processing , vol. 11, no. 6, pp 670-684, 2002. Angshul Majumdar received his BSc of engineering in electronics and telecommunication from Bengal Engineering College, Shibpur, India. Currently, he is pursuing his graduate studies at the University of British Columbia, Canada. His research interests are in the application of multiresolution tools to image processing and computer vision. Arusharka Bhattacharya received his BSc of engineering in information technology from Jadavpur University, India. Currently, he is working at PricewaterhouseCoopers, India. His research interests are in computer vision and machine learning.