Mixed Nonorthogonal Transforms Representation for Face Recognition
- 26 Downloads
An alternative face recognition system that additively combines two-dimensional discrete wavelet transform (2D-DWT) coefficients and two-dimensional discrete cosine transform (2D-DCT) coefficients for image feature extraction is proposed. Each training pose is represented by superimposing the dominant coefficients from the two domains taking into account the nonorthogonality of the coefficients in one domain with respect to the coefficients in the other domain. The recognition system is tested with three publicly available databases, namely ORL, YALE, and FERET. As shown in the sample results, the proposed system significantly reduces the required storage size, a desirable property for big data and when computing resources are limited, while maintaining the accuracy of recognition rates when compared with the 2D-DCT, the 2D-DWT, and the successive 2D-DWT/2D-DCT techniques. In addition, the computational complexity in the testing phase is comparable with that of recently reported techniques.
KeywordsMixed transforms Discrete cosine transform Discrete wavelet transform Face recognition
The authors acknowledge the University of Central Florida Advanced Research Computing Center for providing computational resources that contributed to results reported herein. URL: https://arcc.ist.ucf.edu. Also, the authors would like to thank Mr. André Beckus for his valuable comments.
- 3.O. Database, AT&T laboratories Cambridge database of faces (April 1992–1994). http://www.cl.cam.ac.uk/research/dtg/attarchive/facedatabase.html. Accessed 16 Aug 2018
- 4.Y. Database, UCSD computer vision. http://vision.ucsd.edu/content/yale-face-database. Accessed 16 Aug 2018
- 6.R.C. Gonzalez, R.E. Woods, Digital Image Processing (Prentice Hall, Upper Saddle River, 2002)Google Scholar
- 11.A. Ramaswamy, W.B. Mikhael, Multitransform/multidimensional signal representation, in 1993 IEEE 36th Midwest Symposium on Circuits and Systems (MWSCAS), pp. 1255–1258 (1993)Google Scholar
- 12.S. Rao, M.V.B. Rao, A novel triangular DCT feature extraction for enhanced face recognition, in 2016 IEEE 10th International Conference on Intelligent Systems and Control (ISCO), pp. 1–6 (2016)Google Scholar
- 15.M. Wang, H. Jiang, Y. Li, Face recognition based on DWT/DCT and SVM, in 2010 International Conference on Computer Application and System Modeling (ICCASM), pp. V3-507–V3-510 (2010). https://doi.org/10.1109/ICCASM.2010.5620666
- 17.F. Zhi-Peng, Z. Yan-Ning, H. Hai-Yan, Survey of deep learning in face recognition, in 2014 International Conference on Orange Technologies (ICOT), pp. 5–8 (2014). https://doi.org/10.1109/ICOT.2014.6954663