Authentication systems robustness can be affected by the fingerprint image quality. Fingerprint image denoising is essential for better performance of any authentication system. In this paper, most recent wavelet transform based techniques for fingerprint image denoising are reviewed. It is observed that there are four important components of wavelet transform based denoising techniques. These important components include wavelet filter, thresholding rule, threshold value computation method and the level of decomposition. The stationary wavelet transform and the weighted median are recommended over conventional discrete wavelet transform and median estimator.
Reference:
Mgaga, S.S., Khanyile, N.P. & Tapamo, J. 2019. A review of wavelet transform based techniques for denoising latent fingerprint images. In: Open Innovations Conference (OI), Cape Peninsula University of Technology, South Africa, 2-4 October 2019
Mgaga, S. S., Khanyile, N. P., & Tapamo, J. (2019). A review of wavelet transform based techniques for denoising latent fingerprint images. http://hdl.handle.net/10204/11686
Mgaga, Sboniso S, Nontokozo P Khanyile, and J Tapamo "A review of wavelet transform based techniques for denoising latent fingerprint images." (2019) http://hdl.handle.net/10204/11686
Mgaga SS, Khanyile NP, Tapamo J. A review of wavelet transform based techniques for denoising latent fingerprint images. 2019; http://hdl.handle.net/10204/11686.
Copyright: 2019 IEEE. Due to copyright restrictions, the attached PDF file only contains the abstract of the full text item. For access to the full text item, please consult the publisher's website. The definitive version of the work is published in Open Innovations Conference (OI), Cape Peninsula University of Technology, South Africa, 2-4 October 2019
ResearchSpace
