Abstract
Noise is an unavoidable factor in any signal processing system. It is generally of two types-channel noise and source noise. Performance of algorithms developed to process signals degenerates rapidly with increase in the noise level of the signal. It is, therefore, critical that techniques be developed to "denoise" the signal before it is processed. The objective of this research is to explore the possibility of signal denoising using the recently developed mathematical theory of "oversampled frames". This research will focus primarily on eliminating the source noise in the signal. We intend to develop algorithms that are efficient and can be implemented in real-time. The performance of our algorithms will be compared to the current denoising methods based on thresholding of wavelet coefficients.
Barreto, Joel J (1996). Denoising using oversampled wavelet frames. Master's thesis, Texas A&M University. Available electronically from
https : / /hdl .handle .net /1969 .1 /ETD -TAMU -1996 -THESIS -B377.