Abstract: “The main focus of this paper is denoising of underwater acoustic signal to improve the performance of underwater acoustic instruments. The major sources of underwater ambient noises are distant shipping, wind, rain and biological activities. In this paper we have considered wind driven noise, which occupies wide bandwidth,as ambient noise source. A lot of research work has been done on denoising and most of the researchers have used wavelet as the denoising tool. In this paper we have proposed a novel denoising algorithm based on EEMD (Ensemble Empirical Mode Decomposition) , which is mainly suitable for non-linear and non-stationary signals. The results presented here will give an insight on the performance of this adaptive algorithm.”

Keywords: Feature Extraction, Arabic Character Recognition, Feature Fusion.