Modelling curvelet based signal processing problems via wavelet analysis

Abstract

Until recently, the wavelet transform has been used for Mathematical analysis and signal processing problems. But it suffers from the disadvantage of poor directionality, which has undermined its usage in many applications. The curvelet transform is a new extension of the wavelet transform, which aims to deal with intersecting phenomena occurring along curved edges in 2-D signals/images. In this work, a strong relationship between the curvelet and wavelet transforms has been established. This version of a wavelet based curvelet has been exploited to develop a full-fledged analytical framework, presenting it as an extension of well established wavelets. Due to computational complexity, instead of applying a curvelet directly, the curvelet in terms of wavelets has been employed more conveniently in the proposed signal denoising model. Finally, the performance factor analysis is performed on multispectral sample radar image data to demonstrate the efficiency of the proposed model. Besides computational gain, the proposed model shows better performance than the other signal processing models. Proposed model is equally applicable to both pulse signals and digital images.