The world is constantly changing, and vision helps the humans to understand the environmental changes over time. The changes can be seen by, capturing the images. Hence digital image plays a vital role in day to day life. During the process of acquisition of digital image, the qualities of digital pictures are degraded due to additive noise known as adaptive white Gaussian noise. Therefore, the major challenge of image denoising algorithm is to improve the visual appearance while preserving the other details of the image. For the last two decades, wavelet has become an elegant tool in image denoising techniques. Among all wavelet based denoising methods, wavelet thresholding became popular because, wavelet appropriately separates the noisy signal from the image. The wavelet separation leaves the coarse grain noise in approximation sub-band and fine grain noise in detail sub-bands. Therefore, in wavelet based thresholding methods noise in detail sub-bands are threshold and approximate sub-band noise are kept as such. Hence, the efficiency of all wavelet based shrinkage techniques depends on, the choice of threshold parameter, thresholding technique and how the noise in the approximation sub-bands are handled. This paper presents a brief comparative study of denoising techniques proposed in the research articles based on the above parameters for Gaussian noise reduction using various wavelets transform. With the help of these experiments, we are able to identify the strengths and weaknesses of these methods, as well as seek the way ahead towards a definitive solution to the long-standing problem of image denoising.
A Comparative Study of Wavelet and Curvelet Transform for Image Denoising
