Fetching of texture from image using enhanced morphological component analysis
Loading...
Date
2017-08
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
G.B. Pant University of Agriculture and Technology, Pantnagar - 263145 (Uttarakhand)
Abstract
The Morphological Component Analysis (MCA) is a method which allows us to separate features contained in an image when these features present different morphological aspects. MCA can be used for image inpainting and image separation task. MCA can be very useful for decomposing images into texture and piecewise smooth (cartoon) parts.
MCA followed by TV regularization scheme described by J-L Starck, M.Elad, D. L. Donoho is a very efficient method for separating image into its piecewise smooth content and its texture. Due to the use of curvelet dictionary in MCA piecewise smooth content part suffers from ringing artifact . TV regularization scheme was used to remove ringing artifact from the piecewise smooth part.
In this work we aim at improving the MCA algorithm so that it can separate the piece wise smooth part and texture part more efficiently. The TV regularization scheme is approximated with Daubechies wavelet. Daubechies wavelet transform is applied over the cartoon part of the image then soft thresholding of the coefficient is done and then again the image is reconstructed by taking inverse Daubechies wavelet transform. Simulation result has shown that proposed method is giving better performance than the previous method in terms of various qualities metric such as Peak Signal to Noise Ratio (PSNR), Structural Similarity (SSIM).
Description
Keywords
null