International Conference on Advances In Engineering And Technology - ICAET 2014
Author(s) : PRABHPREET KAUR, RAVREET KAUR
A robust wavelet domain method for noise filtering in medical images is one of the techniques used to reduce the noise. The method adapts various types of image noise as well as to the preference of the medical expert: a single parameter is being used to balance the preservation of (expert-dependent) relevant details against the degree of noise reduction. A versatile wavelet domain despeckling technique to visually enhance the medical ultrasound (US) images for improving the clinical diagnosis is used. The method uses the two-sided generalized Nakagami distribution (GND) for modeling the speckle wavelet coefficients and the signal wavelet coefficients are approximated using the generalized Gaussian distribution (GGD) . Combining these statistical priors with the Bayesian maximum a posteriori (MAP) criterion, the thresholding/shrinkage estimators are derived for processing the wavelet coefficients of detail subbands. Consequently, two blind speckle suppressors named as GNDThresh and GNDShrink have been implemented and evaluated on both the artificial speckle simulated images and real US images. This paper introduces an analysis of a new approach of image enhancement technique based on Genetic Algorithms. The task of the Genetic Algorithm is to analyze the result of a novel image denoising method using various parameters and enhance the quality and details of the image according to an objective fitness criterion i.e SNR and quantitative analysis by subjective criteria. The visual comparison of despeckled US images and the higher values of quality metrics (coefficient of correlation, edge preservation index) indicate that the method suppresses the speckle noise well while preserving the texture and organ surfaces. The method clearly outperforms single-resolution spatially adaptive algorithms, in terms of quantitative performance measures as well as in terms of visual quality of the images.