Application of Genetic Algorithm in Denoising MRI Images Clouded with Rician Noise

Introduction

Genetic Algorithm (GA) is a metaheuristic search process that gains its demeanor from metaphor of process of evolution in nature. Main advantages is that it provides solution to the trouble that can be cast in status that human operator can realize so that their experience can applied in design of the controller. It improves the chance of reaching the global optimum and nearly unbiased optimization techniques for sampling a large solution space. Even though randomized Gas is by no means random, instead they manipulate historical information to direct the search into region of better performance within search space. Genetic Algorithm adjusted in image processing because of this unbiased stochastic sampling. Medical images are usually of low contrast and they frequently have a composite type of disturbance because of several acquisitions, transmission storage and display devices and also because of application of different types of quantization, reconstruction and enhancement algorithms (Sivakumar, 2007). All imaging method is having certain kind of noise, but disturbance is much more dominant in certain types of imaging procedures than in others. Signal-to-noise ratio (SNR) and resolution is plays an important role in Magnetic resonance imaging (MRI). In order to get high signal to noise ratio and to get noise free image various optimization technique can be used. For effective denoising and smoothing an image genetic algorithm is best choice. It is not only used for image quality enhancement but also add positive qualities into it. Using this novel method, it is made possible to have an image filter that can use a totally dissimilar design style that is performed by an evolutionary algorithm.Medical images comprise visual noise. The presence of noise gives an image a clouded, gritty, textured or white appearing. Image noise appears from a number of sources it may be film grain or shot noise from photon detector. Noises are random and obey Gaussian distribution.

In certain cases Analysis of images can be really vital. A little misinterpretation of the image may guide to calamitous conclusions. To examine each and every item in depth, it must be made sure enough that image quality is good and it contains neither extra information nor any information is missing from it. One of the main concerns of image characterization is the quality of image. In order to get complete information of an image it is required that its features should be easily recognizable and perceivable. Image denoising is a main segment for all image processing researches.

Image denoising related to the procedure of removing noise from the image through image enhancement techniques (Ashraf Aboshosha et al. 2009). A lot of attention should be taken while using a smoothing filter to an image because using a wrong filter results to some loss of information. A filter must remove maximum noise from the image without losing its important features. It is usually found that an image signal is clouded either due to unfavorable image capturing conditions or during transmission. The main challenge of image denoising is how to keep the edges and all fine item of an image when reducing the noise (Gonzalez et al. 2001). Minimizing randomness from the image is one of the most worked upon problems in the area of image processing. A lot of work has been done in past in the area of image smoothing. Error reduction can be obtained by blearing with additive filters and nonlinear filters (circular, pyramidal and cone) (Niranjan Damera- Venkata et al. 2000). (Min-Cheng Pan et al. 1998) suggested a spatial domain probability filter which obtains the benefits of median and mean filters. The intention of probability filter is to allow a middle way between the two more conventional filters (Min-Cheng Pan et al. 1998). It anticipates the best potential image when original image is not available. (Michifumi Yoshioka et al. 1997) gave a perspective based on genetic algorithm for minimizing noise from original image. An alternative idea of Modified Spatial Median Filter was introduced by (James C. Church et al. 2008). (Krishnan Nallaperumal et al. 2006) proposed a new Median filter for remotion of impulsive noise from a digital image. An algorithm to minimize Gaussian noise from an image was given by (V. R. Vijaykumar et al. 2009).