Performance analysis of image segmentation methods for noisy MRI images

An accurate Image segmentation is very important in image processing. The main purpose of the image segmentation is to partition the original image into uniform regions. Image segmentation can be applied as the pre-processing stage for the other image processing techniques. There are several techniques for segmentation MR image in image processing. Image segmentation for bio-medical images has become basic fundamental process to perform significant quantitative search to determine the human organs, defected tissues etc. In this paper, we proposed the image segmentation techniques namely Active Contour Method (ACM), Gray threshold Mechanism (GTM), Sobel Gradient Method (SGM) and Watershed Transform (WST). These four segmentation methods are applied to medical Magnetic Resonance Imaging (MRI) images of Knee joints, Brain, Ultrasound and Cardiac images. These segmentation techniques are applied to these above mentioned MRI images of sizes 128×128, 256×256, 512×512, and 1024×1024. Later, the performance measure parameters like Mean Square Error, Peak Signal-to-Noise Ratio, Entropy, and time are calculated and compared for all image sizes. The above-mentioned segmentation techniques are developed and performance parameters are calculated using MATLAB 2014a software.