Image Segmentation Using Unsupervised Techniques

Unsupervised Techniques of segmentation are simple and the segmented output using these techniques gives the best results. This paper presents an automatic segmentation method based on unsupervised segmentation done on Ultrasound (US) images received from the radiologist. US imaging is widely used in clinical diagnosis and image-guided interventions, but suffers from poor quality. One of the most important problems in image processing and analysis is segmentation. US image is difficult to segment due to low contrast and strong speckle noise. Here we present three unsupervised techniques, namely thresholding, K-means clustering and expectation maximization and compare their results. The uniqueness of this paper is that EM technique is used for texture featured image which gives far better results of segmentation. KEYWORDS— medical ultrasound images, segmentation, thresholding, k-means clustering, expectation maximization.