Amr R. Abdel-Dayem and Mahmoud R. El-Sakka, "Multi-Resolution-Based Segmentation Using Watersheds for Carotid Artery Ultrasound Images", International Conference on Graphics, Vision and Image Processing, GVIP'2005, (6 pages), December 2005, Cairo, Egypt.

Abstract

This paper introduces a novel segmentation scheme based on multi-resolution analysis and watershed segmentation algorithm. The proposed scheme consists of six major stages. These stages are 1) pre-processing, 2) wavelet transform, 3) image denoising, 4) watershed segmentation, 5) segmented image projection, and finally 6) boundary extraction. Experimental results demonstrated the efficiency of the proposed scheme in segmenting carotid artery ultrasound images, where the computational cost of the watershed-based segmentation scheme is reduced, as it is applied to a small low resolution image. At the same time, the segmentation accuracy is increased as the proposed scheme is more robust to noise and hence, it prevents over segmentation in final segmented images.