View Printable Version

Amr R. Abdel-Dayem and Mahmoud R. El-Sakka, "Multi-Resolution Segmentation Using Fuzzy Region Growing for Carotid Artery Ultrasound Images", International Computer Engineering Conference,Vol. IP, pp. 40-47, December 2006, Cairo, Egypt.

Abstract

This paper introduces a segmentation method based on multi-resolution analysis and fuzzy region growing technique. The proposed scheme consists of five major stages. These stages are pre-processing, wavelet transform, fuzzy segmentation, segmented image projection and finally boundary extraction stage. Experimental results demonstrate the efficiency of the proposed scheme in segmenting carotid artery ultrasound images. It reduces the computational cost of a fuzzy region growing based segmentation scheme, as the fuzzy region growing algorithm is applied to a small low resolution image. Meanwhile, the segmentation accuracy is increased as the proposed scheme is more robust to noise and hence, it prevents over segmentation in the final segmented images.