Abstract

Due to the presence of speckle noise and similarities, it is difficult to recognize the boundaries of abnormal regions\nin ultrasound images. An automatic segmentation is motivated because manual method is not effective for segmentation of\nlarge data sets. An automatic region growing and region merging algorithm for the segmentation of ultrasound images is\npresented in this paper. In this paper, seed is automatically selected and then far away values of similar regions were also\nmerged to neighbouring regions. The proposed method outperforms the existing state-of-the-art techniques based on the\ntexture features and visual results.