摘要
提出一种基于自动种子区域生长的超声图像缺陷分割方法。首先使用最大类间方差(Otsu)分割法对超声B图像进行一次预分割;其次寻到绝对背景区,并且在此区域内自动设置种子起始点;然后利用区域生长法将缺陷从背景中分割;最后通过数字形态学降噪法来进一步提高缺陷的识别度。实验结果表明:该方法不仅能准确地分割出缺陷,且具有较好的缺陷边界信息,提高了对超声B图像的处理效率,有效地抑制了大部分图像噪声。
An ultrasound image defect segmentation algorithm based on automatic seeded region growing was proposed. First, the pre-segmentation of the ultrasound B image was performed by the Otsu method. Next, the seed starting points were set automatically by seeking the absolute background area. Then, the defects were segmented from the background area by regional growth algorithms. Finally, the defect recognition was further improved by digital morphological noise reduction method. Experimental resuhs shown that the defects were segmented effectively by the proposed algorithm and good defect boundary information has also been provided. The efficiency of processing ultrasonic B images is improved and noise of B-scan image is mostly suppressed effectively.
作者
倪豪
郑慧峰
王月兵
呼刘晨
曹永刚
张凯
NI Hao;ZHENG Hui-feng;WANG Yue-bing;HU Liu-chen;CAO Yong-gang;ZHANG Kai(Institute of Precision Measurement and Control,China Jiliang University,Hangzhou,Zhejiang 310018,China)
出处
《计量学报》
CSCD
北大核心
2018年第6期878-883,共6页
Acta Metrologica Sinica
基金
国家重点研发计划(2017YFF0205004)
国家自然科学基金(11474259)
浙江省自然科学基金(LY15E050012)
关键词
计量学
超声B图像分割
区域生长
自动设置种子
metrology
ultrasound B image segmentation
region growing
seed setting automatically