【作者】 闫成新； 范波涛；

【Author】 Yan Chengxin~1 Fan Botao~2 (1.Department of Mechanical Engineering, China University of Petroleum)(2.Shandong University)

【机构】 中国石油大学(华东)机电工程学院； 山东大学机械学院；

【摘要】 传统的过渡区提取方法依赖于灰度剪切的上、下限值,实际图像往往由于得不到正确的灰度剪切上、下限值而导致过渡区无法提取,从而影响最终的图像分割。本文提出一种基于梯度门限的过渡区提取方法,可以稳定地提取图像的过渡区。对比实验证明了方法的稳定性和有效性。更多还原

【Abstract】 Traditional transition region extraction methods depend much on the clip limits L_lowand L_high.It can’t often obtain appropriate L_lowand L_highvalues from real images,which will esult in incorrect extraction of transition region and finally bad quality of segmentation.We proposed a novel gradient threshold-based transition region extraction method （GT-TREM）. One can steadily extract transition region by GT-TREM. Experimental results demonstrated the robustness and effectiveness of our method..更多还原