摘要
针对在岩石变形实验的熔融图像处理中,图像的曝光不均、单个像素点灰度值异常和裂痕带来的分割噪声问题,本文提出了一种基于数学形态学中的腐蚀、膨胀方法的自适应阈值分割算法,通过和全局阈值法和局部阈值法的对比实验可以看出,这种方法不仅能够解决全局阈值分割法亮度分布不均的问题,也能解决局部阈值分割法(Bernsen算法)抗噪声性能差的问题,同时运算效率提高38.5倍(和Bernsen算法比较)。
In order to solve the imbalance exposure problem and the noise problems caused by single pixel gray value anoma- lies and crack splits of melting images of rock deformation experiments, this paper proposes an adaptive threshold segmentation algorithm based on corrosion and expansion approach of mathematical morphology. Through the contrast experiments of pro- posed method, global threshold method and local threshold value method, it can be seen that this method can not only solve the brightness distribution problem of global threshold segmentation method, also the poor anti-noise performanceproblem of local threshold segmentation method （Bernsen algorithm）, and improve the operational efficiency by 38.5 times.
出处
《电子设计工程》
2015年第13期102-104,共3页
Electronic Design Engineering
基金
国家自然科学基金面上项目(41374185)
关键词
图像处理
图像分割
二值化
数学形态学
image processing
image segmentation
binarization
mathematical morphology
