基于局部熵和分形理论的镁熔液第一气泡图像检测

Image Detection of First Bubble in Magnesium Melt Based on Local Entropy and Fractal Theory

针对复杂背景下镁熔液第一气泡的图像检测,提出一种基于局部熵和分形理论的弱小目标检测算法。首先利用图像的局部熵粗定位弱小目标;然后利用分形理论构造区域的分形维数并对弱小目标进行细定位;最后进行自适应阈值分割处理,检测出弱小气泡。实验结果表明,利用局部熵和分形理论相结合的算法能精确地识别第一气泡,为图像处理技术应用于镁熔液测氢仪器提供了一种新方法。

A detection algorithm was presented for weak and dim target on magnesium melt based on local entropy and fractal theory, which aimed at the image identification of first bubble under complex background. The algorithm firstly uses the local entropy to locate the target coarsely. Secondly, a fractal dimension is constructed based on fractal theory and locating the target carefully. At last, the weak and dim bubble was detected by using self-adaptive threshold. The results show that the algorithm which combines local entropy with fractal theory is effective for the first bubble identification, which can also provide a new method for the detection instrument of hydrogen content in magnesium melt based on image processing technology.