采用改进OTSU法的液位红外图像分割

Improved OTSU method on liquid-level infrared image segmentation

利用图像处理技术对液位进行实时检测过程中,大量的分析研究对象是红外图像信息。本论文针对一实际红外成像液位检测系统,在深入分析了多种比较成熟的目标分割算法的基础上,结合红外图像信息的特点,提出了一种新的基于局部阈值的图像分割算法。该算法采用局部最大类间方差法来确定各个子图像块的阈值,通过三次曲线拟合插值函数对这些阈值进行插值处理,使之成为与原图像大小相同的新矩阵,利用新的阈值矩阵对液位图像进行二值化处理。实验结果表明,利用该方法对液位图像分割具有很好的分割效果。

In the process of using image processing technologies for real-time detection of liquid-level,a large number of analysis objects are infrared image information.In this paper,a practical infrared imaging for the liquid-level detection system,combination of the characteristics of infrared image information,proposed a new image segmentation algorithm based on local threshold and In depth analysis of a variety of more mature object segmentation algorithm.The algorithm uses local OTSU to establish the threshold of sub-image block,interpolated these thresholds through cubic curve-fitting interpolating,making the new matrices has the same size as the original image and binarization processing the liquid-level image with the new threshold matrix.Experimental results show that using this method has a good segmentation effect for liquid-level image segmentation.