二维Otsu拟合线阈值图像分割方法

针对已有二维Otsu线阈值法分割方法存在的因误分类而导致的分割质量下降、抗噪性能不足的问题.结合二维Ot-su折线阈值算法和曲线拟合方法,提出了二维Otsu拟合线阈值图像分割方法.本文方法是在二维Otsu折线阈值法基础上进行改进.先对二维直方图中边界信息或噪声所属区域的像素点迭代分割,并设定迭代停止条件,以获得多个阈值点,然后引入曲线拟合的方法,将多个阈值点拟合成线阈值,最后以此线阈值作为分割标准实现分割.实验结果表明:利用本文方法对边缘丰富的图像分割具有较好的分割效果,抗噪能力和自适应能力更强,普适性更高.

Two-dimensional Otsu Fitting Line Threshold Image Segmentation Method

Aiming at the problems of the existing two-dimensional Otsu line threshold method segmentation method, the segmentation quality is reduced due to misclassification and the anti-noise performance is insufficient. Combining the two-dimensional Otsu polyline threshold algorithm and the curve fitting method, a two-dimensional Otsu fitted line threshold image segmentation method is proposed. This method is based on the improvement of the two-dimensional Otsu polyline threshold method. Firstly, iteratively divide the pixels of the boundary information or the area to which the noise belongs in the two-dimensional histogram, and set the iteration stop condition to obtain multiple threshold points, then introduce the curve fitting method to fit the multiple threshold points into a line Threshold, and finally use this line threshold as the segmentation criterion to achieve segmentation. The experimental results show that this method has a good segmentation effect for image segmentation with rich edges, stronger anti-noise ability and adaptive ability, and higher universality.