基于Otsu理论的灰度图像分割算法研究和改进

The Study of Gray-level Image Segmentation Algorithm Based on Otsu Method and Its Improvement

Otsu算法是利用最大类间方差准则对图像像素进行阈值分割。二维Otsu算法是在一维Otsu算法的基础上提出的,但是其计算量大,且只有当图像每个类的像素数目接近彼此时才能得到满意的结果。对二维直方图重新划分,改变阈值的求解范围,提高分割准确率和减少阈值计算时间。实验结果表明该方法提高分割效率,对含噪声的图像分割效果较好。

Otsu method reference proposed a criterion for maximizing the between-class variance of pixel intensity to perform picture thresholding.Two-dimensional Otsu method is based on One-dimensional Otsu method,but it＇s complexity computation and satisfactory results only when the numbers of pixels in each class are close to each other are got.A method is given that two-dimensional histogram of the redivision of the solution to change the threshold range and increase accuracy and reduce the segmentation threshold value of time.Experimental results show that the method improves the efficiency of segmentation,and for images with noise the proposed method can get better segmentation effect for images with noise.