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

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.