firstly,the license plate image is converted to a binary image with Otsu method;secondly,the regions in the binary image are identified with quick region identification algorithm;lastly,all the character regions are extracted by dealing with every region in the binary image.

A three-dimensional segmentation algorithm based on the one-dimensional Otsu method is proposed in this paper.

It is applied to the multi-object automatic segmentation of B-scan ultrasonic images and gets a better result than one-dimentional Otsu method.

Heart Segmentation Based on Mathematical Morphology And Otsu in Visible Human Project Images;

In terms of the problem that resulted in threshold value cannot be well convergent to overall optimum when traditional OTSU algorithm cannot deal with images with incontinuous gray scale,this paper modifies OTSU algorithm and applies the improved OTSU algorithm in such images with incontinuous gray scale as heart.

From the test s result, it can be seen that the Otsu algorithm can solve the threshold s setting in Canny algorithm and it can improve the the effect of cell image s segmentation and the adaptive ability of Canny algorithm.

Otsu algorithm was combined with mutual information(MI) technique.