An adaptive threshold for the Canny Operator of edge detection

The thresholds play an important role in the Canny Operator which used in the image edge detection. Many self-adaptive threshold algorithms have been proposed to improve the performance of Canny Operator. The Otsu method is one of the most popular improvements. However the Otsu method can not automatically set the low threshold according to the different image intensity adaptively. In order to overcome this defect, an adaptive threshold algorithm for the Canny Operator was proposed which calculated the low threshold adaptively based on a probability model. Experiments show that this method produces better edge detection results both on objective and subjective evaluations than the Otsu method.