The segmentation algorithm of improvement a two-dimensional Otsu and application research

Thresholding is an efficient technique for image segmentation. Otsu is frequently used in digital image processing. Two-dimensional Otsu threshold algorithm has been proposed based on Otsu algorithm. This paper gives an improved two-dimensional Otsu segmentation method which changes the coordinate system of the two-dimensional histogram to strengthen resistance to noise and improve the computing speed. Experimental results show that the method is superior to the traditional one-dimensional and two-dimensional Otsu segmentation, and can be used to Tube-type bottle line machine vision inspection.