A fast recursive algorithm for two-dimensional thresholding

Two-Dimensional (2D) thresholding behaves well in segmenting images of low siginal-to-noise ratio. But the computation complexity of the conventional 2D entropic algorithm is bounded by O(L(4)). In this paper, firstly: a fast recursive 2D entropic thresholding algorithm is proposed. By rewriting the formula for calculation of entropy in recurrence form, a great much of calculation is saved. Analysis shows that the computation complexity of 2D entropic thresholding is reduced to O(L(2)). The fast recursive algorithm is also used successfully in 2D Otsu method. Experimental results show that the processing time of each image is reduced from more than 2h to less than 10sec. The required memory space is also greatly reduced.