Medical image binarization using square wave representation

Abstract

This paper describes a new approach for medical image binarization based on square wave representation. A square wave is a type of wave form, where the input signal has two levels +1 (foreground) and -1 (background). The signal switches between these levels based on the threshold value computed at that level with the specified time interval. In this method, a local threshold value is calculated at every interval using the current intensity value. Then, the image pixel is assigned with a value +1 or -1 using this local threshold value. The experimental results show that the proposed method reduces the complexity and increases the seperability factor in medical image segmentation. The result obtained by our method is comparable to or better than Otsu's thresholding method. © 2011 Springer-Verlag Berlin Heidelberg.