A modification of Otsu's method for detecting eye positions

Otsu's method has a disadvantage of time-consuming for image segmentation. In this paper, a simple but fast multilevel thresholding approach is proposed by means of extending the Otsu's method. We advocate that the gray-level range of an image is first divided into smaller sub-ranges, and that the multilevel thresholds are achieved by iteratively invoking this dividing process. Initially, the gray range of the object image is divided into 2 classes with a threshold value. Following this, the two classes are divided into 4 classes again by applying the Otsu's method to each of the divided sub-ranges. Our experimental results show a possibility that the proposed method could be used for detecting eye positions.