Two stages adaptive normalized cuts and image segmentation

Image segmentation is a fundamental problem in image processing and computer vision. Its goal is to separate an image into a collection of distinct regions, after which other high-level tasks can be performed. Nomalized cut (Ncut) algorithm is the most popular one in image segmentation algorithms. However, the number of segmentation regions needs to be specified by users or experts before the Ncut algorithm is applied to segment the image. It is a shortcoming and also one of the most important factors of bad performance in images recognition and annotation. In this paper, we propose a novel method to adjust the number of regions with two-stage category. In first stage, an initial number is determined by the rank of image richness. In this stage, the gray-level frequency information of image, Marr wavelet transform and extremal detection are employed to get the rank. In second stage, the number of segmentation regions will be re-adjusted with the regional feature consistency measure criterion. Compared with the traditional Ncut algorithm, our method is completely automated, which greatly improves the versatility of the algorithm. The experiments are conducted on the dataset with 1000 images released by Achanta. Experimental results show that the proposed algorithm achieves marked improvements in performance and outperforms traditional Ncut algorithm.