Abstract
In computer vision, image segmentation is the process of partitioning an image into several segments. The goal of image segmentation is to transform the input image into a more meaningful form which is easier to analyze. Nowadays, there are many segmentation approaches, and they can be applied in many fields, such as medical imaging, object detection, face recognition, etc. Generally, image segmentation can be distinguished as supervised and unsupervised two categories. The result of supervised image segmentation is greatly affected by the user. Therefore, we propose an unsupervised method of image segmentation, which can’t be affected by users. We use saliency detection to label some informative and insignificant parts of the image, and then, we apply edge detection to label some details of the image. In this way, we can automatically label the seeds to get the scribble; then segment foreground/background. The results show that our method is good.