Recent advances in the corporate processing of images have exhibited its advantages over the individual processing. Image co-segmentation aims to segment shared objects from two or more relevant images, and is becoming more and more interesting for computer vision researchers. Many applications need accurate and efficient segmentation techniques: indoor navigation, autonomous driving, and virtual reality systems to name a few. Although numerous techniques have been proposed, it is still lacking a deep review of image co-segmentation techniques. In this paper, we provide a review on the fundamentals and challenges of image co-segmentation techniques. We organize the recent advances of image co-segmentation into seven major frameworks: graph based framework, clustering based framework, partial differential equation based framework, quadratic programming based framework, low rank matrix recovery based framework, joint optimization based framework, and machine learning based framework. We expect this review to be beneficial to both fresh and senior researchers in this field. INDEX TERMS Image co-segmentation, deep learning, multiple foreground, single foreground.