Computer vision is the study of making machines capable of understanding the input image and video using some algorithms or techniques. As for humans, understanding a scene given in an image or video is not a difficult task. Humans are blessed to understand images and videos effortlessly without knowing the complexities behind the process of image and video understanding. Making machines also capable of understanding their input image and video is not that simple. With ongoing research for making human-computer interaction more natural and realistic, lots of advancements have been done in different components of computer vision. The paper focuses on the image segmentation process used in computer vision and image processing which is a very crucial component while processing images and video. Image segmentation is the process of extracting only relevant content or information while removing irreverent content or information. Image segmentation is the most researched topic in image processing and computer vision. It is one of the major activities that will help the later process to ease its operation by filtering unnecessary and irrelevant contents. The paper aims to describe the segmentation process and highlight different types of segmentation approaches used in recent trends comparing their performances.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.