Novelty detection affords to identify data patterns that stray strikingly from the normal behavior. it allows a good identification and classification of objects which were not known during the learning phase of the model. In this article, we will introduce an organized and comprehensive review of the study on novelty detection. We have grouped existing methods into three classes. Statistical Based techniques, Machine Learning Based techniques and Deep Learning Based techniques. In addition, we provide a discussion on application domains of novelty detection, and for each category, we have defined the novelty, cited the most used dataset, as well as a description and perspectives of the latest work carried out in this domain. Our article is developed with the aim of facilitating to researchers a better understanding of the interest of using novelty detection in the various fields mentioned in the article, as well as to clarify the different existing novelty detection methods.
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.