Text detection, recognition, and script identification in natural scene images: a Review

Text in natural scene images plays a vital role in scene understanding. It contains a rich and abundant amount of valuable semantic information useful in many applications such as analysis of products' labels, autonomous driving, and blind navigation. Consequently, detection, recognition, and identification of scripts of texts present in scene images have recently received massive attention. This paper intends to walk through the advances on the mentioned topics, mainly focusing on the approaches proposed in the last 8-10 years. As per our knowledge, this paper is the first to provide a review on the scene text script identification. We also provide a clear and precise classification between conventional-, deep learning-, and hybrid-based methods, including their advantages and disadvantages. State-of-the-art evaluation metrics, benchmark datasets' characteristics, and performances of the existing methods are also analyzed and discussed. Lastly, we present an insight into potential research directions to complete the review. We hope this review will provide a brief insight for the researchers into scene text understanding.