Multilingual text recognition is an important research topic in artificial intelligence and computer vision. It provides a powerful tool for extracting text information from images in various applications, such as content-based video and image retrieval. This chapter addresses the challenging task of multilingual text recognition for images captured in an open environment. After a brief review of traditional methods and deep learning-based methods for multilingual text recognition, the content of this book is introduced including the proposed primitive representation learning method, among others.