Introduction

In real-world applications, new data, patterns, and categories that were not covered by the training data can frequently emerge, necessitating the capability to detect and adapt to novel characters incrementally. Researchers refer to these challenges as the Open-Set Text Recognition (OSTR) task, which has, in recent years, emerged as one of the prominent issues in the field of text recognition. In this chapter, we first introduce the evolution and several main trends of preliminary works on novel (unseen) character identification and recognition. Then, we briefly discuss three main challenges in OSTR. Finally, we introduce the overall structure and main content of our book.