ABSTRACT
With the rapid growth in computer communication, storage, and networking technology, discovering and extracting interesting features and patterns for video classification and mining is on the rise. Text in video sequences provides complementary but imperative information for video retrieval and indexing. This chapter aims at the discussion of the extraction of text information from video and multi-modal mining from the same. This chapter classifies and briefs the methods used to extract text from videos, discusses their performance, mentions their merits and drawbacks, enlists available databases, their vulnerabilities, and challenges, and provides recommendations for future development.
