A Review on Text Detection Techniques

Abstract

Text detection in image is an important field. Reading text is challenging because of the variations in images. Text detection is useful for many navigational purposes e.g. text on google API’s and traffic panels etc. This paper analyzes the work done on text detection by many researchers and critically evaluates the techniques designed for text detection and states the limitation of each approach. We have integrated the work of many researchers for getting a brief over view of multiple available techniques and their strengths and limitations are also discussed to give readers a clear picture. The major dataset discussed in all these papers are ICDAR 2003, 2005, 2011, 2013 and SVT(street view text).