A Survey Paper on Scene Text Detection Methods

Manjushree Kaware, Priti Saktel

Abstract: In recent years, with increasing popularity of portable devices for capturing images, visual processing, text extraction, etc. become key problems which gain the attention of many researchers. Extraction of text information from images or scene involves detection, localization, tracking, segmentation, enhancement and character recognition. But because of variations involved in text such as font style, size, orientation, alignment, reflections and illumination effect, as well as low image contrast and complex background details make text extraction process more challenging. A large number of methods have been proposed to address this problem but still none of them are perfect. This paper presents a short survey on various scene text detection methods suggested and implemented recently. General challenges for performing scene text detection are also discussed.

Keywords: text extraction, text detection, localization, segmentation, character recognition