Scene text detection using sequential nontext filtering

We present a scene text detection method based on sequential nontext filtering. Firstly, we start our work with multi-channel maximally stable extremal region (MSER) detection. Then nontext components are eliminated by a four-stage sequential nontext filtering strategy which consists of inner-channel MSER pruning, between-channel MSER pruning, unary feature-based nontext filtering, and binary feature-based nontext filtering. Finally, text components are grouped into words and false positives are eliminated. The proposed method achieves the state-of-the-art on the ICDAR2013 database when compared with some existing methods.