Text detection in nature scene images using two-stage nontext filtering

We present a text detection method in natural scene images based on two-stage nontext filtering. Firstly, we detect multi-channel maximally stable extremal regions (MSERs) as character candidates. To reduce the amount of repeating components, we merge the MSERs by choosing the most character-like ones when overlap happens. Then nontext components are filtered out by a two-stage labeling procedure, wherein we combine random forests with CRF. Finally, components labeled as text are grouped into words by an edge-cut strategy, and false positives are eliminated by a HOG-based classifier. The experimental results on the ICDAR2013 database show the effectiveness of the proposed method.