RFBTD: RFB Text Detector
This work addresses text detection in dense scenes for applications like information extraction, but it appears incremental as it builds on existing receptive field block techniques.
The paper tackled the problem of detecting individual words in dense scene text by proposing a method that predicts words or text lines of arbitrary orientations, achieving an F-score of 47.09 on ICDAR2015 at 720p.
Text detection plays a critical role in the whole procedure of textual information extraction and understanding. On a high note, recent years have seen a surge in the high recall text detectors in scene text images, however text boxes for individual words is still a challenging when dense text is present in the scene. In this work, we propose an elegant solution that promotes prediction of words or text lines of arbitrary orientations and directions, providing emphasis on individual words. We also investigate the effects of Receptive Field Blocks(RFB) and its impact in receptive fields for text segments. Experiments were done on the ICDAR2015 and achieves an F-score of 47.09 at 720p