about
Rfbtd: RFB Text Detector (arxiv.org)
1 point by sel1 on Jul 7, 2019 | hide | past | pdf | discuss on HN

In plain words: A camera-image text detector that draws boxes around single words or lines at any angle, using wider look regions so each word is caught clearly. On the ICDAR2015 test it reached an F-score of 47.09, where usual detectors blur words together in dense scenes.

Abstract · RFBTD: RFB Text Detector

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

Christen M, AB Saravanan
arXiv:1907.02228 · cs.CV · submitted Jul 4, 2019
abstract · pdf

add comment on HN