Detecting Text in News Images with Similarity Embedded Proposals
Miaotong Jiang, Jie-Bo Hou, Chun Hung Yang, Xiaobin Zhu, Xu-Cheng Yin · 2019
Text extraction plays an important role in news images analysis tasks. However, the conglutination of subtitles and station logos makes text detection challenging. In this paper, we develop an effective news text detection framework by introducing a novel similarity embedded proposal mechanism. The main idea is to predict similarity for each fine-scale coarse proposal to help construct text bounding boxes. Specifically, a CNN and bi-directional LSTM based network is used to produce vectors embedded in coarse proposals provided by Connectionist Text Proposal Network (CTPN). Notably, similarity embedded proposal mechanism can be generalized to other sub-text level text detection models. Comparing to the state-of-the-art method (CTPN), our framework improves F-measure by 25.2% on our Private News Dataset and 8.9% on ICDAR 2013 benchmarks, respectively.