Scene Text Detection With Recurrent Instance Segmentation
2018 24TH INTERNATIONAL CONFERENCE ON PATTERN RECOGNITION (ICPR)(2018)
摘要
Convolutional Neural Network (CNN) based scene text detection methods mostly employ the semantic segmentation (text/non-text classification) task to localize the regions of texts. However, they cannot distinguish different text-lines like instance segmentation. In this paper, we propose a novel framework based on Fully Convolutional Networks (FCN) and Recurrent Neural Network (RNN) to achieve both scene text detection and instance segmentation. The FCN is used to classify text and non-text regions, and the RNN utilizes the features extracted by FCN to simultaneously detect and segment one text instance at each time step. Meanwhile, it also extracts bounding boxes by a much simpler way than the non-maximum suppression (NMS) method. The proposed method achieves competitive results on two public benchmarks including ICDAR 2015 Incidental Scene Text Dataset and ICDAR 2013 Focused Scene Text Dataset. Moreover, the benefits of adding regression task in the RNN module are manifested.
更多查看译文
关键词
recurrent instance segmentation,Convolutional Neural Network based scene text detection methods,semantic segmentation task,text/nontext classification,Fully Convolutional Networks,FCN,Recurrent Neural Network,nontext regions,text instance,nonmaximum suppression method,ICDAR 2015 Incidental Scene Text Dataset,ICDAR 2013 Focused Scene Text Dataset,text-lines
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络