FTPN: Scene Text Detection With Feature Pyramid Based Text Proposal Network

• Published in: IEEE access Vol. 7; pp. 44219 - 44228
• Main Authors: Liu, Fagui, Chen, Cheng, Gu, Dian, Zheng, Jingzhong
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2019; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Artificial neural networks; Automatic pilots; Connectors; convolutional neural network; Feature extraction; Gabor filters; Image management; Image retrieval; Microsoft Windows; multi-orientation; Neural networks; Object recognition; Proposals; recurrent neural network; Recurrent neural networks; residual network; Scene text detection; Text recognition; Texts
• ISSN: 2169-3536; 2169-3536
• DOI: 10.1109/ACCESS.2019.2908933

Scene text detection is to detect the position of a text in the natural scene, the quality of which will directly affect the subsequent text recognition. It plays an important role in fields such as image retrieval and autopilot. How to perform multi-scale and multi-oriented text detection in the scene still remains as a problem. This paper proposes an effective scene text detection method that combines the convolutional neural network (CNN) and recurrent neural network (RNN). In order to better adapt to texts in different scales, feature pyramid networks (FPN) have been applied in the CNN part to extract multi-scale features of the image. We then utilize bidirectional long-short-term memory (Bi-LSTM) to encode these features to make full use of the text sequence characteristics with the outputs as a series of text proposals. The generated proposals are finally linked into a text line through a well-designed text connector, which can be flexibly adapted to any oriented texts. The proposed method is evaluated on three public datasets: ICDAR2013, ICDAR2015, and USTB-SV1K. For ICDAR2013 and USTB-1K, we have reached 92.5% and 62.6% <inline-formula> <tex-math notation="LaTeX">{F} </tex-math></inline-formula>-measure, respectively. Our method has reached 72.8% <inline-formula> <tex-math notation="LaTeX">{F} </tex-math></inline-formula>-measure on the more challenging ICDAR2015 which demonstrates the effectiveness of our method.