Scale robust deep oriented-text detection network

作者：

Highlights：

• We propose a highly efficient one-stage deep text-detection model for natural scene multi-oriented text with robustness to scale variation.

• The proposed deep model contains the feature extraction block, the feature refining block and the prediction block.

• The feature refining block embeds upsampling operation, Residual Convolution Unit and Chained Residual Pooling Unit in order to keep text detection in a higher-resolution.

• Our method is implemented on ICDAR2015 and MSRA-TD500, achieving the detection F-score over 83.1 and 79.0%, respectively.

摘要

•We propose a highly efficient one-stage deep text-detection model for natural scene multi-oriented text with robustness to scale variation.•The proposed deep model contains the feature extraction block, the feature refining block and the prediction block.•The feature refining block embeds upsampling operation, Residual Convolution Unit and Chained Residual Pooling Unit in order to keep text detection in a higher-resolution.•Our method is implemented on ICDAR2015 and MSRA-TD500, achieving the detection F-score over 83.1 and 79.0%, respectively.

论文关键词：Scene text detection,One-stage,Scale robust

论文评审过程：Received 6 May 2019, Revised 2 December 2019, Accepted 16 December 2019, Available online 24 December 2019, Version of Record 26 February 2020.

论文官网地址：https://doi.org/10.1016/j.patcog.2019.107180