Detecting Multi-Oriented Text with Corner-based Region Proposals

8 Apr 2018  ·  Linjie Deng, Yanxiang Gong, Yi Lin, Jingwen Shuai, Xiaoguang Tu, Yuefei Zhang, Zheng Ma, Mei Xie ·

Previous approaches for scene text detection usually rely on manually defined sliding windows. This work presents an intuitive two-stage region-based method to detect multi-oriented text without any prior knowledge regarding the textual shape. In the first stage, we estimate the possible locations of text instances by detecting and linking corners instead of shifting a set of default anchors. The quadrilateral proposals are geometry adaptive, which allows our method to cope with various text aspect ratios and orientations. In the second stage, we design a new pooling layer named Dual-RoI Pooling which embeds data augmentation inside the region-wise subnetwork for more robust classification and regression over these proposals. Experimental results on public benchmarks confirm that the proposed method is capable of achieving comparable performance with state-of-the-art methods. The code is publicly available at https://github.com/xhzdeng/crpn

PDF Abstract

Results from the Paper


Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Scene Text Detection COCO-Text Corner-based Region Proposals F-Measure 59.1 # 1
Precision 55.5 # 2
Recall 63.3 # 1
Scene Text Detection ICDAR 2013 Corner-based Region Proposals F-Measure 87.6%% # 9
Precision 91.9 # 8
Recall 83.9 # 10
Scene Text Detection ICDAR 2015 Corner-based Region Proposals F-Measure 84.5 # 22
Precision 88.7 # 21
Recall 80.7 # 27

Methods


No methods listed for this paper. Add relevant methods here