Deep Direct Regression for Multi-Oriented Scene Text Detection

by   Wenhao He, et al.

In this paper, we first provide a new perspective to divide existing high performance object detection methods into direct and indirect regressions. Direct regression performs boundary regression by predicting the offsets from a given point, while indirect regression predicts the offsets from some bounding box proposals. Then we analyze the drawbacks of the indirect regression, which the recent state-of-the-art detection structures like Faster-RCNN and SSD follows, for multi-oriented scene text detection, and point out the potential superiority of direct regression. To verify this point of view, we propose a deep direct regression based method for multi-oriented scene text detection. Our detection framework is simple and effective with a fully convolutional network and one-step post processing. The fully convolutional network is optimized in an end-to-end way and has bi-task outputs where one is pixel-wise classification between text and non-text, and the other is direct regression to determine the vertex coordinates of quadrilateral text boundaries. The proposed method is particularly beneficial for localizing incidental scene texts. On the ICDAR2015 Incidental Scene Text benchmark, our method achieves the F1-measure of 81 approaches. On other standard datasets with focused scene texts, our method also reaches the state-of-the-art performance.


page 1

page 2

page 4

page 5

page 7


Learning to Predict More Accurate Text Instances for Scene Text Detection

At present, multi-oriented text detection methods based on deep neural n...

FC2RN: A Fully Convolutional Corner Refinement Network for Accurate Multi-Oriented Scene Text Detection

Recent scene text detection works mainly focus on curve text detection. ...

Deep Matching Prior Network: Toward Tighter Multi-oriented Text Detection

Detecting incidental scene text is a challenging task because of multi-o...

Scale-Invariant Multi-Oriented Text Detection in Wild Scene Images

Automatic detection of scene texts in the wild is a challenging problem,...

Correlation Propagation Networks for Scene Text Detection

In this work, we propose a novel hybrid method for scene text detection ...

TextField: Learning A Deep Direction Field for Irregular Scene Text Detection

Scene text detection is an important step of scene text reading system. ...

Arbitrary Shape Text Detection using Transformers

Recent text detection frameworks require several handcrafted components ...

Please sign up or login with your details

Forgot password? Click here to reset