An Anchor-Free Oriented Text Detector with Connectionist Text Proposal Network

Chenhui Huang, Jinhua Xu
Proceedings of The Eleventh Asian Conference on Machine Learning, PMLR 101:631-645, 2019.

Abstract

Deep learning approaches have made great progress for the scene text detection in recent years. However, there are still some difficulties such as the text orientation and varying aspect ratios. In this paper, we address these issues by treating a text instance as a sequence of fine-scale proposals. The vertical distances from a text pixel to the text borders are directly regressed without the commonly used anchor mechanism, and then the small local proposals are connected during the post-processing. A U-shape convolutional neural network (CNN) architecture is used to incorporate the context information and detect small text instances. In experiments, the proposed approach, referred to as Anchor-Free oriented text detector with Connectionist Text Proposal Network (AFCTPN), achieves better or comparable performance with less time consumption on benchmark datasets.

Cite this Paper

BibTeX
@InProceedings{pmlr-v101-huang19c, title = {An Anchor-Free Oriented Text Detector with Connectionist Text Proposal Network}, author = {Huang, Chenhui and Xu, Jinhua}, booktitle = {Proceedings of The Eleventh Asian Conference on Machine Learning}, pages = {631--645}, year = {2019}, editor = {Lee, Wee Sun and Suzuki, Taiji}, volume = {101}, series = {Proceedings of Machine Learning Research}, month = {17--19 Nov}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v101/huang19c/huang19c.pdf}, url = {https://proceedings.mlr.press/v101/huang19c.html}, abstract = {Deep learning approaches have made great progress for the scene text detection in recent years. However, there are still some difficulties such as the text orientation and varying aspect ratios. In this paper, we address these issues by treating a text instance as a sequence of fine-scale proposals. The vertical distances from a text pixel to the text borders are directly regressed without the commonly used anchor mechanism, and then the small local proposals are connected during the post-processing. A U-shape convolutional neural network (CNN) architecture is used to incorporate the context information and detect small text instances. In experiments, the proposed approach, referred to as Anchor-Free oriented text detector with Connectionist Text Proposal Network (AFCTPN), achieves better or comparable performance with less time consumption on benchmark datasets.} }
Endnote
%0 Conference Paper %T An Anchor-Free Oriented Text Detector with Connectionist Text Proposal Network %A Chenhui Huang %A Jinhua Xu %B Proceedings of The Eleventh Asian Conference on Machine Learning %C Proceedings of Machine Learning Research %D 2019 %E Wee Sun Lee %E Taiji Suzuki %F pmlr-v101-huang19c %I PMLR %P 631--645 %U https://proceedings.mlr.press/v101/huang19c.html %V 101 %X Deep learning approaches have made great progress for the scene text detection in recent years. However, there are still some difficulties such as the text orientation and varying aspect ratios. In this paper, we address these issues by treating a text instance as a sequence of fine-scale proposals. The vertical distances from a text pixel to the text borders are directly regressed without the commonly used anchor mechanism, and then the small local proposals are connected during the post-processing. A U-shape convolutional neural network (CNN) architecture is used to incorporate the context information and detect small text instances. In experiments, the proposed approach, referred to as Anchor-Free oriented text detector with Connectionist Text Proposal Network (AFCTPN), achieves better or comparable performance with less time consumption on benchmark datasets.
APA
Huang, C. & Xu, J.. (2019). An Anchor-Free Oriented Text Detector with Connectionist Text Proposal Network. Proceedings of The Eleventh Asian Conference on Machine Learning, in Proceedings of Machine Learning Research 101:631-645 Available from https://proceedings.mlr.press/v101/huang19c.html.

Related Material