Accepted Paper: An Anchor-Free Oriented Text Detector with Connectionist Text Proposal Network

Back to list of accepted papers

Authors

Chenhui Huang (East China Normal University); Jinhua Xu (East China Normal University)

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.