Detecting Arbitrary Oriented Text in the Wild with a Visual Attention Model

Wenyi Huang, Dafang He, Xiao Yang, Zihan Zhou, Daniel Kifer, C. Lee Giles

Abstract

Text embedded in images provides important semantic information about a scene and its content. Detecting text in an unconstrained environment is a challenging task because of the many fonts, sizes, backgrounds, and alignments of the characters. We present a novel attention model for detecting arbitrary oriented and curved scene text. Inspired by the attention mechanisms in the human visual system, our model utilizes a spatial glimpse network to processes the attended area and deploys a recurrent neural network that aggregates the information over time to determine the attention movement. Combining this with an off-the-shelf region proposal method, the model achieves the state-of-the-art performance on the highly cited ICDAR2013 dataset, and the MSRA-TD500 dataset which contains arbitrary oriented text.
BibTeX
@inproceedings{huang2016detecting,
  author = {Wenyi Huang and Dafang He and Xiao Yang and Zihan Zhou and Daniel Kifer and C. Lee Giles},
  title = {{Detecting Arbitrary Oriented Text in the Wild with a Visual Attention Model}},
  booktitle = {ACM Multimedia},
  year = {2016},
  doi = {10.1145/2964284.2967282},
}

Loading related content...

Figure