Authors: Xu-Cheng Yin, Shu Tian, Ze-Yu Zuo, Wei-Yi Pei, ChunYang

Description: Text is first detected with USTB_TexStar (Multi-Orientation) [1,2]. Then a word recogniton system (a CNN recognizer [3] and a Character Case sensitive identifier) is performed. Here, text tracking with multi-tracking-strategies [4] is performed for improving both detection and recognition.

[1] Xu-Cheng Yin, Xuwang Yin, Kaizhu Huang, and Hong-Wei Hao, “Robust text detection in natural scene images”, IEEE Trans. Pattern Analysis and Machine Intelligence, 36(5): 970-983, 2014.
[2] Xu-Cheng Yin, Wei-Yi Pei, Xuwang Yin, Jun Zhang, and Hong-Wei Hao, “Multi-orientation scene text detection with adaptive clustering,” IEEE Trans. Pattern Analysis and Machine Intelligence (TPAMI), preprint, 2015.
[3] M. Jaderberg, K. Simonyan, A. Vedaldi, and A. Zisserman, "Reading Text in the Wild with Convolutional Neural Networks", arXiv preprint arXiv:1412.1842, 2014.
[4] Ze-Yu Zuo, Shu Tian, and Xu-Cheng Yin, "Multi-strategy tracking based text detection in scene videos", International Conference on Document Analysis and Recognition, 2015.