Dr. Xiang Bai Professor at the Department of EI, HUST


HUST-TR 400 Dataset

A Unified Framework for Multi-Oriented Text Detection and Recognition [PDF]
Cong Yao, Xiang Bai*, Wenyu Liu
IEEE Transactions on Image Processing (TIP), accepted to appear.


MSRA-TD 500 Dataset 

Detecting Texts of Arbitrary Orientations in Natural Images [PDF]
Cong Yao, Xiang Bai, Wenyu Liu, Yi Ma, and Zhuowen Tu;
IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Providence, Rhode Island, June 16 - 21, 2012.


Vehicle Color Dataset

Vehicle Color Recognition on Urban Road by Feature Context [PDF]
Pan Chen, Xiang Bai, and Wenyu Liu;
IEEE Transactions on Intelligent Transportation Systems (TITS), 2014, Issue: 99, Page(s): 1-7


Animal Dataset

Integrating Contour and Skeleton for Shape Classification. Xiang Bai, Wenyu Liu, Zhuowen Tu, International Workshop on Nordia, 2009. [PDF]




Strokelet [Demo][Readme]

Strokelet: A Learned Multi-Scale Representation for Scene Text Recognition. CVPR, 2014.


Skeleton Pruning [Code]

Skeleton pruning as trade-off between skeleton simplicity and reconstruction error [PDF]
Wei Shen, Xiang Bai, Xingwei Yang, Longin Jan Latecki;
SCIENCE CHINA, April 2013, Vol. 56, No: 1–18

Co-Transduction [Code]

Co-Transduction for Shape Retrieval [PDF]
Xiang Bai, Bo Wang, Cong Yao, Wenyu Liu, and Zhuowen Tu;
IEEE Transactions on Image Processing (TIP), 2012, accepted for publication

Height Functions [Code]

Shape Matching and Classification Using Height Functions [PDF]
Junwei Wang, Xiang Bai, Xinge You, Wenyu Liu, and Longin Jan Latecki;
Pattern Recognition Letters (PRL), 2012, 33(2): 134-143