[1] Liu Xiaoqing, Samarabandu J. Multiscale edge- based text extraction from complex images[C]//ICME 2006. Toronto: [s.n.], 2006: 1721-1724.
[2] Zhu Caifeng, Wang Weiqiang, Ning Qianhui. Text detection in images using texture feature from strokes[C]//PCM 2006. Hangzhou: [s.n.], 2006: 295-301.
[3] Liu Xiaoqian, Wang Weiqiang. Robustly extract ing captions in videos based on stroke-like edges and spatio-temporal analysis[J]. IEEE Transaction on Multimedia, 2012, 14(2): 482-489.
[4] Hua Xiansheng, Chen Xiangrong, Liu Wenyin. Automatic location of text in video frames[C]//MIR 2001. New York: [s.n.], 2001: 24-27.
[5] Zhao Xu, Lin Kaiqiang, Fu Yun. Text from corners: a novel approach to detect text and caption in videos[J]. IEEE Transaction on Image Process, 2011, 20(3): 790-799.
[6] Harris C, Stephens M. A combined corner and edge detector[C]//Alvey Vision Conference. 1988: 147-151.
[7] Horn B K P, Schunck B G. Determiningoptical flow[J]. Artificial Intelligence, 1981, 17(1): 185-203.
[8] Michael E. Tippingsparse bayesian learning and the relevance vector machine[J]. Journal of Machine Learning Research, 2001(2): 211-244.
[9] MacKay D J C. The evidence framework applied to classification networks[J]. Neural Computation, 1992, 4(5): 720-736.
[10] Chang Zhizhong, Lin Zhiren. LIBSVM: a library for support vector machines[J]. ACM Transactio-ns on Intelligent Systems and Technology, 2011(2): 1-27.