Multilingual Text Detection with Nonlinear Neural Network - {Dubstowel}

Abstract:
Multilingual text detection in natural scenes is still a challenging task in computer vision. In this paper, we apply an unsupervised learning algorithm to learn language-independent stroke feature and combine unsupervised stroke feature learning and automatically multilayer feature extraction to improve the representational power of text feature. We also develop a novel nonlinear network based on traditional Convolutional Neural Network that is able to detect multilingual text regions in the images. The proposed method is evaluated on standard benchmarks and multilingual dataset and demonstrates improvement over the previous work. [ABSTRACT FROM AUTHOR]

How to Cite:
APA:
Li, L., Yu, S., Zhong, L., & Li, X. (2015). Multilingual Text Detection with Nonlinear Neural Network. Mathematical Problems In Engineering, 20151-7. doi:10.1155/2015/431608
AMA:
Li L, Yu S, Zhong L, Li X. Multilingual Text Detection with Nonlinear Neural Network. Mathematical Problems In Engineering [serial online]. October 11, 2015;2015:1-7. Available from: Academic Search Complete, Ipswich, MA. Accessed November 15, 2015.
Harvard:
Li, L, Yu, S, Zhong, L, & Li, X 2015, 'Multilingual Text Detection with Nonlinear Neural Network', Mathematical Problems In Engineering, 2015, pp. 1-7, Academic Search Complete, EBSCOhost, viewed 15 November 2015.