Welcome to Francis Academic Press
Login | Register

Academic Journal of Computing & Information Science, 2020, 3(4); doi: 10.25236/AJCIS.2020.030405.

Text Detection in Multi-feature Fusion Natural Scenes Based on Convolution Deep Belief Network

Author(s)

Yuan Zhong*, Jian’an Fang

Corresponding Author:
Yuan Zhong
Affiliation(s)

College of Information Science and Technology, Donghua University, Shanghai 201600, China
*Corresponding author

Abstract

For the traditional MSER algorithm in the background of complex scenes of text detection will appear in the case of false detection. In this paper, a method of multi-feature fusion of natural scene image pseudo-character filtering based on convolution depth confidence network is proposed. The candidate character text regions obtained from MSER algorithm were extracted and fused with LBP feature, HOG feature and CDBN feature, and finally the characters and pseudo-characters were classified by SVM classifier. And merge the resulting characters to produce the final line of text. Experimental results show that this algorithm can filter out more false character areas and improve the accuracy of text location.

Keywords

scene text detection, lbp, hog, cdbn, svm

Cite This Paper

Yuan Zhong, Jian’an Fang. Text Detection in Multi-feature Fusion Natural Scenes Based on Convolution Deep Belief Network. Academic Journal of Computing & Information Science (2020), Vol. 3, Issue 4: 41-49. https://doi.org/10.25236/AJCIS.2020.030405.

References

[1] Zhou G , Liu Y , Meng Q , et al. Detecting multilingual text in natural scene [C] International Symposium on Access Spaces. IEEE, 2011.
[2] Epshtein B, Ofek E, Wexler Y. Detecting text in natural scenes with stroke width transform. Proceedings of Computer Vision and Pattern Recognition. San Francisco,CA, USA. 2010. 2963–2970.
[3] Lee H, Grosse R, Ranganath R, et al. Convolutional deep belief networks for scalable unsupervised learning of hierarchical representations. Proceedings of the 26th Annual International Conference on Machine Learning. Montreal,QC, Canada. 2009. 609–616.
[4] Karatzas D , Shafait F , Uchida S , et al. ICDAR 2013 Robust Reading Competition [C] 2013 12th International Conference on Document Analysis and Recognition. IEEE Computer Society, 2013.
[5] Yin H F, Wu X J. A New Feature Fusion Approach Based on LBP and Sparse Representation and Its Application to Face Recognition [J]. 2013.
[6] Ojala T, Pietikäinen M, Mäenpää T. Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns [J]. IEEE Transactions on Pattern Analysis & Machine Intelligence, 2002, 24 (7): 971-987.
[7] Lee H, Ekanadham C, Ng A Y. Sparse deep belief net model for visual area V2 [C]. International Conference on Neural Information Processing Systems. Vancouver, British  Columbia, Canada Curran Associates Inc, 2007: 873-880.
[8] Wang Lin, Zhang Xiao-Feng. Scene Text Detection in Convolutional Deep Belief Networks [J]. Computer Systems & Applications, 2018, 27 (6): 231–235.
[9] Huang WL, Qiao Y, Tang XO. Robust scene text detection with convolution neural network induced MSER trees.Computer Vision(ECCV 2014). Cham: Springer, 2014.497–511.
[10] Neumann L, Matas J. A Method for Text Localization and Recognition in Real-World Images [J]. 2010.
[11] Pengfei Zhou. Research on text Detection and Recognition in natural Scene images [D]. Xi 'an University of Technology, 2019.