Home   >   CSC-OpenAccess Library   >    Manuscript Information
Full Text Available

(775.06KB)
This is an Open Access publication published under CSC-OpenAccess Policy.
Publications from CSC-OpenAccess Library are being accessed from over 74 countries worldwide.
K2 Algorithm-based Text Detection with An Adaptive Classifier Threshold
Khalid Iqbal, Xu-Cheng Yin, Hong-Wei Hao, Sohail Asghar, Hazrat Ali
Pages - 87 - 94     |    Revised - 10-05-2014     |    Published - 01-06-2014
Volume - 8   Issue - 3    |    Publication Date - June 2014  Table of Contents
MORE INFORMATION
KEYWORDS
Bayesian Network, Adaptive Threshold, Bayesian Logistic Regression, Scene Image.
ABSTRACT
In natural scene images, text detection is a challenging study area for dissimilar content-based image analysis tasks. In this paper, a Bayesian network scores are used to classify candidate character regions by computing posterior probabilities. The posterior probabilities are used to define an adaptive threshold to detect text in scene images with accuracy. Therefore, candidate character regions are extracted through maximally stable extremal region. K2 algorithm-based Bayesian network scores are learned by evaluating dependencies amongst features of a given candidate character region. Bayesian logistic regression classifier is trained to compute posterior probabilities to define an adaptive classifier threshold. The candidate character regions below from adaptive classifier threshold are discarded as non-character regions. Finally, text regions are detected with the use of effective text localization scheme based on geometric features. The entire system is evaluated on the ICDAR 2013 competition database. Experimental results produce competitive performance (precision, recall and harmonic mean) with the recently published algorithms.
CITED BY (1)  
1 Ali, S., Iqbal, K., Khan, S., Tariq, R., & Aqil, Q. Z. (2015). A Review on Text Detection Techniques. VFAST Transactions on Software Engineering, 8(2).
1 Google Scholar 
2 CiteSeerX 
3 refSeek 
4 Scribd 
5 SlideShare 
6 PdfSR 
1 Y.-F. Pan, X. Hou, and C.-L. Liu. A hybrid approach to detect and localize texts in natural scene images. IEEE Transactions on Image Processing, 20(3):800 –813, March 2011.
2 Y.-F. Pan,, X. Hou, and C.-L. Liu. "A hybrid approach to detect and localize texts in natural scene images." Image Processing, IEEE Transactions on 20, no. 3 (2011): 800-813.
3 J.-J. Lee, P.-H. Lee, S.-W. Lee, A. Yuille, and C. Koch. Adaboost for text detection in natural scene. In ICDAR 2011, pages 429 –434, September 2011.
4 B. Epshtein, E. Ofek, and Y. Wexler. Detecting text in natural scenes with stroke width transform. In CVPR 2010, pages 2963 –2970, June 2010.
5 X. Yin, X-C Yin, H-W. Hao, and K. Iqbal. "Effective text localization in natural scene images with MSER, geometry-based grouping and AdaBoost." In Pattern Recognition (ICPR), 2012 21st International Conference on, pp. 725-728. IEEE, 2012.
6 A. Shahab, F. Shafait, and A. Dengel. ICDAR 2011 robust reading competition challenge 2:Reading text in scene images. In ICDAR 2011, pages 1491 –1496, September 2011.
7 G. F. Cooper and E. Herskovits, A Bayesian method for the induction of probabilistic networks from data.Machine Learning, vol. 9, no.4, pp. 309-347, 1992.
8 K. Iqbal, X.-C. Yin, H.-W. Hao, X. Yin, H. Ali, (2013), Classifier Comparison for MSER-Based Text Classification in Scene Images, In Neural Networks (IJCNN), The 2013 International Joint Conference on (pp. 1-6). IEEE.
9 Hosmer, David W.; Lemeshow, Stanley (2000). “Applied Logistic Regression” (2nd ed.).Wiley. ISBN 0-471-35632-8.
10 D. Karatzas, F. Shafait, S. Uchida, M. Iwamura, S. R. Mestre, J. Mas, D. F. Mota, J. A.Almazan, and L. P. de las Heras. "ICDAR 2013 Robust Reading Competition." In Document Analysis and Recognition (ICDAR), 2013 12th International Conference on, pp. 1484-1493.IEEE, 2013.
11 X.-C. Yin, H.-W. Hao, J. Sun, and S. Naoi. Robustvanishing point detection for MobileCambased documents. In ICDAR 2011, pages 136 – 140, September 2011.
12 C. Merino-Gracia, K. Lenc, M. Mirmehdi, A head-mounted device for recognizing text in natural scenes, Camera-Based Document Analysis and Recognition, pages 29--41, 2012.
13 J. Matas, O. Chum, M. Urban, and T. Pajdla. Robust wide baseline stereo from maximally stable extremal regions. In British Machine Vision Conference 2002, volume 1, pages 384–393, 2002.
14 K. Mikolajczyk, T. Tuytelaars, C. Schmid, A. Zisserman, J. Matas, F. Schaffalitzky, T. Kadir,and L. V. Gool. A Comparison of Affine Region Detectors. International Journal of Computer Vision, 65(1):43–72, November 2005.
15 D. M. Chickering, Learning Bayesian networks is NP-complete. In D. Fisher and H.J. Lenz,editors, Learning from Data: Articial Intelligence and Statistics V, Springer-Verlag, pp. 121-130, 1996.
16 N. Friedman, D. Koller, Being Bayesian About Network Structure: A Bayesian Approach to Structure Discovery in Bayesian Networks, Machine Learning 50 (1-2) (2003) 95-125.
17 D. Karatzas, S. Robles Mestre, J. Mas, F. Nourbakhsh, P. Pratim Roy , "ICDAR 2011 Robust Reading Competition - Challenge 1: Reading Text in Born-Digital Images (Web and Email)",In Proc. 11th International Conference of Document Analysis and Recognition, 2011, IEEE CPS, pp. 1485-1490.
18 J. Fabrizio, B. Marcotegui, and M. Cord, “Text segmentation in natural scenes using togglemapping,”in Proc. Int. Conf. on Image Processing,2009.
19 J. Fabrizio, B. Marcotegui, M. Cord, “Text detection in street level images,” Pattern Analysis and Applications, 2013, Volume 16, Issue 4, pp 519-533.
20 L. Neumann and J. Matas, “A method for text localization and recognition in real-world images,” in Proc. Asian Conf. on Computer Vision, 2010, pp. 2067–2078.
21 L. Neumann, and J. Matas. Real-time scene text localization and recognition. in Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on. 2012., pp. 3538–3545.
22 L Neumann, J Matas, “On combining multiple segmentations in scene text recognition,” in Proc. Int. Conf. on Document Analysis and Recognition, 2013. International Conference on Document Analysis and Recognition (ICDAR 2013), Washington D.C., 2013.
23 Y.-M. Zhang, K.-Z. Huang, and C.-L. Liu, “Fast and robust graph-based transductive learning via minimum tree cut,” in Proc. Int. Conf. on Data Mining, 2011.
24 C.-L. L. B. Bai, F. Yin, “Scene text localization using gradient local correlation,” in Proc. Int.Conf. on Document Analysis and Recognition, 2013.
25 C. Shi, C. Wang, B. Xiao, Y. Zhang, S. Gao, and Z. Zhang, “Scene text recognition using part-based tree-structured character detections,” in Proc. Int. Conf. on Computer Vision and Pattern Recognition, 2013.
26 C. Shi, C. Wang, B. Xiao, Y. Zhang, and S. Gao, “Scene text detection using graph model built upon maximally stable extremal regions,” Pattern Recognition Letters, vol. 34, no. 2, pp.107–116, 2013.
27 X.-C Yin, X. Yin, K. Huang, and H.-W. Hao Robust Text Detection in Natural Scene Images.,IEEE Transactions on Pattern Analysis and Machine Intelligence, preprint, 2013.
Dr. Khalid Iqbal
University of Science and Technology Beijing - China
kik.ustb@gmail.com
Associate Professor Xu-Cheng Yin
University of Science and Technology Beijing - China
Professor Hong-Wei Hao
Chinese Academy of Sciences - China
Associate Professor Sohail Asghar
PMAS-Arid Agriculture University - Pakistan
Mr. Hazrat Ali
City University London - United Kingdom