A NOVEL METHOD FOR TEXT DETECTION IN IMAGERY

Author(s) : Jiji Mol, Anisha Mohammed, Nikhil G Kurup

Volume & Issue : VOLUME 2 / 2017 , ISSUE 1

Page(s) : 114-119


Abstract

Imagery is used as an effective tool in visual design. Actually it originated well before the development of web design. Text overlaid on images provides us a more emotionally engaging and contextually rich experience. But detection of scene-text is much more challenging due to complex background, fonts and styles. A novel system for detecting text in images is proposed in this paper. The proposed method uses Fractional Poisson Enhancement for removing Laplacian noise of the input image. The pre-processed image is operated by a threshold to obtain a binary gradient mask. The subsequent steps include morphological operations, identification of text-region using bounding boxes and finally detection of text characters. Fmeasure is used for comparative analysis of the proposed method for different datasets.



Keywords

Laplacian noise, Morphological operations, Poisson Enhancement, Text-region

References

[1]Q. Ye,D.Doermann,“Text detection and recog-nition in imagery: sur- vey”,IEEE Trans .Pattern Anal.Mach.Intell. 37(2015) 1480-1500.
[2]S. Roy, P.Shivakumara, H.A Jalab, R.W Ibrahim, U. Pal, T. Lu “Frac-tional poisson enhancement model for text detection and recognition in video frames”,Pattern Recogn. 52(2016), 433-447.
[3]B.H. Shekar, Smitha M.L, “Morphological Gradient Based Approach for Text Localization in Video/Scene Images” , International Conference on Advances in Computing, Communications and Informatics, IEEE Conference Publications; 2014. p. 2426-2431.
[4]BK. Wadhawan, E. Gajendran, “Automated Recognition of Text in Im-ages: A Survey”, Intern-ational Journal of Computer Applications (0975 8887),Volume 127 No.15, October 2015.
[5]L.Rong, W.Suyu, Z.X.Shi, “A two level algor-ithm for text detection in natural scene images” ,in:Proceedings of DAS,2014,pp.329-333.
[6]X.C. Yin,X.Yin,K.Huang,H.W.Hao, “Robust text detection in natural scene images”,IEEE Trans. Pattern Anal.Mach.Intell.36(2014) 970-983.
[7]H.Chen,S.S.Tsai,G.Schorth,D.M.Chen,R.Grzeszczuk,B.Girod, “Robust text detection in natural scene images with edge-enhanced maximally stable extre-mal regions” ,in:Proceedings of ICIP,2011,pp.2609-2612.

[8]P.Shivakumara,T.Q.Phan,C.L.Tan,“A Laplacian Approach to multi- oriented text detection in video”, IEEE Trans.Pattern Anal.Mach.Intell.33(2011) 412-418.
[9]P.Shivakumara,T.Q.Phan,C.L.Tan, “New wavelet and color features for text detection in video” ,in:Proceedings of ICPR,2010,pp.3996-3999.
[10]T.Q.Phan,P.Shivakumara,C.L.Tan, “A Laplacia method for video text detection”,in:Proceedings of ICDAR,2009,pp.66-70.
[11]B.Epshtein,E.Ofek,Y.Wexler, “Detecting text in natural scenes with stroke width transform” ,in: Proceedings of CVPR,2010,pp.2963-2970.
[12]S.Roy,P.Shivakumara,P.Roy,C.L.Tan, “Wavelet gradient fusion for video text binarization” , in: Proceedings of ICPR,2012,pp.3300-3303.
[13]M. Cai, J. Song and M.R. Lyu, “A New Approach for Video Text Detection”, in Proc. IEEE Intl Conf. Image Processing, pp.117-120.
[14] https://in.mathworks.com
[15] http://homepages.inf.ed.ac.uk/rbf/HIPR2/.
[16]Casey. R, Lecolinet. E.,“A survey of methods and strategies in character segmentation”,IEEE Trans. Pattern Anal. Mach. Intell.18 (7), 690-706 (2002).
[17]J. Greenhalgh and M. Mirmehdi, .Recognizing ,“Text-Based Traffic Signs”,IEEE Trans. Intell. Transp. Syst.,vol. 16, no. 3, pp. 1360-1369, Jun. 2015.