TEXT LOCALIZATION IN SCENE IMAGES BY BENDELET TRANSFORM
In an automated text recognition system, one of the prerequisites is the localization of text. It is a challenging task in scene image due to their background and non uniform size of characters in the images. In this study, an efficient text localization system using bendlet transform is presented. Among the various multi-resolution and multi-directional analysis, bendlet transform has superior property that they classify the curvature precisely. To achieve this property, it uses an addition parameter than shearlets called bending operator. The system decomposes the scene images by bendlet transform and then reconstructs using the bands which contains only the edge information. Then, a series of post processing is applied to locate the text region in a scene image. Results show the robustness of the text localization system by successfully locating the text region in the scene images with different background and non-uniform text sizes.
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, Vol.20, No.3, 2010, pp. 800-813.
K.S. Satwashil, and V.R. Pawar, “Integrated natural scene text localization and recognition”, International conference of Electronics, Communication and Aerospace Technology, 2017, pp. 371-374.
T. Kumuda, and L. Basavaraj, “Detection and localization of text from natural scene images using texture features”, IEEE International Conference on Computational Intelligence and Computing Research, 2015, pp. 1-4.
K.S. Satwashil, and V.R. Pawar, “English text localization and recognition from natural scene image”, International Conference on Intelligent Computing and Control Systems, 2017, pp. 555-559.
R. Soni, B. Kumar, and S. Chand, “Text detection and localization in natural scene images using MSER and fast guided filter”, International Conference on Image Information Processing, 2017, pp. 1-6.
O.Y. Ling, L.B. Theng, A. Chai, and C. McCarthy, “A Model for Automatic Recognition of Vertical Texts in Natural Scene Images”, International Conference on Control System, Computing and Engineering, 2018, pp. 170-175.
J. Jameson, and S.N.H.S. Abdullah, “Extraction of arbitrary text in natural scene image based on stroke width transform”, International Conference on Intelligent Systems Design and Applications, 2014, pp. 124-128.
H. Turki, M.B. Halima, and A.M. Alimi, “Text detection in natural scene images using two masks filtering”, International Conference of Computer Systems and Applications, 2016, pp. 1-6.
A. Ray, A. Shah, and S. Chaudhury, “Recognition based text localization from natural scene images”, International Conference on Pattern Recognition, 2016, pp. 1177-1182.
X. Gironés, and C. Julià, “Real-Time Text Localization in Natural Scene Images Using a Linear Spatial Filter”, International Conference on Document Analysis and Recognition, 2017, pp. 1261-1268.
Y. Zhou, S. Liu, Y. Zhang, Y. Wang, and W. Lin, “Text localization in natural scene images with stroke width histogram and superpixel”, In Signal and Information Processing Association Annual Summit and Conference, 2014, pp. 1-4.
C. Lessig , P. Petersen, and M. Schäfer, “Bendlets. A second-order shearlet transform with bent elements”, Applied and Computational Harmonic Analysis, Vol. 46, No. 2, 2017, pp. 384-399.
S. Mallat, “A wavelet tour of signal processing: the sparse way”, Academic Press, 2008.
M.N. Do, and M. Vetterli, “The contourlet transform: an efficient directional multiresolution image representation”, IEEE Transactions on image processing, Vol, 14, No. 12, 2005, pp. 2091-2106.
W.Q. Lim, “The discrete shearlet transform: a new directional transform and compactly supported shearlet frames”, IEEE Trans. Image Processing, Vol. 19, No. 5, 2010, pp. 1166-1180.
D. Donoho and E. Candes, “Continuous curvelet transform: II. Discretization and frames”, Applied and Computational Harmonic Analysis, Vol. 19, No. 2, 2005, pp. 198-222.
This work is licensed under a Creative Commons Attribution 4.0 International License.