Abstract
Recent years have witnessed an exponential surge in interest to explore the domain of scene text detection as well as analysis in natural scene images. However, owing to the complexities arising due to various factors, it can be said that existing techniques may fail at times while attempting to detect text components. This paper presents a system wherein an image is taken as input and its color components are extracted at first. Next the intensity values from each color channel are grouped together using K-means++ clustering algorithm. Memetic algorithm is then applied to get an optimal set of candidate components from the color maps while eliminating the background. The spurious components are removed on the basis of their dimension and entropy measure. This system is experimentally evaluated on two standard datasets namely MLe2e and KAIST, and on an in-house dataset of 400 images, all having multi-lingual texts. The results obtained are comparable with some state-of-the-art methods.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Y. Zhu, C. Yao, X. Bai, Scene text detection and recognition: recent advances and future trends. Frontiers Comput. Sci. 10(1), 19–36 (2016)
H. Chen, S.S. Tsai, G. Schroth, D.M. Chen, R. Grzeszczuk, B. Girod, Robust text detection in natural images with edge-enhanced maximally stable extremal regions, in 2011 18th IEEE International Conference on Image Processing (IEEE, 2011, September), pp. 2609–2612
B. Epshtein, E. Ofek, Y. Wexler, Detecting text in natural scenes with stroke width transform, in 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (IEEE, 2010, June), pp. 2963–2970
A. Mukhopadhyay, S. Kumar, S.R. Chowdhury, N. Chakraborty, A.F. Mollah, S. Basu, R. Sarkar, Multi-lingual scene text detection using one-class classifier. Int. J. Comput. Vis. Image Process. (IJCVIP) 9(2), 48–65 (2019)
D. Arthur, S. Vassilvitskii, k-means++: The Advantages of Careful Seeding (Stanford, 2006)
P. Moscato, C. Cotta, A modern introduction to memetic algorithms, in Handbook of Metaheuristics (Springer, Boston, MA, 2010), pp. 141–183
K. Fan, S.J. Baek, A robust proposal generation method for text lines in natural scene images. Neurocomputing 304, 47–63 (2018)
L. Li, S. Yu, L. Zhong, X. Li, Multilingual text detection with nonlinear neural network, in Mathematical Problems in Engineering (2015)
L. Gomez, D. Karatzas, A fine-grained approach to scene text script identification, in 2016 12th IAPR Workshop on Document Analysis Systems (DAS) (IEEE, 2016, April), pp. 192–197
L. Gomez, A. Nicolaou, D. Karatzas, Improving patch-based scene text script identification with ensembles of conjoined networks. Pattern Recogn. 67, 85–96 (2017)
J. Matas, O. Chum, M. Urban, T. Pajdla, Robust wide-baseline stereo from maximally stable extremal regions. Image Vis. Comput. 22(10), 761–767 (2004)
N. Chakraborty, S. Biswas, A.F. Mollah, S. Basu, R. Sarkar, Multi-lingual scene text detection by local histogram analysis and selection of optimal area for MSER, in International Conference on Computational Intelligence, Communications, and Business Analytics (Springer, Singapore, 2018, July), pp. 234–242
S. Panda, S. Ash, N. Chakraborty, A.F. Mollah, S. Basu, R. Sarkar, Parameter tuning in MSER for text localization in multi-lingual camera-captured scene text images, in International Conference on Computational Intelligence in Pattern Recognition (Springer, Singapore, 2020), pp. 999–1009
A.C. Özgen, M. Fasounaki, H.K. Ekenel, Text detection in natural and computer-generated images, in 2018 26th Signal Processing and Communications Applications Conference (SIU) (IEEE, 2018, May), pp. 1–4
A. Agrawal, P. Mukherjee, S. Srivastava, B. Lall, Enhanced characterness for text detection in the wild, in Proceedings of 2nd International Conference on Computer Vision & Image Processing (Springer, Singapore, 2018), pp. 359–369
I.N. Dutta, N. Chakraborty, A.F. Mollah, S. Basu, R. Sarkar, Multi-lingual text localization from camera captured images based on foreground homogenity analysis, in Recent Developments in Machine Learning and Data Analytics (Springer, Singapore, 2019), pp. 149–158
Y. Li, Vehicle extraction using histogram and genetic algorithm based fuzzy image segmentation from high resolution UAV aerial imagery, in ISPRS08 (2008,) p. B3b, 529
S. Saha, N. Chakraborty, S. Kundu, S. Paul, A.F. Mollah, S. Basu, R. Sarkar, Multi-lingual scene text detection and language identification, in Pattern Recognition Letters (2020)
T. Khan, A.F. Mollah, Text non-text classification based on area occupancy of equidistant pixels. Proc. Comput. Sci. 167, 1889–1900 (2020)
R. Bagi, T. Dutta, H.P. Gupta, Cluttered textspotter: an end-to-end trainable light-weight scene text spotter for cluttered environment, in IEEE Access (2020)
J. Han, J. Pei, M. Kamber, Data Mining: Concepts and Techniques. Elsevier (2011)
P. Jana, S. Ghosh, S.K. Bera, R. Sarkar, Handwritten document image binarization: an adaptive K-means based approach, in 2017 IEEE Calcutta Conference (CALCON) (IEEE, 2017, December), pp. 226–230
M. Ghosh, T. Kundu, D. Ghosh, R. Sarkar, Feature selection for facial emotion recognition using late hill-climbing based memetic algorithm. Multimedia Tools Appl. 78(18), 25753–25779 (2019)
M. Ghosh, S. Begum, R. Sarkar, D. Chakraborty, U. Maulik, Recursive memetic algorithm for gene selection in microarray data. Expert Syst. Appl. 116, 172–185 (2019)
M. Ghosh, S. Malakar, S. Bhowmik, R. Sarkar, M. Nasipuri, Feature selection for handwritten word recognition using memetic algorithm, in Advances in Intelligent Computing (Springer, Singapore, 2019), pp. 103–124
M. Ghosh, S. Malakar, S. Bhowmik, R. Sarkar, M. Nasipuri, Memetic algorithm based feature selection for handwritten city name recognition, in International Conference on Computational Intelligence, Communications, and Business Analytics (Springer, Singapore, 2017, March), pp. 599–613
Acknowledgements
This work is partially supported by the CMATER research laboratory of the Computer Science and Engineering Department, Jadavpur University, India, PURSE-II and UPE-II, project. SB is partially funded by DBT grant (BT/PR16356/BID/7/596/2016). RS, SB and AFM are partially funded by DST grant (EMR/2016/007213).
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
Chakraborty, N., Ray, A., Mollah, A.F., Basu, S., Sarkar, R. (2021). A Framework for Multi-lingual Scene Text Detection Using K-means++ and Memetic Algorithms. In: Kumar, P., Singh, A.K. (eds) Machine Learning for Intelligent Multimedia Analytics. Studies in Big Data, vol 82. Springer, Singapore. https://doi.org/10.1007/978-981-15-9492-2_9
Download citation
DOI: https://doi.org/10.1007/978-981-15-9492-2_9
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-9491-5
Online ISBN: 978-981-15-9492-2
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)