Call for Paper - March 2022 Edition
IJCA solicits original research papers for the March 2022 Edition. Last date of manuscript submission is February 22, 2022. Read More

Text Recognition using Image Segmentation and Neural Network

Print
PDF
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Year of Publication: 2017
Authors:
Ammar A. Radhi
10.5120/ijca2017914791

Ammar A Radhi. Text Recognition using Image Segmentation and Neural Network. International Journal of Computer Applications 170(10):43-50, July 2017. BibTeX

@article{10.5120/ijca2017914791,
	author = {Ammar A. Radhi},
	title = {Text Recognition using Image Segmentation and Neural Network},
	journal = {International Journal of Computer Applications},
	issue_date = {July 2017},
	volume = {170},
	number = {10},
	month = {Jul},
	year = {2017},
	issn = {0975-8887},
	pages = {43-50},
	numpages = {8},
	url = {http://www.ijcaonline.org/archives/volume170/number10/28119-2017914791},
	doi = {10.5120/ijca2017914791},
	publisher = {Foundation of Computer Science (FCS), NY, USA},
	address = {New York, USA}
}

Abstract

The fast development in worldwide technology makes it essential for us to find solutions for some challenging problems; one of these is the recognition of the important details from images. Text recognition is a process that converts the text that any image contains to something that is recognizable for our modern devices e.g., our smart phones. In this paper an efficient algorithm for the detection of text from an image is proposed. This methodology includes the application of a powerful segmentation method that labels the letters in the image very efficiently, and then the mean of the coordinates of each letter within the image is used after the application of the segmentation method in order to sort the letters correctly, moreover, the algorithm includes the introduction of a new line detection method based on the mean of the labels, and finally some modifications on the work of the autoencoder neural network is proposed in this paper. The transformation of the text in the image to text document is achieved with high accurate result; the results show a complete recognition of the text in wide varieties of images. Examples of the application of this algorithm are for the detection of the text in image with many lines, road sign images and car plate number recognition are shown in this paper.

References

  1. S. Mori, C.Y. Suen, K.Yamamoto, Historical review of OCR research and development, Proc. IEEE, 80(7):1029-1058, 1992.
  2. Y. LeCun, L. Bottou, Y. Bengio, P. Ha®ner, Gradient based learning applied to document recognition, Proc. IEEE, 86(11): 2278-2324, 1998.
  3. C.Y. Suen, K. Kiu, N.W. Strathy, Sorting and recognizing cheques and ¯nancial documents, Document Analysis Systems: Theory and Practice, S.-W. Lee and Y. Nakano (eds.), LNCS 1655, Springer, 1999, pp. 173-187.
  4. Siddhi Sharma1, Neetu Singh2. Optical Character recognition Using Artificial Neural Network Approach. IJETAE. Volume 4, Issue 11, November 2014.
  5. Max Jaderberg, Karen Simonyan, Andrea Vedaldi, Andrew Zisserman. Reading Text in the Wild with Convolution Neural Networks. Springer. International. Journal Computer V. 2016 .116:1-20.
  6. Chen,X.,X & Yuille,A.L.(2004). Detecting and Reading text in natural scenes. In Computer Vision and Pattern Recogntion,2004.CVPR 2004 (Vol.2,pp.II-366). Piscataway,NJ:IEEE.
  7. K. Fukunaga, Introduction to Statistical Pattern Recognition, 2nd edition, Academic Press, 1990.
  8. R.O. Duda, P.E. Hart, D.G. Stork, Pattern Classification, second edition, Wiley Inter science, 2001.
  9. Y. LeCun, L. Bottou, Y. Bengio, P. Ha®ner, Gradient based learning applied to document recognition, Proc.IEEE, 86(11): 2278-2324, 1998.
  10. P.Y. Simard, D. Steinkraus, J.C. Platt, Best practices for convolutional neural networks applied to visual document analysis, Proc. 7th ICDAR, Edinburgh.
  11. Piyush Rai. Kernel Methods and Nonlinear Classification. September 15, 2011
  12. A. Bellili, M. Gilloux, P. Gallinari, An MLP-SVM combination architecture for o²ine handwritten digit recognition: reduction of recognition errors by support vector machines rejection mechanisms, Int. J. Document Analysis and Recognition, 5(4): 244-252, 2003.
  13. A.F.R. Rahman, M.C. Fairhurst, Multiple classifier decision combination strategies for character recognition: a review, Int. J. Document Analysis and Recognition, 5(4): 166-194, 2003.
  14. ‘Angel Johncy: Extraction of Connected Component without using BWLABEL in image processing’http://angeljohnsy.blogspot.com/2012/03/extraction-of-connected-components.html. Accessed October 31, 2014.
  15. Third Generation Neural Network. https://www .mql5.com/en/articles/1103.5th5 February 2015.
  16. Quoc V. Le, A Tutorial on Deep Learning Part 2: Autoencoders, Convolutional Neural Networks and Recurrent Neural Networks, October 20, 2015.
  17. Train Stacked Autoencoders for Image Classification.’https://www.mathworks.com/help/nnet amples/training-a-deep-neural-network-for-digit-classification.html’ 2016.

Keywords

Neural network, Image segmentation, Car plate number detection, Road sign detection.