CFP last date
20 December 2024
Reseach Article

Textual Characters Detection in Complex Scene Images based on Bradley Thresholding Technique in Compare with Statistical Thresholding Technique

by Abdel-Rahiem A. Hashem, Ahmed I. Taloba, Majid A. Askar
International Journal of Computer Applications
Foundation of Computer Science (FCS), NY, USA
Volume 185 - Number 36
Year of Publication: 2023
Authors: Abdel-Rahiem A. Hashem, Ahmed I. Taloba, Majid A. Askar
10.5120/ijca2023923158

Abdel-Rahiem A. Hashem, Ahmed I. Taloba, Majid A. Askar . Textual Characters Detection in Complex Scene Images based on Bradley Thresholding Technique in Compare with Statistical Thresholding Technique. International Journal of Computer Applications. 185, 36 ( Oct 2023), 47-53. DOI=10.5120/ijca2023923158

@article{ 10.5120/ijca2023923158,
author = { Abdel-Rahiem A. Hashem, Ahmed I. Taloba, Majid A. Askar },
title = { Textual Characters Detection in Complex Scene Images based on Bradley Thresholding Technique in Compare with Statistical Thresholding Technique },
journal = { International Journal of Computer Applications },
issue_date = { Oct 2023 },
volume = { 185 },
number = { 36 },
month = { Oct },
year = { 2023 },
issn = { 0975-8887 },
pages = { 47-53 },
numpages = {9},
url = { https://ijcaonline.org/archives/volume185/number36/32926-2023923158/ },
doi = { 10.5120/ijca2023923158 },
publisher = {Foundation of Computer Science (FCS), NY, USA},
address = {New York, USA}
}
%0 Journal Article
%1 2024-02-07T01:27:58.495223+05:30
%A Abdel-Rahiem A. Hashem
%A Ahmed I. Taloba
%A Majid A. Askar
%T Textual Characters Detection in Complex Scene Images based on Bradley Thresholding Technique in Compare with Statistical Thresholding Technique
%J International Journal of Computer Applications
%@ 0975-8887
%V 185
%N 36
%P 47-53
%D 2023
%I Foundation of Computer Science (FCS), NY, USA
Abstract

Thresholding is an important process required to most tasks in computer vision especially characters’ detection from scene images. So, in this paper, we focus to enhance our previous model which is used to detect the characters from scene images and has proven superior to most existing methods. This improvement is fulfilled by replacing the thresholding method in the entire model in the stage of converting the grayscale image into the binary one. The new thresholding method is known by Bradley method. Although our previous model got better when we use Bradley thresholding, the number of false detections still less than in the case of using our previous thresholding method in the entire designed model.

References
  1. Chunna T and et al. 2017 Natural scene text detection with MC–MR candidate extraction and coarse-to-fine filtering, Neurocomputing, 260 (112 – 122).
  2. Zhang H. and er al. 2013 Text extraction from natural scene image: a survey, Neurocomputing 122 (310 - 323).
  3. Yin X.C. and et al. 2016 Text detection, tracking and recognition in video: a comprehensive survey, IEEE Trans. Image Process., 25(6).
  4. Matias V. Toro and et al. 2016 Histogram of Stroke Widths for Multi-script Text Detection and Verification in Road Scenes, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd.
  5. Kongqiao Wang and Jari A. Kangas. 2003 Character location in scene images from digital camera, Pattern Recognition, 36 (2287 – 2299).
  6. Qixiang Ye and David Doermann. 2015 Text Detection and Recognition in Imagery: A Survey, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 37, no. 7, pp. 1480-1500.
  7. Shivakumara P. and et al. 2008 Efficient Video Text Detection using Edge Features, IEEE 19th International Conference on Pattern Recognition.
  8. Shi C. and et al. 2014 End-to-end scene text recognition using tree-structured models, Pattern Recognition, vol. 47.
  9. Lee C. and Kankanhalli A. 1994 Automatic Extraction of Characters in Complex Scene Images, International Joiurnal of Pattern Recognition and Artifial Intelligence, vol. 9, No. 1.
  10. Abdel-Rahiem A. Hashem and et al. 2017 Extraction Characters from Scene Image based on Shape Properties and Geometric Features, International Journal of Computer Applications, Vol. 169, No. 3.
  11. Abdel-Rahiem A. Hashem and et al. 2017 A Comparison study on text detection in scene images based on connected component analysis, IJCSIS, vol. 15, no. 2, pp. 127-139.
  12. Trier D. and Jain K. 1995 Goal-Directed Evaluation of Thresholding Methods, IEEE Transaction on PAMI.
  13. Sahoo P. and et al. 1988 A Survey of Thresholding Techniques, COMPUTER VISION, GRAPHICS, AND IMAGE PROCESSING, 41(233-260).
  14. Bradley D. and Roth G. 2007 Adaptive thresholding using the integral image, Journal of Graphics Tools, Vol. 12, No. 2, PP. 13-21.
  15. Yi-Feng Pan and et al. 2009 Text Localization in Natural Scene Images based on Conditional Random Field, 10th International Conference on Document Analysis and Recognition.
  16. Shivakumara P. and et al. 2008 Efficient Video Text Detection using Edge Features, IEEE 19th International Conference on Pattern Recognition.
  17. Chunmei Liu and et al. 2005 Text Detection in Images Based on Unsupervised Classification of Edge-based Features, in Proceedings of Eight International Conference on Document Analysis and Recognition, pp. 610-614.
  18. Kita K. and Toru W. 2010 Thresholding of Color Characters in scene images Using k-means Clustering and Support Vector Machines, International Conference on Pattern Recognition.
  19. Yu Qiao and et al. 2007 Thresholding based on variance and intensity contrast, Pattern Recognition, 40, pp. 596-608.
  20. Abdel-Rahiem A. Hashem, Mohd Yamani and Abd El-Baset Ahmad. 2018 “Comparative study of different thresholding methods through their effects in characters localization in scene images”, Data & Knowledge Engineering, Vol. 117.
  21. https://www.mathworks.com/help/images/ref/regionpr, ops.html
  22. http://rrc.cvc.uab.es/?ch=2&com=evaluation&task=1&f=1&e=1
Index Terms

Computer Science
Information Sciences

Keywords

Thresholding techniques Characters detection Naïve Bayes classifier Connected-components analysis Bradley thresholding