International Journal of Contents

The Korea Contents Association (한국콘텐츠학회)
권호 표지
DOI QR코드

DOI QR Code

Title Extraction from Book Cover Images Using Histogram of Oriented Gradients and Color Information

  • Do, Yen (School of Electronics & Computer Engineering, Chonnam National University) ;
  • Kim, Soo Hyung (School of Electronics & Computer Engineering, Chonnam National University) ;
  • Na, In Seop (School of Electronics & Computer Engineering, Chonnam National University)
  • Received : 2012.07.25
  • Accepted : 2012.11.16
  • Published : 2012.12.28
Download PDF
⟨ Previous Next ⟩

Abstract

In this paper, we present a technique to extract the title areas from book cover images. A typical book cover image may contain text, pictures, diagrams as well as complex and irregular background. In addition, the high variability of character features such as thickness, font, position, background and tilt of the text also makes the text extraction task more complicated. Therefore, we propose a two steps efficient method that uses Histogram of Oriented Gradients and color information to find the title areas. Firstly, text localization is carried out to find the title candidates. Finally, refinement process is performed to find the sufficient components of title areas. To obtain the best result, we also use other constraints about the size, ratio between the length and width of the title. We achieve encouraging results of extracted title regions from book cover images which prove the advantages and efficiency of the proposed method.

Keywords

References

  1. Do Yen, S. H. Kim, S. C. Park, Ha Le, Y. J. Chen, S. H. Jeong, I. S. Na (2012), "Generation of Training Database Using a Noise Model for OCR Systems", in The 6th International Conference on Ubiquitous Information Management and Communication, Kuala Lumpur, 2012.(CD-Pub.)
  2. Ha Le, S. H. Kim, S. C. Park, Do Yen, Y.J. Chen, S. H. Jeong, I. S. Na (2012), " Automatic Generation of Database to Train New Fonts for OCR Systems" in The 2012 International Workshop on Advanced Image Technology IWAIT2012, Ho Chi Minh City, 2012. pp. 178-182.
  3. Kee chul Jung, K. I. Kim, Anil K. Jain.(2004),"Text Information Extraction in Images and Video: A Survey", Pattern Recognition, Vol. 37 No.5, pp. 977-997. https://doi.org/10.1016/j.patcog.2003.10.012
  4. C. J. Park, K. A. Moon, O. W. Geun, and H. M. Choi(2000), "An efficient extraction of character string positions using morphological operator", in Proc. IEEE Int. Conf. Systems, Man, Cybernetics, 2000, vol. 3, pp. 1616-1620.
  5. Z. Yu, K. Karu, and A. K. Jain (1995),"Locating text in complex color images," in Proc. 3rd Int. Conf. Document Analysis and Recognition,1995, pp. 146-149.
  6. D. Chen, H. Bourlard, and J. P. Thiran (2001), "Text identification in complex background using SVM," in Proc. IEEE Computer Soc.Conf. Computer Vision and Pattern Recognition, 2001, pp. 621-626.
  7. Yassin M. Y. Hasan and Lina J. Karam. (2000),"Morphological Text Extraction from Images", IEEE Transaction on Image Processing, Vol. 9, No. 11, pp.1978-1983. https://doi.org/10.1109/83.877220
  8. M. Chen and X. Ding(2000),"Analysis, understanding and representation of Chinese newspaper with complex layout," in Proc. 7th IEEE Int. Conf. Image Processing, Vancouver, 2000, BC, Canada, vol. 2, pp. 590-593.
  9. A. Antonacopoulos, B. Gatos, and D. Bridson (2005),"ICDAR 2005 page segmentation competition," in Proc. ICDAR,2005, Seoul, Korea, pp.75-80.
  10. A. K. Jain and B. Yu (1998), "Document representation and its application to page decomposition", IEEE Trans. Pattern Anal. Mach. Intell., Vol. 20, No. 3, pp. 294-308. https://doi.org/10.1109/34.667886
  11. Navneet Dalal, Bill Triggs, "Histograms of Oriented Gradients for Human Detection". Computer Vision and Pattern Recognition, 886-893, 2005.
  12. B. Epshtein, E. Ofek, and Y. Wexler, "Detecting Text in Natural Scenes with Stroke Width Transform", in Proc. CVPR, 2010, pp.2963-2970.
  13. Nguyen Noi Bai, Kim Nam and Youngjun Song "Extracting curved text lines using the chain composition and the expanded grouping method", in Korea information processing society, vol. 14-B, No.6, pp.453- 460, Oct. 2007. https://doi.org/10.3745/KIPSTB.2007.14-B.6.453