International Journal of Computer Applications (0975 – 8887) Volume 74– No.19, July 2013 Fig 8:Some example of container name extraction <strong>and</strong> segmentation 21
International Journal of Computer Applications (0975 – 8887) Volume 74– No.19, July 2013 4. COMPARISON WITH OTHER TEXT EXTRACTION TECHNIQUES To evaluate the performance there is a comparison with two existing algorithms [9] <strong>and</strong> [10].The first method has used a complicated method for finding inner,outer <strong>and</strong> inner-outer corners. The second procedure has extracted text by identify edge at different orientation i.e 0,45,90,135 degrees <strong>and</strong> grouping these strokes at different heights.So it is difficult to identify the edges at different orientation.To solve the problems Conneted Component Variance(CCV) has used. For finding a meaningfull word the isolated characters are grouped by dilation operation.The algorithm identifies each connected component <strong>and</strong> measures there properties.If the properties are not match with the properties in section 2.4 then it is symbol not character. 5. CONCLUSION In this paper,we present a algorithm which is suitable to extract the container name of different colors,sizes <strong>and</strong> alignment modes.The experiments with container images captured <strong>from</strong> the real port environment demonstrate the effectiveness of the proposed technique. Future work will focus on extracting container name <strong>from</strong> multiple images captured <strong>from</strong> the same container with one or multiple cameras during its moving.The container images are captured at the different positions or different time. 6. REFERENCES [1] K. Jain <strong>and</strong> B. Yu, “Document representation <strong>and</strong> its application to page decomposition,” IEEE Trans. Pattern Anal. Machine Intell., vol. 20, pp. 294–308, Mar. 1998. [2] J. Ohya, A. Shio, <strong>and</strong> S. Akamatsu, “Recognizing characters in scene images,” IEEE Trans. Pattern Anal. Machine Intell., vol. 16, pp. 215–220, Feb. 1994. [3] H. M. Suen <strong>and</strong> J. F.Wang, “Text string extraction <strong>from</strong> images of colorpriented documents,” Proc. Inst. Elect. Eng. Vis.,Image, Signal Process., vol. 143, no. 4, pp.210–216,1996. [4] Nobuyuki Otsu, A threshold selection method <strong>from</strong> graylevel histograms. IEEE Trans.Sys.,Man., Cyber 9(1):62- 66. [5] Y. K. Ham, M. S. Kang, H. K. Chung, <strong>and</strong> R. H. Park, “Recognition of raised characters for automatic classification of rubber tires,” Opt. Eng.,vol. 34, pp. 102– 108, Jan. 1995. [6] R. Lienhart, “Indexing <strong>and</strong> retrieval of digital video sequences based on automatic text recognition,” in Proc. ACM Int. Conf., Boston, MA, Nov.1996. [7] L. Wang <strong>and</strong> T. Pavlidis, “Direct gray-scale extraction of features for character recognition,” IEEE Trans. Pattern Anal. Machine Intell., vol.15, pp. 1053–1067, Oct. 1993. [8] Y. Zhong, K. Karu, <strong>and</strong> A. K. Jain, “Locating text in complex color images,” Pattern Recognit., vol. 28, no. 10, pp. 1523–1535,1995. [9] Jagath Samarab<strong>and</strong>u, Member, IEEE, <strong>and</strong> Xiaoqing Liu 2007 “An Edge-based Text Region Extraction Algorithm for Indoor Mobile Robot Navigation” ,International Journal of Signal Processing 3(4 )2007. [10] Yassin M. Y. Hasan <strong>and</strong> Lina J. Karam 2000 “Morphological Text Extraction <strong>from</strong> <strong>Images</strong>” IEEE Transaction on Image Processing vol. 9,no.11,Nov.2000 IJCA TM : www.ijcaonline.org 22