TEXT LOCALIZATION IN IMAGES USING REVERSE THRESHOLDS ALGORITHM
DOI:
https://doi.org/10.11113/jt.v75.4980Keywords:
Text localization, color similarity, reverse thresholdAbstract
High color similarity between text pixels and background pixels is the major problem that causes failure during text localization. In this paper, a novel algorithm, Reverse Thresholds (RT) algorithm is proposed to localize text from the images with various text-background color similarities. First, a rough calculation is proposed to determine the similarity index for every text region. Then, by applying reverse operation, the best thresholds for each text region are calculated by its similarity index. To remove other uncertainties, self-generated images with the same text features but different similarity index are used as experiment dataset. Experiment result shows that RT algorithm has higher localizing strength which is able to localize text in a wider range of similarity index.
References
Li Sun, Guizhong Liu, Xueming Qian, Danping Guo. 2009. A Novel Text Detection and Localization Method Based on Corner Response. Multimedia and Expo, 2009. ICME 2009. IEEE International Conference on. 28 June– 3 July 2009. 390-393.
Sushma, J., Padmaja, M. 2009. Text Detection in Color Images. Intelligent Agent & Multi-Agent Systems, 2009. IAMA 2009. International Conference on. 22-24 July 2009. 1-6.
Quan Meng, Yonghong Song. 2012. Text Detection in Natural Scenes with Salient Region. Document Analysis Systems (DAS), 2012 10th IAPR International Workshop on. 27-29 March 2012. 384-388.
Emmanouilidis, C., Batsalas, C., Papamarkos, N. 2009. Development and Evaluation of Text Localization Techniques Based on Structural Texture Features and Neural Classifiers. Document Analysis and Recognition, 2009. ICDAR '09. 10th International Conference on. 26-29 July 2009. 1270- 1274.
Angadi, S. A., Kodabagi, M. M. 2010. Text Region Extraction from Low Resolution Natural Scene Images Using Texture Features. Advance Computing Conference (IACC), 2010 IEEE 2nd International. 19-20 Feb. 2010. 121-128.
Li, Z., Liu, G., Qian, X., Guo, D., Jiang, H. 2011. Effective and Efficient Video Text Extraction Using Key Text Points. Image Processing, IET. 5(8): 671-683.
Shivananda, N., Nagabhushan, P. 2009. Separation of Foreground Text from Complex Background in Color Document Images. Advances in Pattern Recognition, 2009. ICAPR '09. Seventh International Conference on. 4-6 Feb. 2009. 306-309.
Dinh, T. N., J. Park, G. Lee. 2010. Text localization using Image Cues and Text Line Information. Image Processing (ICIP), 2010 17th IEEE International Conference on. 26-29 Sept. 2010. 2261-2264.
Lelore, T.; Bouchara, F. 2011. Super-Resolved Binarization of Text Based on the FAIR Algorithm. Document Analysis and Recognition (ICDAR), 2011 International Conference on. 18-21 Sept. 2011.839-843.
Dempster, A. P., Laird, N. M., & Rubin, D. B. 1977. Maximum Likelihood from Incomplete Data via the Em Algorithm. J. of the Royal Statistical Society B. 39(1): 1-38.
Liu, X., W. Wang. 2012. Robustly Extracting Captions in Videos Based on Stroke-Like Edges and Spatio-Temporal Analysis. Multimedia, IEEE Transactions on. 14(2): 482-489.
Yi, C., Ying Li Tian. 2012. Localizing Text in Scene Images by Boundary Clustering, Stroke Segmentation, and String Fragment Classification. Image Processing. IEEE Transactions on. 21(9): 4256-4268.
Liu, J., S. Zhang, H. Li, W. Yang. 2010. A Novel Method For Flash Character Localization. Audio Language and Image Processing (ICALIP), 2010 International Conference on. 23-25 Nov. 2010. 811-814.
Yin, X., Yin, X. C., Hao, H. W., Iqbal, K. 2012. Effective Text Localization in Natural Scene Images with MSER, Geometry-Based Grouping and AdaBoost. Pattern Recognition (ICPR), 2012 21st International Conference on. 11-15 Nov. 2012. 725-728.
Pillai, A. V., Balakrishnan, A. A., Simon, R. A., Johnson, R. C., Padmagireesan, S. 2013. Detection and Localization of Texts from Natural Scene Images Using Scale Space and Morphological Operations. Circuits, Power and Computing Technologies (ICCPCT), 2013 International Conference on. 20-21 March 2013. 880-885.
Downloads
Published
Issue
Section
License
Copyright of articles that appear in Jurnal Teknologi belongs exclusively to Penerbit Universiti Teknologi Malaysia (Penerbit UTM Press). This copyright covers the rights to reproduce the article, including reprints, electronic reproductions, or any other reproductions of similar nature.
