Abstract
Document Segmentation is a process that aims to filter documents while identifying certain regions of interest. Generally, the regions of interest include texts, graphics (image occupied regions) and the background. This paper presents a novel top-bottom approach to perform document segmentation using texture features that are extracted from the specified/selected documents. A mask of suitable size is used to summarize textural features, and statistical parameters are captured as blocks in document images. Four textural features that are extracted from masks using the gray level co-occurrence matrix (glcm) include entropy, contrast, energy and homogeneity. Furthermore, two statistical parameters extracted from corresponding masks are the modal and median pixel values. The extracted attributes allow the classification of each mask or block as text, graphics, and background. A feedforward network is trained on the 6 extracted attributes, using documents obtained from a public database ; an error rate of 15.77 % is achieved. Furthermore, it is shown that this novel approach produces promising performance in segmenting documents and is expected to be significantly efficient for content-based information retrieval systems. Detection of duplicate documents within large databases is another potential area of application.
Similar content being viewed by others
References
Najafabadi MN, Villanustre F, Khoshgoftaar TM, Seliya N, Wald1 R, Muharemagic E (2015) Deep learning applications and challenges in big data analytics. J Big Data 2(1):1–21. doi:10.1186/s40537-014-0007-7
Kay K, Naselaris T, Prenger R, Gallant J (2008) Identifying natural images from human brain activity. Nature 452:352–355
McMains S, Kastner S (2011) Interactions of top-down and bottom-up mechanisms in human visual cortex. J Neurosci 31(2):587–597. doi:10.1523/JNEUROSCI.3766-10.2011
Rauss K, Pourtois G (2013) What is bottom-up and what is top-down in predictive coding Front Psychol 4:276. doi:10.3389/fpsyg.2013.00276
Patel GA, Sathian K (2000) Visual search: bottom-up or top-down Front Biosci 5:D169–193
Kruatrachue B, Suthaphan P (2001) A fast and efficient method for document segmentation for OCR, TENCON.. In: Proceedings of IEEE Region 10 International Conference on Electrical and Electronic Technology, 19-22 Aug 2001, Vol. 1, 81 - 383 10.1109/TENCON.2001.949618
Zagoris K, Chatzichristofis SA, Papamarkos N (2011) Text localization using standard deviation analysis of structure elements and support vector machines. EURASIP J Adv Signal Process 1(1–12). doi:10.1186/1687-6180-2011-47
Amin A, Shiu R (2001) Int J Image Grap 01:345. doi:10.1142/S0219467801000219
Drivas D, Amin A Page segmentation and classification utilising a bottom-up approach. In: Proceedings of the Third International Conference on Document Analysis and Recognition 14-16 Aug 1995, Montreal, Que., vol. 2, 610 - 614. doi:10.1109/ICDAR.1995.601970
hashemi SY, Hesarlo PS (2014) Persian/Arabic document segmentation based on hybrid approach. Int J Comput Sci Appl (IJCSA) 4(1):23–34. doi:10.5121/ijcsa.2014.4103
Saeedi J, Safabakhsh R, Mozaffari S Document Image Segmentation Using Fuzzy Classifier and the Dual-Tree DWT, 14th International CSI conference (CSICC2009), July 1-2, 2009, Tehran, Iran, 385-390
Kumar MR, Shetty NN, Pragathi BP Text Line Segmentation of Handwritten Documents using Clustering Method based on Thresholding Approach, International Journal of Computer Applications (0975–8878) on National Conference on Advanced Computing and Communications - NCACC, April 2012, India, 9-12
Nazemi A, Murray I, Mc Meekin DA (2014) Practical Segmentation Methods for Logical and Geometric Layout Analysis to Improve Scanned PDF Accessibility to Vision Impaired. Int J Signal Process Image Process Pattern Recogn 7(4):23–36
Lin M-W, Tapamo J-R, Ndovie B (2006) A Texture-based Method for Document Segmentation and Classification, South African Computer Journal Joint Special Issue — Advances in end-user data mining techniques, 36, 48–56
Wang H Automatic character location and segmentation in color scene images. In: Proceedings 11th International Conference on Image Analysis and Processing, 26-28 Sep 2001, Palermo, 2-7. doi:10.1109/ICIAP.2001.956977
Jing Z, Wei D, Youhui Z An Algorithm for Scanned Document Image Segmentation Based on Voronoi Diagram, 2012 International Conference on Computer Science and Electronics Engineering (ICCSEE), 23-25 March 2012, Hangzhou, 156 – 159
Vil’kin AM, Safonov IV, Egorova MA (2013) Algorithm for segmentation of documents based on texture features. Pattern Recognit Image Anal 23(1):153–159
Likforman-Sulem L, Zahour A, Taconet B (2007) Text Line Segmentation of Historical Documents: a Survey. Int J Doc Anal Recognit (IJDAR) 9(2–4):123–138
Thanh ND, Binh VD, Mi NTT, Giang NT A Robust Document Skew Estimation Algorithm Using Mathematical Morphology. In: 19th IEEE International Conference on Tools with Artificial Intelligence, 29-31 Oct. 2007, Patras, 496 - 503. doi:10.1109/ICTAI.2007.124
Das AK, Chanda B (2001) A fast algorithm for skew detection of document images using morphology. Int J Doc Anal Recognit 4(2):109–114
Vilkin A, Safonov I (2012) NRNU MEPhI: Newspaper and magazine images segmentation dataset Data Set. Retrieved from: http://archive.ics.uci.edu/ml/datasets/Newspaper+and+magazine+images+segmentation+dataset%23
Soujanya P, Koppula KV, Gaddam K, Sruthi P (2010) Comparative Study of Text Line Segmentation Algorithms on Low Quality Documents. Special Issue of Int J Comput Sci Inform 2(1-2):2231–5292
Arsenault E, Yoonessi A, Baker C Jr (2011) Higher order texture statistics impair contrast boundary segmentation. J Vis September 11:14. doi:10.1167/11.10.14
Shinde B, Mhaske D, Dani AR (2012) Study of Noise Detection and Noise Removal Techniques in Medical Images. I.J. Image, Graphics and Signal Processing 2:51–60. doi:10.5815/ijigsp.2012.02.08
Ma HR, Cheng XW (2014) Automatic Image Segmentation with PCNN Algorithm Based on Grayscale Correlation. Int J Signal Process, Image Process Pattern Recogn 7(5):249–258. doi:10.14257/ijsip.2014.7.5.22
LeCun Y, et al. (1998) Gradient-Based Learning Applied to Document Recognition, Proceedings of the IEEE, 1–46
Chaugule A, Mali SN (2014) Evaluation of Texture and Shape Features for Classification of Four Paddy Varieties Journal of Engineering, Article ID 617263, 1–8. doi:10.1155/2014/617263 10.1155/2014/617263
Abdalla1 AMM, Dress S, Zaki N (2011) Detection of Masses in Digital Mammogram Using Second Order Statistics and Artificial Neural Network. Int Electron J Comput Sci Inf Technol (IJCSIT) 3(3):176–186. doi:10.5121/ijcsit.2011.3312
Sethuraman TR, Chettiar G (2007) Artificial Neural Network in Marine Traffic Modelling. Res J Appl Sci 2:1043– 1047
Krogh A (2008) What are artificial neural networks Nat Biotechnol 26:195–197. doi:10.1038/nbt1386
Goyal S, Goyal GK (2012) Potential of artificial neural network technology for predicting shelf life of processed cheese. J Knowl Manag, Econ Inf Technol 4:33–39
Jafara R, Shahroura I, Juranb I (2010) Application of Artificial Neural Networks (ANN) to model the failure of urban water mains. Math Comput Model 51(9–10):1170–1180. doi:10.1016/j.mcm.2009.12.033
Zhang G, Patuwo BE, Hu MY (1988) Forecasting with artificial neural networks: The state of the art. Int J Forecast 14:35–62
Basheera IA, Hajmeerb M (2000) Artificial neural networks: fundamentals, computing, design, and application. J Microbiol Methods 43:3–31
Oyedotun OK, Tackie SN, Olaniyi EO, Khashman A (2015) Data Mining of Students’ Performance: Turkish Students as A Case Study. I.J. Intell Syst Appl 09:20–27. doi:10.5815/ijisa.2015.09.03
Jwo D-J, Chin K-P (2002) Applying Back-propagation Neural Networks to GDOP Approximation. J Navig 55(1):97–108. doi:10.1017/S0373463301001606
Acknowledgments
The authors wish to thank Assist. Prof. Dr. Pinar Akpinar, for proofreading this manuscript, and suggesting clearer re-expressions of ideas within the work.
Author information
Authors and Affiliations
Corresponding author
Appendix
Appendix
Rights and permissions
About this article
Cite this article
Oyedotun, O.K., Khashman, A. Document segmentation using textural features summarization and feedforward neural network. Appl Intell 45, 198–212 (2016). https://doi.org/10.1007/s10489-015-0753-z
Published:
Issue Date:
DOI: https://doi.org/10.1007/s10489-015-0753-z