Visually impaired persons use Braille language as they can’t access digital or print media. Braille document is mostly embossed on Braille plate and are captured and processed using Optical Braille Recognition (OBR) system. OBR converts the Braille document into natural text. The quality of converted documents largely affected by the skew generated during the document scanning. Skew angle detection is one of the most important requirements in preprocessing stage of OBR. The introduction of skew is unavoidable in digitized document. Skew may get introduced while scanning the Braille plate due to human error. In this paper, two different algorithms based on Sobel edge detector, Gaussian filter method and another histogram and blob properties are used to estimate skew angle and its correction. The preprocessing, skew detection and skew correction algorithms are evaluated on MATLAB. The obtained results are compared to identify the efficient algorithm

Braille, Gaussian Filter, Histogram Equalization, image segmentation, Linear regression, Skew angle, OBR, preprocessing, sobel, skew detection

[1] H. Zhang, J. Li , "A Research on Paper-Mediated Braille Automatic Extraction Method," 2010 International Conference on Intelligent Computation Technology and Automation, Changsha, China, 2010, pp. 328-331. doi:10.1109/ ICICTA.2010.145.
[2] J. Subur, T. A. Sardjono and R. Mardiyanto, "Braille character recognition using find contour method," 2015 International Conference on Electrical Engineering and Informatics (ICEEI), Denpasar, 2015, pp. 699-703. doi: 10.1109/ ICEEI. 2015. 7352588.
[3] J. Mennens, L. Van Tichelen, G. Francois and J. J. Engelen, "Optical recognition of Braille writing using standard equipment," in IEEE Transactions on Rehabilitation Engineering, vol. 2, no. 4, pp. 207-212, Dec 1994. doi: 10.1109/86.340878.
[4] Jie Li and Xiaoguang Yan, "Optical Braille character recognition with Support-Vector Machine classifier," 2010 International Conference on Computer Application and System Modeling (ICCASM 2010), Taiyuan, 2010, pp. V12-219-V12-222.
doi: 10.1109/ICCASM.2010.5622245
[5] L. Nian-feng and W. Li-rong, "A kind of Braille paper automatic marking system," 2011 International Conference on Mechatronic Science, Electric Engineering and Computer (MEC), Jilin, 2011, pp. 664-667. doi: 10.1109/MEC.2011.6025553.
[6] M. Hanumanthappa and V. V. Murthy, "Optical Braille recognition and its correspondence in the conversion of Braille script to text — A literature review," 2016 International Conference on Computation System and Information Technology for Sustainable Solutions (CSITSS), Bangalore, 2016, pp. 297-301. doi: 10.1109/CSITSS.2016.7779374
[7] Padmavathi.S, Aishwarya.A.V, Iswaryah,. “Geometric Correction for Braille Document Images.”, 2016 International Conference on Pedagogic Advances in Computer Science (ICPACS-2016), Computer Science & Information Technology (CS & IT), Amrita School of Engineering, Amrita Vishwa Vidyapeetham, Coimbatore, India. (2016).
[8] T. Shreekanth and V. Udayashankara, "A two stage Braille Character segmentation approach for embossed double sided Hindi Devanagari Braille documents," 2014 International Conference on Contemporary Computing and Informatics (IC3I), Mysore, 2014, pp. 533-538.
doi: 10.1109/IC3I.2014.7019590.
[9] Wang Changjie, Nian Hua. "Algorithm of remote sensing image matching based on corner-point", 2017 Int ernat ional Workshop on Remote Sensing with Intelligent Processing (RSIP), 2017, doi:10.1109/RSIP.2017.79588