In this paper, we propose a novel method to enhance the OCR (Optical Character Recognition) readability of public signboards captured by smart-phone cameras—both outdoors and indoors, and subject to various lighting conditions. A distinct feature of our technique is the detection of these signs in the HSV (Hue, Saturation and Value) color space, done in order to filter out the signboard from the background, and correctly interpret the textual details of each signboard. This is then binarized using a thresholding technique that is optimized for text printed on contrasting backgrounds, and passed through the Tesseract engine to detect individual characters. We test out our technique on a dataset of over 200 images taken in and around the campus of our college, and are successful in attaining better OCR results in comparison to traditional methods. Further, we suggest the utilization of a method to automatically assign ROIs (Regions Of Interest) to detected signboards, for better recognition of textual information.
References
[1]
Koistinen, M., Kettunen, K. and Pääkkönen, T. (2017) Improving Optical Character Recognition of Finnish Historical Newspapers with a Combination of Fraktur& Antiqua Models and Image Preprocessing. Proceedings of the 21st Nordic Conference on Computational Linguistics, NoDaLiDa, Gothenburg, Sweden, May 2017, 277-283.
[2]
Lefevere, F. and Saric, M. (2009) Detection of Grooves in Scanned Images, Assigned to Google. US Patent Number 7508978B1, 24 March 2009.
[3]
Kaehler, A. and Bradski, G. (2016) Learning OpenCV 3: Computer Vision in C++ with the OpenCV Library. O’Reilly Media, 1-2.
[4]
Kasar, T., Kumar, J. and Ramakrishnan, A.G. (2007) Font and Background Color Independent Text Binarization. Second International Workshop on Camera-Based Document Analysis and Recognition on Camera-Based Document Analysis and Recognition, 3-9.
[5]
Canny, J. (1986) A Computational Approach to Edge Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 8, 679-698. https://doi.org/10.1109/TPAMI.1986.4767851
[6]
Sobel, I. and Feldman, G. (1968) A 3x3 Isotropic Gradient Operator for Image Processing. At the Stanford Artificial Intelligence Project (SAIL).
[7]
Tektronix, Inc. (1991) Display-Based Color System. US Patent Number 4,985,853, January 1991.
[8]
Schwarz, M.W., Cowan, W.B. and Beatty, J.C. (1987) An Experimental Comparison of RGB, YIQ, LAB, HSV, and Opponent Color Models. ACM Transactions on Graphics (TOG), 6, 123-158. https://doi.org/10.1145/31336.31338
[9]
Rice, MS.V., Jenkins, F.R. and Nartker, T.A. (1995) The HP Research Protoype. The Fourth Annual Test of OCR Accuracy, Technical Report 95-03, Information Science Research Institute, University of Nevada, Las Vegas.
[10]
Liu, C., Lu, X., Ji, S. and Geng, W. (2014) A Fog Level Detection Method Based on Image HSV Color Histogram. 2014 IEEE International Conference on Progress in Informatics and Computing, Shanghai, 373-377. https://doi.org/10.1109/PIC.2014.6972360
[11]
Zheng, X.X., et al. (2016) RGB and HSV Quantitative Analysis of Autofluorescence Bronchoscopy Used for Characterization and Identification of Bronchopulmonary Cancer. Cancer Medicine, 5, 3023-3030. https://doi.org/10.1002/cam4.831