Abstract
The technology of mathematical expression identification and recognition extracts mathematical expressions in document images, and it has been studied for over a decade. Based on previous works, we develop an automatic recognition tool, named EqnEye, which leverages the OpenCV library to perform image processing and Tesseract tool to recognize mathematical symbols. We also apply correction methods before the recognition stage to improve the recognition accuracy. To improve the efficiency for processing images of high resolution, the parallel implementation of thresholding method on GPU is integrated into this work. Experimental results exhibit the success of our correction methods to enhance the accuracy and the slight improvement to the performance. In addition, porting the recognition tool to handy devices can produce more value-added applications.
Similar content being viewed by others
References
OpenCV, http://opencv.org/
tesseract-ocr, https://github.com/tesseract-ocr
Farber R (2011) CUDA application design and development. Morgan Kaufmann, Waltham, MA
Sandes E, de Melo A (2013) Retrieving Smith-Waterman alignments with optimizations for megabase biological sequences using GPU. IEEE Trans Parallel Distrib Syst 24(5):1009–1021
Zhu X, Li K, Salah A, Shi L, Li K (2015) Parallel implementation of MAFFT on CUDA-enabled graphics hardware. IEEE/ACM Trans Comput Biol Bioinform 12(1):205–218
NVIDIA CUDA TOOLKIT 7.5, http://developer.download.nvidia.com/
Chan K-F, Yeung D-Y (2000) Mathematical expression recognition: a survey. Int J Doc Anal Recognit 3(1):3–15
Zanibbi R, Blostein D, Cordy JR (2002) Recognizing mathematical expressions using tree transformation. IEEE Trans Pattern Anal Mach Intell 24(11):1455–1467
Raja A et al (2006) Towards a parser for mathematical formula recognition. In: Mathematical knowledge management, LANI, vol 4108, pp 139–151
Álvaro F, Sánchez JA (2010) Comparing several techniques for offline recognition of printed mathematical symbols. In: 20th International Conference on Pattern Recognition (ICPR), Istanbul
Guo Y-S, Huang L, Liu C-P(2007) A new approach for understanding of structure of printed mathematical expression. In: International Conference on Machine Learning and Cybernetics, Hong Kong
Lin X et al (2013) A text line detection method for mathematical formula recognition. In: 12th International Conference on Document Analysis and Recognition (ICDAR), Washington, DC
Chu W-T, Liu F (2013) Mathematical formula detection in heterogeneous document images. In: Conference on Technologies and Applications of Artificial Intelligence (TAAI), Taipei
Kumar PP, Agarwal A, Bhagvati C (2014) A knowledge-based design for structural analysis of printed mathematical expressions. In: 8th International Workshop on Multi-disciplinary Trends in Artificial Intelligence, LNCS, vol. 8875, pp 112–123
Sezgin M, Sankur B (2004) Survey over image thresholding techniques and quantitative performance evaluation. J Electron Imaging 13(1):146–168
Parker JR (2010) Algorithms for image processing and computer vision, 2nd edn. Wiley, Hoboken, NJ
Singh BM, Sharma R, Mittal A, Ghosh D (2010) Parallel implementation of Otsu’s binarization approach on GPU. Int J Comput Appl 32(2):16–21
Li S, Shen Q, Sun J (2007) Skew detection using wavelet decomposition and projection profile analysis. Pattern Recognit Lett 28:555–562
Acknowledgments
This work is partially supported by the Ministry of Science and Technology under contract number MOST 104-2633-S-035-001.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Lin, YC., Wang, CY. & Zeng, JY. A case study on mathematical expression recognition to GPU. J Supercomput 73, 3333–3343 (2017). https://doi.org/10.1007/s11227-016-1819-3
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11227-016-1819-3