Abstract
Unlike a standard text document, a STEM document not
only consists of text information but different components such as tables, figures, captions, mathematical equations etc. This paper presents a novel technique to detect mathematical equations in PDF documents and convert those equations into a more accessible format such as 
. We use visual features of the document to detect the mathematical equations using object detection and subsequently apply heuristics to the generated bounding boxes to precisely cover the complete equation. These detections are passed to a tool called Maxtract which will rewrite the equations in 
.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Baker, J.B., Sexton, A.P., Sorge, V.: A linear grammar approach to mathematical formula recognition from PDF. In: Carette, J., Dixon, L., Coen, C.S., Watt, S.M. (eds.) CICM 2009. LNCS (LNAI), vol. 5625, pp. 201–216. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-02614-0_19
Baker, J.B., Sexton, A.P., Sorge, V.: MaxTract: Converting PDF to LaTeX, MathML and Text. In: Jeuring, J., et al. (eds.) CICM 2012. LNCS (LNAI), vol. 7362, pp. 422–426. Springer, Heidelberg (2012). https://doi.org/10.1007/978-3-642-31374-5_29
Bochkovskiy, A., Wang, C.Y., Liao, H.Y.M.: YOLOv4: optimal speed and accuracy of object detection. arXiv preprint arXiv:2004.10934 (2020)
Gao, L., Yi, X., Liao, Y., Jiang, Z., Yan, Z., Tang, Z.: A deep learning-based formula detection method for PDF documents. In: 14th International Conference on Document Analysis and Recognition, vol. 1, pp. 553–558. IEEE (2017)
Inoue, K., Miyazaki, R., Suzuki, M.: Optical recognition of printed mathematical documents. In: Proceedings of the Third Asian Technology Conference in Mathematics, pp. 280–289 (1998)
Kacem, A., Belaïd, A., Ahmed, M.B.: Automatic extraction of printed mathematical formulas using fuzzy logic and propagation of context. Int. J. Doc. Anal. Recogn. 4(2), 97–108 (2001)
Mali, P., Kukkadapu, P., Mahdavi, M., Zanibbi, R.: ScanSSD: scanning single shot detector for mathematical formulas in PDF document images. arXiv preprint arXiv:2003.08005 (2020)
Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. Adv. Neural Inf. Process. Syst. 28, 91–99 (2015)
Sorge, V., Bansal, A., Jadhav, N.M., Garg, H., Verma, A., Balakrishnan, M.: Towards generating web-accessible stem documents from PDF. In: Proceedings of the 17th International Web for All Conference, pp. 1–5 (2020)
Suzuki, M., Tamari, F., Fukuda, R., Uchida, S., Kanahori, T.: INFTY: an integrated OCR system for mathematical documents. In: Proceedings of the 2003 ACM Symposium on Document Engineering, pp. 95–104 (2003)
Tesseract-Ocr: https://github.com/tesseract-ocr/tesseract
Zhong, Y., et al.: 1st place solution for ICDAR 2021 competition on mathematical formula detection. arXiv preprint arXiv:2107.05534 (2021)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 Springer Nature Switzerland AG
About this paper
Cite this paper
Juyal, S., Sharma, S., Jadhav, N., Sorge, V., Balakrishnan, M. (2022). Making Equations Accessible in Scientific Documents. In: Miesenberger, K., Kouroupetroglou, G., Mavrou, K., Manduchi, R., Covarrubias Rodriguez, M., Penáz, P. (eds) Computers Helping People with Special Needs. ICCHP-AAATE 2022. Lecture Notes in Computer Science, vol 13341. Springer, Cham. https://doi.org/10.1007/978-3-031-08648-9_4
Download citation
DOI: https://doi.org/10.1007/978-3-031-08648-9_4
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08647-2
Online ISBN: 978-3-031-08648-9
eBook Packages: Computer ScienceComputer Science (R0)