{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T08:06:26Z","timestamp":1759133186815,"version":"3.40.4"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2013,12,21]],"date-time":"2013-12-21T00:00:00Z","timestamp":1387584000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2014,9]]},"DOI":"10.1007\/s10032-013-0216-1","type":"journal-article","created":{"date-parts":[[2013,12,20]],"date-time":"2013-12-20T19:14:29Z","timestamp":1387566869000},"page":"239-255","source":"Crossref","is-referenced-by-count":23,"title":["Mathematical formula identification and performance evaluation in PDF documents"],"prefix":"10.1007","volume":"17","author":[{"given":"Xiaoyan","family":"Lin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangcai","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Josef","family":"Baker","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Volker","family":"Sorge","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2013,12,21]]},"reference":[{"key":"216_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, R.H.: Syntax-directed recognition of hand-printed two-dimensional mathematics. PhD thesis, Harvard University, Cambridge, Massachusetts (1968)","DOI":"10.1016\/B978-0-12-395608-8.50048-7"},{"key":"216_CR2","doi-asserted-by":"crossref","unstructured":"Lin, X., Gao, L., Tang, Z., Lin, X., Hu, X.: Mathematical formula identification in PDF documents. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 1419\u20131423. IEEE (2011)","DOI":"10.1109\/ICDAR.2011.285"},{"key":"216_CR3","doi-asserted-by":"crossref","unstructured":"Lin, X., Gao, L., Tang, Z., Hu, X., Lin, X.: Identification of embedded mathematical formulas in PDF documents using SVM. In: Document Recognition and Retrieval (DRR) XIX, pp. 8297 0D 1\u20138 (2012)","DOI":"10.1117\/12.912445"},{"key":"216_CR4","doi-asserted-by":"crossref","unstructured":"Lin, X., Gao, L., Tang, Z., Lin, X., Hu, X.: Performance evaluation of mathematical formula identification. In: The 10th IAPR International Workshop on Document Analysis Systems (DAS), pp. 287\u2013291. IEEE (2012)","DOI":"10.1109\/DAS.2012.68"},{"key":"216_CR5","unstructured":"Adobe. PDF reference, 7th edition (2008)"},{"key":"216_CR6","doi-asserted-by":"crossref","unstructured":"Zanibbi, R., Blostein, D.: Recognition and retrieval of mathematical expressions. Int. J. Document Anal. Recognit. pp. 1\u201327 (2011)","DOI":"10.1117\/12.873312"},{"key":"216_CR7","unstructured":"Baker, J.B.: A linear grammar approach for the analysis of mathematical documents. PhD thesis, University of Birmingham (2012)"},{"key":"216_CR8","doi-asserted-by":"crossref","unstructured":"Rahman, F., Alam, H.: Conversion of PDF documents into HTML: a case study of document image analysis. In: Conference Record of the Thirty-Seventh Asilomar Conference on Signals, Systems and Computers, vol. 1, pp. 87\u201391. IEEE (2003)","DOI":"10.1109\/ACSSC.2003.1291873"},{"key":"216_CR9","doi-asserted-by":"crossref","unstructured":"Baker, J.B., Sexton, A.P., Sorge, V.: A linear grammar approach to mathematical formula recognition from PDF. In: Proceedings of the 8th International Conference on Mathematical Knowledge Management, vol. 5625 of LNAI, pp. 201\u2013216. Springer (2009)","DOI":"10.1007\/978-3-642-02614-0_19"},{"issue":"1","key":"216_CR10","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1006\/jvci.1996.0002","volume":"7","author":"RJ Fateman","year":"1996","unstructured":"Fateman, R.J., Tokuyasu, T., Berman, B.P., Mitchell, N.: Optical character recognition and parsing of typeset mathematics. J. Vis. Commun. Image Represent. 7(1), 2\u201315 (1996)","journal-title":"J. Vis. Commun. Image Represent."},{"issue":"3","key":"216_CR11","doi-asserted-by":"crossref","first-page":"289","DOI":"10.1016\/S0167-8655(97)87048-1","volume":"18","author":"HJ Lee","year":"1997","unstructured":"Lee, H.J., Wang, J.S.: Design of a mathematical expression understanding system. Pattern Recognit. Lett. 18(3), 289\u2013298 (1997)","journal-title":"Pattern Recognit. Lett."},{"key":"216_CR12","doi-asserted-by":"crossref","unstructured":"Toumit, J.Y., Garcia-Salicetti, S., Emptoz, H.: A hierarchical and recursive model of mathematical expressions for automatic reading of mathematical documents. In: Proceedings of the Fifth International Conference on Document Analysis and Recognition (ICDAR), pp. 119\u2013122. IEEE (1999)","DOI":"10.1109\/ICDAR.1999.791739"},{"key":"216_CR13","doi-asserted-by":"crossref","unstructured":"Garain, U., Chaudhuri, B.B.: A syntactic approach for processing mathematical expressions in printed documents. In: Proceedings of the 15th International Conference on Pattern Recognition (ICPR), vol. 4, pp. 523\u2013526. IEEE (2000)","DOI":"10.1109\/ICPR.2000.902972"},{"key":"216_CR14","unstructured":"Kacem, A., Bela\u00efd, A., Ben Ahmed, M.: Automatic extraction of printed mathematical formulas using fuzzy logic and propagation of context. Int. J. Document Anal. Recognit. 4(2), 97\u2013108 (2001)"},{"key":"216_CR15","unstructured":"Inoue, K., Miyazaki, R., Suzuki, M.: Optical recognition of printed mathematical documents. In: Proceedings of the Third Asian Technology Conference on Mathematics, pp. 280\u2013289 (1998)"},{"key":"216_CR16","doi-asserted-by":"crossref","unstructured":"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\u2013104. ACM (2003)","DOI":"10.1145\/958220.958239"},{"key":"216_CR17","unstructured":"Baker, J.B., Sexton, A.P., Sorge, V.: Towards reverse engineering of PDF documents. In: Towards a Digital Mathematics Library, pp. 65\u201375. Masaryk University Press (2011)"},{"key":"216_CR18","doi-asserted-by":"crossref","unstructured":"Lee, H.J., Wang, J.S.: Design of a mathematical expression recognition system. In: Proceedings of the Third International Conference on Document Analysis and Recognition (ICDAR), vol. 2, pp. 1084\u20131087. IEEE (1995)","DOI":"10.1109\/ICDAR.1995.602097"},{"key":"216_CR19","doi-asserted-by":"crossref","unstructured":"Chowdhury, S.P., Mandal, S., Das, A.K., Chanda, B.: Automated segmentation of math-zones from document images. In: 7th International Conference on Document Analysis and Recognition (ICDAR), vol. 2, pp. 755\u2013759 (2003)","DOI":"10.1109\/ICDAR.2003.1227763"},{"key":"216_CR20","doi-asserted-by":"crossref","unstructured":"Chang, T.Y., Takiguchi, Y., Okada, M.: Physical structure segmentation with projection profile for mathematic formulae and graphics in academic paper images. In: The Ninth International Conference on Document Analysis and Recognition (ICDAR), vol. 2, pp. 1193\u20131197. IEEE (2007)","DOI":"10.1109\/ICDAR.2007.4377104"},{"key":"216_CR21","doi-asserted-by":"crossref","unstructured":"Garain, U., Chaudhuri, B.B., Chaudhuri, A.R.: Identification of embedded mathematical expressions in scanned documents. In: Proceedings of the 17th International Conference on Pattern Recognition (ICPR), vol. 1, pp. 384\u2013387. IEEE (2004)","DOI":"10.1109\/ICPR.2004.1334132"},{"key":"216_CR22","doi-asserted-by":"crossref","unstructured":"Garain, U.: Identification of mathematical expressions in document images. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 1340\u20131344. IEEE (2009)","DOI":"10.1109\/ICDAR.2009.203"},{"key":"216_CR23","unstructured":"Jin, J., Han, X., Wang, Q.: Mathematical formulas extraction. In: International Conference on Document Analysis and Recognition (ICDAR), pp. 1138\u20131141. IEEE (2003)"},{"key":"216_CR24","doi-asserted-by":"crossref","unstructured":"Drake, D.M., Baird, H.S.: Distinguishing mathematics notation from English text using computational geometry. In: Proceedings. Eighth International Conference on Document Analysis and Recognition (ICDAR), pp. 1270\u20131274. IEEE (2005)","DOI":"10.1109\/ICDAR.2005.89"},{"key":"216_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Y., Bai, K., Gao, L.: An efficient pre-processing method to identify logical components from PDF documents. Adv. Knowl. Discov. Data Min. pp. 500\u2013511 (2011)","DOI":"10.1007\/978-3-642-20841-6_41"},{"issue":"4","key":"216_CR26","doi-asserted-by":"crossref","first-page":"211","DOI":"10.1007\/s10032-005-0142-y","volume":"7","author":"S Uchida","year":"2005","unstructured":"Uchida, S., Nomura, A., Suzuki, M.: Quantitative analysis of mathematical documents. Int. J. Document Anal. Recognit. 7(4), 211\u2013218 (2005)","journal-title":"Int. J. Document Anal. Recognit."},{"key":"216_CR27","unstructured":"Phillips, I., Chanda, B., Haralick, R: University of Washington UW-III English technical document image database (1996)"},{"key":"216_CR28","unstructured":"http:\/\/ntcir-math.nii.ac.jp\/ (2013)"},{"key":"216_CR29","doi-asserted-by":"crossref","unstructured":"Gao, L., Tang, Z., Lin, X., Qiu, R.: Comprehensive global typography extraction system for electronic book documents. In: The Eighth IAPR International Workshop on Document Analysis Systems (DAS), pp. 615\u2013621. IEEE (2008)","DOI":"10.1109\/DAS.2008.30"},{"key":"216_CR30","unstructured":"http:\/\/www.cs.cmu.edu\/~quake\/triangle.html (2013)"},{"key":"216_CR31","unstructured":"Bishop, C.M.: Pattern Recognition and Machine Learning, vol. 4. Springer, New York (2006)"},{"key":"216_CR32","unstructured":"Chawla, N.V., Japkowicz, N., Kotcz, A.: Editorial: special issue on learning from imbalanced data sets. ACM SIGKDD Explor. Newsl. 6(1), 1\u20136 (2004)"},{"key":"216_CR33","unstructured":"Batista, G.E., Prati, R.C., Monard, M.C.: A study of the behavior of several methods for balancing machine learning training data. ACM SIGKDD Explor. Newsl. 6(1), 20\u201329 (2004)"},{"key":"216_CR34","unstructured":"Chawla, N.V., Bowyer, K.W., Hall, L.O., Kegelmeyer, W.P.: Smote: synthetic minority over-sampling technique. J. Artif. Intell. Res. 16, 321\u2013357 (2002)"},{"key":"216_CR35","doi-asserted-by":"crossref","unstructured":"Kim, S.H., Jeong, C.B., Kwag, H.K., Suen, C.Y.: Word segmentation of printed text lines based on gap clustering and special symbol detection. In: Proceedings. 16th International Conference on Pattern Recognition (ICPR), vol. 2, pp. 320\u2013323. IEEE (2002)","DOI":"10.1109\/ICPR.2002.1048304"},{"issue":"3","key":"216_CR36","first-page":"27","volume":"2","author":"CC Chang","year":"2011","unstructured":"Chang, C.C., Lin, C.J.: Libsvm: a library for support vector machines. ACM Trans. Intell. Syst. Technol. (TIST) 2(3), 27 (2011)","journal-title":"ACM Trans. Intell. Syst. Technol. (TIST)"},{"issue":"1","key":"216_CR37","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1145\/1656274.1656278","volume":"11","author":"M Hall","year":"2009","unstructured":"Hall, M., Frank, E., Holmes, G., Pfahringer, B., Reutemann, P., Witten, I.H.: The WEKA data mining software: an update. ACM SIGKDD Explor. Newsl. 11(1), 10\u201318 (2009)","journal-title":"ACM SIGKDD Explor. Newsl."}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-013-0216-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s10032-013-0216-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-013-0216-1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T08:24:47Z","timestamp":1746087887000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s10032-013-0216-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013,12,21]]},"references-count":37,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2014,9]]}},"alternative-id":["216"],"URL":"https:\/\/doi.org\/10.1007\/s10032-013-0216-1","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"type":"print","value":"1433-2833"},{"type":"electronic","value":"1433-2825"}],"subject":[],"published":{"date-parts":[[2013,12,21]]}}}