Combining Algorithms for
Recognition and Retrieval of Mathematics

NSF Award Summary (Grant No. IIS-1016815)

   

Project Summary

This project aims to produce new methods for retrieving math in documents, using mathematical expressions as queries (query-by-expression). We are working to develop retrieval tools that are intuitive to use, both for math experts and (perhaps more importantly) non-experts. Methods developed for the project might later be adapted for retrieving other non-textual document elements such as chemical diagrams, tables, and figures. Source code and experimental data developed for the project will be made public via the project web site (http://www.cs.rit.edu/~dprl/msearch.html). To promote mathematical literacy, the principal investigator and graduate students working on the project will visit middle schools and talk about the history, recognition and retrieval of mathematical notation. The project will also provide opportunties for students to obtain research experience, including students in the McNair Scholars program at RIT. The McNair Scholars program seeks to provide research experiences to low-income, first-generation college students that are interested in pursuing doctoral studies.

News (2011-2012)

Project Team

Richard Zanibbi, PhD, Principal Investigator
Lei Hu, PhD Student (Computer Science, RIT), Sept. 2010-
Siyu Zhu, PhD Student (Imaging Science, RIT) Sept. 2011-
Robert Li Volsi, MSc Student (Computer Engineering, RIT), Jan. 2011-
Christopher Sasarak, NSF REU Student, Summer 2012 (BSc Computer Science Student, RIT)
David Stalnaker, BSc/MSc Student (Computer Science, RIT), Dec. 2011-May 2012
Meridangela Gutierrez Jhong, BSc Student and McNair Scholar (Computer Science), Jan.-May 2011
Kevin Hart, NSF REU Summer 2011 (BSc Computer Science, RIT), RA Sept. 2011-Feb. 2012
Thomas Schellenberg, MSc Student (Computer Science, RIT), Sept. 2010-Nov. 2011
Benjamin Holm, MSc Student (Computer Science, RIT), April 2010-Aug. 2011
Richard Pospesel, Research Programmer (Master's in Game Design and Development Student, RIT), Sept. 2010-July 2011

Collaborators

Dorothea Blostein (Queen's University at Kingston, Canada)
Matthew Fluet (RIT)
Harold Mouchère (IRCCyN/IVC, Nantes, France)
George Nagy, (Prof. Emeritus, RPI)
Christian Viard-Gaudin (IRCCyN/IVC, Nantes, France)
Bo Yuan (RIT)

Software

Please Note: the software below is currently under active development.

Web-based math entry interface (click image at left; works best with Firefox 4; iPad compatiable)

Publications

T. Schellenberg, B. Yuan and R. Zanibbi (2012). Layout-based substitution tree indexing and retrieval for mathematical expressions, Proc. Document Recognition and Retrieval XIX, pp. 8297OI-1 - 8297OI-8, San Francisco.

R. Zanibbi and B. Yuan. (2011) Keyword and image-based retrieval of mathematical expressions. Proc. Document Recognition and Retrieval XVIII, vol. 7874 Proc. SPIE, pp. OI1-OI9, San Francisco, CA.

R. Zanibbi and L. Yu. (2011) Math Spotting: Retrieving Math in Technical Documents Using Handwritten Query Images. Proc. Int'l Conf. Document Analysis and Recognition, pp. 446-451, Beijing.

Zanibbi, R. and Blostein, D. (2011) Recognition and Retrieval of Mathematical Notation, International Journal of Document Analysis and Recognition, to appear, available online.

L. Hu and R. Zanibbi. (2011) HMM-Based Recognition of Online Handwritten Mathematical Symbols Using Segmental K-means Initialization and a Modified Pen-up/down Feature. Proc. Int'l. Conf. Document Analysis and Recognition, pp. 457-462, Beijing.

R. Zanibbi, A. Pillay, H. Mouchere, C. Viard-Gaudin, and D. Blostein. (2011) Stroke-Based Performance Metrics for Handwritten Mathematical Expressions. Int'l Conf. Document Analysis and Recognition, pp. 334-338, Beijing.


Last updated: $$Date: 2013/02/22 15:57:45 $$