Document and Pattern Recognition Lab
( dprl@RIT )

We research systems that recognize and retrieve information
in documents, images, and videos.

News: 2024

  • (Nov 2024) Congratulations to Ayush Kumar Shah, who has submitted his dissertation proposal. His defense will be in the latter part of December.
  • (Aug 2024) We welcome Patrick Philippy as a new PhD student this fall. Patrick has been working on the ChemScraper project for the MMLI NSF AI Center while exploring dissertation topics.
  • (Aug 2024) Bryan Amador and Matt Langsenkamp have released a paper on arXiv regarding 2D pyramidal character histograms, and the use of rectangular regions and level-skipping that improve formula search effectiveness and space efficiency: https://arxiv.org/abs/2408.09283
  • (Aug 2024) The first draft of the MIR book Richard is writing with Behrooz Mansouri and Anurag Agarwal for Foundations and Trends in Information Retrieval is now complete (link). 
  • (May 2024) The dprl lab's paper on ChemScraper has been accepted to the ICDAR 2024 journal track. The paper describes (1) a fast and accurate technique for parsing born-digital (vector) PDF images, and (2) its use to create training data for a new approach to visual parsing of molecule diagrams in raster images (i.e., pixel-based such as from PNGs). Code is also available. The paper will appear in a special issue of IJDAR.
  • (May 2024) Internships: This summer PhD student Abhisek Dey is completing an internship with the drug design company Insitro in San Francisco (Daphne Koller is the CEO). Former RA Ming Creekmore will be working until January with Ying Diao's group in the MMLI NSF AI Center at Univ. Illinois Urbana-Champaign, applying AI to improve solar cell designs. 
  • (May 2024) Prof. Zanibbi published a new survey on handwritten math recognition with Masaki Nakagawa's group and Harold Mouchère: A Survey of Handwritten Mathematical Expression Recognition: The Rise of Encoder-Decoder and GNN Models. The paper has been published in the journal Pattern Recognition. (preprint)
Address

Room 70-3500, GCCIS
Dept. Computer Science
Rochester Inst. Technology
Rochester, NY, 14623-5608
USA

Contacts

Email: rxzvcs@rit.edu
Phone: +1 (585) 475-4536
Fax: +1 (585) 475-4935