David Doermann

Research Scientist Emeritus
Ph.D., University of Maryland (Computer Science)

David Doermann is a research scientist emeritus in UMIACS.

In April, 2018, Doermann relocated to the University at Buffalo where he is a professor of computer science and engineering and director of the University at Buffalo Artificial Intelligence Institute.

At the University of Maryland, he served as co-director of the Laboratory for Language and Media Processing in UMIACS and as an adjunct member of the graduate faculty.

Doermann's team of researchers focus on topics related to document image analysis and multimedia information processing. Recent intelligent document image analysis projects include page decomposition, structural analysis and classification, page segmentation, logo recognition, document image compression, duplicate document image detection, image based retrieval, character recognition, generation of synthetic OCR data, and signature verification. In video processing, projects have centered on the segmentation of compressed domain video sequences, structural representation and classification of video, detection of reformatted video sequences, and the performance evaluation of automated video analysis algorithms.

In 2002 he received an Honorary Doctorate of Technology Sciences from the University of Oulu for his contributions to digital media processing and document analysis research. Doermann is a founding co-editor of the International Journal on Document Analysis and Recognition, has served as the general chair or co-chair of more than a half dozen international conferences and workshops, including the International Conference on Document Analysis and Recognition (ICDAR), which was held in Washington, D.C., in 2013. He has authored more than 30 journal publications and more than 125 refereed conference papers.

He received a B.Sc. degree in computer science and mathematics from Bloomsburg University in 1987, a M.Sc. degree in 1989 in the Department of Computer Science at the University of Maryland, College Park. He continued his studies in the Computer Vision Laboratory, where he earned a doctorate in 1993.



Zheng Y, Li H, Doermann D.  2002.  Segmentation and Identification of Handwriting in Noisy Documents. IAPRConference on Document Analysis System.

Rautiainen M, Doermann D.  2002.  Temporal Color Correlograms in Video Retrieval. International Conference on Pattern Recognition.

Gupta P, Doermann D, DeMenthon D.  2002.  Beam Search for Feature Selection in Automatic SVMDefect Classification. International Conference on Pattern Recognition.


Doermann D, Ma H, Karagol-Ayan B, Oard D.  2001.  Translation lexicon acquisition from bilingual dictionaries. Proceedings of SPIE. 4670:37-37.


Koivisto A, Pietkainen P, Sauvola J, Doermann D.  2000.  Live multimedia adaptation through wireless hybrid networks. Multimedia and Expo, 2000. ICME 2000. 2000 IEEE International Conference on. 3:1697-1700vol.3-1697-1700vol.3.

Kia OE, Doermann D.  2000.  Residual coding in document image compression. Image Processing, IEEE Transactions on. 9(6):961-969.

Doermann D, DeMenthon D.  2000.  Data and Content Based Adaptation for Video Over Low Bandwidth Networks. SPIE- Multimedia and Systems Applicaitons III.

DeMenthon D, Stuckelberg VM, Doermann D.  2000.  Hidden Markov Models for Images. ICPR.

Kobla V, DeMenthon D, Doermann D.  2000.  Identifying Sports Videos using Replay, Text and Camera Motion Features. SPIE Conference on Storage and Retrieval for Image and Video Databases.

Li H, Doermann D.  2000.  Superresolution-based enhancement of text in digital video. Pattern Recognition, 2000. Proceedings. 15th International Conference on. 1:847-850vol.1-847-850vol.1.

Li H, Doermann D, Kia O.  2000.  Automatic Text Detection and Tracking in Digital Video. IEEE Transactions on Image Processing - Special Issue on Image and Video Processing for Digital Libraries. 9(1):147-156.


Li H, Doermann D.  1999.  Text enhancement in digital video using multiple frame integration. Proceedings of the seventh ACM international conference on Multimedia (Part 1).

Jones R, DeMenthon D, Doermann D.  1999.  Building mosaics from video using MPEG motion vectors. LAMP-TR-035,CAR-TR-918,CS-TR-4034

Stuckelberg MV, Doermann D.  1999.  On musical score recognition using probabilistic reasoning. Document Analysis and Recognition, 1999. ICDAR '99. Proceedings of the Fifth International Conference on.

Kobla V, DeMenthon D, Doermann D.  1999.  Special effect edit detection using VideoTrails: a comparison with existing techniques. Proceedings of SPIE - Conference on Storage and Retrieval for Image and Video Databases VII.

Stuckelberg MV, Doermann D.  1999.  Model Based Graphics Recognition. GREC.

Xingyuan L, Doermann D, Oh W, Gao W.  1999.  ARobust Method for Unknown Forms Analysis. ICDAR.

Kobla V, DeMenthon D, Doermann D.  1999.  Detection of slow-motion replay sequences for identifying sports videos. Proceedings of IEEE 1999 Workshop on Multimedia Signal Processing.

Okun O, Doermann D, Pietikainen M.  1999.  Page Segmentation and Zone Classification: The State of the Art. LAMP-TR-036,CAR-TR-927,CS-TR-4079

Li H, Kia O, Doermann D.  1999.  Text Enhancement in Digital Video. Proceedings of SPIE - Conference on Document Recognition and Retrieval VI.


Li H, Doermann D, Kia O.  1998.  Text Extraction and Recognition in Digital Video. Proceedings of Third IAPRWorkshop on Document Analysis Systems.

Doermann D, Li H, Kia O.  1998.  The detection of duplicates in document image databases. Image and Vision Computing. 16(12–13):907-920.

Kobla V, Doermann D, Faloutsos C.  1998.  Developing High-Level Representations of Video Clips using VideoTrails. Proceedings of the SPIEConference on Storage and Retrieval for Image and Video Databases VI. 3312:81-92.

Doermann D, Rivlin E, Rosenfeld A.  1998.  The function of documents. Image and Vision Computing. 16(11):799-814.

Li H, Doermann D.  1998.  Automatic Identification of Text In Digital Video Key Frames. Proceedings of International Conference on Pattern Recognition.

Li H, Doermann D, Kia O.  1998.  Automatic Text Detection and Tracking in Digital Video. LAMP-TR-028,CFAR-TR-900,CS-TR-3962

Kia O, Doermann D.  1998.  Document Image Coding for Processing and Retrieval. Journal of VLSI Signal Processing. 20:121-135.

Kobla V, Doermann D.  1998.  Indexing and Retrieval of MPEG-compressed video. The Journal of Electronic Imaging.

DeMenthon D, Doermann D, Kobla V.  1998.  Video Summarization by Curve Simplification. Proceedings of ACM - Multimedia 98, Bristol, England.

DeMenthon D, Kobla V, Doermann D.  1998.  Video Summarization by Curve Simplification. LAMP-TR-018,CFAR-TR-889,CS-TR-3916

Li H, Doermann D.  1998.  Automatic Text Tracking In Digital Videos. Proceedings of IEEE 1998 Workshop on Multimedia Signal Processing.

Doermann D.  1998.  Document Image Understanding - 1997. LAMP-TR-025,CFAR-TR-897,CS-TR-3936


Doermann D.  1997.  Document Understanding - 1996. LAMP-TR-008,CFAR-TR-853,CS-TR-3775

Guo JK, Doermann D, Rosenfeld A.  1997.  Local correspondence for detecting random forgeries. Document Analysis and Recognition, 1997., Proceedings of the Fourth International Conference on. 1:319-323vol.1-319-323vol.1.

Kobla V, Doermann D.  1997.  Extracting Features for Indexing MPEG-Compressed Video. Proceedings of the IEEEFirst Workshop on Multimedia Signal Processing.

Sauvola JJ, Doermann D, Pietikaeinen M.  1997.  Locally adaptive document skew detection. Proceedings of SPIE. 3027(1):96-108.

Kobla V, Doermann D, Lin K-I, Faloutsos C.  1997.  Compressed Domain video indexing techniques using DCT and motion vector information in MPEG video. Proceedings of SPIE - conference on Storage and Retrieval for Image and Video Databases V.

Kia O, Doermann D, Rosenfeld A, Chellappa R.  1997.  Symbolic Compression and Processing of Document Images. LAMP-TR-004,CFAR-TR-849,CS-TR-3734

Doermann D, Rosenfeld A, Rivlin E.  1997.  The Function of Documents. ICDAR.

Zhong S, Doermann D, Rosenfeld A.  1997.  Image Indexing with Minimum Adaptive Spatial Segmentation. Proceedings of VISUAL 1997.

Etemad K, Doermann D, Chellappa R.  1997.  Multiscale Document Page Segmentation Using Soft Decision Integration. IEEE Transactions on Pattern Analysis and Machine Intelligence.

Sauvola J, Kauniskangas H, Doermann D, Pietikainen M.  1997.  Techniques for Automated Testing for Automated Testing of Document Analysis Algorithms. Proceedings of the First Brazilian Symposium on Document Image Analysis.

Doermann D, Sauvola J, Haapakoski S, Kauniskangas H, Seppanen T, Pietikainen M.  1997.  ADistributed Management System for Testing Document Image Database Analysis Algorithms. ICDAR.

Kobla V, Doermann D, Faloutsos C.  1997.  VideoTrails: Representing and Visualizing Structure in Video Sequences. Proceedings of the ACMInternational Multimedia Conference.

Kauniskangas H, Sauvola J, Pietikainen M, Doermann D.  1997.  Content-based Image Retrieval Using Composite Features. Proceedings of the 1997 Scandinavian Conference on Image Analysis.

Sauvola J, Doermann D, Kauniskangas H, Shin C, Koivusaari M, Pietikainen M.  1997.  Graphical Tools and Techniques for Querying Document Databases. BSDIA.

Kia OE, Doermann D.  1997.  OCR-based rate-distortion analysis of residual coding. Image Processing, 1997. Proceedings., International Conference on. 3:690-693vol.3-690-693vol.3.

Kia O, Doermann D.  1997.  The role of compressed document images in transmission and retrieval. Multimedia Signal Processing, 1997., IEEE First Workshop on.


Doermann D, Rivlin E, Weiss I.  1996.  Applying algebraic and differential invariants for logo recognition. Machine Vision and Applications. 9(2):73-86.

Kobla V, Doermann D, Lin K-I.  1996.  Archiving, indexing, and retrieval of video in compressed domain. SPIEConference on Multimedia Storage and Archiving Systems. 2916:78-89.

Kia OE, Doermann D.  1996.  Structural compression for document analysis. Pattern Recognition, 1996., Proceedings of the 13th International Conference on. 3:664-668vol.3-664-668vol.3.

Doermann D, Sauvola J, Kauniskangas H, Shin C, Pietikainen M, Rosenfeld A.  1996.  The Development of a General Framework for Intelligent Document Image Retrieval. Proceedings in the International Workshop on Document Analysis Systems.

Kobla V, Doermann D, Lin K-I(D), Faloutsos C.  1996.  Feature Normalization for Video Indexing and Retrieval. LAMP-TR-003,CFAR-TR-847,CS-TR-3732

Kobla V, Doermann D, Rosenfeld A.  1996.  Compressed Video Segmentation. LAMP-TR-001,CFAR-TR-839,CS-TR-3688

Hori O, Doermann D.  1996.  Table-Form Structure Analysis Based on Box-Driven Reasoning. IEICE TRANSACTIONS on Information and Systems. E79-D(5):542-547.

Doermann D, Rivlin E, Rosenfeld A.  1996.  The Function of Documents. LAMP-TR-002,CFAR-TR-841,CS-TR-3697

Kia OE, Doermann D, Chellappa R.  1996.  Compressed-domain document retrieval and analysis. SPIE Conference of Multimedia Storage and Archiving Systems. 2916(1):176-187.

Hori O, Doermann D.  1996.  Quantitative Measurement of the Performance of Raster-to-vector Conversion Algorithms. Graphics Recognition: Methods and ApplicationsGraphics Recognition: Methods and Applications.


Doermann D, Kia O.  1995.  Hybrid thinning through reconstruction. Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on. 2:632-635vol.2-632-635vol.2.

Hori O, Doermann D.  1995.  Robust table-form structure analysis based on box-driven reasoning. Document Analysis and Recognition, 1995., Proceedings of the Third International Conference on. 1:218-221vol.1-218-221vol.1.