报告题目: Processing Heterogeneous Collections Of Highly Degraded Document Images

报告人: Dr. David Doermann University of Maryland, College Park, USA

报告时间: 2009-5-11 上午10:00

报告地点: FIT楼1-312

主办单位: 电子工程系

联系人： 丁晓青教授

Abstract：

In recent years, the field of document image analysis has continued to expand to include topics such as the processing of text from less commonly taught languages, complex documents and alternative imaging devices (video, mobile phones, etc), while significant progress continues to be made in processing standard heterogeneous collections of office documents, mail pieces, journal publication and similar structured content. At the same time, there has been a tremendous increase in the desire to scan and access heterogeneous collections through mass digitization, introducing new problems when we can no longer make assumptions about content.

We will present and overview of challenges in this area and the work that has been addressed at the University of Maryland. In particular we will look at technologies for document triage, document indexing and retrieval, and document classification. When neither the content nor the structure is known a priori, problems such as robust machine-print/handprint discrimination, language and script identification, page layout similarity, logo and signature detection and adaptable OCR are valuable tools. Furthermore, when these documents are highly degraded, clutter removal, line removal and various other enhancements techniques are required. Our research is focused on triage and being able to organize very large collections of unknown content at an early stage.

The talk will also include an overview of the Graduate programs in the ECE and Computer Science Departments at the University of Maryland for prospective graduate students. It will highlight the opportunities and expectations of the program, and provide some guidance for those applying and preparing to attend graduate school.

Biography：

Dr. David Doermann received a B.Sc. degree in Computer Science and Mathematics from Bloomsburg University in 1987, and 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 Ph.D. 1993. Since 1993, he has served as co-director of the Laboratory for Language and Media Processing in the University of Maryland's Institute for Advanced Computer Studies and as an adjunct member of the graduate faculty. His team of researchers focuses 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. He is the co-editor of the International Journal on Document Analysis and Recognition. He has over 25 journal publications and over 100 refereed conference papers.