Title
Document Image Analysis: Big Data or Small Data
Name
Cheng-Lin LiuAbstract
Like other artificial intelligence problems, document image analysis (DIA) has largely benefitted from bid data, typically by training models with bid data to promote the performance of recognition. I would claim that from either big data or small data view, there are many remaining research works to do. From bid data view, (1) in training, the large amount of unlabeled or weakly labeled data has not been used adequately; (2) in recognition, a lot of related data (e.g. Web texts, image contexts) can help understanding documents. From small data view, (3) some applications (e.g., Chinese historical documents) do not have big labeled data for training; (4) in real life, data usually appear in stream, and only small data is available in a time period.
Short Bio
Cheng-Lin Liu is a Professor at the National Laboratory of Pattern Recognition (NLPR), Institute of Automation of Chinese Academy of Sciences, Beijing, China, and is now the director of the laboratory. He received the B.S. degree in electronic engineering from Wuhan University, Wuhan, China, the M.E. degree in electronic engineering from Beijing Polytechnic University, Beijing, China, the Ph.D. degree in pattern recognition and intelligent control from the Chinese Academy of Sciences, Beijing, China, in 1989, 1992 and 1995, respectively. He was a postdoctoral fellow at Korea Advanced Institute of Science and Technology (KAIST) and later at Tokyo University of Agriculture and Technology from March 1996 to March 1999. From 1999 to 2004, he was a research staff member and later a senior researcher at the Central Research Laboratory, Hitachi, Ltd., Tokyo, Japan. His research interests include pattern recognition, image processing, neural networks, machine learning, and especially the applications to character recognition and document analysis. He has published over 200 technical papers at prestigious international journals and conferences. He won the IAPR/ICDAR Young Investigator Award of 2005. He is on the editorial board of Pattern Recognition Journal, Image and Vision and Computing, International Journal on Document Analysis and Recognition, and Cognitive Computation. He is a Fellow of the IAPR and the IEEE.