@article{oai:nagoya.repo.nii.ac.jp:00005339,
 author = {Watanabe, Toyohide and Luo, Qin and Sugie, Noboru},
 journal = {Proceedings of the 11th IAPR International Conference on Pattern Recognition II, Conference B: Pattern Recognition Methodology and Systems},
 month = {Aug},
 note = {The main objective of document understanding is to extract and classify the meaningful data automatically from documents. Some researchers, concerning this issue, have already been reported. However, these methods are not always successful because the recognition procedures analyze document images on the basis of only physical coodinate values of compositive items. In this paper, we propose a more advanced method based on the spatial relationships among neighboring segments of compositive items, in addition to the geometric aspects. In our method, the knowledge about documents is not a single layer, but organized as multilevel layers: knowledge about layout structures, knowledge about item sequences and knowledge about item properties. 3 kinds of knowledge are not only specified hierarchially, but also interrelates mutually between the layout recognition, item recognition and character recognition procedures. Additionally, this paper makes it clear through some experiments that our method for document understanding is very excellent in the adaptability, applicability and flexibility.},
 pages = {689--692},
 title = {A cooperative document understanding method among multiple recognition procedures},
 year = {1992}
}