Lixi Zhou, Jiaqing Chen, et al.
VLDB
While document-image systems for the management of collections of documents, such as forms, offer significant productivity improvements, the entry of information from documents remains a labor-intensive and costly task for most organizations. In this paper, we describe a software system for the machine reading of forms data from their scanned images. We describe its major components: form recognition and "dropout," intelligent character recognition (ICR), and contextual checking. Finally, we describe applications for which our automated forms reader has been successfully used.
Lixi Zhou, Jiaqing Chen, et al.
VLDB
Yigal Hoffner, Simon Field, et al.
EDOC 2004
Liat Ein-Dor, Y. Goldschmidt, et al.
IBM J. Res. Dev
Kaoutar El Maghraoui, Gokul Kandiraju, et al.
WOSP/SIPEW 2010