Automatic annotation extension and classification of documents using a probabilistic graphical model

摘要: With the fast growth of document images, annotation has become a research area great interest. Annotation allows to describe semantic content documents and facilitates their use research. However, for huge number documents, manual each becomes tedious task. A solution is annotate small part extend it automatically whole dataset. In this paper, we propose model extension classification using probabilistic graphical model. latter, combine visual textual characteristics show that integration user feedback improves step.