@inproceedings{Lu2006,
title = {Automatic categorization of figures in scientific documents},
author = {Xiaonan Lu and Prasenjit Mitra and James Z. Wang and C. Lee Giles},
booktitle = {ACM/IEEE-CS Joint Conference on Digital Libraries},
pages = {129--138},
url = {http://clgiles.ist.psu.edu/papers/jcdl2006_scientific-figures.pdf},
year = {2006},
abstract = {Figures are very important non-textual information contained in scientific
documents. Current digital libraries do not provide users tools to
retrieve documents based on the information available within the
figures. We propose an architecture for retrieving documents by integrating
figures and other information. The initial step in enabling integrated
document search is to categorize figures into a set of pre-defined
types. We propose several categories of figures based on their functionalities
in scholarly articles. We have developed a machine-learning-based
approach for automatic categorization of figures. Both global features,
such as texture, and part features, such as lines, are utilized in
the architecture for discriminating among figure categories. The
proposed approach has been evaluated on a testbed document set collected
from the CiteSeer scientific literature digital library. Experimental
evaluation has demonstrated that our algorithms can produce acceptable
results for realworld use. Our tools will be integrated into a scientific
document digital library.},
keywords = {Classification }
}
::