Multiscale Segmentation of Unstructured Document Pages Using Soft Decision Integration

Kamran Etemad, David S. Doermann, Rama ChellappaIEEE TPAMI 1997 · DOI · OpenReview

Abstract

We present an algorithm for layout-independent document page segmentation based on document texture using multiscale feature vectors and fuzzy local decision information. Multiscale feature vectors are classified locally using a neural network to allow soft/fuzzy multi-class membership assignments. Segmentation is performed by integrating soft local decision vectors to reduce their "ambiguities".
BibTeX
@article{etemad1997multiscale,
  author = {Kamran Etemad and David S. Doermann and Rama Chellappa},
  title = {{Multiscale Segmentation of Unstructured Document Pages Using Soft Decision Integration}},
  journal = {IEEE Trans. Pattern Anal. Mach. Intell.},
  year = {1997},
  doi = {10.1109/34.566817},
}

Loading related content...

Figure