Issue No. 01 - January (1997 vol. 19)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/34.566817
<p><b>Abstract</b>—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."</p>
Document processing, multiscale analysis, context dependent classification, soft decision integration, wavelet packets, neural networks.
Kamran Etemad, David Doermann, Rama Chellappa, "Multiscale Segmentation of Unstructured Document Pages Using Soft Decision Integration", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 19, no. , pp. 92-96, January 1997, doi:10.1109/34.566817