TY - JOUR
T1 - Multimodal page classification in administrative document image streams
AU - Rusiñol, Marçal
AU - Frinken, Volkmar
AU - Karatzas, Dimosthenis
AU - Bagdanov, Andrew D.
AU - Lladós, Josep
PY - 2014/1/1
Y1 - 2014/1/1
N2 - © 2014, Springer-Verlag Berlin Heidelberg. In this paper, we present a page classification application in a banking workflow. The proposed architecture represents administrative document images by merging visual and textual descriptions. The visual description is based on a hierarchical representation of the pixel intensity distribution. The textual description uses latent semantic analysis to represent document content as a mixture of topics. Several off-the-shelf classifiers and different strategies for combining visual and textual cues have been evaluated. A final step uses an n-gram model of the page stream allowing a finer-grained classification of pages. The proposed method has been tested in a real large-scale environment and we report results on a dataset of 70,000 pages.
AB - © 2014, Springer-Verlag Berlin Heidelberg. In this paper, we present a page classification application in a banking workflow. The proposed architecture represents administrative document images by merging visual and textual descriptions. The visual description is based on a hierarchical representation of the pixel intensity distribution. The textual description uses latent semantic analysis to represent document content as a mixture of topics. Several off-the-shelf classifiers and different strategies for combining visual and textual cues have been evaluated. A final step uses an n-gram model of the page stream allowing a finer-grained classification of pages. The proposed method has been tested in a real large-scale environment and we report results on a dataset of 70,000 pages.
KW - Digital mail room
KW - Multimodal page classification
KW - Visual and textual document description
U2 - 10.1007/s10032-014-0225-8
DO - 10.1007/s10032-014-0225-8
M3 - Article
SN - 1433-2833
VL - 17
SP - 331
EP - 341
JO - International Journal on Document Analysis and Recognition
JF - International Journal on Document Analysis and Recognition
IS - 4
ER -