Abstract
Document analysis plays an important role in office
automation, especially in intelligent signal processing. The
proposed system consists of two modules: block segmentation
and block identification. In this approach, first a document is
segmented into several non-overlapping blocks by utilizing a
novel recursive segmentation technique, and then extracts
the features embedded in each segmented block are extracted.
Two kinds of features, connected components and image
boundary/perimeter features are extracted. The features are
verified to be effective in characterizing document blocks.
Last, the identification module to determine the identity of
the considered block is developed. Wide verities of documents
are used to verify the feasibility of this approach.
Users
Please
log in to take part in the discussion (add own reviews or comments).