BINARY IMAGE PREPROCESSOR FOR DOCUMENT QUALITY IMPROVEMENT AND DATA REDUCTION.

Abstract

A binary image-enhancement operation is proposed to suppress noise in documents introduced, e. g. , by poor-quality copying. As opposed to approaches previously published, the new technique does not erode characters, symbols, drawing elements, etc. , and thus improves the intelligibility of documents. It is shown that the new preprocessing method significantly reduces the data volume necessary to represent documents in compressed form. A low-cost hardware implementation is proposed, suitable for integration, e. g. , in future scanning devices.