Document filters using morphological and geometrical features of characters

This paper aims at irregular noise removal in binary document images. A new filtering algorithm called modified directional morphological filter is in troduced with dual properties for eliminating document salt-and-pepper nois es, and for remedying eroded character stroke distortions. For eliminating larger noises other than salt-and-pepper shape, an enhanced algorithm calle d image geometric structure filter (IGSF) is proposed based on the geometri c stroke information of characters. IGSF can especially be used for noise r emoval in printed/ printed-handwritten alphanumeric documents. Experiments demonstrate that the combining performance of two filters is robust, which can feasibly filter out various isolated noises in the binary document imag es. (C) 2001 Elsevier Science B.V. All rights reserved.