%0 Journal Article
%T A NOVEL MORPHOLOGICAL TECHNIQUE FOR SEGMENTATION OF DOCUMENT IMAGES IN NIST DATABASE
%A DHORE M.P
%A THAKARE V.M
%A KALE K.V.
%J International Journal of Machine Intelligence
%D 2011
%I Bioinfo Publications
%X This paper proposes a novel morphological approach for segmentation of document images in the National Institute of Standards and Technology (NIST) Database. Document Image Analysis involves transformation of any information presented on paper into an equivalent symbolic representation accessible to computer information processing. For better storage and intelligent processing, information presented on paper is now being converted into electronic form. This needs processing of documents using image analysis algorithms. The morphological approach quantitatively describes operations effective for the shape of objects in an image. The mathematical morphology describes such operations by combinations of basic set operations between an image and a small object called a structuring element. The segmentation oriented geometrical features such as size, shape, contrast, or connectivity are efficiently dealt in mathematical morphology. In this paper, morphological approach is used for segmenting the document images. The performance of the proposed method has been evaluated using many text documents. The National Institute of Standards and Technology, Technology Administration, U. S. database of document images has been used in order to carry out experimental work. The image document database used is NIST DATABASE, Federal Register Document Image Database. NIST Special Database 25 ¨C volume 1.(NISTIR 6245). The proposed technique has been tested for various documents like multi-column, multi-article, multi-font, multi-orientation and promising results are obtained. At the end the obtained performance is also compared with other well-known page segmentation algorithms.
%K Document Image Analysis
%K Page segmentation
%K Document segmentation
%K Mathematical Morphology
%K Structuring Element
%K NIST Database
%U http://www.bioinfo.in/uploadfiles/13259110983_5_1_IJMI.pdf