Authors : S.Abirami and D. Manjula
Abstract: This study performs an efficient Information Retrieval from scanned Tamil Document Images. Keywords are valuable indexing tools and if they can be identified at the image level, extensive computation during recognition will be avoided. Printed documents can be scanned to produce document images. Instead of converting entire document images into text equivalent, a Feature String algorithm has been designed to generate feature strings for the word images in Tamil documents based on the features extracted from it. During retrieval, the same features could be extracted from the user specified word and can be matched with the word images in the document .This system also adapts the documents of various font size instead of limiting to a particular font size .This yields a faster result even in a quality degraded document. This kind of Information Retrieval(Keyword Based Search) can be adapted in Digital Libraries which employs digitized documents instead of text processing.
S.Abirami and D. Manjula , 2006. Enabling Intelligent Information Retrieval from Tamil Document Images. Asian Journal of Information Technology, 5: 996-1000.