Detection and retargeting of emphasized text for content summarization

In this paper, we propose a simple and robust algorithm for detection and retargeting of emphasized words, written as italics, in a scanned document page. The detection of italics is done using an appropriate use of Principal Component Analysis (PCA), applied on a selected subset of pixels coming from the input character image boundary. The proposed method is font and style invariant. The localization of the emphasized words helps us in information retrieval by means of retargeted words. It is seen that, a good number of publication houses use emphasized (italic) words for specifying the keywords, author's affiliations etc., in the front page of the articles. Our method extracts and retargets the emphasized words to summarize the content of the papers. Experimental result shows the robustness and degree of precision.