Text Categorization of Low Quality Images

Categorization of text images into content oriented classes would be a useful capability in a variety of document handling systems Many methods can be used to cat egorize texts once their words are known but OCR can garble a large proportion of words particularly when low quality images are used Despite this we show for one data set that fax quality images can be cat egorized with nearly the same accuracy as the original text Further the categoriza tion system can be trained on noisy OCR output without need for the true text of any image or for editing of OCR output The use of a vector space classi er and train ing method robust to large feature sets com bined with discarding of low frequency OCR output strings are the key to our approach