The Community for Technology Leaders
Green Image
Issue No. 12 - December (2005 vol. 27)
ISSN: 0162-8828
pp: 1882-1895
This work presents categorization experiments performed over noisy texts. By noisy, we mean any text obtained through an extraction process (affected by errors) from media other than digital texts (e.g., transcriptions of speech recordings extracted with a recognition system). The performance of a categorization system over the clean and noisy (Word Error Rate between \sim 10 and \sim 50 percent) versions of the same documents is compared. The noisy texts are obtained through handwriting recognition and simulation of optical character recognition. The results show that the performance loss is acceptable for Recall values up to 60-70 percent depending on the noise sources. New measures of the extraction process performance, allowing a better explanation of the categorization results, are proposed.
Index Terms- Text categorization, noisy text, indexing, offline cursive handwriting recognition, optical character recognition.
Alessandro Vinciarelli, "Noisy Text Categorization", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 27, no. , pp. 1882-1895, December 2005, doi:10.1109/TPAMI.2005.248
313 ms
(Ver 3.3 (11022016))