caa a22 4500 467884064 CHVBK 20180406152729.0 cr unu---uuuuu 170328e20060401xx s 000 0 eng 10.1007/s10032-005-0147-6 doi (NATIONALLICENCE)springer-10.1007/s10032-005-0147-6 Retrieving poorly degraded OCR documents [Elektronische Daten] [Y. Fataicha, M. Cheriet, J. Nie, C. Suen] A significant portion of currently available documents exist in the form of images, for instance, as scanned documents. Electronic documents produced by scanning and OCR software contain recognition errors. This paper uses an automatic approach to examine the selection and the effectiveness of searching techniques for possible erroneous terms for query expansion. The proposed method consists of two basic steps. In the first step, confused characters in erroneous words are located and editing operations are applied to create a collection of erroneous error-grams in the basic unit of the model. The second step uses query terms and error-grams to generate additional query terms, identify appropriate matching terms, and determine the degree of relevance of retrieved document images to the user's query, based on a vector space IR model. The proposed approach has been trained on 979 document images to construct about 2,822 error-grams and tested on 100 scanned Web pages, 200 advertisements and manuals, and 700 degraded images. The performance of our method is evaluated experimentally by determining retrieval effectiveness with respect to recall and precision. The results obtained show its effectiveness and indicate an improvement over standard methods such as vectorial systems without expanded query and 3-gram overlapping. Springer-Verlag, 2005 Document processing nationallicence Optical character recognition (OCR) nationallicence Information retrieval (IR) nationallicence Error-grams nationallicence Query expansion nationallicence Fataicha Y. Laboratory for Imagery, Vision, and Artificial Intelligence (LIVIA), École de Technologie Supérieure, 1100 Notre-Dame West, H3C 1K3, Montreal, Quebec, Canada aut Cheriet M. Laboratory for Imagery, Vision, and Artificial Intelligence (LIVIA), École de Technologie Supérieure, 1100 Notre-Dame West, H3C 1K3, Montreal, Quebec, Canada aut Nie J. Department Informatique et Recherche opérationnelle, University of Montreal, CP 6128, succursale Centre-ville, H3C 3J7, Montreal, Quebec, Canada aut Suen C. Centre for Pattern Recognition and Machine Intelligence (CENPARMI), Concordia University, Suite GM-606, 1455 de Maisonneuve Boulevard West, H3G 1M8, Montreal, Quebec, Canada aut International Journal of Document Analysis and Recognition (IJDAR) Springer-Verlag 8/1(2006-04-01), 1-99999 1433-2833 8:1<1 2006 8 10032 https://doi.org/10.1007/s10032-005-0147-6 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/s10032-005-0147-6 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Fataicha Y. Laboratory for Imagery, Vision, and Artificial Intelligence (LIVIA), École de Technologie Supérieure, 1100 Notre-Dame West, H3C 1K3, Montreal, Quebec, Canada aut NATIONALLICENCE 700 1- Cheriet M. Laboratory for Imagery, Vision, and Artificial Intelligence (LIVIA), École de Technologie Supérieure, 1100 Notre-Dame West, H3C 1K3, Montreal, Quebec, Canada aut NATIONALLICENCE 700 1- Nie J. Department Informatique et Recherche opérationnelle, University of Montreal, CP 6128, succursale Centre-ville, H3C 3J7, Montreal, Quebec, Canada aut NATIONALLICENCE 700 1- Suen C. Centre for Pattern Recognition and Machine Intelligence (CENPARMI), Concordia University, Suite GM-606, 1455 de Maisonneuve Boulevard West, H3G 1M8, Montreal, Quebec, Canada aut NATIONALLICENCE 773 0- International Journal of Document Analysis and Recognition (IJDAR) Springer-Verlag 8/1(2006-04-01), 1-99999 1433-2833 8:1<1 2006 8 10032 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer