A search engine for imaged documents in PDF files

Large quantities of documents in the Internet and digital libraries are simply scanned and archived in image format, many of which are packed in PDF files. The word search tool provided by Adobe Reader/Acrobat does not work for these imaged documents. In this paper, we present a search engine to deal with this issue for imaged documents in PDF files. The experimental results show an encouraging performance. Categories and Subject Descriptors H.3.3 [Information Storage and retrieval]: Information Search and Retrieval  retrieval models, search process; I.4.8 [Image Processing and Computer Vision]: Scene Analysis  Object Recognition. General Terms Algorithms, Measurement, Design, Experimentation. Keywords Imaged Document, Word searching, PDF files.

• Type: Conference
• Year: 2004
• Where: SIGIR
• Authors: Yue Lu, Li Zhang, Chew Lim Tan
• Keywords: Imaged Document, Keywords Imaged Document, PDF Files, SIGIR 2004