Title :
A Fast Keyword-Spotting Technique
Author :
Li, Linlin ; Lu, Shijian ; Tan, Chew Lim
Author_Institution :
Nat. Univ. of Singapore, Singapore
Abstract :
In order to capture the content of an imaged document but avoid the time-consuming full-scale OCR which is fragile to handle touching characters, a fast and segmentation- free keyword spotting method is proposed in this paper. The keyword spotting method is based on word shape coding technique. The proposed coding scheme has little ambiguity, and can be swiftly executed. It is a promising technique to boost better document image retrieval. The strength of the proposed method is demonstrated in a document filtering experiment. The experimental results show that document filtering based on the proposed method is more than 20 times faster than the one based on OCR, and has comparable filtering accuracy.
Keywords :
document image processing; image retrieval; optical character recognition; document filtering; document image retrieval; full-scale OCR; imaged document; segmentation-free keyword spotting method; touching characters; word shape coding technique; Character recognition; Computer science; Filtering; Image coding; Image retrieval; Image segmentation; Information retrieval; Optical character recognition software; Shape; Software libraries;
Conference_Titel :
Document Analysis and Recognition, 2007. ICDAR 2007. Ninth International Conference on
Conference_Location :
Parana
Print_ISBN :
978-0-7695-2822-9
DOI :
10.1109/ICDAR.2007.4378677