Title :
Segmentation-free word spotting using SIFT
Author :
Lee, Duk-Ryong ; Hong, Wonju ; Oh, Ll-Seok
Author_Institution :
Dept. of Comput. Sci. & Eng., Chonbuk Nat. Univ., Jeonju, South Korea
Abstract :
This paper presents a method for word spotting using SIFT. The method performs well for multi-lingual document images and it works without skew correction and without any segmentation process. The algorithm for detecting words in test images is described, including the processes of detecting keypoints, matching them, and clustering matching pairs. Experiments on English and Korean document image collections showed that the proposed method is promising.
Keywords :
document image processing; image matching; image segmentation; natural language processing; pattern clustering; word processing; English document image collection; Korean document image collection; SIFT; clustering matching pairs; keypoint detection; keypoint matching; muItilingual document image; segmentation-free word spotting; word detection; Frequency locked loops; Image segmentation; Manganese; document image retrieval; local descriptor; scale and rotation invariance;
Conference_Titel :
Image Analysis and Interpretation (SSIAI), 2012 IEEE Southwest Symposium on
Conference_Location :
Santa Fe, NM
Print_ISBN :
978-1-4673-1831-0
Electronic_ISBN :
978-1-4673-1829-7
DOI :
10.1109/SSIAI.2012.6202454
