Title :
Thai Font Type Recognition Using SIFT
Author :
Jamjuntr, Pitchaya ; Dejdumrong, Natasha
Author_Institution :
Dept. of Comput. Eng., King Mongkut´´s Univ. of Technol. Thonburi, Bangkok, Thailand
Abstract :
This paper presents a Thai font type recognition on Thai document by using Scale-invariant feature transform (SIFT). The features are extracted by Scale-invariant feature transform (SIFT) that is widely used in image processing. Sift is an algorithm for detecting local features in order to find similar objects. Our system contains ten fonts and ten text images in each font. We use ten text images each font total one hundred images for our experiment. Our results show accuracy for 97.37% for ten Thai fonts.
Keywords :
feature extraction; natural language processing; optical character recognition; text analysis; transforms; SIFT; Thai document; Thai font type recognition; image processing; local feature detection; scale-invariant feature transform; text image; Accuracy; Character recognition; Feature extraction; Image recognition; Optical character recognition software; Optical imaging; Text recognition; Font type recognition; Scale-invariant feature transform;
Conference_Titel :
Computer Graphics, Imaging and Visualization (CGIV), 2012 Ninth International Conference on
Conference_Location :
Hsinchu
Print_ISBN :
978-1-4673-2335-2
Electronic_ISBN :
978-0-7695-4778-7
DOI :
10.1109/CGIV.2012.23
