Title :
SVM output score based text line refinement for accurate text localization
Author :
Jung, Cheolkon ; Liu, Qifeng ; Kim, Joongkyu
Author_Institution :
Sch. of Inf. & Commun. Eng., Sungkyunkwan Univ., Suwon
fDate :
March 31 2008-April 4 2008
Abstract :
In this paper, we propose the text line refinement method based on the SVM (support vector machine) output score for accurate text localization. In general, SVM output scores for the verification of text candidates provide a measure of the closeness to the text. Up to the present, most researchers used the score for the verification of the text candidate region. However, we use the output score for refining the initial text localization results. By means of the proposed approach, we can obtain more accurate text localization results. The effectiveness and efficiency of the proposed method is validated by extensive experiments on a complex database containing 435 images.
Keywords :
support vector machines; text analysis; accurate text localization; support vector machine; text candidate region verification; text line refinement method; Flowcharts; Focusing; Image databases; Image edge detection; Indexing; Pattern classification; Support vector machine classification; Support vector machines; Text processing; Text recognition; Text processing; accurate text localization; text line refinement; the SVM output score;
Conference_Titel :
Acoustics, Speech and Signal Processing, 2008. ICASSP 2008. IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-1483-3
Electronic_ISBN :
1520-6149
DOI :
10.1109/ICASSP.2008.4518017