Title :
DCT Feature Based Text Capturing and Tracking
Author :
Shi, Jianyong ; Luo, Xiling ; Zhang, Jun
Author_Institution :
Sch. of Electron. & Inf. Eng., Beihang Univ., Beijing, China
Abstract :
An autonomous text capturing and tracking method for digital video is proposed in this paper. Frames are divided into blocks. Text blocks are extracted first using a discrete cosine transformation (DCT) based method, then the optimal text region is extracted from duplicate regions within the consecutive frames using the method of text tracking, and is used as an input for optical character recognition (OCR) system. With the reduction of duplicate regions and optimization of region extraction, OCR´s recognition efficiency and accuracy are both improved.
Keywords :
discrete cosine transforms; feature extraction; optical character recognition; tracking; video signal processing; DCT feature; digital video; discrete cosine transformation; optical character recognition system; region extraction; text capturing; text tracking; Character recognition; Data mining; Discrete cosine transforms; Gold; Histograms; Motion estimation; Optical character recognition software; Robots; Text analysis; Text recognition;
Conference_Titel :
Pattern Recognition, 2009. CCPR 2009. Chinese Conference on
Conference_Location :
Nanjing
Print_ISBN :
978-1-4244-4199-0
DOI :
10.1109/CCPR.2009.5344105
