Title :
Videotext OCR using hidden Markov models
Author :
Natarajan, Prem ; Elmieh, Baback ; Schwartz, Richard ; Makhoul, John
Author_Institution :
BBN Technol./Verizon, Cambridge, MA, USA
fDate :
6/23/1905 12:00:00 AM
Abstract :
We present a method for performing optical character recognition (OCR) of text in video images. Recognition of videotext is a challenging problem due to various factors such as the presence of rich, dynamic backgrounds, low resolution, color, etc. Our strategy is to process the video images to produce high-resolution binarized text images that resemble printed text. We describe a novel clustering and relaxation procedure that combines stroke and color information to separate the text from the background. The binarized text image is then recognized with our Byblos OCR engine (Natarajan et al., 2001; Schwartz et al., 1996) using hidden Markov models trained on similar data. We present experimental results on a video-data corpus collected from broadcast news programs. Currently the system delivers a character error rate of 8.3% on independent multi-font test data from this corpus
Keywords :
hidden Markov models; image colour analysis; image resolution; optical character recognition; Byblos; OCR engine; binarized text images; clustering; experimental results; hidden Markov models; high-resolution images; image color; multi-font test data; optical character recognition; relaxation procedure; stroke information; video images; videotext OCR; Character recognition; Feature extraction; Hidden Markov models; Image recognition; Image segmentation; Layout; Multimedia systems; Optical character recognition software; Text recognition; Topology;
Conference_Titel :
Document Analysis and Recognition, 2001. Proceedings. Sixth International Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7695-1263-1
DOI :
10.1109/ICDAR.2001.953925
