One difficulty with using text from digital video for indexing and retrieval is that video images are often in low resolution and poor quality, and as a result, the text can not be recognized adequately by most commercial OCR software. Text image enhancement is necessary to achieve reasonable OCR accuracy. Our enhancement consists of two main procedures, resolution enhancement based on Shannon interpolation and text separation from complex image background. Experiments show our enhancement approach improves OCR accuracy considerably.
Text enhancement in digital video
Document Recognition and Retrieval VI ; 1999 ; San Jose,CA,USA
Proc. SPIE ; 3651
1999-01-07
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Text enhancement with asymmetric filter for video OCR
IEEE | 2001
|Text Enhancement with Asymmetric Filter for Video OCR
British Library Conference Proceedings | 2001
|Super-Resolution Enhancement of Native Digital Video Versus Digitized NTSC Sequences
British Library Conference Proceedings | 2002
|