Video OCR

• Capture of text overlaid on the video image

• Detected, filtered, OCR’d, incorporated into annotations and indexed

• Character recognition - 83%Word recognition - 70%

• Language model post processing will improve word recognition rate, but new names and places will not be in language model

• Important adjunct to Name-It: name/face correlation through co-occurrence matrices

Previous slide

Next slide

Back to first slide

View graphic version