Video OCR: indexing digital news libraries by recognition of superimposed captions

The automatic extraction and recognition of news captions and annotations c an be of great help locating topics of interest in digital news video libra ries. To achieve this goal, we present a technique, called Video OCR (Optic al Character Reader), which detects, extracts, and reads text areas in digi tal video data. In this paper, we address problems, describe the method by which Video OCR operates, and suggest applications for its use in digital n ews archives. To solve two problems of character recognition for videos, lo w-resolution characters and extremely complex backgrounds, we apply an inte rpolation filter, multiframe integration and character extraction filters. Character segmentation is performed by a recognition-based segmentation met hod, and intermediate character recognition results are used to improve the segmentation. We also include a method for locating text areas using text- like properties and the use of a language-based postprocessing technique to increase word recognition rates, The overall recognition results are satis factory for use in news indexing. Performing Video OCR on news video and co mbining its results with other video understanding techniques will improve the overall understanding of the news video content.