Abstract | ||
---|---|---|
We present a heuristic approach to enhancing speech synchronized captions for video OCR, as a pre-process for subsequent tasks of multimedia indexing, segmentation and retrieval. We use a bi-search based caption transition detection method to improve efficiency, which adopts a simple heuristics that the same caption content usually lasts for a period for stable viewing. We propose a combination of color mask, changing mask and region mask to perform caption enhancement based on the discriminative characteristics of captions and backgrounds. Elaborate enhancement on individual characters is further used to remove small background residues. OCR experiments show that our caption enhancement approach brings a high character accuracy of 89.24%. |
Year | DOI | Venue |
---|---|---|
2008 | 10.1007/978-3-540-87442-3_44 | ICIC (1) |
Keywords | Field | DocType |
video ocr,caption transition detection method,heuristic approach,color mask,region mask,caption content,ocr experiment,caption enhancement,elaborate enhancement,caption enhancement approach,effective video ocr | Computer vision,Heuristic,Video retrieval,Segmentation,Computer science,Speech recognition,Heuristics,Artificial intelligence,Discriminative model,Multimedia indexing | Conference |
Volume | ISSN | Citations |
5226 | 0302-9743 | 0 |
PageRank | References | Authors |
0.34 | 6 | 2 |