Video text recognition using feature compensation as category-dependent feature extraction
ICDAR '03 Proceedings of the Seventh International Conference on Document Analysis and Recognition - Volume 2
| Hi-index | 0.00 |
The recognition of telop characters in video has two problems: edge degradation and background noise. To overcome these problems, this paper proposes; (1) a feature that describes the shape of background region in addition to character region, (2) a classifier that dynamically decreases the influence of noise using the difference in number of pixel within a local area.Experiments show that the two proposals achieve the recognition rate of 76% and the cumulative classification rate within the best ten of 92%. Both values are significantly better than those of conventional methods.