Abstract:
Video text can play a vital role in content-based video indexing, retrieval and analysis. Text tracking can speed up the text extraction process for videos. A methodology for text tracking approach is proposed in this paper for efficient multimedia indexing and retrieval. The method employs fuzzy logic based text tracking for videos. Single output rule-based fuzzy inference engine was applied on multiple inputs for text tracking. The analysis of a diverse dataset indicated that the proposed method can be successfully applied for text tracking in videos.