Telop and flip frame detection and character extraction from TV news articles

The purpose of this study is to automatically extract telop and flip characters. The process starts with the extraction of stable frame sections including the telop and flip characters. The next process is character region extraction and we propose the application of local line density to discriminate the telop characters from other elements such as lines and symbols. The final process is telop character extraction and we show the effectiveness of floating adaptive three level thresholding (FATLT) which thresholds the image intensity into three levels and finally binarizes the character regions precisely even at low contrast, taking topological relationships between characters and their background into consideration.