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. It starts from the extraction of stable frame sections including the telop and flip characters. Next process is the character region extraction and here we propose application of local line density to discriminate the telop characters from other elements such as lines and symbols. Final process is the telop character extraction and we show the effectiveness of the floating adaptive three level thresholding (FATLT) which thresholds the image intensity into three levels and finally binarizes the character regions precisely even in low contrast, taking topological relation between characters and their background into consideration.