Video text extraction using temporal feature vectors
Xiaoau Tang, Bo Luo, Xinbo Gao, Edwige E. Pissaloux, Hangjiang Zhan · 2003
A new caption text extraction algorithm that takes full advantage of the temporal information in a video sequence is developed. By detecting the (dis)appearance of caption text in a video stream, we first identify the video segment that contains the same caption text. Then using the gray-level vector traced across the segment as the feature vector for a pixel point, we can clearly separate a caption pixel from a background pixel for the entire segment.