Abstract: In order to extract caption in digital video, this paper presents a method which utilizes many features of caption such as temporal and spatial, edges, color. The caption’s regions are located by detecting edges so text’s colors are known. Universal Gaussian Mixture Model（GMM） is trained for text’s color. The color layer of texts is extracted based on the trained GMM. The method to judge whether content of caption changes is to add mask bitmap to frame. Experiments show that this method performs well even if the background is complex and the color of caption is not single.

Key words: video caption extraction, edge detection, color modeling, text mask bitmap

摘要： 提出一种综合运用文字边缘特征、颜色信息以及视频时空特性的字幕提取方法。通过边缘检测获取字幕位置进而得到文字颜色，采用全局混合高斯模型对颜色建模，建模完成后直接利用模型从视频文字变化帧中提取文字颜色层。在判断字幕是否变化时，提出了“与”掩码图的方法。实验结果表明，对于复杂背景下包含1~2种颜色字幕颜色的视频，该方法具有良好的提取效果。

关键词: 视频字幕提取, 边缘检测, 颜色建模, 文字掩码图