以獨立成份分析法進行影片字幕粹取

Abstract

在本論文中，我們針對影片中的字幕提出一個創新的文字粹取方法，在此，我們利用獨立成份分析法（Independent Component Analysis, ICA）來分離影像中的文字區及非文字區。為了符合ICA的處理程序，我們提出了兩種資料的表示方法，分別為「片段特徵表示方式」及「單張影像特徵表示方式」。為了分析本方法的強韌性（robustness），我們改變了字幕中文字的字型、顏色、尺寸以及排列方式。本研究採用影像的灰階強度做為特徵，實驗結果顯示本研究所提出的方法比傳統的方法能更有效率且更正確分離出影像中的文字區域及非文字區域。

In this paper, a new text extraction method is proposed for digital video. The text in the video frames is extracted by means of the independent component analysis (ICA). Two representations of the image frames are introduced to fit the need of the ICA procedure. The font, color, scale, and orientation of the subtitles in the sample videos are changed to evaluate the performance of our method. We use the gray values as the features. The experimental results show that the method we developed in this research can extract the texts in digital video more efficiently and accurately than the conventional work, without any influence on the variations of font, color, scale, and orientation of texts.