비디오 자막 추출을 위한 색상 극화 알고리즘

Abstract

In this paper, we propose a color polarity method to extract text regions in videos. Based on the observation for the text and background regions, the proposed method uses the ratios of sizes and standard deviations of bright and dark regions. At first, we employ Otsu`s method for binarization of gray scale image. The two largest segments among the bright and the dark regions are selected and the ratio of their sizes is defined as the first measure for color polarity classification. Again, we select the segments that have the smallest standard deviation of the distance from its center among two groups of regions and evaluate the ratio of their standard deviations as the second measure. We use these two ratio features to determine the text color polarity. The proposed method robustly classify color polarity of the text, which has shown by experimental results for various font types and sizes.