在复杂背景下,传统的视频文字自动定位方法难以稳健地定位文字。丈章提出一种基于小波变换和穿越线的视频文字定位方法,该方法分为两个阶段,在第一阶段,利用小波变换和非监督聚类方法来获得候选文字区域;在第二阶段,引入穿越线和及其幅度谱概念,通过提取穿越线特征进行聚类来定位单行文字。实验表明,该方法能够在复杂背景下有效定位文字,不受文字颜色、字体、大小等因素的影响,性能优于文献和文献提出的方法。
In the complicated background, conventional automatic video-text location methods can not robustly locate text. Anovel video-text location method is proposed in this paper. It falls into two stages: in the first stage, an unsupervised paradigm based on wavelet is applied to obtain candidate text region; in the second stage, traversing line with its amplitude spectrum is introduced and applied to create boundary for each text line. Experiment indicates that this scheme can robustly locate the text of various colors, fonts, and sizes in the complicated background, and performs better than schemes in and .