Conditional random field for text segmentation from images with complex background

Text contained in images and video frames provide important clues for information indexing and retrieval. But it is difficult to segment text from images, especially those images with complex background. This paper presents a new conditional random field approach, in which contextual features are introduced into text segmentation. Local visual information and contextual label information are integrated into a conditional random field by several components. Some components focus on visual image information to predict the category within the image sites, while others focus on contextual label information to determine the patterns within the label field. Integrating contextual label information in conditional random field can effectively resolve local ambiguities and improve text segmentation performance in complex background. The comparing results demonstrate that the proposed method outperforms other methods for text segmentation from complex background.