Foreground segmentation based on multi-resolution and matting

• DOI: 10.48550/arxiv.1402.2013
• Publication Date: 2014-01-01
• Authors: Xintong Yu; Xiaohan Liu; Yisong Chen
• Keywords: Minimum bounding box; Figure–ground; Bounding overwatch

We propose a foreground segmentation algorithm that does extraction under different scales and refines the result by matting. First, input image is filtered resampled to 5 resolutions. Then each of them segmented adaptive figure-ground classification best automatically selected an evaluation score maximizes difference between background. This upsampled original size, corresponding trimap built. Closed-form matting employed label boundary region, refined final classification. Experiments show success our method in treating challenging images with cluttered background adapting loose initial bounding-box.