Foreground segmentation based on multi-resolution and matting
This is an incremental improvement for computer vision applications requiring robust foreground extraction.
The paper tackles foreground segmentation by combining multi-resolution analysis with matting to handle cluttered backgrounds and loose bounding boxes, achieving success in experiments on challenging images.
We propose a foreground segmentation algorithm that does foreground extraction under different scales and refines the result by matting. First, the input image is filtered and resampled to 5 different resolutions. Then each of them is segmented by adaptive figure-ground classification and the best segmentation is automatically selected by an evaluation score that maximizes the difference between foreground and background. This segmentation is upsampled to the original size, and a corresponding trimap is built. Closed-form matting is employed to label the boundary region, and the result is refined by a final figure-ground classification. Experiments show the success of our method in treating challenging images with cluttered background and adapting to loose initial bounding-box.