Due to distortion, noise, segmentation errors, overlap, and occlusion of objects in digital images, it is usually impossible to extract complete object contours or to segment the ...
Content-based image retrieval, which provides convenient ways to retrieve images from large image databases, has been studied actively. While many previous image retrieval techniq...
Jun-Wei Hsieh, W. Eric L. Grimson, Cheng-Chin Chia...
The use of statistical shape models is a promising approach for robust segmentation of medical images. One of the major challenges in building a 3D shape model from a training set ...
We present an over-segmentation based, dense stereo algorithm that jointly estimates segmentation and depth. For mixed pixels on segment boundaries, the algorithm computes foregro...
Yuichi Taguchi, Bennett Wilburn, C. Lawrence Zitni...
Mean shift is a nonparametric estimator of density which has been applied to image and video segmentation. Traditional mean shift based segmentation uses a radially symmetric kerne...
Jue Wang, Bo Thiesson, Yingqing Xu, Michael F. Coh...