We describe a segmentation method and associated file format for storing images of color documents. We separate each page of the document into three layers, containing the backgro...
Daniel P. Huttenlocher, Pedro F. Felzenszwalb, Wil...
In this paper, a discriminative representation method of head images is proposed, which is based on parts and poses for identity-independent head pose estimation. Head images are ...
We propose a new scheme, named contourlet, that provides a flexible multiresolution, local and directional image expansion. The contourlet transform is realized efficiently via a ...
Human visual recognition is based largely on shape, yet effectively using shapes in natural image retrieval is a challenging task. Most existing methods are based on the geometric...
Recent work has shown impressive transform-invariant modeling and clustering for sets of images of objects with similar appearance. We seek to expand these capabilities to sets of...