Abstract. We propose a new generative model, and a new image similarity kernel based on a linked hierarchy of probabilistic segmentations. The model is used to efficiently segment ...
We report an automatic feature discovery method that achieves results comparable to a manually chosen, larger feature set on a document image content extraction problem: the locat...
Texture is a fundamental feature which provides significant information for image classification, and is an important content used in content-based image retrieval (CBIR) system. ...
We propose an adaptive figure-ground classification algorithm to automatically extract a foreground region using a user-provided bounding-box. The image is first over-segmented wi...
We present a new approach to robust pose-variant face
recognition, which exhibits excellent generalization ability
even across completely different datasets due to its weak
depe...
John Wright (University of Illinois), Gang Hua (Mi...