We combine and extend the previous work on DCT-based image signatures and face detection to determine the visual saliency. To this end, we transfer the scalar definition of image...
In this paper, using hypergraph theory, we introduce an image model called Adaptive Image Neighborhood Hypergraph (AINH). From this model we propose a combinatorial definition of ...
Retrieving images in response to textual queries requires some knowledge of the semantics of the picture. Here, we show how we can do both automatic image annotation and retrieval...
A statistical correlation model for image retrieval is proposed. This model captures the semantic relationships among images in a database from simple statistics of userprovided r...
—In this paper, we present a robust and accurate algorithm for interactive image segmentation. The level set method is clearly advantageous for image objects with a complex topol...