We address document image classification by visual appearance. An image is represented by a variable-length list of visually salient features. A hierarchical Bayesian network is ...
In this paper, we propose a generalized shock model for the enhancement and restoration of degraded gray-level character images. This model is a quasi-linear hyperbolic partial di...
A tangible material is a primary element in the everyday creative practice of any craft artist. Although craft artists implicitly understand the expressive aspects of the tangible...
Recently the light-field and lumigraph systems have been proposed as general methods of representing the visual information present in a scene. These methods represent this infor...
Recognizing categories of articulated objects in real-world scenarios is a challenging problem for today's vision algorithms. Due to the large appearance changes and intra-cla...