Most approaches to learn classifiers for structured objects (e.g., images) use generative models in a classical Bayesian framework. However, state-of-the-art classifiers for vecto...
Abstract—The traditional virtual machine usage model advocates placing security mechanisms in a trusted VM layer and letting the untrusted guest OS run unaware of the presence of...
Daniela Alvim Seabra de Oliveira, Shyhtsun Felix W...
The rapid growth of XML adoption has urged for the need of a proper representation for semi-structured documents, where the document structural information has to be taken into ac...
Convolution surface has the advantage of being crease-free and bulge-free over other kinds of implicit surfaces. Among the various types of skeletal elements, line segments can be...
Decoding noisy document images is commonly needed in applications such as enterprise content management. Available OCR solutions are still not satisfactory especially on noisy ima...