Deep convolutional networks (DCNNs) are achieving previously unseen performance in
object classification, raising questions about whether DCNNs operate similarly to human …

Pattern recognition, image processing and computer vision are closely linked areas which
have seen enormous progress in the last fifty years. Their applications in our daily life …

This paper presents an empirical study of personal pronouns in scientific journal articles.
Viewing written text as interaction, this study investigates how the use of personal pronouns …

Twenty Years of Document Image Analysis in PAMI Toggle navigation IEEE Computer
Society Digital Library Jobs Tech News Resource Center Press Room Advertising About Us …

Deep convolutional neural networks (DCNNs) show impressive similarities to the human
visual system. Recent research, however, suggests that DCNNs have limitations in …

A new account of how we perceive the 3D shapes of objects and how to design machines
that can see shapes the way we do. The uniqueness of shape as a perceptual property lies …

We propose a model-based approach to automated 3D extraction of buildings from aerial
images. We focus on a reconstruction strategy that is not restricted to a small class of …

This paper describes an algorithm that robustly locates salient convex collections of line
segments in an image. The algorithm is guaranteed to find all convex sets of line segments …

Vanishing point detection algorithms based on a Gaussian sphere representation have
been employed in a variety of computer vision systems, for extracting 3D line orientations as …

3-D object recognition involves using image-computable features to identify 3-D object. A
single view of a 3-D object may not contain sufficient features to recognize it unambiguously …