Real-time control architectures for active vision impose strong constraints on the computational complexity of image processing algorithms. In many cases, fast and reactive visual routines are achieved by drastically reducing the image size, at the cost of degrading the accuracy of the algorithms. The non-uniform sampling of the images, such as the log-polar mapping, is an eecient way of reduci...

In this work we demonstrate the relationship existing between two important issues in vision: multi-scale local spectrum analysis, and log-polar foveatization. We show that, when applying a continuous set of self-similar (rotated and scaled) band-pass filters to estimate the local spectrum at a given point of attention of the image, the inverse Fourier transform of this local spectrum is a log-...

The study of natural image statistics considers the statistical properties of large collections of images from natural scenes, and has applications in image processing, computer vision, and visual computational neuroscience. In the past, a major focus in the field of natural image statistics have been the statistics of outputs of linear filters. Recently, attention has been turning to nonlinear...

Aerial image registration requires a high degree of precision. To improve the feature-based registration accuracy, this paper proposes a novel Log-Polar Transform (LPT) based image registration. Instead of using the whole image in the conventional method, feature points are used here, which reduces the computational time. It is not important how the image patch is rotated for rotation invarianc...

In this work we demonstrate the relationship existing between two important issues in vision: multi-scale local spectrum analysis, and log-polar foveatization. We show that, when applying a continuous set of self-similar (rotated and scaled) band-pass lters to estimate the local spectrum at a given point of attention of the image, the inverse Fourier transform of this local spectrum is a log-po...

We consider log-supermodular models on binary variables, which are probabilistic models with negative log-densities which are submodular. These models provide probabilistic interpretations of common combinatorial optimization tasks such as image segmentation. In this paper, we focus primarily on parameter estimation in the models from known upper-bounds on the intractable log-partition function...