Abstract. Experimenting and building integrated, operational systems in computational vision poses both theoretical and practical challenges, involving methodologies from control t...
The Discrete Pulse Transform (DPT), a well known method for the analysis of signals, was recently extended to images. Here we propose an efficient algorithm generating DPT on a g...
The maximum flow algorithm for minimizing energy functions of binary variables has become a standard tool in computer vision. In many cases, unary costs of the energy depend linea...
Maximum likelihood (ML) estimation is widely used in many computer vision problems involving the estimation of geometric parameters, from conic fitting to bundle adjustment for s...
Traditionally computer vision and pattern recognition algorithms are evaluated by measuring differences between final interpretations and ground truth. These black-box evaluations ...
Richard Zanibbi, Dorothea Blostein, James R. Cordy