Most face recognition systems only work well under quite constrained environments. In particular, the illumination conditions, facial expressions and head pose must be tightly con...
The problem of cosegmentation consists of segmenting the same object (or objects of the same class) in two or more distinct images. Recently a number of different models have been...
Most current methods for multi-class object classification and localization work as independent 1-vs-rest classifiers. They decide whether and where an object is visible in an imag...
Structured light vision systems have been successfully used for accurate measurement of 3-D surfaces in computer vision. However, their applications are mainly limited to scanning ...
— This paper describes the mapping of a recently introduced template matching algorithm based on the Normalized Cross Correlation (NCC) on a general purpose processor endowed wit...
Luigi di Stefano, Stefano Mattoccia, Federico Tomb...