— Many modern computer vision algorithms are built atop of a set of low-level feature operators (such as SIFT [1], [2]; HOG [3], [4]; or LBP [5], [6]) that transform raw pixel va...
We present a component-based method and two global methods for face recognition and evaluate them with respect to robustness against pose changes. In the component system we first...
Image variability due to changes in pose and illumination can seriously impair object recognition. This paper presents appearance-based methods which, unlike previous appearance-b...
Athinodoros S. Georghiades, Peter N. Belhumeur, Da...
In several pattern recognition problems, particularly in image recognition ones, there are often a large number of features available, but the number of training samples for each p...
Carlos E. Thomaz, Duncan Fyfe Gillies, Raul Queiro...
—This paper introduces the new color face recognition (FR) method that makes effective use of boosting learning as color-component feature selection framework. The proposed boost...
Jae Young Choi, Yong Man Ro, Konstantinos N. Plata...