Ranklets: Orientation Selective Non-Parametric Features Applied to Face Detection
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 3 - Volume 3
Object Recognition from Local Scale-Invariant Features
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Statistical Comparisons of Classifiers over Multiple Data Sets
The Journal of Machine Learning Research
Real-time object detection using an evolutionary boosting strategy
Proceedings of the 2006 conference on Artificial Intelligence Research and Development
Hi-index | 0.00 |
The complexity of any learning task depends as in the learning method as on finding a good representation of the data. In the concrete case of object recognition in computer vision, the representation of the images is one of the most important decisions in the design step. As a starting point, in this work we use the representation based on Haar-like filters, a biological inspired feature based on local intensity differences. From this commonly used representation, we jump to the dissociated dipoles, another biological plausible representation which also includes non-local comparisons. After analyzing the benefits of both representations, we present a more general representation which brings together all the good properties of Haar-like and dissociated dipoles representations. All these feature sets are tested with an evolutionary learning algorithm over different object recognition problems. Besides, an extended statistically study of these results is performed in order to verify the relevance of these huge feature spaces applied to different object recognition problems.