Orientation invariant features for multiclass object recognition

Conference Article


Iberoamerican Congress on Pattern Recognition (CIARP)





Doc link


Download the digital copy of the doc pdf document


We present a framework for object recognition based on simple scale and orientation invariant local features that when combined with a hierarchical multiclass boosting mechanism produce robust classifiers for a limited number of object classes in cluttered backgrounds. The system extracts the most relevant features from a set of training samples and builds a hierarchical structure of them. By focusing on those features common to all trained objects, and also searching for those features particular to a reduced number of classes, and eventually, to each object class. To allow for efficient rotation invariance, we propose the use of non-Gaussian steerable filters, together with an Orientation Integral Image for a speedy computation of local orientation.


automation, pattern recognition.

Author keywords

vision, object detection, invariant feature

Scientific reference

M. Villamizar, A. Sanfeliu and J. Andrade-Cetto. Orientation invariant features for multiclass object recognition, 11th Iberoamerican Congress on Pattern Recognition, 2006, Cancún, Mèxic, in Progress in Pattern Recognition, Image Analysis and Applications, Vol 4225 of Lecture Notes in Computer Science, pp. 655-664, 2006, Springer, Berlin, Alemanya.