2024-03-29T11:28:05Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/303072019-05-31T10:53:39Zcom_10261_106com_10261_4col_10261_1241
Orientation invariant features for multiclass object recognition
Villamizar, Michael
Sanfeliu, Alberto
Andrade-Cetto, Juan
Ministerio de Educación y Ciencia (España)
European Commission
Vision
Object detection
Invariant feature
Automation
Pattern recognition
Automation
Pattern recognition systems
Presentado al 11th Iberoamerican Congress on Pattern Recognition (CIARP/2006) celebrado en Cancún (México).
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.
2010-12-17T07:12:00Z
2010-12-17T07:12:00Z
2006
comunicación de congreso
Progress in Pattern Recognition, Image Analysis and Applications: 655-664 (2006)
978-3-540-46556-0
http://hdl.handle.net/10261/30307
10.1007/11892755_68
http://dx.doi.org/10.13039/501100000780
eng
Lecture Notes in Computer Science 4225
http://dx.doi.org/10.1007/11892755_68
openAccess
Springer