2024-03-29T12:12:53Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/963152019-06-11T11:23:47Zcom_10261_106com_10261_4col_10261_359
Bootstrapping boosted random Ferns for discriminative and efficient object classification
Villamizar, Michael
Andrade-Cetto, Juan
Sanfeliu, Alberto
Moreno-Noguer, Francesc
European Commission
Random ferns
Object detection
Boosting
Bootstrapping
Best Papers of Iberian Conference on Pattern Recognition and Image Analysis (IbPRIA'2011).
In this paper we show that the performance of binary classifiers based on Boosted Random Ferns can be significantly improved by appropriately bootstrapping the training step. This results in a classifier which is both highly discriminant and computationally efficient and is particularly suitable when only small sets of training images are available. During the learning process, a small set of labeled images is used to train the boosting binary classifier. The classifier is then evaluated over the training set and warped versions of the classified and misclassified patches are progressively added into the positive and negative sample sets for a new retraining step. In this paper we thoroughly study the conditions under which this bootstrapping scheme improves the detection rates. In particular we assess the quality of detection both as a function of the number of bootstrapping iterations and the size of the training set. We compare our algorithm against state-of-the-art approaches for several databases including faces, cars, motorbikes and horses, and show remarkable improvements in detection rates with just a few bootstrapping steps.
2014-05-07T10:58:14Z
2014-05-07T10:58:14Z
2012
2014-05-07T10:58:14Z
artículo
Pattern Recognition 45(9): 3141-3153 (2012)
http://hdl.handle.net/10261/96315
10.1016/j.patcog.2012.03.025
http://dx.doi.org/10.13039/501100000780
eng
Preprint
http://dx.doi.org/10.1016/j.patcog.2012.03.025
Sí
info:eu-repo/grantAgreement/EC/FP7/287617
info:eu-repo/grantAgreement/EC/FP7/258749
openAccess
Elsevier