DocumentCode :
13997
Title :
Asymmetric Pruning for Learning Cascade Detectors
Author :
Paisitkriangkrai, Sakrapee ; Chunhua Shen ; van den Hengel, A.
Author_Institution :
Australian Center for Visual Technol., Univ. of Adelaide, Adelaide, SA, Australia
Volume :
16
Issue :
5
fYear :
2014
fDate :
Aug. 2014
Firstpage :
1254
Lastpage :
1267
Abstract :
Cascade classifiers are one of the most important contributions to real-time object detection. Nonetheless, there are many challenging problems arising in training cascade detectors. One common issue is that the node classifier is trained with a symmetric classifier. Having a low misclassification error rate does not guarantee an optimal node learning goal in cascade classifiers, i.e., an extremely high detection rate with a moderate false positive rate. In this work, we present a new approach to train an effective node classifier in a cascade detector. The algorithm is based on two key observations: 1) Redundant weak classifiers can be safely discarded; 2) The final detector should satisfy the asymmetric learning objective of the cascade architecture. To achieve this, we separate the classifier training into two steps: finding a pool of discriminative weak classifiers/features and training the final classifier by pruning weak classifiers which contribute little to the asymmetric learning criterion (asymmetric classifier construction). Our model reduction approach helps accelerate the learning time while achieving the pre-determined learning objective. Experimental results on both face and car data sets verify the effectiveness of the proposed algorithm. On the FDDB face data sets, our approach achieves the state-of-the-art performance, which demonstrates the advantage of our approach.
Keywords :
face recognition; learning (artificial intelligence); object detection; pattern classification; real-time systems; FDDB face data sets; asymmetric pruning; cascade architecture; cascade classifiers; learning cascade detectors; misclassification error; optimal node learning; real-time object detection; symmetric classifier; Boosting; Detectors; Face; Feature extraction; Object detection; Real-time systems; Training; Asymmetric classification; asymmetric pruning; boosting; cascade classifier; feature selection; object detection;
fLanguage :
English
Journal_Title :
Multimedia, IEEE Transactions on
Publisher :
ieee
ISSN :
1520-9210
Type :
jour
DOI :
10.1109/TMM.2014.2308723
Filename :
6750697
Link To Document :
بازگشت