Please use this identifier to cite or link to this item: https://hdl.handle.net/2440/85744
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: Asymmetric pruning for learning cascade detectors
Author: Paisitkriangkrai, S.
Shen, C.
van den Hengel, A.
Citation: IEEE Transactions on Multimedia, 2014; 16(5):1254-1267
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Issue Date: 2014
ISSN: 1520-9210
1941-0077
Statement of
Responsibility: 
Sakrapee Paisitkriangkrai, Chunhua Shen, and Anton van den Hengel
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: Asymmetric classification; asymmetric pruning; boosting; cascade classifier; feature selection; object detection
Rights: © 2014 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission
DOI: 10.1109/TMM.2014.2308723
Grant ID: http://purl.org/au-research/grants/arc/FT120100969
Appears in Collections:Aurora harvest 2
Computer Science publications

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.