Abstract
To resolve the problem that AdaBoost face detection training is very time consuming, the paper put forward a new approach of reducing training time by removing characteristics with little category effect. The main characteristic of the approach is that it can reduce characteristics according to the detection accuracy. Experiments prove that the improved approach can greatly reduce training time in the case of nearly no influence on detection.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsReferences
Lu-Hong L, Hai-Zhou A, Guagn-You X et al (2002) A survey of human face detection. Chin J Comput 25(5):449–458
Viola P, Jones M (2001) Robust real time object detection. In: 8th IEEE international conference on computer vision(ICCV), 2001. IEEE Computer society Press, Vancouver
Freund Y, Schapire RE (1995) A decision-theoretic generalization of on-line learning and an application to boosting. Computational learning theory: eurocolt95, 1995. Springer, Barcelona Spain, Germany
Hai-cuan W, Li-Ming Z (2004) A novel fast training algorithm for Adaboost. J Fudan Univ(Nat Sci) 43(1):27–32
Z Nan, Face detection based on AdaBoost algorithm physics. Physics college of Peking University
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer Science+Business Media, LLC
About this paper
Cite this paper
Wang, X., Liu, Y., Ye, Q., Yue, K. (2012). Face Detection of AdaBoost Fast Training Algorithm Based on Characteristic Reduction. In: Hou, Z. (eds) Measuring Technology and Mechatronics Automation in Electrical Engineering. Lecture Notes in Electrical Engineering, vol 135. Springer, New York, NY. https://doi.org/10.1007/978-1-4614-2185-6_28
Download citation
DOI: https://doi.org/10.1007/978-1-4614-2185-6_28
Published:
Publisher Name: Springer, New York, NY
Print ISBN: 978-1-4614-2184-9
Online ISBN: 978-1-4614-2185-6
eBook Packages: EngineeringEngineering (R0)