Title :
Research of Image Detection Based on Improved AdaBoost Algorithm
Author :
Wu, Peng ; Qu, Shenming
Abstract :
In order to prevent more effectively the occurrence of the distortion of target weights’ distribution and further reduce system errors, a comprehensive improvement has been conducted on the algorithm’s weight updating and weight normalization to avoid the defects of the traditional AdaBoost image detection algorithm. It is proved that the improved algorithm is more effective.
Keywords :
Boosting; Computer errors; Computer interfaces; Computer vision; Degradation; Detection algorithms; Distributed computing; Face detection; Machine vision; Man machine systems; AdaBoost algorithm; weight normalization; weight updating;
Conference_Titel :
Machine Vision and Human-Machine Interface (MVHI), 2010 International Conference on
Conference_Location :
Kaifeng, China
Print_ISBN :
978-1-4244-6595-8
Electronic_ISBN :
978-1-4244-6596-5
DOI :
10.1109/MVHI.2010.104
