The modified Adaboost algorithm for Chinese handwritten character recognitionThe modified Adaboost algorithm for Chinese handwritten character recognition

Ding Xiaoqing、Fu Qiang

Strategic Study of CAE ›› 2009, Vol. 11 ›› Issue (10) : 19-24.

PDF(1100 KB)
PDF(1100 KB)
Strategic Study of CAE ›› 2009, Vol. 11 ›› Issue (10) : 19-24.

The modified Adaboost algorithm for Chinese handwritten character recognitionThe modified Adaboost algorithm for Chinese handwritten character recognition

  • Ding Xiaoqing、Fu Qiang

Author information +
History +

Abstract

The proposed modified Adaboost algorithm adopts the descriptive model based on multi-class classifiers (modified quadratic discriminant function, MQDF) as element classifiers which perform multi-class classification directly. It does not need to convert multi-class classifications to multiple binary classifications and has lower training complexity. Besides, it updates sample weights according to the generalized confidence which is simple and effective. In order to reduce the recognition complexity, the pruning method was performed to pick out only one best element classifier from all boosted classifiers to do the classification. Applying the algorithm to Chinese handwritten character recognition on HCL2000 and THOCR-HCD databases, the relative error rate reduced 14.3 %, 8.1 % and 19.5 % respectively.

Keywords

multiclass Adaboost algorithm / Chinese handwritten character recognition / generalized confidence / modified quadratic discriminant function

Cite this article

Download citation ▾
Ding Xiaoqing,Fu Qiang. The modified Adaboost algorithm for Chinese handwritten character recognitionThe modified Adaboost algorithm for Chinese handwritten character recognition. Strategic Study of CAE, 2009, 11(10): 19‒24
AI Summary AI Mindmap
PDF(1100 KB)

Accesses

Citations

Detail

Sections
Recommended

/