A revised training mechanism for AdaBoost algorithm

Abstract

Focusing on the disadvantages of classical AdaBoost algorithm, this paper mainly analyzes the issues of excessive training, overfitting for classifiers and time-consuming in the training process, and a new method is advanced to avoid the problems. The new method is to update the training samples in time, regulate the update rules of sample weights and buffer the computational results of sorted feature values. As a result, the method used for training a cascade license plate, the experimental results show that the new method does not lead to the issues of excessive training, overfitting and time-consuming like classical AdaBoost often does, and moreover, the training time is shorted to 50 percent with a high detection rate and a low false alarm rate.