摘要
提出了基于模板匹配的集成学习AdaBoost演化算法。在该演化算法中,采取训练正反类样本加权模板的方法来构造各个弱学习分类器,克服了常规的基于单一特征构造弱分类器的不足。实验表明,该算法不仅对印刷体字符和部分手写体数字具有较高的识别率,而且减少了分类器构造的训练时间,是稳定、有效的算法。
t: An evolutionary algorithm of AdaBoost based on template match was proposed. The algorithm used weighted templates to structure each weak learning classifier, which overcame the shortcoming of structuring classifier by using a single feature. Experiments show that the proposed algorithm can not only obtain high recognition accuracy for printing character and some kinds of handwritten digits, but also enormously shorten the training time when structuring classifiers. The evolutionary algorithm is stable and effective.
出处
《计算机应用》
CSCD
北大核心
2007年第12期3072-3074,共3页
journal of Computer Applications