综合肤色模型和多模板匹配增强Adaboost人耳检测

Combining Skin Color Model and Multi-template Matching for Enhancing Adaboost Ear Detection

为克服传统的Adaboost算法出现的样本训练时间过长、过于依赖样本质量等问题,在训练不足及初始人耳定位不好的情况下,引入YCbCr肤色模型和多模板匹配技术策略对人耳进行精确定位。实验表明,改进后的人耳检测性能得到较大的提高,对动、静态人耳均能达到准确定位和检测的效果,算法的鲁棒性较好。

In order to overcome many problems caused by the traditional algorithm of Adaboost,such as the long training time,and excessive dependence on the quality of samples,we introduced the model of YCbCr and the strategies of multi-template matching to perform ear location accurately under the conditions of insufficient training with Adaboost and the bad positioning of raw detection.The experiments of practical detection show the performance of the proposed method is kept well and sufficiently whether under the static or the dynamic environments for ear detection.And the robustness of the algorithm is better.