基于AdaBoost和AAM的面部特征点检测技术研究  

Research on Facial Feature Point Detection Technology Based on AdaBoost and AAM

作　　者：贾晓琪 JIA Xiaoqi(Department of Computer and Information Engineering,Shanxi Institute of Energy,Jinzhong 030600,China)

机构地区：[1]山西能源学院计算机与信息工程系,山西晋中030600

出　　处：《现代信息科技》2024年第18期172-175,共4页Modern Information Technology

摘　　要：文章报告了面部特征点检测的现状,分析了AdaBoost算法的分类性能和AAM模型的建模特性。对面部特征点检测进行了研究,通过训练多个弱分类器并组合它们,提高了面部特征点检测的准确性和鲁棒性。利用AdaBoost强分类器识别的结果作为AAM模型训练的输入,提取面部特征点候选区域,降低了AAM模型重构次数,进一步降低了计算复杂度,尤其是在面部姿态和表情变化较大的情况下,提高了匹配的准确率。同时,AAM模型可以为AdaBoost提供一个更为精细的面部特征点定位,从而提高整体的面部特征点检测性能。This paper reports the current status of facial feature point detection and analyzes the classification performance of the AdaBoost algorithm and the modeling characteristics of the AAM model.It researches the facial feature point detection,and improves the accuracy and robustness by training multiple weak classifiers and combining them.It uses the results identified by the AdaBoost strong classifier as inputs for training the AAM model,extracts candidate regions for facial feature points,reduces the reconstruction frequency of the AAM model and further lowers the computational complexity,particularly in cases where there are significant variations in facial pose and expression,thereby improving the matching accuracy.Additionally,the AAM model can provide a more precise localization of facial feature points for AdaBoost,thus enhancing the overall performance of facial feature point detection.

关 键 词：特征点检测 ADABOOST AAM模型 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]