摘要
人的年龄变化是引起人脸外观变化的主要原因,由于每个人的生活方式和条件不同,所以很难准确的从人脸图像中估计人的年龄。为此,论文提出一种基于人脸图像的年龄估计方法,利用AAM方法自动提取用于年龄估计的人脸特征,然后按不同年龄段将特征进行分类,为了提高分类的准确性,提出了一种基于PARTIALHAUSDORFF距离的人工免疫识别系统方法,给出了系统的训练、分类实现过程,实验证明了该方法的正确性。
Age changes is the mainly factor of causing variations in the appearance of human faces.Due to many lifestyle factors,it is difficult to precisely estimate age from face images.This paper presents a method to estimate age from facial images.Firstly,we extract the facial features for age estimating automatically using AAM,then classify these facial features by different ages.In order to improve the precision of the classifying,we present a method which is Artificial Immune Recognition System based on Partial Hausdorff distance,describe the process of how to train the system and how to classify the facial features.Experiment results show good estimation performance of our newly presented method.
出处
《计算机工程与应用》
CSCD
北大核心
2006年第26期186-188,共3页
Computer Engineering and Applications
基金
国家自然科学基金重大资助项目(编号:79816101)
中国科学院知识创新工程领域前沿项目
