Computer Engineering and Applications ›› 2019, Vol. 55 ›› Issue (21): 135-141.DOI: 10.3778/j.issn.1002-8331.1903-0045

Previous Articles     Next Articles

Research on Face Age Estimation Based on Multi-Scale YOLO Model

FANG Guozhi, SUN Kangtong   

  1. College of Measurement and Control Technology and Communication Engineering, Harbin University of Science and Technology, Harbin 150080, China
  • Online:2019-11-01 Published:2019-10-30



  1. 哈尔滨理工大学 测控技术与通信工程学院,哈尔滨 150080

Abstract: To improve the accuracy of age estimation in face images, a feature extraction method based on YOLO model is proposed. The idea of multi-scale regression is applied to Convolutional Neural Network(CNN), which improves the ability of extracting small-scale targets by multi-scale convolution. Combining the idea of feature channel weighting, the problem of feature information loss in feature extraction operation is improved. A decision tree regression is constructed to obtain age estimation. The Mean Absolute Error(MAE) is 3.43 on FG-NET, and the interval matching(AEM) is 62.4% on GROUP dataset. The experimental results show that the face information can be detected more accurately by multi-scale feature regression and channel weight allocation, and a more robust face age estimation model can be established.

Key words: face age estimation, feature extraction algorithm, convolutional neural network, characteristic channel weight assignment, multiscale feature regression

摘要: 通过观察人脸估计年龄较为常见,但如何准确预测年龄则是一个难题。为提高人脸图像年龄估计的准确率,提出一种基于YOLO(You Only Look Once)模型的目标检测方法。将多尺度回归思想应用于卷积神经网络(Convolutional Neural Network,CNN),通过多尺度卷积改善模型对小尺寸目标的提取能力,结合特征通道分权重思想,改善特征提取操作中特征信息丢失的问题,构造决策树回归得到年龄估计。这种方法在人脸年龄图像库FG-NET上获得平均绝对误差(MAE)3.43,在GROUP数据集获得区间匹配度(AEM)62.4%。实验结果表明,通过多尺度特征回归以及通道权重分配,可以较为准确地进行人脸信息检测,并由此建立鲁棒性更强的人脸年龄估计模型。

关键词: 人脸年龄估计, 特征提取算法, 卷积神经网络, 特征通道权重分配, 多尺度特征回归