一种基于CNN-SE-ELM的年龄和性别识别模型  

An age and gender recognition model based on CNN-SE-ELM

作　　者：陈文兵[1,2] 李育霖 陈允杰 CHEN Wen-bing;LI Yu-lin;CHEN Yun-jie(School of Mathematics and Statistics,Nanjing University of Information Science & Technology,Nanjing 210044;Key Laboratory of Traffic Meteorology,China Meteorological Administration,Nanjing 210009,China)

机构地区：[1]南京信息工程大学数学与统计学院,江苏南京210044 [2]中国气象局交通重点实验室,江苏南京210009

出　　处：《计算机工程与科学》2021年第5期872-882,共11页Computer Engineering & Science

基　　金：国家自然科学基金(61672291);北极阁基金(BJG201504)。

摘　　要：基于人脸图像识别年龄及性别是当前人工智能研究的热点之一。提出一种综合卷积神经网络CNN、挤压-激励网络SENet及极限学习机ELM的混合模型。模型中的卷积层用于从人脸图像中提取面部特征,SENet层用于优化卷积层提取的特征,误差最小化极限学习机(EM-ELM)用作分类器以实现面部图像的年龄及性别识别。与现有的流行模型相比,所提模型由于采用了CNN+SENet架构能够从面部图像中提取到更具代表性及最优的特征映射,而EM-ELM的极速计算使得模型更快速、更高效。在多个非限制人脸数据集上的实验结果表明,相比近期其他基于深度学习的相关模型,所提模型具有更高的识别准确率和更快的识别速度。Recognizing age and gender based on facial images is one of the current hot spots in artificial intelligence research.This paper proposes a hybrid model that integrates Convolution Neural Network(CNN),Squeeze-Excitation Network(SENet)and Extreme Learning Machine(ELM).The con-volutional layer in the model is used to extract facial features from the face image,the SEnet layer is used to optimize the features extracted by the convolutional layer,and the error minimization extreme learning machine(EM-ELM)is used as a classifier to realize the age and gender recognition of facial images.Compared with the existing popular models,the proposed model adopts the CNN+SENet architecture so that it can extract more representative and optimal feature maps from facial images,and the extremely fast calculation of EM-ELM makes the model faster and more efficient.Experimental results on multiple unrestricted face datasets show that the proposed model has higher recognition accuracy and speed than other recent related models based on deep learning.

关 键 词：卷积神经网络 极限学习机 SENet网络 年龄分类 性别分类 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]