摘要
针对复杂环境下人脸图像美感分类准确率低的问题,给出一种适用于人脸图像美感分类的网络模型F-Net。该模型以LeNet-5为基础网络,使用卷积层提取复杂背景下的人脸图像特征,优化网络模型中的参数,改变模型中卷积层和全连接层特征元的数量。结果表明,本文给出的F-Net网络模型在复杂环境背景下的人脸图像分类准确率达到73%,较其他经典的卷积神经网络分类模型相比性能更佳。
Aimed at the problem that the accuracy of face image classification in complex environment is not high,a network model F-Net suitable for aesthetic classification of face images is proposed.Based on LeNet-5,the model uses convolutional layers to extract facial image features in complex backgrounds,optimizes parameters in the network model,and changes the number of convolutional layers and fully connected layer feature elements in the model.The experimental results show that the F-Net network model proposed in this paper has a face image classification accuracy of 73%in complex environment background,which is better than other classical convolutional neural network classification models.
作者
吴菲
朱欣娟
吴晓军
MATTHIAS R?tsch
WU Fei;ZHU Xinjuan;WU Xiaojun;MATTHIAS R?tsch(School of Computer Science, Xi′an Polytechnic University, Xi′an 710048, China;School of Computer Science, Shannxi Normal University, Xi′an 710062, China;Department of Mechatronics, Reutlingen University, Reutlingen 72762, Germany)
出处
《西安工程大学学报》
CAS
2019年第6期673-678,共6页
Journal of Xi’an Polytechnic University
基金
国家重点研发计项目(2017YFB1402102)
陕西省重点研发计划项目(2019ZDLSF07-01)
关键词
卷积神经网络
LeNet-5
人脸识别
美感分类
图像处理
convolutional neural network
LeNet-5
face recognition
aesthetic classification
image processing
