重庆理工大学学报（自然科学版）2017，Vol.31Issue(3)：110-115,6.DOI:10.3969/j.issn.1674-8425(z).2017.03.016
基于改进的卷积神经网络的图像分类性能
Research on Image Classification Performance Based on Improved Convolution Neural Network
摘要
Abstract
An improved convolution neural network is applied to image object recognition.In order to improve the accuracy of classification prediction,this paper improves the structure of the basic convolution neural network.The concrete structure is as follows:Convolution layer C1-Pool layer S1-Convolution layer C2-Pool layer S2-Convolution layer C3-pool Layer S3-full-connect layer FC-output,ant it mainly increased the number of convolution layers,and unified selection of 5 × 5 in the convolution filter specification.Finally,this model is compared with other models (ReNet,APAC,PACNet) for CIFAR-10 database.Through the final prediction accuracy,it can be seen that the improved convolutional nerve has a better precision of 90.37％ than the other three models.关键词
卷积神经网络/图像分类技术/卷积层/池化层Key words
convolution neural network/image classification technique/convolution layer/pooling layer分类
信息技术与安全科学引用本文复制引用
常祥,杨明..基于改进的卷积神经网络的图像分类性能[J].重庆理工大学学报（自然科学版）,2017,31(3):110-115,6.基金项目
国家自然科学基金资助项目(61171179) （61171179）
