摘要
传统的服装分类方法主要是提取图像的颜色、纹理、边缘等特征,过程繁琐且分类精度较低。为了提高服装图像的分类性能和时效性,提出一种基于迁移学习的卷积神经网络服装图像分类方法。将训练好的模型在服装图像数据集上进行迁移训练,保留预训练模型所有卷积层的参数,冻结前层网络参数并精调网络模型,使其能适应服装图像的识别。选取VGG16等六种模型并以DeepFashion为实验数据集进行实验,结果表明,迁移学习后,模型分类精度和时效性得到有效提高。
The traditional clothing classification method is mainly to extract the color,texture,edge and other features of the image.These methods of selecting features are cumbersome and the classification accuracy is low.In order to improve the classification performance and timeliness of clothing images,this paper proposes a classification method of convolutional neural network clothing images based on transfer learning.It transferred the trained model on the clothing image data set,retained the parameters of all convolution layers of the pre-training model,and frozen the network parameters of the front layer and fine-tuned the network model,so that it could adapt it to the recognition of the clothing image.Six models such as VGG16 were selected and the experiment was carried out with DeepFashion as the experimental data set.The results show that these models are effectively improved in classification accuracy and timeliness after transfer learning.
作者
谢小红
陆建波
李文韬
刘春霞
黄华梅
Xie Xiaohong;Lu Jianbo;Li Wentao;Liu Chunxia;Huang Huamei(School of Computer and Information Engineering,Nanning Normal University,Nanning 530299,Guangxi,China)
出处
《计算机应用与软件》
北大核心
2020年第9期88-93,共6页
Computer Applications and Software
基金
国家自然科学基金项目(61866006)
广西创新驱动发展专项资金项目(桂科AA18118047)。
关键词
迁移学习
服装识别分类
深度学习
卷积神经网络
Transfer learning
Clothing identification and classification
Deep learning
Convolutional neural network
