基于AlexNet网络的服装风格识别分析  

Research and Analysis of Clothing Style Based on AlexNet

作　　者：李淑霞[1] 杨俊成[1,2] LI Shuxia;YANG Juncheng(Department of Computer Engineering, Henan Polytechnic Institute, Nanyang 473000, China;Computer School, Wuhan University, Wuhan 430072, China)

机构地区：[1]河南工业职业技术学院电子信息工程学院,河南南阳473000 [2]武汉大学计算机学院,湖北武汉430072

出　　处：《微型电脑应用》2022年第1期48-50,54,共4页Microcomputer Applications

基　　金：河南省高等学校青年骨干教师培养计划(2018GGJS230);河南工业职业技术学院青年骨干教师培养计划;全国高等院校计算机基础教育研究会纵向课题(2020-AFCEC-196)。

摘　　要：将深度学习引入机器学习使人工智能的研究上了一个新的台阶,深度学习的建模与表征能力强大,在图像处理领域有着非常重要的作用,这为服装风格分类提供了发展机会。为了进一步得到服装图片的风格信息,对原始训练集进行图片增广,扩增数据集,同时通过训练AlexNet卷积神经网络模型,对扩充数据集进行服装风格分类,从而提高服装风格识别精度。Introducing deep learning into machine learning has advanced a new level for the study of artificial intelligence.Deep learning has strong modeling and representation capabilities,it plays a very important role in the field of image processing.At the same time,it also provides development for clothing style classification.In order to get the style information of the clothing pictures,this paper enhances the original training set with pictures,augmented data sets,at the same time,the AlexNet convolutional neural network model is used to classify the clothing style of the expanded data set.Thus,the accuracy of clothing style recognition is improved.

关 键 词：深度学习 机器学习 AlexNet卷积神经网络 服装风格 服装图片 

分 类 号：TS941.1[轻工技术与工程—服装设计与工程]