基于生成式对抗网络的用户下装搭配推荐

doi:10.13475/j.fzxb.20200803505

纺织学报 ›› 2021, Vol. 42 ›› Issue (07): 164-168.doi: 10.13475/j.fzxb.20200803505

基于生成式对抗网络的用户下装搭配推荐

杨争妍¹, 薛文良¹(), 张传雄², 丁亦¹, 马颜雪¹

1.东华大学纺织学院, 上海 201620
2.纺织工业科学技术发展中心, 北京 100020

收稿日期:2020-08-05 修回日期:2021-04-22 出版日期:2021-07-15 发布日期:2021-07-22
通讯作者: 薛文良
作者简介:杨争妍(1998—),女,硕士生。主要研究方向为人工智能在纺织品设计中的应用。

Recommendations for user's bottoms matching based on generative adversarial networks

YANG Zhengyan¹, XUE Wenliang¹(), ZHANG Chuanxiong², DING Yi¹, MA Yanxue¹

1. College of Textiles, Donghua University, Shanghai 201620, China
2. Science and Technology Development Center of Textile Industry, Beijing 100020, China

Received:2020-08-05 Revised:2021-04-22 Published:2021-07-15 Online:2021-07-22
Contact: XUE Wenliang

摘要/Abstract

摘要：

为解决消费者由于频繁购入相似服装以及不知如何穿搭的问题,设计了一款智能搭配系统,为用户提供穿搭建议,减少重复购入相似衣服导致的浪费。利用爬虫技术获取大量中高端品牌的服装搭配数据,利用深度学习的新兴模型生成式对抗网络,对服装搭配数据进行学习,挖掘搭配的颜色、款式等视觉规律,训练模型能够实现输入上装图像时智能生成下装图像功能,再通过图像相似度计算匹配到用户预设的个人衣柜,最后结合温度为用户推荐合适的下装。通过对比原搭配和模型生成搭配,验证了该方法的有效性,为智能穿搭提供了新思路。

关键词: 深度学习, 生成式对抗网络, 智能穿搭, 服装搭配

Abstract:

In order to avoid repetitive purchases of similar clothes and to solve the clothing matching problem, this research worked on an intelligent clothing matching system for providing recommendations to customers and end-users. A crawler technology was used to obtain a large number of clothing matching data from mid-to-high end brands, and the model of deep learning-generative adversarial network (GAN) was adopted to learn clothing data to explore the visual perceptions of colors, styles, and so on. When inputting a piece of top clothing in the system, a bottom picture can be generated intelligently and then matched to the user's personal wardrobe together with the consideration of the surrounding temperature. The effectiveness of this method was verified by comparing the original matching with the model generated matching.This work provides new ideas for intelligent clothing matching.

Key words: deep learning, generative adversarial networks, intelligent decision on clothing match, clothing match

中图分类号:

TS941.13

杨争妍, 薛文良, 张传雄, 丁亦, 马颜雪. 基于生成式对抗网络的用户下装搭配推荐[J]. 纺织学报, 2021, 42(07): 164-168.

YANG Zhengyan, XUE Wenliang, ZHANG Chuanxiong, DING Yi, MA Yanxue. Recommendations for user's bottoms matching based on generative adversarial networks[J]. Journal of Textile Research, 2021, 42(07): 164-168.

图/表 5

图1

图2

图3

图4

图5

参考文献 10

[1]	唐婕. 基于iOS平台的智能衣柜管理APP的设计与实现[D]. 北京:北京邮电大学, 2017:5-7.
	TANG Jie. Design and implementation of an intelligent clothing management APP based on iOS platform[D]. Beijing:Beijing University of Posts and Telecommunications, 2017:5-7.
[2]	张泽堃, 张海波. 服装智能搭配研究现状综述[J]. 网络安全技术与应用, 2019(10):128-130.
	ZHANG Zekun, ZHANG Haibo. A summary of the research status of intelligent clothing collocation[J]. Network Security Technology and Application, 2019(10):128-130.
[3]	曹纯, 仲兆满. 智能衣物搭配系统的设计与实现[J]. 福建电脑, 2019, 35(7):21-25.
	CAO Chun, ZHONG Zhaoman. Design and implementation of intelligent clothing matching system[J]. Journal of Fujian Computer, 2019, 35(7):21-25.
[4]	梁俊杰, 韦舰晶, 蒋正锋. 生成对抗网络GAN综述[J]. 计算机科学与探索, 2020, 14(1):1-17.
	LIANG Junjie, WEI Jianjing, JIANG Zhengfeng. Overview of GAN generation adversarial network[J]. Computer Science and Exploration, 2020, 14(1):1-17.
[5]	邹秀芳, 朱定局. 生成对抗网络研究综述[J]. 计算机系统应用, 2019, 28(11):1-9.
	ZHOU Xiufang, ZHU Dingju. Review on generative adversarial network[J]. Computer Systems & Applications, 2019, 28(11):1-9.
[6]	ISOLA Phillip, ZHU Junyan, ZHOU Tinghui, et al. Image-to-image translation with conditional adversarial networks[C] // 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). New Jersey: Institute of Electrical and Electronic Engineers, 2017:5967-5976.
[7]	BARDIS Michelle. Deep learning with limited data: organ segmentation performance by U-Net[J]. Electronics, 2020, 9(8) :1199. doi: 10.3390/electronics9081199
[8]	DONG C, LOY C C, HE K, et al. Image Super-Resolution Using Deep Convolutional Networks[C]// IEEE Transactions on Pattern Analysis and Machine Intelligence. New Jersey: Institute of Electrical and Electronic Engineers, 2016: 295-307.
[9]	GULRAJANI I, AHMED F, ARJOVSKY M, et al. Improved training of Wasserstein GANs[C] // NIPS'17 Proceedings of the 31st International Conference on Neural Information Processing Systems. Long Beach: Curran Associates, 2017:5769-5779.
[10]	刘方园, 王水花, 张煜东. 方向梯度直方图综述[J]. 计算机工程与应用, 2017, 53(19):1-7,25.
	LIU Fangyuan, WANG Shuihua, ZHANG Yudong. Survey on histogram-based optimization[J]. Computer Engineering and Applications, 2017, 53(19):1-7,25.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed

基于生成式对抗网络的用户下装搭配推荐

Recommendations for user's bottoms matching based on generative adversarial networks

RichHTML

PDF (PC)

摘要/Abstract

引用本文

使用本文

图/表 5

参考文献 10

相关文章 5

Metrics

本文评价

推荐阅读 0

[1]	甘美辰, 李敏. 女装搭配推荐系统的设计与实现[J]. 纺织学报, 2020, 41(10): 122-131.
[2]	许倩, 陈敏之. 基于深度学习的服装丝缕平衡性评价系统[J]. 纺织学报, 2019, 40(10): 191-195.
[3]	刘正东, 刘以涵, 王首人. 西装识别的深度学习方法[J]. 纺织学报, 2019, 40(04): 158-164.
[4]	汪珊娜张华熊康锋. 基于卷积神经网络的领带花型情感分类[J]. 纺织学报, 2018, 39(08): 117-123.
[5]	何晓昀韦平张林邓斌攸潘云峰苏真伟. 基于深度学习的籽棉中异性纤维检测方法[J]. 纺织学报, 2018, 39(06): 131-135.