基于深度学习的女衬衫图案样式识别分类

doi:10.19398/j.att.202109010

现代纺织技术 ›› 2022, Vol. 30 ›› Issue (4): 207-213.DOI: 10.19398/j.att.202109010

基于深度学习的女衬衫图案样式识别分类

李青¹, 冀艳波¹, 郭濠奇², 刘凯旋¹

1.西安工程大学服装与艺术设计学院,西安 710048;
2.江西理工大学电气工程与自动化学院,江西赣州 341000

收稿日期:2021-09-04 出版日期:2022-07-10 网络出版日期:2022-08-25
通讯作者:冀艳波,E-mail:190696850@qq.com
作者简介:李青(1995-),女,河南周口人,硕士研究生,主要从事服装结构设计方面的研究。
基金资助:
陕西省教育厅自然专项基金项目(18JK0352)

Pattern recognition and classification of women's shirts based on deep learning

Li Qing¹, Ji Yanbo¹, Guo Haoqi², Liu Kaixuan¹

1. School of Fashion and Art Design, Xi'an Polytechnic University, Xi'an 710048, China;
2. School of Electrical Engineering and Automation, Jiangxi University of Science and Technology, Ganzhou 341000, China

Received:2021-09-04 Published:2022-07-10 Online:2022-08-25

摘要/Abstract

摘要： 针对服装图案分类效率低的问题,设计一种基于Inception v3算法与迁移学习技术对女衬衫图案进行分类的方法。在Inception v3基础上,拓展训练网络架构,对8121张8类女衬衫图片进行训练,并与GoogLeNet等典型算法模型进行准确率与损失值对比。结果表明:在相同的识别精度上Inception v3具有较好的收敛速率;并且将迁移学习应用到Inception v3优化算法中,在保持初始模型识别速度情况下,可使模型识别平均精度提高6%,达到98%,同时参与训练的参数量减少了约91%。研究结果可有效解决服装图案分类困难问题,并为服装图案可视化分类研究提供技术参考。

关键词: Inception v3, 迁移学习, 衬衫图案, 卷积神经网络

Abstract: In order to solve the problem of low efficiency of clothing pattern classification, a method based on Inception v3 algorithm and transfer learning technology to classify blouse patterns is designed. On the basis of Inception v3, this paper expand the training network architecture. 8121 pictures of blouses are divided into 8 categories to train, and the accuracy and loss value were compared with typical algorithm models such as GoogLeNet. The results show that: Inception v3 has a better convergence rate at the same recognition accuracy; and transfer learning is applied to the Inception v3 optimization algorithm, while maintaining the initial model recognition speed, the average accuracy of model recognition is increased to 98%, and the amount of parameters involved in training has been reduced by 91%. The results of this research can effectively solve the difficult problem of clothing pattern classification and provide a technical reference for its visual classification research.

Key words: Inception v3, transfer learning, patterns of blouses , convolutional neural network

中图分类号:

TB383

李青, 冀艳波, 郭濠奇, 刘凯旋. 基于深度学习的女衬衫图案样式识别分类[J]. 现代纺织技术, 2022, 30(4): 207-213.

Li Qing, Ji Yanbo, Guo Haoqi, Liu Kaixuan. Pattern recognition and classification of women's shirts based on deep learning[J]. Advanced Textile Technology, 2022, 30(4): 207-213.

参考文献

[1] FU R, LI B, GAO Y, et al. Visualizing and analyzing convolution neural networks with gradient information[J]. Neurocomputing, 2018, 293: 12-17.
[2] 盖荣丽,蔡建荣,王诗宇,等.卷积神经网络在图像识别中的应用研究综述[J].小型微型计算机系统,2021,42(9):1980-1984.
GAI Rongli, CAI Jianrong, WANG Shiyu, et al. Research review on image recognition based on deep learning[J]. Journal of Chinese Computer Systems, 2021, 42(9):1980-1984.
[3] 张振焕,周彩兰,梁媛.基于残差的优化卷积神经网络服装分类算法[J].计算机工程与科学,2018,40(2):354-360.
ZHANG Zhenhuan, ZHOU Cailan, LIANG Yuan. An optimized clothing classification algorithm based on residual convolutional neural network[J]. Computer Engineering & Science, 2018, 40(2): 354-360.
[4] 厉智,孙玉宝,王枫,等.基于深度卷积神经网络的服装图像分类检索算法[J].计算机工程,2016,42(11):309-315.
LI Zhi, SUN Yubao, WANG Feng, et al. Clothing image classification and retrieval algorithm based on deep convolutional neural network[J]. Computer Engineering, 2016, 42(11): 309-315.
[5] ZHE X, CHEN S, YAN H. Directional statistics-based deep metric learning for image classification and retrieval[J]. Pattern Recognition, 2019, 93(9):113-123.
[6] 汤清云.基于深度学习特征提取的服装图像检索[D].武汉:华中科技大学,2019.
TANG Qingyun. Clothing Image Retrieval Basedon Deep Learning for Extract Feature[D]. Wuhan: Huazhong University of Science and Technology, 2019.
[7] 于雨桐.基于多特征融合的服装图像款式识别的研究与应用[D].北京:北京工业大学,2016.
YU Yutong. The Research and Application on Clothing Style Image Recognition Based on Multi-Feature Fusion[D]. Beijing: Beijing University of Technology, 2016.
[8] 胡梦莹,钟跃崎.少样本学习下的服装风格分析与评价[J].毛纺科技,2021,49(4):13-17.
HU Mengying, ZHONG Yueqi. Fashion style analysis and evaluation based on few-shot learning[J]. Wool Textile Journal, 2021, 49(4): 13-17.
[9] LÜ N, YAN H, ZHU S, et al. Clothing images attributes classification based on deep neural network[C]//International Conference on Smart Internet of Things (SmartIoT). Tianjing: IEEE, 2019:1187-1193.
[10] LIU Z, LUO P, QIU S, et al. DeepFashion: Powering robust clothes recognition and retrieval with rich annotations[C]//Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016:96-1104.
[11] MEDNIKOV Y, NEHEMIA S, ZHENG B, et al. Transfer representation learning using inception-v3 for the detection of masses in mammography[C]//Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC). Honolulu, Hawaii: IEEE, 2018:2587-2590.
[12] 蔡汉明,刘明.基于Inceptionv3模型的金属板材表面缺陷检测系统[J].轻工机械,2020,163(1):76-79.
CAI Hanming, LIU Ming. Surface defect inspection equipment for sheet metal based on inception-V3 model[J]. Light Industry Machinery, 2020, 38(1): 71-74.
[13] 谢小红,陆建波,李文韬,等.基于迁移学习的服装图像分类模型研究[J].计算机应用与软件,2020,37(9):94-99.
XIE Xiaohong, LU Jianbo, LI Wentao, et al. Classification model of clothing image based on migration learning[J]. Computer Applications and Software, 2020, 37(9):88-93
[14] 康庄,杨杰,郭濠奇.基于机器视觉的垃圾自动分类系统设计[J].浙江大学学报(工学版),2020,54(7):1272-1280.
KANG Zhuang, YANG Jie, GUO Haoqi. Automatic garbage classification system based on machine vision[J]. Journal of Zhejiang University: Engineering Edition, 2020(7): 1272-1280, 1307.
[15] SZEGEDY C, VANHOUCKE V, IOFFE S, et al. Rethinking the inception architecture for computer vision[C]//Conference on Computer Vision and Pattern Recognition (CVPR). Las Vegas, NV, USA: IEEE, 2016:2818-2826.
[16] 庄福振,罗平,何清,等.迁移学习研究进展[J].软件学报,2015,26(1):26-39.
ZHUANG Fuzhen, LUO Ping, HE Qing,et al. Survey on transfer learning research[J]. Journal of Software, 2015, 26(1): 26-39.

基于深度学习的女衬衫图案样式识别分类

Pattern recognition and classification of women's shirts based on deep learning

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 5

编辑推荐

Metrics

[1]	郑雨婷, 王成群, 陈亮亮, 吴江, 吕文涛. 基于卷积神经网络的织物图像识别方法研究进展[J]. 现代纺织技术, 2022, 30(5): 1-11.
[2]	邓莹洁,罗戎蕾. 基于卷积神经网络的半身裙款式特征分类识别[J]. 现代纺织技术, 2021, 0(6): 98-105.
[3]	李敏，杨珊，何儒汉，姚迅，崔树芹. 结合视觉显著性和卷积神经网络的提花织物疵点检测技术[J]. 现代纺织技术, 2021, 0(6): 62-66.
[4]	殷鹏，景军锋. 基于改进DANN网络的织物缺陷检测[J]. 现代纺织技术, 2020, 0(5): 57-63.
[5]	尹光灿，罗戎蕾. 基于卷积神经网络的服装领型识别与分类研究[J]. 现代纺织技术, 2020, 0(3): 48-53.