[1]韩曙光,姜凯文,赵丽妍.基于深度学习的服装三要素识别[J].服装学报,2022,7(05):399-407.
 HAN Shuguang,JIANG Kaiwen,ZHAO Liyan.Recognition of Clothing "Three Elements" Based on Deep Learning[J].Journal of Clothing Research,2022,7(05):399-407.
点击复制

基于深度学习的服装三要素识别()
分享到:

《服装学报》[ISSN:2096-1928/CN:32-1864/TS]

卷:
第7卷
期数:
2022年05期
页码:
399-407
栏目:
服装信息与工程
出版日期:
2022-10-31

文章信息/Info

Title:
Recognition of Clothing "Three Elements" Based on Deep Learning
作者:
韩曙光1;  姜凯文2;  赵丽妍3
1.浙江理工大学 理学院,浙江 杭州 310018; 2.浙江理工大学 服装学院,浙江 杭州 310018; 3.浙江理工大学 国际教育学院,浙江 杭州 310018
Author(s):
HAN Shuguang1;  JIANG Kaiwen2;  ZHAO Liyan3
1.School of Science,Zhejiang Sci-Tech University,Hangzhou 310018,China; 2.School of Fashion Design and Engineering,Zhejiang Sci-Tech University,Hangzhou 310018,China; 3. School of International Education,Zhejiang Sci-Tech University,Hangzhou 310018,China
分类号:
TS 941.26
文献标志码:
A
摘要:
为快速自动获取服装三要素信息,提高服装图像多特征识别效率,提出一种利用深度学习识别服装三要素的方法。考虑款式、颜色、图案3种要素,建立了一个包含3种上衣款式、6种颜色、6种图案,共计15种类别的样本库,利用改进的VGGNet神经网络进行款式与颜色识别,结合YOLOv3,Faster R-CNN,SSD目标检测算法实现图案识别及定位。对比实验结果,得出改进的VGGNet对服装款式与颜色识别准确率达到96.49%; 目标检测算法中YOLOv3对服装图案识别与定位的mAP达到86.66%,3大类图案中纹理类图案的检测效果最好,其mAP为96.14%,动物类图案mAP为83.69%,文字类图案mAP为79.80%。研究结论为顾客服装偏好信息的快速获取提出了新思路。
Abstract:
To quickly and automatically obtain the information of the three elements of clothing and improve the efficiency of multi-feature recognition of clothing images, a method for identifying the three elements of clothing using deep learning was proposed. Considering the three elements of style, color and pattern, a sample library was established including 3 tops styles, 6 colors and 6 patterns, a total of 15 categories.It used the improved VGGNet to identify colors and styles, and combined with YOLOv3, Faster R-CNN and SSD target detection algorithms to achieve rapid pattern recognition and positioning. The comparative experimental results show that the improved VGGNet have an accuracy of 96.49% for clothing style and color recognition, and the YOLOv3 in the target detection algorithm have a mAP of 86.66% for clothing pattern recognition and positioning. Among the three types of patterns, texture patterns have the best detection effect. Its mAP, animal mAP and text pattern mAP are 96.14%, 83.69% and 79.80% respectively. This study puts forward a new idea for the rapid acquisition of customer clothing preference information.

参考文献/References:

[1] 晏栖云.浅析服装构成要素对服装舒适性的影响[J].牡丹,2019(21):120-122.
YAN Qiyun. Analysis on the influence of clothing components on clothing comfort[J]. Peony, 2019(21): 120-122.(in Chinese)
[2] 庹武,王哓玉,高雅昆,等.基于改进边缘检测算法的服装款式识别[J].纺织学报,2021, 42(10):157-162.
TUO Wu, WANG Xiaoyu, GAO Yakun, et al. Clothing style identification based on improved edge detection algorithm[J]. Journal of Textile Research, 2021, 42(10): 157-162.(in Chinese)
[3] QIAN S Q, JIANG L F, DONG A H. Silhouette shape and detail texture based garment style recognition[C]//2011 IEEE International Conference on Computer Science and Automation Engineering. Shanghai:IEEE,2011:441- 445.
[4] 李东,万贤福,汪军.采用傅里叶描述子和支持向量机的服装款式识别方法[J].纺织学报,2017, 38(5):122-127.
LI Dong, WAN Xianfu, WANG Jun. Clothing style recognition approach using Fourier descriptors and support vector machines[J]. Journal of Textile Research, 2017, 38(5): 122-127.(in Chinese)
[5] 李东,万贤福,汪军,等.基于轮廓曲率特征点的服装款式识别方法[J].东华大学学报(自然科学版),2018,44(1):87-92.
LI Dong, WAN Xianfu, WANG Jun, et al. Clothing style recognition approach based on the curvature feature points on the contour[J]. Journal of Donghua University(Natural Science), 2018, 44(1): 87-92.(in Chinese)
[6] KRIZHEVSKY A, SUTSKEVER I, HINTON G E. ImageNet classification with deep convolutional neural networks[J]. Communications of the ACM, 2017, 60(6): 84-90.
[7] KIAPOUR M H, HAN X F, LAZEBNIK S, et al. Where to buy it: matching street clothing photos in online shops[C]//2015 IEEE International Conference on Computer Vision. Santiago:IEEE,2015:3343-3351.
[8] 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,2020,28(3):48-53.
YIN Guangcan, LUO Ronglei. Research on recognition and classification of garment collar type based on convolutional neural network[J]. Advanced Textile Technology, 2020, 28(3): 48-53.(in Chinese)
[9] 黄健,张钢.深度卷积神经网络的目标检测算法综述[J].计算机工程与应用,2020,56(17):12-23.
HUANG Jian, ZHANG Gang. Survey of object detection algorithms for deep convolutional neural networks[J]. Computer Engineering and Applications, 2020, 56(17): 12-23.(in Chinese)
[10] REN S Q, HE K M, GIRSHICK R, et al. Faster R-CNN: towards real-time object detection with region proposal networks[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 39(6): 1137-1149.
[11] REDMON J, DIVVALA S, GIRSHICK R, et al. You only look once: unified, real-time object detection[C]//2016 IEEE Conference on Computer Vision and Pattern Recognition. Las Vegas:IEEE,2016: 779-788.
[12] LIU W, ANGUELOV D, ERHAN D, et al. SSD: single shot MultiBox detector[M]//Computer vision—ECCV 2016. Cham: Springer International Publishing, 2016: 21-37.
[13] HUO X, ZHANG L, GUO M, et al. RGB-D SLAM algorithm suitable for dynamic environment based on target detection[C]//2021 5th International Conference on Automation, Control and Robots.Nanning:IEEE, 2021: 64- 68.
[14] 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(4):158-164.
LIU Zhengdong, LIU Yihan, WANG Shouren. Depth learning method for suit detection in images[J]. Journal of Textile Research, 2019, 40(4): 158-164.(in Chinese)
[15] 张艳清,刘成霞.基于Faster R-CNN的连衣裙衣领自动识别[J].浙江理工大学学报(自然科学版),2021,45(6):751-757.
ZHANG Yanqing, LIU Chengxia. Automatic recognition of dress collar based on Faster R-CNN[J]. Journal of Zhejiang Sci-Tech University(Natural Sciences Edition), 2021, 45(6): 751-757.(in Chinese)
[16] 李扬,黄荣,董爱华.基于改进Bilinear-CNN的服装图像风格识别[J].东华大学学报(自然科学版),2021,47(3):90-95.
LI Yang, HUANG Rong, DONG Aihua. Fashion style recognition based on an improved Bilinear-CNN[J]. Journal of Donghua University(Natural Science), 2021, 47(3): 90-95.(in Chinese)
[17] 刘于昆,高郭瑞,王淑焜,等.基于VGG网络不同模型的建筑物自动提取[J].电子测试,2021(22):58-59,131.
LIU Yukun, GAO Guorui, WANG Shukun, et al. Automatic building extraction based on different models of VGG network[J]. Electronic Test, 2021(22): 58-59, 131.(in Chinese)
[18] 黄杰.基于Python TensorFlow的深度神经网络应用研究——以服装图像识别为例[J].山西大同大学学报(自然科学版),2020,36(5):54-58.
HUANG Jie. Application of deep neural network based on Python TensorFlow—taking pattern recognition as an example[J]. Journal of Shanxi Datong University(Natural Science Edition), 2020, 36(5): 54-58.(in Chinese)
[19] 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(8):117-123.
WANG Shanna, ZHANG Huaxiong, KANG Feng. Emotion classification of necktie pattern based on convolution neural network[J]. Journal of Textile Research, 2018, 39(8): 117-123.(in Chinese)
[20] 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,2021,29(6):98-105.
DENG Yingjie, LUO Ronglei. Classification and recognition of bust skirt style and common features based on convolutional neural network[J]. Advanced Textile Tech-nology, 2021, 29(6): 98-105.(in Chinese)
(责任编辑:沈天琦)

更新日期/Last Update: 2022-10-30