[1]黄振华,李 涛,蒋玉萍,等.基于Mask R-CNN的款式图衣领识别[J].服装学报,2021,6(01):36-41.
　HUANG Zhenhua,LI Tao,JIANG Yuping,et al.Collar Flat Sketch Recognition Based on Mask R-CNN[J].Journal of Clothing Research,2021,6(01):36-41.
点击复制

基于Mask R-CNN的款式图衣领识别()
分享到：

《服装学报》[ISSN:2096-1928/CN:32-1864/TS]

卷:
第6卷
期数:
2021年01期
页码:
36-41
栏目:
服装信息与工程
出版日期:
2021-02-28

文章信息/Info

Title:
Collar Flat Sketch Recognition Based on Mask R-CNN
作者:
黄振华1; 2; 3;  李 涛1; 2; 3;  蒋玉萍1; 2; 3;  杜 磊*1; 2; 3
1. 浙江理工大学 丝绸文化传承与产品设计数字化技术文化和旅游部重点实验室,浙江 杭州 310018; 2. 浙江理工大学 浙江省服装工程技术研究中心,浙江 杭州 310018; 3. 浙江理工大学 服装数字化技术浙江省工程实验室, 浙江 杭州 310018
Author(s):
HUANG Zhenhua1; 2; 3;  LI Tao1; 2; 3;  JIANG Yuping1; 2; 3;  DU Lei*1; 2; 3
1. Key Laboratory of Silk Culture Heritage and Products Design Digital Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China; 2. Clothing Engineering Research Center of Zhejiang Province, Zhejiang Sci-Tech University, Hangzhou 310018, China; 3. Zhejiang Provincial Engineering Laboratory of Clothing Digital Technology, Zhejiang Sci-Tech University, Hangzhou 310018, China
分类号:
TS 941.26
文献标志码:
A
摘要:
为提升服装款式图领型识别精度,提出一种基于Mask R-CNN神经网络的服装款式图领型定位与识别方法。建立共1 800张包含无领、立领、翻领与驳领4种领型的款式图样本库,利用迁移学习与Mask R-CNN神经网络实现领型定位与识别。结果表明,4种领型的平均识别精确度高于98%,测试集平均精确度达到99.2%,mAP值达到90%。该识别方法可以减少样板生成中的人工失误,为数字化样板生成提供参考。
Abstract:
In order to improve the recognition accuracy of collar flat, this paper proposed a fine-grained localization and recognition method of garment collar based on Mask R-CNN neural network.A database of 1800 images which contained collarless, lapel, turndown collar and stand collar,was created. Transfer learning and Mask R-CNN neural network were used to realize collar location and recognition. The results showed that the average recognition accuracy of four collar types were higher than 98%. The average accuracy of the test set and mAP were reached to 99.2% and 90% respectively. The recognition method can reduce the manual errors in the pattern generation, and provide a reference for the digital pattern generation.

参考文献/References:

[1] 李涛, 杜磊, 黄振华, 等.服装款式图识别与样板转换技术研究进展[J]. 纺织学报, 2020, 41(8): 145-151.
LI Tao, DU Lei, HUANG Zhenhua,et al. Review on pattern conversion technology based on garment flat recognition[J]. Journal of Textile Research, 2020, 41(8): 145-151.(in Chinese)
[2] 尹晓芳, 蒋晓文. 基于感性工学的女衬衫领型评价[J]. 服装学报, 2020, 5(2): 111-118.
YIN Xiaofang, JIANG Xiaowen. Evaluation of blouse collar type based on kansei engineering[J]. Journal of Clothing Research, 2020, 5(2): 111-118.(in Chinese)
[3] 李楠. 基于行业需求的服装款式图绘制方法[J]. 服装学报, 2016, 1(1): 53-58.
LI Nan. Research on the fashion style drawing method according to industry needs[J]. Journal of Clothing Research, 2016, 1(1): 53-58.(in Chinese)
[4] 陈巧红, 陈翊, 孙麒, 等. 服装图像分类技术综述[J]. 浙江理工大学学报(自然科学版), 2019, 41(5): 631- 643.
CHEN Qiaohong, CHEN Yi, SUN Qi, et al. Overview of clothing image classification technology[J]. Journal of Zhejiang Sci-Tech University(Natural Sciences Edition), 2019, 41(5): 631- 643.(in Chinese)
[5] HUANG P, YAO J, ZHAO H. Automatic realistic 3D garment generation based on two images[C]// China VR.2016 International Conference on Virtual Reality and Visualization.New York:IEEE, 2016: 250-257.
[6] 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, WANG Xianfu, WAN Jun. Clothing style recognition approach using fourier descriptors and support vector machines[J]. Journal of Textile Research, 2017, 38(5): 122-127.(in Chinese)
[7] DING X J, ZOU C H, CHEN K J, et al. Extraction and classification of She nationality clothing via visual features[J]. Textile Research Journal, 2016, 86(12): 1259-1269.
[8] SURAKARIN W, CHONGSTIVATANA P. Classification of clothing with weighted SURF and local binary patterns[C]// International Computer Science and Engineering Conference.2015 International Computer Science and Engineering Conference(ICSEC). New York:IEEE, 2015: 1- 4.
[9] AN L X, LI W. An integrated approach to fashion flat sketches classification[J]. International Journal of Clothing Science and Technology, 2014, 26(5): 346-366.
[10] 吴欢, 丁笑君, 李秦曼, 等. 采用卷积神经网络CaffeNet 模型的女裤廓形分类[J]. 纺织学报, 2019, 40(4): 117-121.
WU Huan, DING Xiaojun, LI Qinman, et al. Classification of women’s trousers silhouette using convolution neural network CaffeNet model[J]. Journal of Textile Research, 2019, 40(4): 117-121.(in Chinese)
[11] 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(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(3): 48-53.(in Chinese)
[12] HE K M, GKIOXARI G, DOLLAR P, et al. Mask R-CNN[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017(99):1.
[13] 刘舒康,唐鹏,金炜东. 基于智能数据增强和改进YOLOv3算法的接触网吊弦及支架检测研究[J].计算机科学,2020,47(Sup.2):178-182.
LIU Shukang, TANG Peng, JIN Weidong. Study on catenary dropper and support detection based on intelligent data augmentation and improved YOLOv3[J]. Computer Science, 2020,47(Sup.2):178-182.(in Chinese)
[14] 张文斌. 服装结构设计[M]. 3版. 北京: 中国纺织出版社, 2007: 88-89.
(责任编辑:卢 杰)

相似文献/References:

[1]于 洋,范作泽,初晓玲*.基于视错觉原理的肥胖体男士T恤设计[J].服装学报,2020,5(04):323.
　YU Yang,FAN Zuoze,CHU Xiaoling*.T-Shirt Design for Men with Fat Body Based on the Visual Illusion Theory[J].Journal of Clothing Research,2020,5(01):323.

更新日期/Last Update: 2020-02-28