Journal of Textile Research ›› 2022, Vol. 43 ›› Issue (05): 143-149.doi: 10.13475/j.fzxb.20210506507

• Apparel Engineering • Previous Articles     Next Articles

Classification and recognition of young males' neck-shoulder shape based on 2-D photos

ZHANG Jian1, XU Kaiyi1, ZHAO Songling1, GU Bingfei1,2,3()   

  1. 1. School of Fashion Design & Engineering, Zhejiang Sci-Tech University, Hangzhou, Zhejiang 310018, China
    2. Clothing Engineering Research Center of Zhejiang Province, Hangzhou, Zhejiang 310018, China
    3. Key Laboratory of Silk Culture Heritage and Products Design Digital Technology, Ministry of Culture and Tourism, Hangzhou, Zhejiang 310018, China
  • Received:2021-05-25 Revised:2022-01-07 Online:2022-05-15 Published:2022-05-30
  • Contact: GU Bingfei E-mail:gubf@zstu.edu.cn

RichHTML

15

PDF (PC)

57

Abstract:

In order to explore the classification of the neck and shoulder shape of young men and to facilitate the automatic recognition based on 2-D photos, this study obtained the point cloud data of 180 male college students using a three-dimensional body scanner, and measured 22 characteristic parameters relating to the male neck and shoulder shape. According to the analysis of the coefficient of variation, the forward angle, back angle, shoulder oblique angle, neck-to-shoulder width ratio, and neck transverse sagittal diameter ratio were selected as cluster analysis variables to classify the neck and shoulder shapes for establishing the discriminant rules. Combining the 2-D photos of the human body to extract the parameters required for body type classification, an automatic recognition system for the shape of the neck-shoulders was constructed. The results show that the neck-shoulder shape of young men can be divided into three types, namely round-neck-drop-shoulder, forward-round-neck and wide-neck-straight-body. The discrimination accuracy rate of the constructed form automatic recognition system reached 93.33%, indicating that this method is effective and feasible, and can meet the needs of consumers' personalized customization.

Key words: neck-shoulder shape, body classification, 2-D photographs, automatic body identification, clothing personalized customization

CLC Number: 

  • TS941.17

Fig.1

Schematic diagram of measurement of morphological parameters of neck-shoulder"

Tab.1

Specific definition of morphological parameters of neck-shoulder"

序号 测量项目 测量及计算方法 序号 测量项目 测量及计算方法
1 身高(H) 头顶点至地面的垂直距离 12 腋下宽(WA) 左腋点(PLA)与右腋点(PRA)的水平距离
2 肩腋角(ANA) 肩端点(PLS)和腋下点(PLA)的连线与水平线的夹角 13 腋下厚(TA) 腋下部截面中心厚度
3 肩斜角(AST) 侧颈点(PSN)和肩端点(PLS)的连线与水平线的夹角 14 颈横矢径比(RN) 颈宽(WN)/颈厚(TN)
4 背入角(ADE) 侧面背部最凸点(PB)和下后颈点(PDBN)(第7颈椎点)的连线与垂直线的夹角 15 肩横矢径比(RS) 肩宽(WS)/肩厚(TS)
5 前倾角(AFL) 侧视图中颈部线条与垂直线的夹角 16 腋下横矢径比(RA) 腋下宽(WA)/腋下厚(TA)
6 肩弓角(ASA) 肩部截面曲线前后中点与左肩端点所成夹角 17 颈肩宽比(RWNS) 颈宽(WN)/肩宽(WS)
7 颈宽(WN) 左颈点(PLN)与右颈点(PRN)的水平距离 18 颈腋宽比(RWNA) 颈宽(WN)/腋下宽(WA)
8 颈厚(TN) 上前颈点(PUFN)与上后颈点(PUBN)的水平距离 19 肩腋宽比(RWSA) 肩宽(WS)/腋下宽(WA)
9 前颈角(AFN) 侧视图中颈部与上身的夹角 20 颈肩厚比(RTNS) 颈厚(TN)/肩厚(TS)
10 肩宽(WS) 左肩端点(PLS)与右肩端点(PRS)的水平距离 21 颈腋厚比(RTNA) 颈厚(TN)/腋下厚(TA)
11 肩厚(TS) 肩部截面中心厚度 22 肩腋厚比(RTSA) 肩厚(TS)/腋下厚(TA)

Tab.2

Descriptive statistical analysis of related parameters"

指标 AFL/(°) ADE/(°) AST/(°) RWNS RN WN/cm RS TS/cm RWNA TN/cm RTNS
最大值 38.00 28.40 34.95 0.52 1.60 18.90 3.40 18.00 0.57 17.26 1.07
最小值 8.90 9.41 14.32 0.28 0.82 10.70 1.98 10.40 0.34 9.90 0.69
平均值 23.66 18.96 24.43 0.39 1.17 14.16 2.68 13.81 0.42 12.14 0.88
标准差 5.52 3.90 4.52 0.05 0.14 1.62 0.28 1.43 0.04 1.18 0.08
变异系数/% 23.34 20.57 18.51 13.14 12.28 11.46 10.45 10.35 9.52 9.72 9.09
指标 TA/cm RA RTNA RTSA ASA/(°) WS/cm ANA/(°) RWSA WA/cm AFN/(°) H/cm
最大值 25.50 2.21 0.74 0.89 88.50 43.70 98.10 1.28 40.10 147.33 180
最小值 15.60 1.32 0.47 0.58 57.18 29.93 64.50 0.91 29.00 114.20 162
平均值 19.58 1.75 0.62 0.71 71.41 36.69 83.91 1.08 34.12 131.92 173.85
标准差 1.87 0.15 0.05 0.06 5.95 2.56 5.49 0.07 2.00 7.35 5.765
变异系数/% 9.55 8.57 8.06 8.43 8.33 6.97 6.55 6.48 5.86 5.57 3.32

Fig.2

Method for determining optimal number of clusters. (a) Elbow method; (b) Silhouette coefficient"

Tab.3

Cluster analysis results"

变量 聚类均方 组间自由度 误差均方 组内自由度 F值 Sig. 聚类中心
1 2 3
前倾角AFL 1 544.572 2 10.958 171 140.958 0.000 20.584 0 29.325 3 20.533 6
背入角ADE 229.870 2 13.872 171 16.571 0.000 20.662 1 20.341 7 17.037 5
肩斜角AST 877.361 2 9.885 171 88.760 0.000 29.178 9 25.545 0 21.241 8
颈肩宽比RWNS 0.014 2 0.003 171 5.190 0.006 0.362 9 0.383 3 0.394 0
颈横矢径比RN 0.090 2 0.020 171 4.390 0.014 1.148 5 1.135 8 1.209 1
各类人数 — — — — — — 54 63 57
各类占比/% — — — — — — 31.03 36.21 32.76

Fig.3

Comparison of 3 different types of neck-shoulder. (a) Side morphology; (b) Front morphology"

Tab.4

Discriminant rule"

聚类类别 判别规则
1 F1>F2且F1>F3
2 F2>F1且F2>F3
3 F3>F1且F3>F2

Fig.4

Image acquisition and contour extraction. (a) Photo pose; (b) Image binary processing; (c) Image contour extraction"

Fig.5

Coordinate point marking of neck-shoulder"

Tab.5

Parameter calculation formula"

参数 相关特征点 计算方法
前倾角AFL 前上颈点PUFN、前下颈点PDFN AFL=arctan{abs[(yPUFN-yPDFN)/(xPUFN-xPDFN)]}×180°/π
背入角ADE 背凸点PD、后下颈点PDBN ADE=arctan{abs[(yPDBN-yPB)/(xPDBN-xPB)]}×180°/π
肩斜角AST 侧颈点PSN、左肩点PLS AST=arctan{abs[(xPSN-xPLS)/(yPSN-yPLS)]}×180°/π
颈肩宽比RWNS 左颈点PLN、右颈点PRN、左肩点PLS、右肩点PRS RWNS=abs[(yPRN-yPLN)/(yPRS-yPLS)]
颈横矢径比RN 左颈点PLN、右颈点PRN、上后颈点PUBN、上前颈点PUFN RN=abs[(yPRN-yPLN)/(yPUFN-yPUBN)]

Fig.6

Automatic recognition result of neck and shoulder shape"

Tab.6

Error analysis table"

参数 取值方式 均值 标准差 平均误差 误差范围 配对样本T检验显著性
肩斜角 照片提取值 28.760 5° 3.119 9° 0.860 1° -1.877 1°~1.895 6° 0.937
点云测量值 28.775 5° 2.899 1°
背入角 照片提取值 21.821 3° 4.040 8° 0.837 6° -1.807 7°~1.730 7° 0.616
点云测量值 21.727 3° 4.181 6°
前倾角 照片提取值 23.070 2° 4.655 9° 0.628 2° -1.235 6°~1.707 5° 0.713
点云测量值 23.019 4° 4.686 1°
颈横矢径比 照片提取值 0.947 7 0.110 7 0.146 5 -0.137 0~0.071 1 0.398
点云测量值 1.081 4 0.105 9
颈肩宽比 照片提取值 0.323 9 0.020 7 0.025 9 -0.097 8~0.046 6 0.581
点云测量值 0.327 2 0.034 3
[1] CHA Sujoung. Lower body shape classification of male university students[J]. Journal of The Korea Society of Computer and Information, 2019, 24(3):135-141.
[2] 牟旭. 18-25岁女性颈部形态分析与女装立领结构设计[D]. 武汉: 武汉纺织大学, 2018:1.
MOU Xu. Analysis of neck shape of 18-25 years old women and structure design of stand-collar for lady dress[D]. Wuhan: Wuhan Textile University, 2018:1.
[3] TSUNAWAKE N, TAHARA Y, YUKAWA K, et al. Classification of body shape of male athletes by factor analysis[J]. Ann Physiol Anthropol, 1994, 13(6):383-392.
doi: 10.2114/ahs1983.13.383
[4] YAN J, KUZMICHEV V E. A virtual e-bespoke men's shirt based on new body measurements and method of pattern drafting[J]. Textile Research Journal, 2020, 90(19/20):2223-2244.
doi: 10.1177/0040517520913347
[5] 季开宸. 基于青年男体二维非接触测量系统围度拟合的完善[D]. 苏州: 苏州大学, 2014:16-18.
JI Kaichen. The improvement of circumference fit based on youth men's 2D non-contact measurement system[D]. Suzhou: Soochow University, 2014:16-18.
[6] 王婷, 顾冰菲. 基于二维二维图像的青年女性颈肩部形态自动识别[J]. 纺织学报, 2020, 41(12):111-117.
WANG Ting, GU Bingfei. Automatic identification of young women's neck-shoulder shapes based on images[J]. Journal of Textile Research, 2020, 41(12):111-117.
[7] 王珊珊, 王鸿博. 基于三维人体测量的江浙在职男青年颈部形态[J]. 纺织学报, 2013, 34(10):131-136.
WANG Shanshan, WANG Hongbo. Neck morphology research of on-the-job young men in Jiangsu and Zhejiang areas by means of three-dimensional anthropometry[J]. Journal of Textile Research, 2013, 34(10):131-136.
[8] 金娟凤, 庞程方, 陈伟杰, 等. 青年男性肩点横截面曲线及其体型细分[J]. 纺织学报, 2016, 37(8):100-106.
JIN Juanfeng, PANG Chengfang, CHEN Weijie, et al. Study on subdivision of young male's shoulder shapes and cross-section curve[J]. Journal of Textile Research, 2016, 37(8):100-106.
[9] 余佳佳, 李健. 中国东部地区青年女性人体体型分类[J]. 纺织学报, 2020, 41(5):134-139.
YU Jiajia, LI Jian. Classification of young women's somatotypes in eastern china[J]. Journal of Textile Research, 2020, 41(5):134-139.
doi: 10.1177/004051757104100208
[10] 王祺明. 基于人体三围截面面积的江浙地区女性体型分类[J]. 纺织学报, 2016, 37(5):131-136.
WANG Qiming. Female body classification in jiangsu and zhejiang based on cross-sectional area of body[J]. Journal of Textile Research, 2016, 37(5):131-136.
[11] 姚怡, 马静, 吴欢, 等. 基于小波系数的青年女性体型分类及原型纸样[J]. 纺织学报, 2017, 38(12):119-123.
YAO Yi, MA Jing, WU Huan, et al. Young female body shape classification and prototype patterns based on wavelet coefficient[J]. Journal of Textile Research, 2017, 38(12):119-123.
[12] 周捷, 毛倩. 基于改进快速搜索和发现密度峰值的男童体型分类及判别[J]. 纺织学报, 2020, 41(5):146-152.
ZHOU Jie, MAO Jie. Classification and recognition of body type for young boys based on improved fast search and finding of density peak algorithms[J]. Journal of Textile Research, 2020, 41(5):146-152.
doi: 10.1177/004051757104100210
[13] 黄英, 崔志英, 夏明. 华东地区成年女性下体体型研究[J]. 东华大学学报(自然科学版), 2012, 38(3):397-302.
HUANG Ying, CUI Zhiying, XIA Ming. Reschear on lower body shape of adult female in east china[J]. Journal of Donghua University(Natural Science), 2012, 38(3):297-302.
[14] 吴广建, 章剑林, 袁丁. 基于K-means的手肘法自动获取K值方法研究[J]. 软件, 2019, 40(5):167-170.
WU Guangjian, ZHANG Jianlin, YUAN Ding. Automatically obtaining K value Based on K-means elbow method[J]. Computer Engineering & Software, 2019, 40(5):167-170.
[15] 林锦荣, 武云发, 廖如超, 等. 基于K-Means算法的架空输电线路载流量计算[J]. 南京信息工程大学学报(自然科学版), 2021, 13(1):82-90.
LIN Jinrong, WU Yunfa, LIAO Ruchao, et al. Calculation of current carrying capacity for overhead transmission lines based on K-means algorithm[J]. Journal of Nanjing University of Information Science & Technology(Natural Science Edition), 2021, 13(1):82-90.
[16] GU B, LIU G, XU B. Girth prediction of young female body using orthogonal silhouettes[J]. The Journal of The Textile Institute, 2017, 108(1):140-146.
doi: 10.1080/00405000.2016.1160756
[1] WANG Ting, GU Bingfei. 3-D modeling of neck-shoulder part based on human photos [J]. Journal of Textile Research, 2021, 42(01): 125-132.
[2] WANG Ting, GU Bingfei. Automatic identification of young women's neck-shoulder shapes based on images [J]. Journal of Textile Research, 2020, 41(12): 111-117.
[3] . Female body classification in Jiangsu and Zhejiang based on cross0sectional area of body [J]. Journal of Textile Research, 2016, 37(05): 131-136.
[4] QI Jing;LI Yi;ZHANG Xin. Description and classification of young men’s body type in the west China [J]. JOURNAL OF TEXTILE RESEARCH, 2010, 31(5): 107-111.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
京ICP备14006648号
Copyright 2021 © Editorial office of Journal of Textile Research
Supported by Beijing Magtech Co.Ltd