Non-contact anthropometric measurement is suitable for remote and rapid acquisition of human body dimensions. Especially, anthropometric measurements based on 2D images provide a basis for garment mass customization. In this paper, we reviewed two decades of research on non-contact body measurement based on 2D images, detailing critical processes such as image acquisition, contour extraction, feature point detection, and dimension calculation. Then, we summarized the applications of 2D non-contact body measurement in the garment industry. We found that the current research is confronted with the following three predicaments: Contour extraction in complex backgrounds; Accurate body dimension estimation or calculation; Applicable only to the nude body or tight-fitting status. These limitations restricted the application of 2D non-contact body measurement in garment mass customization. Future research should be focused on rapid body contour extraction from complex backgrounds from the images provided by consumers with tight-fitting or loose-fitting conditions, additionally improving the accuracy of body dimension measurement caused by multi-step iteration error. Reconstruction of the 3D human body model for body dimension measurement, and estimation of body shape and dimensions from the dressed body will be the feasible and reliable approaches for accurate non-contact body measurement based on 2D images.
JiaJ.Research of human body anthropomertic measurement based on image. Master Thesis, Shanghai Normal University, China, 2020.
2.
LuoS. Application research on 2D image-based non-contact anthropometric technology in clothing e-commerce. In: 2017 7th International Conference on Applied Science, Engineering and Technology (ICASET 2017), 2017, pp.112–118. Atlantis Press.
3.
GuBLiuGXuB.Girth prediction of young female body using orthogonal silhouettes. J Text Inst2017;
108: 140–146.
4.
UyunSEfendiT.Classification of human weight based on image. Indones J Comput Cybern Syst2019;
13: 105–116.
5.
ZhangYLuX.Measurement method for human body anteflexion angle based on image processing. Int J Imaging Syst Technol2019;
29: 518–530.
6.
GhazalSKhanUS. Human posture classification using skeleton information. In: 2018 International Conference on Computing, Mathematics and Engineering Technologies (iCoMET), Sukkur, Pakistan, 3–4 March 2018, pp. 1–4.
7.
YaoTMinYWangJ, et al.
Classification of female body shape based on two-dimensional image and computer vision technology. Text Res J2023;
93: 4383–4391.
8.
HuYXiaYGuB.An image-based shape analysis approach and its application to young women’s waist-hip-leg position. Ergonomics2023;
66: 2074–2090.
9.
GeSLinRXuP, et al.
Personalized customization of curved surface pillows based on machine vision. J Text Res2024;
45: 214–220.
10.
GuBLiXYanY, et al.
Predicting human dimensions in body images for automatic generation of female pants patterns. Text Res J2019;
89: 3792–3801.
11.
PanphattarasapPPraiwattanaPKraisangkaJ, et al.
Utilizing image processing to measure foot parameters for insole production. Comput-Aided Des Appl2024;
21: 904–921.
12.
LiSTanYWillisS, et al.
Toward mass customization through additive manufacturing: An automated design pipeline for respiratory protective equipment validated against 205 faces. Int J Bioprinting2021;
7: 123–134.
13.
YanSKämäräinenJ-K.Learning anthropometry from rendered humans. ArXiv2021; abs/2101.02515.
14.
ChenGKongHTanF, et al. Research of non-contact 2D body measurement system. In: 2011 International Conference on Control, Automation and Systems Engineering (CASE), Singapore, 30–31 July 2011, pp.1–4.
15.
BhatSSAnanthADsouzaP, et al. Human body measurement extraction from 2D images. In: International Conference on VLSI, Signal Processing, Power Electronics, IoT, Communication and Embedded Systems, Udupi, India, 22–23 December 2020, pp. 343–352. Singapore: Springer.
16.
LiYJiangLLiX, et al.
Non-contact clothing anthropometry based on two-dimensional image contour detection and feature point recognition. Ind Textila2023;
74: 67–73.
17.
SehgalRGuptaRAnandN.Automatic extraction of 3D body measurements from 2D images of a female form. IOSR J Polymer Text Eng2018;
5: 07–17.
18.
SunKChiuYChenY, et al.
A 2D-3D non-contact anthropometric method for daily dressing state-takes young Asian women as example. J Meas Eng2017;
5: 161–175.
19.
HungPCYWitanaCPGoonetillekeRS.Anthropometric measurements from photographic images. Comput Syst2004;
29: 764–769.
20.
XiaSLiJIstookCL, et al.
A 2D image body measurement system developed with neural networks and a color-coded measurement garment. Int J Clothing Sci Technol2022;
34: 967–978.
21.
GuBKongHGuP, et al. Study of 2D non-contact anthropometric system and application. In: 2011 International Conference on Future Computer Sciences and Application, Hong Kong, China, 18–19 June 2011, pp.150–153.
22.
JinSGuBZhangB, et al.
Pants design and pattern generation based on body images. Ind Textila2023: 74–80.
23.
AlySAbdallahASherifS, et al. Toward smart internet of things (iot) for apparel retail industry: Automatic customer’s body measurements and size recommendation system using computer vision techniques. In: 2021 Second International Conference on Intelligent Data Science Technologies and Applications (IDSTA), Tartu, Estonia, 15–17 November 2021, pp. 99–104.
24.
XiaSWestAIstookC, et al. Acquiring accurate body measurements on a smartphone from supplied colored garments for online apparel purchasing platforms and e-retailers. In: Proceedings of 3DBODYTECH 2018 - 9th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Lugano, Switzerland, 16–17 October 2018, pp. 126–130.
25.
XiongSLiYZhuY, et al. Foot measurements from 2D digital images. In: 2010 IEEE International Conference on Industrial Engineering and Engineering Management, 2010, pp.497–501. IEEE.
26.
StrajnicLPerićMŽivkovićN, et al.
Comparison of face anthropometry and digital 2D-face photogrammetry as methods for predicting vertical dimension of occlusion. Int J Prosthodont2024;
37: 282–292.
27.
ZareAJahangiriMSeifM, et al.
Anthropometric survey of dynamic hand dimensions: A pilot study. Measurement2024;
240: 115554.
28.
BallesterAWrightWValeroJ, et al. Comparative analysis of anthropometric methods: Past, present, and future. In: Proceedings of 3DBODYTECH 2020 - 11th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, 17–18 November 2020.
29.
ZhiL.Research and application of automatic measurement technology of human body size based on 2D images. Master Thesis, Wuhan University, 2020.
30.
ZhangZ.A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell2000;
22: 1330–1334.
31.
ReuP.Calibration: A good calibration image. Exp Tech2013;
37: 1–3.
32.
TsaiR.A versatile camera calibration technique for high-accuracy 3D machine vision metrology using off-the-shelf tv cameras and lenses. IEEE Robot Autom1987;
3: 323–344.
33.
MartinDRFowlkesCCMalikJ.Learning to detect natural image boundaries using local brightness, color, and texture cues. IEEE Trans Pattern Anal Mach Intell2004;
26: 530–549.
34.
SobelIFeldmanG.A 3 × 3 isotropic gradient operator for image processing. Pattern Classif Scene Anal1968: 271–272.
35.
RobertsL.Machine perception of three-dimensional solids. PhD Thesis, Massachusetts Institute of Technology, USA, 1963.
36.
PrewittJM.Object enhancement and extraction.
Orlando:
Academic Press, 1970, pp. 15–19.
37.
CannyJ.A computational approach to edge detection. IEEE Trans Pattern Anal Mach Intell1986;
8: 679–698.
MojarradMKargarS.Measuring the main parameters of the human body in images by Canny edge detector. Sci J Circuits Syst Signal Process2013;
2: 100.
41.
DewanDChapainBJaiswalM, et al.
Estimate human body measurement from 2D image using computer vision. J Emerging Technol Innovative Res2022;
9: 438–445.
42.
KothapalliVAroraSHanmandluM.Edge detection using fractional derivatives and information sets. J Electron Imaging2018;
27.
43.
MaksimovićVJakšićBPetrovicM, et al.
Analysis of edge detection on compressed images with different complexities. Acta Polytechnica Hungarica2020;
17: 123–143.
44.
ThirumavalavannSJayaramanS.An improved teaching-learning based robust edge detection algorithm for noisy images. J Adv Res2016;
7: 979–989.
45.
BertasiusGShiJTorresaniL. Deepedge: A multi-scale bifurcated deep network for top-down contour detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp.4380–4389.
46.
ShenWWangXWangY, et al. Deepcontour: A deep convolutional feature learned by positive-sharing loss for contour detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2015, pp. 3982–3991.
47.
XieSTuZ. Holistically-nested edge detection. In: Proceedings of the IEEE international conference on computer vision, 2015, pp.1395–1403.
48.
GuBZhangJXuK, et al.
Human contour and parameter extraction from complex background. J Text Res2023;
44: 168–175.
49.
HuangX.Research on measurement of human body dimension based on frontal human body image. Master Thesis, Beijing Institute Of Fashion Technology, China, 2022.
50.
Aja-FernándezSCurialeAHVegas-Sánchez-FerreroG.A local fuzzy thresholding methodology for multiregion image segmentation. Knowledge Based Syst2015;
83: 1–12.
51.
WangLWanTTangW, et al. An efficient human body contour extraction method for mobile apps. In: 11th International Conference on E-Learning and Games, Bournemouth, UK, 26–28 June 2017, pp. 173–181. Cham: Springer.
52.
WangYWuXChenH.An intrusion detection method for wireless sensor network based on mathematical morphology. Secur Commun Netw2016;
9: 2744–2751.
53.
DengWLuGWangJ, et al.
Extraction of feature parameters of three-dimensional human body based on image. J Zhejiang Univ (Eng Sci)2010;
44: 837–840.
54.
NingJZhangDWuC, et al.
Automatic tongue image segmentation based on gradient vector flow and region merging. Neural Comput Appl2012;
21: 1819–1826.
55.
WuJZhangYBaiJ. Tongue area extraction in tongue diagnosis of traditional Chinese medicine. In: 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference, Shanghai, China, 1–4 September 2005, pp.4955–4957. Piscataway, NJ: IEEE.
56.
WuKZhangD.Robust tongue segmentation by fusing region-based and edge-based approaches. Expert Syst Appl2015;
42: 8027–8038.
57.
SoJYoumSKimS.A human body simulation using semantic segmentation and image-based reconstruction techniques for personalized healthcare. Appl Sci2024;
14: 7107.
58.
HerriZSiregarYFahmiF. Person segmentation in human height measurement using bodypix. In: 2022 6th International Conference on Electrical, Telecommunication and Computer Engineering (ELTICOM), 2022, pp.206–209. IEEE.
59.
HeKGkioxariGDollárP, et al. Mask R-CNN. In: Proceedings of the IEEE international conference on computer vision, 2017, pp.2961–2969.
60.
KassMWitkinATerzopoulosD.Snakes: Active contour models. Int J Comput Vision1988;
1: 321–331.
61.
ZareeiAKarimiA.Liver segmentation with new supervised method to create initial curve for active contour. Comput Biol Med2016;
75: 139–150.
62.
CohenLD.On active contour models and balloons. CVGIP: Image Understanding1991;
53: 211–218.
63.
XuCPrinceJL.Snakes, shapes, and gradient vector flow. IEEE Trans Image Process1998;
7: 359–369.
64.
YezziATsaiAWillskyA. A statistical approach to snakes for bimodal and trimodal imagery. In: Proceedings of the Seventh IEEE International Conference on Computer Vision, Kerkyra, Greece, 20–27 September 1999, pp. 898–903 Piscataway, NJ: IEEE.
65.
ChanTFVeseLA.Active contours without edges. IEEE Trans Image Process2001;
10: 266–277.
66.
TalebiMAyatollahiA. Genetic snake for medical ultrasound image segmentation. In: Proceedings of the 8th International Conference on Image Analysis and Recognition, Burnaby, BC, Canada, 2011, pp. 48–58. Berlin, Heidelberg: Springer
67.
PanwarPGulatiN.Genetic algorithms for image segmentation using active contours. J Global Res Comput Sci2013;
4: 34–37.
68.
MacEachernLAMankuT. Genetic algorithms for active contour optimization. In: Proceedings of the 1998 IEEE International Symposium on Circuits and Systems, ISCAS, Monterey, CA, USA, 31 May–3 June 1998, pp. 229–232. Piscataway, NJ: IEEE.
69.
LeYXuXZhaL, et al.
Tumor boundary detection in ultrasound imagery using multi-scale generalized gradient vector flow. J Med Ultrasonics2015;
42: 25–38.
70.
WuYWangYJiaY.Segmentation of the left ventricle in cardiac cine MRI using a shape-constrained snake model. Comput Vision Image Underst2013;
117: 990–1003.
71.
ZouKMaLFuY, et al.
Anthropometry oriented local contour extraction based on unclosed snake model. J Comput-Aided Des Comput Graphics2018;
30: 147–154.
72.
LoweDG.Distinctive image features from scale-invariant keypoints. Int J Comput Vision2004;
60: 91–110.
73.
BayHEssATuytelaarsT, et al.
Speeded-up robust features (SURF). Comput Vision Image Underst2008;
110: 346–359.
74.
HarrisCStephensM. A combined corner and edge detector. In: Alvey vision conference, 1988, pp.3674–3683. Citeseer.
75.
FengWHuYLiX, et al.
Research status and prospect of visual image feature point detection in body measurements. J Text Inst2022;
114: 1–8.
76.
DingGQiaoYYiW, et al.
Improved sift feature extraction and matching technology based on hyperspectral image. Opt Precis Eng2020;
28: 954–962.
77.
ZhongBLiY. Image feature point matching based on improved sift algorithm. In: 2019 IEEE 4th International Conference on Image, Vision and Computing (ICIVC), 2019, pp.489–493. IEEE.
78.
GohKMMokjiMMAbu-BakarSAR. Improved rotational matching of SIFT and SURF. In: 4th International Conference on Digital Image Processing, Kuala Lumpur, Malaysia, 7–8 April 2012, pp. 393–398.
79.
DongMYuanY.3D human feature recognition based on speeded-up robust features algorithm. J Beijing Inst Fashion Technol (Nat Sci Ed)2018;
38: 37–44.
80.
NawazSALiJBhattiUA, et al.
A novel hybrid discrete cosine transform speeded up robust feature-based secure medical image watermarking algorithm. J Med Imaging Health Inf2020;
10: 2588–2599.
81.
RamakrishnanNWuMLamS-K, et al.
Enhanced low-complexity pruning for corner detection. J Real Time Image Process2016;
12: 197–213.
82.
LuoCSunXSunX, et al. Improved Harris corner detection algorithm based on Canny edge detection and gray difference preprocessing. In: Journal of Physics: Conference Series, 2021, p.012088. IOP Publishing.
83.
LiJXuXLanX, et al.
Feature extraction and measurement of the human body based on Harris corner detection. Comput Meas Control2014;
22: 367–369.
84.
KimJYYouJWKimMS.South Korean anthropometric data and survey methodology:‘Size Korea’project. Ergonomics2017;
60: 1586–1596.
85.
PargasR. Automating information extraction from 3D scan data. DTIC Document1998.
86.
GB/T 16160-2017. Anthropometric definitions and methods for garment.
87.
YinLAnnett-HitchcockK.Comparison of body measurements between Chinese and U.S. females. J Text Inst2019;
110: 1–9.
88.
AslamMRajbdadFKhattakS, et al.
Automatic measurement of anthropometric dimensions using frontal and lateral silhouettes. IET Comput Vision2017;
11: 434–447.
89.
ZouKMaLLiR, et al.
Image-based non-contacting anthropometric method. Comput Eng Des2017;
38: 511–516.
90.
FreemanHDavisL.A corner-finding algorithm for chain-coded curves. IEEE Trans Comput1977;
C-26: 297–303.
91.
JiangLYaoJLiB, et al.
Automatic body feature extraction from front and side images. J Software Eng Appl2012;
05: 94–100.
92.
LinYLWangMJ.Automated body feature extraction from 2D images. Expert Syst Appl2011;
38: 2585–2591.
93.
OuelletSMichaudF.Enhanced automated body feature extraction from a 2D image using anthropomorphic measures for silhouette analysis. Expert Syst Appl2017;
91: 270–276.
94.
DengZWangJJinX, et al.
Detection of human shoulder feature points based on image analysis. J Text Res2023;
44: 175–179.
95.
SunYWangXTangX. Deep convolutional network cascade for facial point detection. In: 2013 IEEE Conference on Computer Vision and Pattern Recognition, Portland, OR, USA, 23–28 June 2013, pp.3476–3483.
96.
XieRZhangQYangE, et al. A method of small face detection based on CNN. In: 2019 4th International Conference on Computational Intelligence and Applications (ICCIA), Nanchang, China, 21–23 June 2019, pp.78–82. US: IEEE.
97.
ToshevASzegedyC. DeepPose: Human pose estimation via deep neural networks. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, United states, 23–28 June 2014, pp. 1653–1660.
98.
PishchulinLInsafutdinovETangS, et al. DeepCut: Joint subset partition and labeling for multi person pose estimation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, United states, 26 June–1 July 2016, pp.4929–4937.
99.
CaoZSimonTWeiS-E, et al.
OpenPose: Realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans Pattern Anal Mach Intell2019;
43: 172–186.
100.
ZhuXYeX.GAN-BodyPose: Real-time 3D human body pose data key point detection and quality assessment assisted by generative adversarial network. Image Vision Comput2024;
149: 105144.
101.
PfisterTCharlesJZissermanA. Flowing ConvNets for human pose estimation in videos. In: 2015 IEEE International Conference on Computer Vision (ICCV), Santiago, Chile, 11–18 December 2015, pp. 1913–1921. US: IEEE.
102.
ChuXOuyangWLiH, et al. Structured feature learning for pose estimation. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, 27–30 June 2016, pp. 4715–4723.
103.
JiangDLiGSunY, et al.
Gesture recognition based on skeletonization algorithm and CNN with ASL database. Multimed Tools Appl2019;
78: 29953–29970.
104.
HatakeyamaKIidaNNagaeS, et al.
A study on a measuring system for human body by image prossesing. J Graphic Sci Jpn1988;
22: 7–16.
105.
HuXXuB.Reconstruction of individualized dress forms using parameterized silhouettes. Int J Clothing Sci Technol2010;
22: 114–126.
106.
GuBAhmedKZhongZ, et al.
3D female upper body modelling based on 2D images. Int J Clothing Sci Technol2020;
32: 471–482.
107.
KuangCJiKJinR, et al.
Prediction of the main girths of young female based on 3D point cloud data. J Fiber Bioeng Inf2012;
5: 289–298.
108.
LiXJingX.The establishment of human body three vital measurements regression relationship based on SVR method. Int J Clothing Sci Technol2015;
27: 148–158.
109.
TanXPengXLiuL, et al. Automatic human body feature extraction and size measurement by random forest regression analysis of geodesics distance. In: 2017 International Conference on Virtual Reality and Visualization (ICVRV), 2017, pp.261–266. IEEE.
110.
VassilevTDimitrovM. Predicting human body measurements from a front image. In: Proceedings of the 24th International Conference on Computer Systems and Technologies, Ruse, Bulgaria, 16–17 June 2023, pp.100–105. New York, NY, United States: ACM.
111.
FoysalKChangHBruessF, et al.
Body size measurement using a smartphone. Electronics2021;
10: 1338.
112.
ZhuSZhouYChuaK, et al. Shape customisation of human subjects based on human parsing technology. In: Proceedings of 3DBODYTECH 2017 - 8th International Conference and Exhibition on 3D Body Scanning and Processing Technologies, Montreal QC, Canada, 11–12 October 2017, pp.288–295.
113.
SongDTongRChangJ, et al.
3D body shapes estimation from dressed human silhouettes. Comput Graphics Forum2016;
35: 147–156.
114.
SmithBMChariVAgrawalA, et al. Towards accurate 3D human body reconstruction from silhouettes. In: 2019 International Conference on 3D Vision (3DV), Quebec, QC, Canada, 15–18 September 2019, pp.279–288. US: IEEE.
115.
LiXLiGLiM, et al.
3D human body modeling with orthogonal human mask image based on multi-channel swin transformer architecture. Image Vision Comput2023; 137.
116.
LiYMaY.Non-contact human waist circumference measurement based on 2D image. Video Eng2019;
43: 15–18 + 21.
117.
WangYLiX.Establishment of a ridge regression model for estimating body hip circumference. Knitting Ind2006;
07: 27–29.
118.
LiuX.Calculation of human chest width in natural dress state. Tianjin Text Sci Technol2011;
02: 26–27 + 31.
119.
ZhuSMokPY.Predicting realistic and precise human body models under clothing based on orthogonal-view photos. Procedia Manuf2015;
3: 3812–3819.
120.
LuSLuFShouX, et al.
DeepProfile: Accurate under-the-clothes body profile estimation. Appl Sci2022;
12: 2220.
121.
LoperMMahmoodNRomeroJ, et al.
SMPL: A skinned multi-person linear model. ACM Trans Graphics2015;
34: 1–16.
122.
AdikariAGanegodaNWanniarachchiW.
Non contact human body parameter measurement based on kinect sensor. IOSR Journal of Computer Engineering2017;
19: 80–85.
