Foot Measurement Based on Deep Alignment Network

doi:10.16182/j.issn1004731x.joss.19-VR0467

Abstract

Abstract: Foot measurement plays an important role in many areas. Limited by equipment and algorithms, three-dimensional foot measurement cannot make a convenient and quick foot measurement. A method is proposed by combining the image measurement with the deep neural network. Based on the physiological structure analysis of foot, key points are extracted and the measurement parameters are defined. During the key point detection of foot, the activation function and loss function of DAN (Deep Alignment Network) model is optimized, and a data acquisition method is defined based on the handheld camera. Foot key points are detected, and main parameters are measured. Experimental results show that collecting data based on handheld camera can conveniently measure foot parameters and the precision is high.

Key words: anthropometrics, foot measurement, target detection, deep network, DAN model

CLC Number:

TP391.9

Shi Min, Yao Hanqin, Li Chunpeng, Chen Liangchen. Foot Measurement Based on Deep Alignment Network[J]. Journal of System Simulation, 2020, 32(7): 1267-1278.

References 23

[1]	Pheasant S, Haslegrave C M.Bodyspace: Anthropometry, ergonomics and the design of work[M]. Boca Raton, FL, USA: CRC Press, 2005.
[2]	Song S C, Yu S P, Xu W J.Study on 3 D body scanning, reconstruction and measurement techniques based on Kinect[J]. Tianjin Gongye Daxue Xuebao (S1671-024X), 2012, 31(5): 34-37.
[3]	Zhong K, Li Z, Zhou X, et al.Enhanced phase measurement profilometry for industrial 3D inspection automation[J]. The International Journal of Advanced Manufacturing Technology (S1433-3015), 2015, 76(9-12): 1563-1574.
[4]	王俊青, 周旭, 姚志明, 等. 基于计算机视觉的脚型参数测量系统的设计与实现[J]. 仪表技术, 2012, (7): 36-40.Wang Junqing, Zhou Xu, Yao Zhiming, et al.Design and Implementation of the Foot Parameter Measurement System Based on Computer Vision[J]. Instrumentation Technology, 2012, (7): 36-40
[5]	毋戈. 基于多个深度相机的足部三维重建及形态分析[D]. 上海: 东华大学, 2017.Wu Ge.Three-dimensional Reconstruction and Shape Analysis of Human Feet Based on Multiple Depth Cameras[D]. Shanghai: Donghua University, 2017.
[6]	刘长青, 陈兵旗. 基于机器视觉的玉米果穗参数的图像测量方法[J]. 农业工程学报, 2014, 30(6): 131-138.Liu Changqing, Chen Bingqi.Method of image detection for ear of corn based on computer vision[J]. Transactions of the Chinese Society of Agricultural Engineering, 2014, 30(6): 131-138.
[7]	Momin M A, Yamamoto K, Miyamoto M, et al.Machine vision based soybean quality evaluation[J]. Computers and Electronics in Agriculture (S0168-1699), 2017, 140: 452-460.
[8]	柳革命, 刘鹏. 基于机器视觉的弹壳多尺寸测量[J]. 工业控制计算机, 2016, 29(4): 60-61.Liu Geming, Liu Peng.Sizes Measurement of Cartridge Case Based on Machine Vision[J]. Industrial Control Computer, 2016, 29(4): 60-61.
[9]	Hao M, Yu H, Li D.The measurement of fish size by machine vision-a review[C]// International Conference on Computer and Computing Technologies in Agriculture. Berlin, German: Springer, Cham, 2015: 15-32.
[10]	Kang T J, Choi S H, Kim S M, et al.Automatic structure analysis and objective evaluation of woven fabric using image analysis[J]. Textile Research Journal (S0040-5175), 2001, 71(3): 261-270.
[11]	Dollár P, Welinder P, Perona P.Cascaded pose regression[C]// 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2010: 1078-1085.
[12]	Sun Y, Wang X, Tang X.Deep convolutional network cascade for facial point detection[C]// 2013 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2013: 3476-3483.
[13]	Zhang K, Zhang Z, Li Z, et al.Joint face detection and alignment using multitask cascaded convolutional networks[J]. IEEE Signal Processing Letters (S1070-9908), 2016, 23(10): 1499-1503.
[14]	Liu W.Accuracy and reliability of a technique for quantifying foot shape, dimensions and structural characteristics[J]. Ergonomics (S0014-0139), 1999, 42(2): 346-358.
[15]	Zhao J, Xiong S, Bu Y, et al.Computerized girth determination for custom footwear manufacture[J]. Computers & Industrial Engineering (S0360-8352), 2008, 54(3): 359-373.
[16]	朱晓兰, 吴壮志. 三维足型参数自动测量系统设计与实现[J]. 体育科学, 2010, 30(9): 44-48, 81.Zhu Xiaolan, Wu Zhuangzhi.Design and Implementation of 3D Foot Size Measurement System[J]. China Sport Science, 2010, 30(9): 40-48, 81.
[17]	王明鑫, 俞光荣, 陈雁西, 等. 正常中国成年人足底压力分析[J]. 中国矫形外科杂志, 2008(9): 687-690.Wang Mingxin, Yu Guangrong, Chen Yanxi, et al.Analysis of the plantar pressure distribution of the normal Chinese adult[J]. Orthopedic Journal of China, 2008(9): 687-690.
[18]	Howard A G, Zhu M, Chen B, et al.Mobilenets: Efficient convolutional neural networks for mobile vision applications[DB/OL]. [2019-10-05] https://arxiv.org/abs/ 1704.04861.
[19]	Yosinski J, Clune J, Bengio Y, et al.How transferable are features in deep neural networks?[C]// Advances in neural information processing systems. New York: Curran Associates, 2014: 3320-3328.
[20]	Srivastava N, Hinton G, Krizhevsky A, et al.Dropout: a simple way to prevent neural networks from overfitting[J]. The journal of machine learning research (S1532-4435), 2014, 15(1): 1929-1958.
[21]	Kowalski M, Naruniec J, Trzcinski T.Deep alignment network: A convolutional neural network for robust face alignment[C]// 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW). Piscataway, NJ: IEEE, 2017: 88-97.
[22]	Feng Z H, Kittler J, Awais M, et al.Wing loss for robust facial landmark localisation with convolutional neural networks[C]// 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2018: 2235-2245.
[23]	Kazemi V, Sullivan J.One millisecond face alignment with an ensemble of regression trees[C]// 2014 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2014: 1867-1874.