Share This Article:

Automatic Body Feature Extraction from Front and Side Images

Abstract Full-Text HTML Download Download as PDF (Size:315KB) PP. 94-100
DOI: 10.4236/jsea.2012.512B019    4,095 Downloads   6,570 Views   Citations

ABSTRACT

Human body feature extraction based on 2D images provides an efficient method for many applications, e.g. non-contact body size measurements, constructing 3D human model and recognizing human actions. In this paper a systematic approach is proposed to detect feature points of human body automatically from its front and side images. Firstly, an efficient approach for silhouette and contour detection is used to represent the contour curves of a human body shape with Freeman’s 8-connected chain codes. The contour curves are considered as a number of segments connected together. Then, a series of feature points on human body are extracted based on the specified rules by measuring the differences between the directions of the segments. In total, 101 feature points with clearly geometric properties (that rather accurately reflect the bump or turning of the contours) are extracted automatically, including 27 points corresponding to the definitions of the landmarks about garment measurements. Finally, the proposed approach was tested on ten human subjects and the entire 101 feature points with specific geography geometrical characteristics were correctly extracted, indicating an effective and robust performance.

 

Conflicts of Interest

The authors declare no conflicts of interest.

Cite this paper

L. Jiang, J. Yao, B. Li, F. Fang, Q. Zhang and M. Meng, "Automatic Body Feature Extraction from Front and Side Images," Journal of Software Engineering and Applications, Vol. 5 No. 12B, 2012, pp. 94-100. doi: 10.4236/jsea.2012.512B019.

References

[1] S.A. Rahman, S.-Y. Cho and M.K.H. Leung, “Recognis-ing human actions by analyzing negative spaces,” IET Computer Vision, Vol. 6, No. 3, 2012, pp. 197–213. doi: 10.1049/iet-cvi.2011.0185
[2] N. Ikizler and D.A. Forsyth, “Searching for complex human activities with no visual examples,” Int. Journal of Comput. Vision, Vol. 80, No. 3, 2008, pp. 337–357. doi: 10.1007/s11263-008-0142-8
[3] C. Bregler, “Learning and recognizing human dynamics in video Sequences,” Proc. Computer Vision and Pattern Recognition, San Juan, 1997, pp. 568–574.
[4] J.M. Lu and M.J. Wang, “Automated data collection using 3D whole body scanner,” Expert Systems with Applications, Vol. 35, No. 1-2, 2008, pp. 407–414. doi: 10.1016/j.eswa.2007.07.008
[5] P. Meunier and S. Yin, “Performance of a 2D image-based anthropometric measurement and clothing sizing system,” Applied Er-gonomics, Vol. 31, No. 5, 2000, pp. 445–451. doi:10.1016/S0003-6870(00)00023-5
[6] H. Freeman, “On the encoding of arbitrary geometric configuration,” IRE Transactions on Electronics Computers, Vol. EC-10, No. 2, 1961, pp. 264–268. doi:10.1109/TEC.1961.5219197
[7] H. Freeman and L.S. Davis, “A corner-finding algorithm for chain-coded curves,” IEEE Transactions on Computers, Vol. C-26, No. 3, 1977, pp. 297–303. doi:10.1109/TC.1977.1674825
[8] J. Canny, “A computa-tional approach to edge detection,” IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 8, No. 6, 1986, pp. 679-698. doi:10.1109/TPAMI.1986.4767851
[9] Y.L. Lin and M.J. Wang, “Constructing 3D Human Model from 2D im-ages,” Int. Conf. on Industrial Engineering and Engi-neering Management, Xiamen, Oct, 2010, pp.1902-1906.
[10] Y.L. Lin and M.J. Wang, “Con-structing 3D human model from front and side images,” Expert Systems with Applications, Vol. 39, No. 5, April 2012, pp. 5012–5018. doi:10.1016/j.eswa.2011.10.011
[11] Y.L. Lin and M.J. Wang, “Automatic Feature Extraction from Front and Side Images,” Int. Conf. on Industrial Engineering and Engineering Management, Singapore, Dec, 2008, pp. 1949-1953.
[12] Y.L. Lin and M.J. Wang, “Automated body feature extraction from 2D images,” Expert Sys-tems with Applications, Vol. 38, No. 3, 2011, pp. 2585–2591. doi:10.1016/j.eswa.2010.08.048
[13] A. Ali and J.K. Ag-garwal, “Segmentation and recognition of continuous human activity,” Proc. IEEE Workshop on Detection & Recog. of Events in Video, Vancouver, BC, 2001, pp. 28–35.
[14] M. Kouchi and M. Mochimaru, “Errors in landmarking and the evaluation of the accuracy of traditional and 3D anthropometry,” Applied Ergonomics, Vol. 42, No. 3, 2011, pp. 518-527. doi:10.1016/j.eswa.2010.08.048
[15] Iat-Fai Leong, “A study of automatic anthropometry and construction of computer manikins,” Master's thesis of National Cheng Kung University, 1992. (In Chinese)
[16] ISO8559-1989 garment construction and anthropometric surveys body dimensions.
[17] GB/T16160-2008 location and method of anthropometric surveys for garment.

  
comments powered by Disqus

Copyright © 2018 by authors and Scientific Research Publishing Inc.

Creative Commons License

This work and the related PDF file are licensed under a Creative Commons Attribution 4.0 International License.