Toggle Main Menu Toggle Search

Open Access padlockePrints

Computer vision for shoe upper profile measurement via upper and sole conformal matching

Lookup NU author(s): Dr Zhongxu Hu, Dr Bob Bicker, Professor Paul Taylor, Christopher Marshall


Full text for this publication is not currently held within this repository. Alternative links are provided below where available.


This paper describes a structured light computer vision system applied to the measurement of the 3D profile of shoe uppers. The trajectory obtained is used to guide an industrial robot for automatic edge roughing around the contour of the shoe upper so that the bonding strength can be improved. Due to the specific contour and unevenness of the shoe upper, even if the 3D profile is obtained using computer vision, it is still difficult to reliably define the roughing path around the shape. However, the shape of the corresponding shoe sole is better defined, and it is much easier to measure the edge using computer vision. Therefore, a feasible strategy is to measure both the upper and sole profiles, and then align and fit the sole contour to the upper, in order to obtain the best fit. The trajectory of the edge of the desired roughing path is calculated and is then smoothed and interpolated using NURBS curves to guide an industrial robot for shoe upper surface removal; experiments show robust and consistent results. An outline description of the structured light vision system is given here, along with the calibration techniques used. © 2006 Elsevier Ltd. All rights reserved.

Publication metadata

Author(s): Hu Z, Bicker R, Taylor P, Marshall C

Publication type: Article

Publication status: Published

Journal: Optics and Lasers in Engineering

Year: 2007

Volume: 45

Issue: 1

Pages: 183-190

ISSN (print): 0143-8166

ISSN (electronic): 1873-0302

Publisher: Elsevier Ltd


DOI: 10.1016/j.optlaseng.2006.04.004


Altmetrics provided by Altmetric