This paper presents a new approach for image digitizing in the Cartizian three dimension XYZ coordinates. It is defined as the displacement vector concept based on the hierarchical stereo vision technique depending on multi camera system, distributed around the tested object. Optical sensors without any mechanical parts under the control of a host computer with an integrated full automatic calibra- tion process are introduced. Problems of this automated style are in- vestigated. Different factors such as calibration, feature extraction, point to point correspondence, determination of cartizian coordinates, transformation into symbolic computer aided design form are includ- ed. Performance of the proposed system is analyzed and results of the application to a human foot model as a sample of testing are deter- mined. The execution time and effort are dramatically decreased with increased measured accuracy.
[1]
André Oosterlinck,et al.
Range Image Acquisition with a Single Binary-Encoded Light Pattern
,
1990,
IEEE Trans. Pattern Anal. Mach. Intell..
[2]
Marc Levoy,et al.
Display of surfaces from volume data
,
1988,
IEEE Computer Graphics and Applications.
[3]
Bruce J. Schachter,et al.
Computer display of height fields
,
1980,
Comput. Graph..
[4]
David Nitzan,et al.
Three-Dimensional Vision Structure for Robot Applications
,
1988,
IEEE Trans. Pattern Anal. Mach. Intell..
[5]
M. Hamed.
A quick neural network for computer vision of gray images
,
1997
.