Shape and surface measurement technology by an improved shape-from-shading neural algorithm

作者: Sin-Yeung Cho , T.W.S. Chow

DOI: 10.1109/41.824148

关键词:

摘要: A new approach for measuring the shape and surface of an object observed from a single camera is proposed. The proposed based on using neural networks as parametric representation three-dimensional shape-from-shading problem formulated minimization intensity error function with respect to network weights. Experimental results demonstrate that authors' methodology exhibits high efficiency accuracy inspecting product's in manufacturing industry.

参考文章(7)
Siu-yeung Cho, Tommy W.S. Chow, A Fast Heuristic Global Learning Algorithm for Multilayer Neural Networks Neural Processing Letters. ,vol. 9, pp. 177- 187 ,(1999) , 10.1023/A:1018685627113
M. Gori, A. Tesi, On the problem of local minima in backpropagation IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 14, pp. 76- 86 ,(1992) , 10.1109/34.107014
Berthold K. P. Horn, Height and gradient from shading International Journal of Computer Vision. ,vol. 5, pp. 37- 75 ,(1990) , 10.1007/BF00056771
Berthold K.P Horn, Michael J Brooks, The variational approach to shape from shading Graphical Models \/graphical Models and Image Processing \/computer Vision, Graphics, and Image Processing. ,vol. 33, pp. 174- 208 ,(1986) , 10.1016/0734-189X(86)90114-3
Guo-Qin Wei, G. Hirzinger, Learning shape from shading by a multilayer network IEEE Transactions on Neural Networks. ,vol. 7, pp. 985- 995 ,(1996) , 10.1109/72.508940
Guo-Qing Wei, G. Hirzinger, Parametric shape-from-shading by radial basis functions IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 19, pp. 353- 365 ,(1997) , 10.1109/34.588016