Fast subpixel digital image correlation using artificial neural networks
暂无分享,去创建一个
Digital image correlation has been used to measure microscopic deformation in thermally stressed microelectronics devices. Displacement precisions of better than 0.03 pixels have been achieved by combining nonintegral pixel shifting of subimages and artificial neural networks (ANNs). The ANNs are trained to estimate the subpixel element of the object displacement from the digital correlation. Although similar accuracies can be obtained by curve-fitting to the correlation peaks and differentiating, the neural approach has the advantage that it allows fast subpixel. displacement analysis over a range of object textures without knowledge of the analytical form of the correlation peaks.
[1] Bongtae Han,et al. Recent advancements of moiré and microscopic moiré interferometry for thermal deformation analyses of microelectronics devices , 1998 .
[2] Mikael Sjödahl,et al. Electronic speckle photography: increased accuracy by nonintegral pixel shifting. , 1994, Applied optics.
[3] Bernd Michel,et al. Microdac - a novel approach to measure in situ deformation fields of microscopic scale , 1996 .
[4] Joey Rogers. Object-oriented neural networks in C++ , 1996 .