Multi-layer neural network applied to phase and depth recovery from fringe patterns

A multi-layer neural network (MLNN) is used to carry out calibration processes in fringe projection profilometry in which the explicit knowledge of the experimental set-up parameters is not required. The MLNN is trained by using the fringe pattern irradiance and the height directional gradients provided from a calibration object. After the MLNN has been trained, profilometric height data are estimated from the projected fringe patterns onto the test object. The MLNN method works adequately on an open fringe pattern, but it can be extended to closed fringe patterns. In the proposed technique, edge effects do not appear when the field view is limited in the fringe pattern. In order to show the application of the MLNN method, three different experiments are presented: (a) shape determination of a spherical optical surface; (b) optical phase calculation from a computer-simulated closed fringe pattern; and (c) height determination of a real surface target. An analysis is also made of how noise, spatial carrier frequencies, and different training sets affect the MLNN performance.

[1]  Emile Fiesler,et al.  The Interchangeability of Learning Rate and Gain in Backpropagation Neural Networks , 1996, Neural Computation.

[2]  David M. Skapura,et al.  Neural networks - algorithms, applications, and programming techniques , 1991, Computation and neural systems series.

[3]  Manuel Servin,et al.  Two-dimensional Phase Locked Loop Demodulation of Interferograms , 1993 .

[4]  Francisco J. Cuevas,et al.  Depth object recovery using radial basis functions , 1999 .

[5]  Y Ichioka,et al.  Direct phase detecting system. , 1972, Applied optics.

[6]  T. R. Judge,et al.  A review of phase unwrapping techniques in fringe analysis , 1994 .

[7]  Daniel Malacara,et al.  Noisy fringe pattern demodulation by an iterative phase locked loop , 1995 .

[8]  Manuel Servin,et al.  A Robust Cellular Processor for Phase Unwrapping , 1994 .

[9]  Wolfgang Osten,et al.  A robust procedure for absolute phase measurement , 1996 .

[10]  Xiaoyu Zhang,et al.  Range estimation from two-dimensional images using phase modulation , 1994 .

[11]  R. Rodríguez-Vera,et al.  Phase locked loop profilometry , 1994 .

[12]  Jonathan M. Huntley,et al.  Profilometry using temporal phase unwrapping and a spatial light modulator based fringe projector , 1997 .

[13]  Xianyu Su,et al.  Two-dimensional Fourier transform profilometry for the automatic measurement of three-dimensional object shapes , 1995 .

[14]  Robert J. Schalkoff,et al.  Artificial neural networks , 1997 .

[15]  M Servin,et al.  Phase unwrapping with a regularized phase-tracking system. , 1998, Applied optics.

[16]  David Kerr,et al.  Electronic speckle contouring , 1992 .

[17]  D J Bone,et al.  Fourier fringe analysis: the two-dimensional phase unwrapping problem. , 1991, Applied optics.

[18]  Kenneth H. Womack,et al.  Interferometric Phase Measurement Using Spatial Synchronous Detection , 1983 .

[19]  Charles Joenathan,et al.  Phase Measurement by Differentiating Interferometric Fringes , 1992 .

[20]  Fabrice Brémand.  A phase unwrapping technique for object relief determination , 1994 .

[21]  M. Takeda,et al.  Fourier transform profilometry for the automatic measurement of 3-D object shapes. , 1983, Applied optics.

[22]  Hong Zhao,et al.  Automatic analysis technique of spatial carrier-fringe patterns , 1996 .

[23]  Xianyu Su,et al.  A direct mapping algorithm for phase-measuring profilometry , 1994 .

[24]  Mitsuo Takeda,et al.  Phase unwrapping by a maximum cross‐amplitude spanning tree algorithm: a comparative study , 1996 .

[25]  Daniel Malacara-Hernández,et al.  Direct-phase detection of modulated Ronchi rulings using a phase-locked loop , 1994 .

[26]  D Malacara,et al.  Phase-locked-loop interferometry applied to aspheric testing with a computer-stored compensator. , 1994, Applied optics.

[27]  Guozhong An,et al.  The Effects of Adding Noise During Backpropagation Training on a Generalization Performance , 1996, Neural Computation.

[28]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[29]  Jiang Yi,et al.  Modified Fourier transform profilometry for the measurement of 3-D steep shapes , 1997 .

[30]  Janusz Kozlowski,et al.  New modified phase locked loop method for fringe pattern demodulation , 1997 .

[31]  David R. Burton,et al.  Applying backpropagation neural networks to fringe analysis , 1995 .

[32]  M. Takeda,et al.  Fourier-transform method of fringe-pattern analysis for computer-based topography and interferometry , 1982 .