论文信息 - Neural net selection of features for defect inspection

Neural net selection of features for defect inspection

An artificial neural network (ANN) fed with optically generated features is applied to IC inspection. The data used are characters with defects in them that model those expected in IC patterns. The ANN is used in training to select the best features. This results the required number of neurons needed during defect testing. Simulation results are provided for four types of defects using optical Fourier Wedge-Ring (WR) sampled Fourier and Hough feature spaces.

[1] Michael J. Chen,et al. High-speed inspection architectures, barcoding, and character recognition : 5-7 November 1990, Boston, Massachusetts , 1991 .

[2] D P Casasent,et al. Adaptive-clustering optical neural net. , 1990, Applied optics.

[3] D Casasent,et al. Industrial use of a real-time optical inspection system. , 1988, Applied optics.

[4] A. Ono,et al. Video high-density disk surface testing with a laser diode and a position sensor. , 1988, Applied optics.

[5] D. E. Glover. An optical Fourier/electronic neurocomputer automated inspection system , 1988, IEEE 1988 International Conference on Neural Networks.

[6] David Casasent,et al. Practical Optical Fourier Analysis For High Speed Inspection , 1988 .

[7] Jeffrey Richards,et al. Optical Hough And Fourier Processors For Product Inspection , 1988 .

[8] D. Casasent,et al. Diffraction pattern sampling using a computer-generated hologram. , 1986, Applied optics.

[9] David Casasent,et al. Coherent Optical Pattern Recognition: A Review , 1985 .

[10] R.J.T. Morris,et al. A comparison of feedforward and self-organizing approaches to the font orientation problems , 1989, International 1989 Joint Conference on Neural Networks.

[11] D. Brzakovic,et al. A self-training visual inspection system with a neural network classifier , 1989, International 1989 Joint Conference on Neural Networks.