Feature Extraction From Analog Wafermaps: A Comparison of Classical Image Processing and a Deep Generative Model

Semiconductor manufacturing is a highly innovative branch of industry, where a high degree of automation has already been achieved. For example, devices tested to be outside of their specifications in electrical wafer test are automatically scrapped. In this paper, we go one step further and analyze test data of devices still within the limits of the specification, by exploiting the information contained in the analog wafermaps. To that end, we propose two feature extraction approaches with the aim to detect patterns in the wafer test dataset. Such patterns might indicate the onset of critical deviations in the production process. The studied approaches are: 1) classical image processing and restoration techniques in combination with sophisticated feature engineering and 2) a data-driven deep generative model. The two approaches are evaluated on both a synthetic and a real-world dataset. The synthetic dataset has been modeled based on real-world patterns and characteristics. We found both approaches to provide similar overall evaluation metrics. Our in-depth analysis helps to choose one approach over the other depending on data availability as a major aspect, as well as on available computing power and required interpretability of the results.

[1]  Dong-Chen He,et al.  Texture Unit, Texture Spectrum, And Texture Analysis , 1990 .

[2]  Ming-Ju Wu,et al.  Wafer Map Failure Pattern Recognition and Similarity Ranking for Large-Scale Data Sets , 2015, IEEE Transactions on Semiconductor Manufacturing.

[3]  Donald Geman,et al.  Stochastic relaxation, Gibbs distributions, and the Bayesian restoration of images , 1984 .

[4]  Roman Kern,et al.  Understanding wafer patterns in semiconductor production with variational auto-encoders , 2018, ESANN.

[5]  อนิรุธ สืบสิงห์,et al.  Data Mining Practical Machine Learning Tools and Techniques , 2014 .

[6]  Daan Wierstra,et al.  Stochastic Backpropagation and Approximate Inference in Deep Generative Models , 2014, ICML.

[7]  Heeyoung Kim,et al.  Classification of Mixed-Type Defect Patterns in Wafer Bin Maps Using Convolutional Neural Networks , 2018, IEEE Transactions on Semiconductor Manufacturing.

[8]  En Zhu,et al.  Deep Clustering with Convolutional Autoencoders , 2017, ICONIP.

[9]  Thomas Brox,et al.  Striving for Simplicity: The All Convolutional Net , 2014, ICLR.

[10]  Max Welling,et al.  Auto-Encoding Variational Bayes , 2013, ICLR.

[11]  Ran Jin,et al.  A hierarchical model for characterising spatial wafer variations , 2014 .

[12]  Claude Yugma,et al.  Equipment Condition Diagnosis and Fault Fingerprint Extraction in Semiconductor Manufacturing , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[13]  Fei-Long Chen,et al.  A neural-network approach to recognize defect spatial pattern in semiconductor fabrication , 2000 .

[14]  Jürgen Pilz,et al.  Device level Maverick screening - detection of risk devices through Independent Component Analysis , 2014, Proceedings of the Winter Simulation Conference 2014.

[15]  Xin Li,et al.  Identifying Wafer-Level Systematic Failure Patterns via Unsupervised Learning , 2018, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems.

[16]  Paul D. Yoo,et al.  Clustering the Dominant Defective Patterns in Semiconductor Wafer Maps , 2018, IEEE Transactions on Semiconductor Manufacturing.

[17]  S. F. Liu,et al.  Wafer bin map recognition using a neural network approach , 2002 .

[18]  P. Rousseeuw.  Silhouettes: a graphical aid to the interpretation and validation of cluster analysis , 1987 .

[19]  Graham W. Taylor,et al.  Deconvolutional networks , 2010, 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[20]  An Sheng Chung,et al.  Using Wavelet Transform and Neural Network Approach to Develop a Wafer Bin Map Pattern Recognition Model , 2008 .

[21]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  N. Otsu.  A threshold selection method from gray level histograms , 1979 .

[23]  Roman Kern,et al.  Markov random fields for pattern extraction in analog wafer test data , 2017, 2017 Seventh International Conference on Image Processing Theory, Tools and Applications (IPTA).

[24]  Elmar Wolfgang Lang,et al.  A Nonnegative Tensor Factorization Approach for Three-Dimensional Binary Wafer-Test Data , 2016, 2016 15th IEEE International Conference on Machine Learning and Applications (ICMLA).

[25]  Takeshi Nakazawa,et al.  Wafer Map Defect Pattern Classification and Image Retrieval Using Convolutional Neural Network , 2018, IEEE Transactions on Semiconductor Manufacturing.

[26]  Karen O. Egiazarian,et al.  Dominant Rotated Local Binary Patterns (DRLBP) for texture classification , 2016, Pattern Recognit. Lett..