Defect Segmentation of Semiconductor Wafer Image Using k-Means Clustering

Abstract:

Nowadays, quality control becomes an important issue in semiconductor manufacturing industry. The rate of production with respect to time gives a lot of issues in the industry. In most semiconductor assemblies, a lot of defects generated from various processes in semiconductor wafer manufacturing need to be inspected manually using human experts and this process required full concentration of the operators. This human inspection procedure, however, is time consuming and highly subjective. In order to overcome this problem, implementation of machine vision will be the best solution. This paper presents defect segmentation of semiconductor wafer image based on colour features with k-Means clustering algorithm which can be adopted in machine vision system. In this work, the segmentation process is carried out in two stages. The first stage comprised of clustering the pixels in the image based on their colour and spatial features. Then the clustered pixels are merged to a specific number of regions. The proposed approach is being evaluated using defected wafer image. The experimental results show that it can be used to segment the defect correctly. By using this method, it is possible to increase the computational efficiency since it will avoid feature extraction for every pixel in the image.

• Periodical: Applied Mechanics and Materials (Volume 815)
• Pages: 374-379
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.815.374
• Online since: November 2015
• Authors: N.H. Saad, N. Mohamad Sabri, A.F. Hasan, Azuwa Ali, Hariyanti Mohd Saleh
• Keywords: Defect Segmentation, Image Processing, Image Segmentation, K-Means Clustering, Semiconductor Wafer

References

[1] Shankar, N.G. and Zhong, Z.W., Defect detection on semiconductor wafer surfaces,. Microelectronics Engineering, 77, 337-346, (2005).

DOI: 10.1016/j.mee.2004.12.003

[2] Chen, F. -L. and Liu, S. -F., A neural-network approach to recognize defect spatial pattern in semiconductor fabrication,. IEEE Transactions on Semiconductor Manufacturing, 13, 366-373, (2000).

DOI: 10.1109/66.857947

[3] J. B. MacQueen, Some methods for classification and analysis of multivariate observations, in Proceedings of the 5th Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, University of California Press, pp.281-297, (1967).

[4] Rajeshwar Dass, Priyanka, Swapna Devi, Image Segmentation Techniques, International Journal on Electronics & Communication Technology (IJECT), Vol. 3, Issue 1, pp.66-70, Jan. - March (2012).

[5] Shiv Ram Dubey, Pushkar Dixit, Nishant Singh, Jay Prakash Gupta, Infected Fruit Part Detection using K-Means Clustering Segmentation Technique., International Journal of Artificial Intelligence and Interactive Multimedia, Vol. 2, No. 2, (2013).

DOI: 10.9781/ijimai.2013.229

[6] Zhe LIU and Xiuchen WANG, Image Defect Recognition Based on "Super Fuzzy" Characteristic., Journal Of Multimedia, Vol. 5, No. 2, April (2010).

[7] J. selvakumar, A. Lakshmi, Brain Tumor Segmentation and Its Area Calculation in Brain MR Images using K-Mean Clustering and Fuzzy C-Mean Algorithm., I.E.E.E. International Conference On Advances In Engineering, Science And Management (ICAESM -2012) March 30, 31, (2012).

[8] K. Alsabti, S. Ranka, and V. Singh. An Efficient K-Means Clustering Algorithm. Information on http: /www. cise. ufl. edu/~ ranka.