Development of an Low Cost Platform for IC Printed Mark Defects Inspection

  • Hung-Shiang Chuang
Conference paper
Part of the Lecture Notes in Electrical Engineering book series (LNEE, volume 293)


The objective of this research is to develop an low cost automated visual inspection system for IC printed defect marks which consists of two parts: hardware setup and software program based on machine vision technique. The characteristics of the experimental setup is that it is simple and effective to achieve the purpose of defect detection. The core software module is divided into two main parts, namely, image pre-processing and defect detection. The normalized correlation scheme designed to detect the IC printed marks is proposed. Experimental results show that the normalized correlation scheme could help us to decide whether the printed marks are non-defective within a very short period of time.


Visual inspection system Normalized correlation scheme IC printed marks 



The authors would like to thank B.Z. Liao and C.Y. Chen for their help on experiments.


  1. 1.
    Jiang, B. C., Wang, Y. M., & Wang, C. C. (2001). Bootstrap sampling techniques applied to the PCB golden fingers defects classification study. International Journal of Production Research, 39(10), 2215–2230.CrossRefGoogle Scholar
  2. 2.
    Chang, M. C., & Fuh, C. S. (2001). Fast Search Algorithms for industrial Inspection. International Journal Pattern Recognition and Artificial Intelligence, 15(4), 675–690.CrossRefGoogle Scholar
  3. 3.
    Sumimoto, T., Maruyama, T., Azuma, Y., Goto, S., Mondou, M., Furukawa, N., & Okada, S. (2003). Development of image analysis for detection of defects of bga by using X-ray images. In: Instrumentation and Measurement Technology Conference 2003, Vail, CO, USA, 20–23 May 2003, (pp. 1131–1136).Google Scholar
  4. 4.
    Sa-nguannam, A., Srinonchat, J. (2008). Analysis ball grid array defects by using new image technique. ICSP 2008. In: Proceedings, Beijing, China, 26–29 Oct. 2008, (pp. 785–788).Google Scholar
  5. 5.
    Asha, V. (2012). Similarity measures for automatic defect detection on patterned textures. International Journal of Image Processing and Vision Sciences, 1, 18–24.Google Scholar
  6. 6.
    Wei, S. D., & Lai, S. H. (2008). Fast template matching based on normalized cross correlation with adaptive multilevel winner update. IEEE Transactions on Image Processing, 17(11), 2227–2235.CrossRefMathSciNetGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2014

Authors and Affiliations

  1. 1.Department of Electrical EngineeringKao Yuan UniversityKaohsiungTaiwan, Republic of China

Personalised recommendations