Nonlinear pattern recognition for the quality control of chips on circuit boards

Steeve Perreault; Henri H. Arsenault; Alain Bergeron

doi:10.1117/12.519638

Translator Disclaimer

30 September 2003 Nonlinear pattern recognition for the quality control of chips on circuit boards

Steeve Perreault, Henri H. Arsenault, Alain Bergeron

Author Affiliations +

Proceedings Volume 5227, Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies; (2003) https://doi.org/10.1117/12.519638
Event: 2003 Chapter books, 2003, Bellingham, WA, United States

Abstract

Quality control of integrated circuits using pattern recognition is usually carried out in a controlled environment. Colored pigments on the serial numbers of chips cause variations of intensity of the reflected light. So there is a need for methods to detect targets independently of the illumination. We apply a technique that yields correlation peaks that are invariant under a linear transformation of object intensity, for the detection of chips on integrated circuits. The method can identify the chip, detect if the chips are present or absent, if it is the wrong chip and if it is placed and oriented correctly.

Citation Download Citation

Steeve Perreault, Henri H. Arsenault, and Alain Bergeron "Nonlinear pattern recognition for the quality control of chips on circuit boards", Proc. SPIE 5227, Advanced Topics in Optoelectronics, Microelectronics, and Nanotechnologies, (30 September 2003); https://doi.org/10.1117/12.519638

ACCESS THE FULL ARTICLE