Share Email Print

Proceedings Paper

Robust template matching using run-length encoding
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

In this paper we propose a novel template matching algorithm for visual inspection of bare printed circuit board (PCB).1 In the conventional template matching for PCB inspection, the matching score and its relevant offsets are acquired by calculating the maximum value among the convolutions of template image and camera image. While the method is fast, the robustness and accuracy of matching are not guaranteed due to the gap between a design and an implementation resulting from defects and process variations. To resolve this problem, we suggest a new method which uses run-length encoding (RLE). For the template image to be matched, we accumulate data of foreground and background, and RLE data for each row and column in the template image. Using the data, we can find the x and y offsets which minimize the optimization function. The efficiency and robustness of the proposed algorithm are verified through a series of experiments. By comparing the proposed algorithm with the conventional approach, we could realize that the proposed algorithm is not only fast but also more robust and reliable in matching results.

Paper Details

Date Published: 22 September 2015
PDF: 9 pages
Proc. SPIE 9599, Applications of Digital Image Processing XXXVIII, 95992S (22 September 2015); doi: 10.1117/12.2188940
Show Author Affiliations
Hunsue Lee, Samsung Electro-Mechanics (Korea, Republic of)
Sungho Suh, Samsung Electro-Mechanics (Korea, Republic of)
Hansang Cho, Samsung Electro-Mechanics (Korea, Republic of)

Published in SPIE Proceedings Vol. 9599:
Applications of Digital Image Processing XXXVIII
Andrew G. Tescher, Editor(s)

© SPIE. Terms of Use
Back to Top