Robust template matching using run-length encoding

Hunsue Lee; Sungho Suh; Hansang Cho

doi:10.1117/12.2188940

22 September 2015 Robust template matching using run-length encoding

Hunsue Lee, Sungho Suh, Hansang Cho

Proceedings Volume 9599, Applications of Digital Image Processing XXXVIII; 95992S (2015) https://doi.org/10.1117/12.2188940
Event: SPIE Optical Engineering + Applications, 2015, San Diego, California, United States

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.

Citation Download Citation

Hunsue Lee, Sungho Suh, and Hansang Cho "Robust template matching using run-length encoding", Proc. SPIE 9599, Applications of Digital Image Processing XXXVIII, 95992S (22 September 2015); https://doi.org/10.1117/12.2188940

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available