Article,

Fast normalized cross correlation for defect detection

, and .
Pattern Recogn. Lett., 24 (15): 2625--2631 (November 2003)
DOI: 10.1016/S0167-8655(03)00106-5

Abstract

Normalized cross correlation (NCC) has been used extensively for many machine vision applications, but the traditional normalized correlation operation does not meet speed requirements for time-critical applications. In this paper, we propose a fast NCC computation for defect detection. A sum-table scheme is utilized, which allows the calculations of image mean, image variance and cross-correlation between images to be invariant to the size of template window. For an image of size <i>M &#215; N</i> and a template window of size <i>m &#215; n</i>, the computational complexity of the traditional NCC involves 3 &#267; <i>m &#267; n &#267; M &#267; N</i> additions/subtractions and 2 &#267; <i>m &#267; n &#267; M &#267; N</i> multiplications. The required numbers of computations of the proposed sum-table scheme can be significantly reduced to only 18 &#267; <i>M &#267; N</i> additions/subtractions and 2 &#267; <i>M &#267; N</i> multiplications.

Tags

Users

  • @daill

Comments and Reviews