A modified Normalized Cross-Correlation algorithm for Embedded Systems

Abstract

Problems related to image matching, such as processing time, performance, and changes in rotation and scale are widely studied. However, creating simple solutions for image matching that can be implemented in an embedded system has been overlooked. Therefore, this paper proposes a modified Normalized Cross-Correlation algorithm for embedded systems aimed at creating a low-cost solution for a cement tile application. The algorithm relies on the concept of template matching and it makes use of cross-correlation, zero-mean normalization, and thresholding for its implementation. Experimental results show that the algorithm is suitable for a cement tile application and appropriate to detect defective cement tiles during an on-site installation or manufacturing process. Finally, it is shown that the algorithm can act as a discriminator to identify quality non-conformance issues.