Invariant Target Detection in Images through the Normalized 2-D Correlation Technique

TL;DR

This paper demonstrates that the normalized 2-D correlation technique effectively detects targets in images despite variations in position and size, showing high accuracy and stability across different scenarios.

Contribution

It provides an analysis of the impact of translation and scaling on target detection, confirming the robustness of the normalized 2-D correlation method under these transformations.

Findings

High detection accuracy despite target variations

Strong correlation coefficients between original and extracted targets

Stable detection times across different target types

Abstract

The normalized 2-D correlation technique is a robust method for detecting targets in images due to its ability to remain invariant under rotation, translation, and scaling. This paper examines the impact of translation, and scaling on target identification in images. The results indicate a high level of accuracy in detecting targets, even when they are exhibit variations in location and size. The results indicate that the similarity between the image and the two used targets improves as the resize ratio increases. All statistical estimators demonstrate a strong similarity between the original and extracted targets. The elapsed time for all scenarios falls within the range (44.75-44.85), (37.48-37.73) seconds for bird and children targets respectively, and the correlation coefficient displays stable relationships with values that fall within the range of (0.90-0.98) and (0.87-0.93) for bird and children targets respectively.