Template Matching in Images using Segmented Normalized Cross-Correlation

TL;DR

This paper introduces a novel segmented approximation method for normalized cross-correlation in image template matching, significantly improving computational efficiency with minimal accuracy loss, especially for simpler or smaller templates.

Contribution

It proposes a split-and-merge segmentation approach for template approximation that enhances NCC computation speed while maintaining accuracy comparable to FFT-based methods.

Findings

Achieves faster NCC computation for simple or small templates.

Maintains comparable accuracy to FFT-based NCC in many cases.

Offers a trade-off between speed and accuracy depending on template complexity.

Abstract

In this paper, a new variant of an algorithm for normalized cross-correlation (NCC) is proposed in the context of template matching in images. The proposed algorithm is based on the precomputation of a template image approximation, enabling more efficient calculation of approximate NCC with the source image than using the original template for exact NCC calculation. The approximate template is precomputed from the template image by a split-and-merge approach, resulting in a decomposition to axis-aligned rectangular segments, whose sizes depend on per-segment pixel intensity variance. In the approximate template, each segment is assigned the mean grayscale value of the corresponding pixels from the original template. The proposed algorithm achieves superior computational performance with negligible NCC approximation errors compared to the well-known Fast Fourier Transform (FFT)-based NCC algorithm, when applied on less visually complex and/or smaller template images. In other cases, the proposed algorithm can maintain either computational performance or NCC approximation error within the range of the FFT-based algorithm, but not both.