# Template Matching in Images using Segmented Normalized Cross-Correlation

arXiv: https://arxiv.org/abs/2502.01286 · HTML: https://mlsanity.com/paper/2502.01286/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 18 references that are in the map.
- First posted on arXiv 3 Feb 2025.

## Builds on (most cited first, 4 of 4)

- [Learning Accurate Template Matching with Differentiable Coarse-to-Fine Correspondence Refinement](https://mlsanity.com/paper/2303.08438/) (2023)
- [Template Matching Advances and Applications in Image Analysis](https://mlsanity.com/paper/1610.07231/) (2016)
- [Fast Normalized Cross-Correlation for Template Matching with Rotations](https://mlsanity.com/paper/2311.07561/) (2023)
- [Deep Learning Improves Template Matching by Normalized Cross Correlation](https://mlsanity.com/paper/1705.08593/) (2017)

## Built on by (most cited first, 1 of 1)

- [An Efficient Deep Template Matching and In-Plane Pose Estimation Method via Template-Aware Dynamic Convolution](https://mlsanity.com/paper/2510.01678/) (2025)

## Abstract (arXiv)

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.