Editing Template matching (section)

==Feature-based approach==
[[File:Artificial Neural Network.jpg|thumb|The hidden layer outputs a vector that holds classification information about the image and is used in the Template Matching algorithm as the features of the image]]
The feature-based approach to template matching relies on the extraction of [[Feature (computer vision)|image features]], such as shapes, textures, and colors, that match the target image or frame. This approach is usually achieved using [[Neural network|neural networks]] and [[Deep learning|deep-learning]] [[Statistical classification|classifiers]] such as VGG, [[AlexNet]], and [[Residual neural network|ResNet]].{{Citation needed|date=January 2023}}[[Convolutional neural network|Convolutional neural networks]] (CNNs), which many modern classifiers are based on, process an image by passing it through different hidden layers, producing a [[Vector space|vector]] at each layer with classification information about the image. These vectors are extracted from the network and used as the features of the image. [[Feature extraction]] using [[deep neural networks]], like CNNs, has proven extremely effective has become the standard in state-of-the-art template matching algorithms.<ref>{{cite arXiv|last1=Zhang|first1=Richard|last2=Isola|first2=Phillip|last3=Efros|first3=Alexei A.|last4=Shechtman|first4=Eli|last5=Wang|first5=Oliver|date=2018-01-11|title=The Unreasonable Effectiveness of Deep Features as a Perceptual Metric|eprint=1801.03924|class=cs.CV}}</ref>

This feature-based approach is often more robust than the template-based approach described below. As such, it has become the state-of-the-art method for template matching, as it can match templates with non-rigid and out-of-plane [[Rigid transformation|transformations]], as well as high background clutter and illumination changes.<ref>{{Cite arXiv|title=Template Matching with Deformable Diversity Similarity|last=Talmi, Mechrez, Zelnik-Manor|eprint = 1612.02190|class = cs.CV|year = 2016}}</ref><ref>Li, Yuhai, L. Jian, T. Jinwen, X. Honbo. “[https://www.spiedigitallibrary.org/conference-proceedings-of-spie/6043/60431P/A-fast-rotated-template-matching-based-on-point-feature/10.1117/12.654932.short A fast rotated template matching based on point feature].” Proceedings of the SPIE 6043 (2005): 453-459. MIPPR 2005: SAR and Multispectral Image Processing.</ref><ref>B. Sirmacek, C. Unsalan. “[https://www.iro.umontreal.ca/~mignotte/IFT6150/Articles/graphbuilding.pdf Urban Area and Building Detection Using SIFT Keypoints and Graph Theory]”, IEEE Transactions on Geoscience and Remote Sensing, Vol.47 (4), pp. 1156-1167, April 2009.</ref>