Template Matching Techniques in Computer Vision: Theory and Practice

By Roberto Brunelli. 2009

832 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning (2019, methodology): “Iyer et al. (2018) use template matching, a common computer vision technique (Brunelli, 2009), to detect (template) objects within an input image and measure salience through changes in Q-values for masked and unmasked objects.”
Vehicle detection in aerial imagery : A small target detection benchmark (2016, methodology): “For completeness, we have also implemented a template matching approach [80], as template matching was considered in the past as the standard approach for small target detection, and we tested a non window protocol based on the Hough forest [81].”
Wavelet analysis in neurodynamics (2012, methodology): “This approach is, in fact, a variant of the known template matching method [147] and thus can be applied to effectively extract sleep spindles, standardize the EEG structure, and create a reference base of EEG patterns.”
Feed-forward Hierarchical Model of the Ventral Visual Stream Applied to Functional Brain Image Classification (2012, unknown): “It is a technique which matches image regions to stored representative templates using a specific scoring function (Brunelli 2009).”
Saliency and Gist Features for Target Detection in Satellite Images (2011, background): “…as belonging to three broad categories: A ﬁrst, relatively straight-forward approach is to use a provided (or trained) target template or model (hence, the feature is the image itself), to match against targets in the image of interest, at different locations, orientation and scales [4]–[6].”
Transparency and Explanation in Deep Reinforcement Learning Neural Networks (2018, background): “It requires two components – source image and template image (Brunelli 2009).”
AdderNet: Do We Really Need Multiplications in Deep Learning? (2019, unknown): “(1) has a connection with template matching [3] in computer vision, which aims to ﬁnd the parts of an image that match the template.”
A Survey of Digital Map Processing Techniques (2014, background): “A detailed survey of various template matching algorithms and their applications can be found in Brunelli [2009]. In general, the main goal of these template matching algorithms is to find objects in the document of interest that are similar in shape and size to an object given as a template.”
Learning Shape Templates With Structured Implicit Functions (2019, methodology): “Template Fitting: The most related techniques to ours are methods that explicitly ﬁt templates to shapes [7].”
A Review of Automated Microinjection Systems for Single Cells in the Embryogenesis Stage (2016, background): “template matching techniques (see [92] for details): 1) minimization of the SSD [19], [93], 2) minimization of the sum of”