Fast-Match: Fast Affine Template Matching

Korman, Simon; Reichman, Daniël; Tsur, Gilad; Avidan, Shai

doi:10.1007/s11263-016-0926-1

Cited by 89 publications

(132 citation statements)

References 23 publications

Supporting

Mentioning

132

Contrasting

Order By: Relevance

“…In order to handle general transformations, in [14] a grayscale template matching algorithm that considered variations of scale and rotation was presented. More recently FAst-Match [15] was proposed as an efficient way to handle general affine transformations; although it was not the first successful approach to try so [9], FAstMatch remains to this day the approach that shows best results in literature. FAst-Match [15] lies between discrete template matching and full search approaches.…”

Section: Related Workmentioning

confidence: 99%

“…More recently FAst-Match [15] was proposed as an efficient way to handle general affine transformations; although it was not the first successful approach to try so [9], FAstMatch remains to this day the approach that shows best results in literature. FAst-Match [15] lies between discrete template matching and full search approaches. In particular it considers all the affine transformation space but, using a tree search approach, avoids searching high error subspaces.…”

Section: Related Workmentioning

confidence: 99%

“…Yet, most of these improvements have been designed for the algorithms that do not perform a full search. In this work we will bring these improvements to algorithms that perform full search, and in particular we will consider FAst-Match [15], a recent method that performs near full search at reasonable speed.…”

Section: Introductionmentioning

confidence: 99%

“…Furthermore, they are only able to estimate affine transformations: this is enough to approximate small projective deformations, but produces bigger errors in the general case (as seen on the third experiment of [15]). We aim to provide a template selection approach to partially overcome these problems.…”

Section: Introductionmentioning

confidence: 99%

“…We use the overlap error as it seems the community agrees on it [15,19,20]; this is discussed extensively in [19,20].…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Matchability Prediction for Full-Search Template Matching Algorithms

Peñate-Sánchez

Porzi

Moreno-Noguer

2015

2015 International Conference on 3D Vision

View full text Add to dashboard Cite

While recent approaches have shown that it is possible to do template matching by exhaustively scanning the parameter space, the resulting algorithms are still quite demanding. In this paper we alleviate the computational load of these algorithms by proposing an efficient approach for predicting the matchability of a template, before it is actually performed. This avoids large amounts of unnecessary computations. We learn the matchability of templates by using dense convolutional neural network descriptors that do not require ad-hoc criteria to characterize a template. By using deep learning descriptions of patches we are able to predict matchability over the whole image quite reliably. We will also show how no specific training data is required to solve problems like panorama stitching in which you usually require data from the scene in question. Due to the highly parallelizable nature of this tasks we offer an efficient technique with a negligible computational cost at test time.

show abstract

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…We use the overlap error as it seems the community agrees on it [15,19,20]; this is discussed extensively in [19,20].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Matchability Prediction for Full-Search Template Matching Algorithms

Peñate-Sánchez

Porzi

Moreno-Noguer

2015

2015 International Conference on 3D Vision

View full text Add to dashboard Cite

show abstract

A Projectivity Diagnosis of Local Feature Using Template Matching

Ohki

Taniguchi

Inoue³

et al. 2017

Elect Comm in Japan

View full text Add to dashboard Cite

SUMMARY It is well known that points on a plane in 3D world are related to corresponding image points in a view of a moving camera by projective translation. Good image features have robust projectivity under any camera movements. In the standard performance evaluation of image processing, real captured images of a scene are used ordinarily. However, it is not enough to evaluate in detail because the variation of camera angle and distance to target objects are limited and the capturing cost is expensive. During the early stage of the image processing development, the basic performance measurement should be the most important in an easy way. We propose a projectivity diagnosis method to measure the performance of local descriptor base template matching between a template image and reference images which are created by deforming the template image. This template matching consists of a feature image point extraction and a local descriptor matching. The proposed method evaluates the positional accuracy of the extracted feature points and the matching with local descriptor. Four metrics are introduced to evaluate the projectivity of template matching. In the experiment, our proposed diagnosis method expose the projectivity of SIFT, SURF, and ORB. SIFT showed the better robustness than the others.

show abstract

Testing convexity of figures under the uniform distribution

Berman

Murzabulatov

Raskhodnikova

2018

Random Struct Algorithms

View full text Add to dashboard Cite

We consider the following basic geometric problem: Given ϵ∈(0,1/2), a 2‐dimensional black‐and‐white figure is ∊‐ far from convex if it differs in at least an ∊ fraction of the area from every figure where the black object is convex. How many uniform and independent samples from a figure that is ∊‐ far from convex are needed to detect a violation of convexity with constant probability? This question arises in the context of designing property testers for convexity. We show that Θ(ϵ−4/3) uniform samples (and the same running time) are necessary and sufficient for detecting a violation of convexity in an ∊‐far figure and, equivalently, for testing convexity of figures with 1‐sided error. Our algorithm beats the Ω(ϵ−3/2) lower bound by Schmeltz [32] on the number of samples required for learning convex figures under the uniform distribution. It demonstrates that, with uniform samples, we can check if a set is approximately convex much faster than we can find an approximate representation of a convex set.

show abstract

Fast-Match: Fast Affine Template Matching

Cited by 89 publications

References 23 publications

Matchability Prediction for Full-Search Template Matching Algorithms

Matchability Prediction for Full-Search Template Matching Algorithms

A Projectivity Diagnosis of Local Feature Using Template Matching

Testing convexity of figures under the uniform distribution

Contact Info

Product

Resources

About