ASIFT: An Algorithm for Fully Affine Invariant Comparison

By G. Yu, Jean-Michel Morel. Image Processing On Line, 2011

375 citations recorded by the source corpus.

If a physical object has a smooth or piecewise smooth boundary, its images obtained by cameras in varying positions undergo smooth apparent deformations. These deformations are locally well approximated by affine transforms of the image plane. In consequencethe solid object recognition problem has often been led back to the computation of affine invariant image local features. The similarity invariance (invariance to translation, rotation, and zoom) is dealt with rigorously by the SIFT method The method illustrated and demonstrated in this work, AffineSIFT (ASIFT), simulates a set of sample views of the initial images, obtainable by varying the two camera axis orientation parameters, namely the latitude and the longitude angles, which are not treated by the SIFT method. Then it applies the SIFT method itself to all images thus generated. Thus, ASIFT covers effectively all six parameters of the affine transform. Source Code The source code (ANSI C), its documentation, and the online demo are accessible at the IPOL web page of this article 1 .

Subfields: Aerospace Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/031c1e858a72b3faaa2d30de6755810f2ef17762

How researchers see this paper

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

In Aerospace Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Learning to Match Aerial Images with Deep Attentive Architectures (2016, methodology): “As this data is significantly easier, the baselines (notably A-SIFT) perform much better, but our method achieves the highest accuracy of 96%.”
Convolutional Neural Network Architecture for Geometric Matching (2017, methodology): “The proposed method is compared against state-of-the-art methods for this dataset, such as SIFT features (DoG+SIFT) [6], [18], SIFT features with affinecovariant detectors (DoG-affine+SIFT) [19] and ASIFT [57].”
D2-Net: A Trainable CNN for Joint Description and Detection of Local Features (2019, background): “Out of the 116 available sequences collected from various datasets [1, 5, 11, 23, 33, 63, 67], we selected 108.”
HPatches: A Benchmark and Evaluation of Handcrafted and Learned Local Descriptors (2017, background): “We have captured 51 sequences by a camera, 33 scenes are from [16], 12 scenes from [1], 5 scenes from [10], 4 scenes from [22], 2 scenes from [35] scene from [40].”
Optical flow modeling and computation: A survey (2015, background): “The similarity measures can be patch-based distances (see Section 3.1.2), or more complex and sparse feature descriptions often based on histogram of oriented gradients [20,71,169,282], or segment matching [258].”