KAZE Features

1,316 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.

Key.Net: Keypoint Detection by Handcrafted and Learned CNN Filters (2019, methodology): “Multi-scale improvements were proposed in KAZE [21] and its extension, A-KAZE [22], where Hessian detector was applied to a non-linear diffusion scale space in contrast to widely used Gaussian pyramid.”
A comparative analysis of SIFT, SURF, KAZE, AKAZE, ORB, and BRISK (2018, methodology): “put forward KAZE features in 2012 that exploit non-linear scale space through non-linear diffusion filtering [15].”
Pose Estimation for Augmented Reality: A Hands-On Survey (2016, neutral): “Recently, KAZE [2] employs a non-liner diffusion ﬁl-tering as a non-linear scale space so that object boundaries can be retained and keypoints extraction be more robust, and accelerated for real-time detection [3].”
Street-view change detection with deconvolutional networks (2016, methodology): “QUERY IMAGE D - SIFT [23] CNN [32] DEPTH CDNET ( OURS ) reconstruction for image alignment in our approach.”
Automatic Classification of Defective Photovoltaic Module Cells in Electroluminescence Images (2018, neutral): “KAZE [23] 3 3”
Universal Correspondence Network (2016, methodology): “The accuracy of our features outperforms all traditional features including SIFT [22], DAISY [29] and KAZE [2].”
LF-Net: Learning Local Features from Images (2018, methodology): “In [1, 4], the comparison metric is learned by training Siamese networks.”