Fast Computation of Rotation-Invariant Image Features by an Approximate Radial Gradient Transform

被引：42

作者：

Takacs, Gabriel ^{[1
]}

Chandrasekhar, Vijay ^{[2
]}

Tsai, Sam S. ^{[2
]}

Chen, David ^{[2
]}

Grzeszczuk, Radek ^{[1
]}

Girod, Bernd ^{[2
]}

机构：

[1] Microsoft Corp, Sunnyvale, CA 94089 USA

[2] Stanford Univ, Stanford, CA 94305 USA

来源：

IEEE TRANSACTIONS ON IMAGE PROCESSING | 2013年 / 22卷 / 08期

基金：

美国国家科学基金会;

关键词：

Computer vision; signal processing; real-time systems; feature representation; invariants;

D O I：

10.1109/TIP.2012.2230011

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

We present the radial gradient transform (RGT) and a fast approximation, the approximate RGT (ARGT). We analyze the effects of the approximation on gradient quantization and histogramming. The ARGT is incorporated into the rotation-invariant fast feature (RIFF) algorithm. We demonstrate that, using the ARGT, RIFF extracts features 16x faster than SURF while achieving a similar performance for image matching and retrieval.

引用

页码：2970 / 2982

页数：13

共 50 条

[41] Rotation-Invariant Magnetic Features for Inertial Indoor-Localization
Klipp, Konstantin
Rose, Helge
Willaredt, Jonas
Sawade, Oliver
Radusch, Ilja
2018 NINTH INTERNATIONAL CONFERENCE ON INDOOR POSITIONING AND INDOOR NAVIGATION (IPIN 2018), 2018,
[42] Rotation-invariant features based on directional coding for texture classification
Ouslimani, Farida
Ouslimani, Achour
Ameur, Zohra
NEURAL COMPUTING & APPLICATIONS, 2019, 31 (10): : 6393 - 6400
[43] 2D rotation-invariant U transform and its application
Chen W.
Chen, Wei (wchen_jdsm@163.com), 1600, Science Press (42): : 1380 - 1388
[44] Generating rotation-invariant texture features by randomization of operator orientation
Pannekamp, J
Westkämper, E
PATTERN RECOGNITION, PROCEEDINGS, 2003, 2781 : 515 - 522
[45] A ROTATION-INVARIANT CONVOLUTIONAL NEURAL NETWORK FOR IMAGE ENHANCEMENT FORENSICS
Chen, Yifang
Lyu, Zixian
Kang, Xiangui
Wang, Z. Jane
2018 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP), 2018, : 2111 - 2115
[46] Texture image classification based on rotation-invariant U transforms
2016, Institute of Computing Technology (28):
[47] Position-invariant, rotation-invariant, and scale-invariant process for binary image recognition
Levkovitz, J
Oron, E
Tur, M
APPLIED OPTICS, 1997, 36 (14): : 3035 - 3042
[48] Rotation-Invariant Restricted Boltzmann Machine Using Shared Gradient Filters
Giuffrida, Mario Valerio
Tsaftaris, Sotirios A.
ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2016, PT II, 2016, 9887 : 480 - 488
[49] Fast Rotation-Invariant Template Matching with Candidate Reduction Using CUDA
Kim, Seung-ho
Song, Sang-hyeob
Kim, Jong-hak
Yuan, Zhongyun
Cho, Jun-dong
2015 IEEE INTERNATIONAL SYMPOSIUM ON CONSUMER ELECTRONICS (ISCE), 2015,
[50] Discrimination-sensitive rotation-invariant joint-transform correlator using gradient preprocessing and circular harmonic components
Pati, GS
Singh, K
OPTICAL ENGINEERING, 1998, 37 (01) : 43 - 48

← 1 2 3 4 5 →