short-paper

Kernel Local Descriptors with Implicit Rotation Matching

Authors:

Andrei Bursuc,

Giorgos Tolias,

Hervé JégouAuthors Info & Claims

ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

Pages 595 - 598

https://doi.org/10.1145/2671188.2749379

Published: 22 June 2015 Publication History

Get Access

Abstract

In this work we design a kernelized local feature descriptor and propose a matching scheme for aligning patches quickly and automatically. We analyze the SIFT descriptor from a kernel view and identify and reproduce some of its underlying benefits. We overcome the quantization artifacts of SIFT by encoding pixel attributes in a continous manner via explicit feature maps. Experiments performed on the patch dataset of Brown et al. [3] show the superiority of our descriptor over methods based on supervised learning.

References

[1]

R. Arandjelovic and A. Zisserman. Three things everyone should know to improve object retrieval. In CVPR, 2012.

Digital Library

Google Scholar

[2]

L. Bo, X. Ren, and D. Fox. Kernel descriptors for visual recognition. In NIPS, Dec. 2010.

Digital Library

Google Scholar

[3]

M. Brown, G. Hua, and S. Winder. Discriminative learning of local image descriptors. Trans. PAMI, 33(1):43--57, 2011.

Digital Library

Google Scholar

[4]

M. Calonder, V. Lepetit, C. Strecha, and P. Fua. Brief: Binary robust independent elementary features. In ECCV, Oct. 2010.

Digital Library

Google Scholar

[5]

L. Fei-Fei and P. Perona. A bayesian hierarchical model for learning natural scene categories. In CVPR, 2005.

Digital Library

Google Scholar

[6]

J. F. Henriques, J. Carreira, R. Caseiro, and J. Batista. Beyond hard negative mining: Efficient detector learning via block-circulant decomposition. In ICCV, 2013.

Digital Library

Google Scholar

[7]

D. Lowe. Distinctive image features from scale-invariant keypoints. IJCV, 60(2):91--110, Nov. 2004.

Digital Library

Google Scholar

[8]

T. Ojala, M. Pietikainen, and T. Maenpaa. Multiresolution gray-scale and rotation invariant texture classification with local binary patterns. Trans. PAMI, 24(7):971--987, 2002.

Digital Library

Google Scholar

[9]

A. Rahimi and B. Recht. Random features for large-scale kernel machines. In NIPS, 2007.

Digital Library

Google Scholar

[10]

K. Simonyan, A. Vedaldi, and A. Zisserman. Learning local feature descriptors using convex optimisation. Trans. PAMI, 2014.

Digital Library

Google Scholar

[11]

G. Tolias, T. Furon, and H. Jégou. Orientation covariant aggregation of local descriptors with embeddings. In ECCV, Sep. 2014.

Crossref

Google Scholar

[12]

A. Vedaldi and A. Zisserman. Efficient additive kernels via explicit feature maps. Trans. PAMI, 34(3):480--492, Mar. 2012.

Digital Library

Google Scholar

Cited By

View all

Nkrumah IMoshrefizadeh MTahri OBlasch EPalaniappan KAliAkbarpour H(2024)EC-WAMI: Event Camera-Based Pose Optimization in Remote Sensing and Wide-Area Motion ImagerySensors10.3390/s2423749324:23(7493)Online publication date: 24-Nov-2024
https://doi.org/10.3390/s24237493
Yang HHu ASi WCui TMiao J(2024)PMMWPoint: Weakly Supervised Dense Keypoint Detection and Description for Passive Millimeter-Wave Image MatchingIEEE Transactions on Instrumentation and Measurement10.1109/TIM.2023.334379073(1-16)Online publication date: 2024
https://doi.org/10.1109/TIM.2023.3343790
Fu YZhang PTang FWu Y(2023)Covariant Peak Constraint for Accurate Keypoint Detection and Keypoint-Specific Descriptor LearningIEEE Transactions on Multimedia10.1109/TMM.2023.333321126(5383-5397)Online publication date: 15-Nov-2023
https://dl.acm.org/doi/10.1109/TMM.2023.3333211
Show More Cited By

Index Terms

Kernel Local Descriptors with Implicit Rotation Matching
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision representations
        Image representations

Recommendations

Feature based local binary pattern for rotation invariant texture classification

The paper presents a novel texture descriptor based on Local Binary Pattern.We address the problems of rotation invariance and illumination invariance.The proposed texture descriptor FbLBP is low-dimension.The results of FbLBP are compared with the ...
Continuous rotation invariant features for gradient-based texture classification

Four highly discriminative and continuous rotation invariant methods are proposed.We use the Hessian matrix and Gaussian derivative filters.Verified on the CUReT, KTH-TIPS, KTH-TIPS2-a, UIUC and Brodatz texture datasets. Extracting rotation invariant ...
Extended local binary patterns for texture classification

This paper presents a novel approach for texture classification, generalizing the well-known local binary pattern (LBP) approach. In the proposed approach, two different and complementary types of features (pixel intensities and differences) are ...

Comments

Information & Contributors

Information

Published In

ICMR '15: Proceedings of the 5th ACM on International Conference on Multimedia Retrieval

June 2015

700 pages

ISBN:9781450332743

DOI:10.1145/2671188

General Chairs:
Alex Hauptmann
Carnegie Mellon University, USA
,
Chong-Wah Ngo
City University of Hong Kong, China
,
Xiangyang Xue
Fudan University, China
,
Program Chairs:
Yu-Gang Jiang
Fudan University, China
,
Cees Snoek
University of Amsterdam and Qualcomm Research Netherlands
,
Nuno Vasconcelos
University of California, San Diego, USA

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 22 June 2015

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Short-paper

Funding Sources

Conference

ICMR '15

Sponsor:

SIGMM

ICMR '15: International Conference on Multimedia Retrieval

June 23 - 26, 2015

Shanghai, China

Acceptance Rates

ICMR '15 Paper Acceptance Rate 48 of 127 submissions, 38%;

Overall Acceptance Rate 254 of 830 submissions, 31%

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

21
Total Citations
View Citations
114
Total Downloads

Downloads (Last 12 months)3
Downloads (Last 6 weeks)1

Reflects downloads up to 13 Jan 2025

Other Metrics

View Author Metrics

Citations

Cited By

View all

Nkrumah IMoshrefizadeh MTahri OBlasch EPalaniappan KAliAkbarpour H(2024)EC-WAMI: Event Camera-Based Pose Optimization in Remote Sensing and Wide-Area Motion ImagerySensors10.3390/s2423749324:23(7493)Online publication date: 24-Nov-2024
https://doi.org/10.3390/s24237493
Yang HHu ASi WCui TMiao J(2024)PMMWPoint: Weakly Supervised Dense Keypoint Detection and Description for Passive Millimeter-Wave Image MatchingIEEE Transactions on Instrumentation and Measurement10.1109/TIM.2023.334379073(1-16)Online publication date: 2024
https://doi.org/10.1109/TIM.2023.3343790
Fu YZhang PTang FWu Y(2023)Covariant Peak Constraint for Accurate Keypoint Detection and Keypoint-Specific Descriptor LearningIEEE Transactions on Multimedia10.1109/TMM.2023.333321126(5383-5397)Online publication date: 15-Nov-2023
https://dl.acm.org/doi/10.1109/TMM.2023.3333211
Nouduri KJames JFraser JAliAkbarpour HPalaniappan K(2022)A comparison of features Synthetic WAMI and GES of the same location2022 IEEE Applied Imagery Pattern Recognition Workshop (AIPR)10.1109/AIPR57179.2022.10092236(1-8)Online publication date: 11-Oct-2022
https://doi.org/10.1109/AIPR57179.2022.10092236
Gao KAliakbarpour HFraser JNouduri KBunyak FMassaro RSeetharaman GPalaniappan K(2021)Local Feature Performance Evaluation for Structure-From-Motion and Multi-View Stereo Using Simulated City-Scale Aerial ImageryIEEE Sensors Journal10.1109/JSEN.2020.304281021:10(11615-11627)Online publication date: 15-May-2021
https://doi.org/10.1109/JSEN.2020.3042810
Masone CCaputo B(2021)A Survey on Deep Visual Place RecognitionIEEE Access10.1109/ACCESS.2021.30549379(19516-19547)Online publication date: 2021
https://doi.org/10.1109/ACCESS.2021.3054937
Zhang LRupnik EPierrot-Deseilligny M(2021)Feature matching for multi-epoch historical aerial imagesISPRS Journal of Photogrammetry and Remote Sensing10.1016/j.isprsjprs.2021.10.008182(176-189)Online publication date: Dec-2021
https://doi.org/10.1016/j.isprsjprs.2021.10.008
Wang SGuo XTie YQi LGuan L(2020)Deep Local Feature Descriptor Learning With Dual Hard Batch ConstructionIEEE Transactions on Image Processing10.1109/TIP.2020.302942429(9572-9583)Online publication date: 2020
https://doi.org/10.1109/TIP.2020.3029424
Liu XZheng YKilleen BIshii MHager GTaylor RUnberath M(2020)Extremely Dense Point Correspondences Using a Learned Feature Descriptor2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)10.1109/CVPR42600.2020.00490(4846-4855)Online publication date: Jun-2020
https://doi.org/10.1109/CVPR42600.2020.00490
Bellavia FColombo C(2020)RootsGLOH2IET Computer Vision10.1049/iet-cvi.2019.071614:4(138-143)Online publication date: 15-Apr-2020
https://dl.acm.org/doi/10.1049/iet-cvi.2019.0716
Show More Cited By

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Cited By

Index Terms

Recommendations

Feature based local binary pattern for rotation invariant texture classification

Continuous rotation invariant features for gradient-based texture classification

Extended local binary patterns for texture classification