Improved Global Context Descriptor for Describing Interest Regions

doi:10.1007/s12204-012-1244-6

上海交通大学学报（英文版） ›› 2012, Vol. 17 ›› Issue (2): 147-152.doi: 10.1007/s12204-012-1244-6

Improved Global Context Descriptor for Describing Interest Regions

LIU Jing-neng ^∗(刘景能), ZENG Gui-hua (曾贵华)

(State Key Laboratory of Advanced Optical Communication Systems and Networks, Key Laborotory on Navigation and Location-Based Service, Department of Electronic Engineering, Shanghai Jiaotong University, Shanghai 200240, China)

出版日期:2012-04-28 发布日期:2012-05-31
通讯作者: LIU Jing-neng (刘景能), E-mail: bzljn@163.com

Improved Global Context Descriptor for Describing Interest Regions

LIU Jing-neng ^∗(刘景能), ZENG Gui-hua (曾贵华)

(State Key Laboratory of Advanced Optical Communication Systems and Networks, Key Laborotory on Navigation and Location-Based Service, Department of Electronic Engineering, Shanghai Jiaotong University, Shanghai 200240, China)

Online:2012-04-28 Published:2012-05-31
Contact: LIU Jing-neng (刘景能), E-mail: bzljn@163.com

摘要/Abstract

摘要： The global context (GC) descriptor is improved for describing interest regions, uses gradient orientation for binning, and thus provides more robust invariance for geometric and photometric transformations. The performance of the improved GC (IGC) to image matching is studied through extensive experiments on the Oxford Affine dataset. Empirical results indicate that the proposed IGC yields quite stable and robust results, significantly outperforms the original GC, and also can outperform the classical scale-invariant feature transform (SIFT) in most of the test cases. By integrating the IGC to the SIFT, the resulting of hybrid SIFT+IGC performs best over all other single descriptors in these experimental evaluations with various geometric transformations.

关键词: global context (GC), scale-invariant feature transform (SIFT), region description, image matching

Abstract: The global context (GC) descriptor is improved for describing interest regions, uses gradient orientation for binning, and thus provides more robust invariance for geometric and photometric transformations. The performance of the improved GC (IGC) to image matching is studied through extensive experiments on the Oxford Affine dataset. Empirical results indicate that the proposed IGC yields quite stable and robust results, significantly outperforms the original GC, and also can outperform the classical scale-invariant feature transform (SIFT) in most of the test cases. By integrating the IGC to the SIFT, the resulting of hybrid SIFT+IGC performs best over all other single descriptors in these experimental evaluations with various geometric transformations.

Key words: global context (GC), scale-invariant feature transform (SIFT), region description, image matching

中图分类号:

TP 311

LIU Jing-neng (刘景能), ZENG Gui-hua (曾贵华). Improved Global Context Descriptor for Describing Interest Regions[J]. 上海交通大学学报（英文版）, 2012, 17(2): 147-152.

LIU Jing-neng (刘景能), ZENG Gui-hua (曾贵华). Improved Global Context Descriptor for Describing Interest Regions[J]. Journal of shanghai Jiaotong University (Science), 2012, 17(2): 147-152.

参考文献

[1] Li J, Allinson N M. A comprehensive review of current local features for computer vision [J]. Neurocomputing,2008, 71(10-12): 1771-1787.

[2] Sivic J, Zisserman A. Video google: A text retrieval approach to object matching in videos [C]//Proceedings of 9th International Conference on

Computer Vision. Piscataway, NJ: IEEE, 2003: 1470-1478.

[3] Mikolajczyk K, Schmid C. Indexing based on scale invariant interest points [C]//Proceedings of 8th IEEE International Conference on Computer Vision. Piscataway,

NJ: IEEE, 2001: 525-531.

[4] Tuytelaars T, Van Gool L. Matching widely separated views based on affine invariant regions [J]. International Journal of Computer Vision, 2004, 59(1):

61-85.

[5] Lowe D. Distinctive image features from scaleinvariant keypoints [J]. International Journal of Computer Vision, 2004, 2(60): 91-110.

[6] Lazebnik S, Schmid C, Ponce J. A sparse texture representation using local affine regions [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,

2005, 27(8): 1265-1278.

[7] H¨orster E, Greif T, Lienhart R, et al. Comparing local feature descriptors in pLSA-based image models [C]// Proceedings of 30th Annual Symposium of the

German Association for Pattern Recognition (DAGM) 2008. Berlin: Springer-Verlag, 2008: 446-455.

[8] Se S, Lowe D, Little J. Global localization using distinctive visual features [C]// Proceedings of 2002 IEEE/RSJ International Conference on Intelligent

Robots and System. Piscataway, NJ: IEEE, 2002:226-231.

[9] Mortensen E, Deng H, Shapiro L. A SIFT descriptor with global context [C]//Proceedings of 2005 IEEE Conferrence on Computer Vision and Pattern Recognition

(CVPR). Piscataway, NJ: IEEE, 2005: 184-190.

[10] Li C L, Ma L Z. A new framework for feature descriptor based on SIFT [J]. Pattern Recognition Letters, 2009, 30(5): 544-557.

[11] Carmichael G, Lagani`ere R, Bose P. Global context descriptors for SURF and MSER feature descriptors [C]//Proceedings of Canadian Conference on

Computer and Robot Vision (CRV). Piscataway, NJ:IEEE, 2010: 309-316.

[12] Bay H, Tuytelaars T, van Gool L. SURF:Speeded up robust features [C]// Proceedings of European Conference on Computer Vision. Berlin:

Springer-Verlag, 2006: 404-417.

[13] Matas J, Chum O, Urba M, et al. Robust wide baseline stereo from maximally stable extremal regions [C]//Proceedings of British Machine Vision Conference.

Cardiff, UK: British Machine Vision Association, 2002: 384-396.

[14] Cao B, Ma C W, Liu Z T. Affine-invariant SIFT descriptor with global context [C]// Proceedings of 3rd International Congress on Image and Signal Processing

(CISP’10). Piscataway, NJ: IEEE, 2010: 68-71.

[15] Yu G, Morel J M. A fully affine invariant image comparison method [C]// Proceedings of IEEE International Conference on Acoustics, Speech, and Signal

Processing (ICASSP). Piscataway, NJ: IEEE, 2009:1597-1600.

[16] Heikkil¨a M, Pietik¨ainen M, Schmid C. Description of interest regions with local binary patterns [J].Pattern Recognition, 2009, 42(3):425-436.

[17] Tuytelaars T, Mikolajczyk K. Local invariant feature detectors: A survey [J]. Foundations and Trends in Computer Graphics and Vision, 2008, 3(3): 177-

280.

[18] Mikolajczyk K, Tuytelaars T, Schmid C, et al. A comparison of affine region detectors [J]. International Journal of Computer Vision, 2005, 65(1-2): 43-72.

[19] Mikolajczyk K, Schmid C. A performance evaluation of local descriptors [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2005, 27(10):

1615-1630.

[20] Ke Y, Sukthankar R. PCA-SIFT: A more distinctive representation for local image descriptors [C]//Proceedings of IEEE Conference on Computer

Vision and Pattern Recognition. Piscataway, NJ:IEEE, 2004: 506-513.

[21] Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence,

2002, 24 (4): 509-522.

[22] Ling H, Jacobs D W. Deformation invariant image matching [C]// Proceedings of 10th IEEE International Conference on Computer Vision. Piscataway,

NJ: IEEE, 2005: 1466-1473.

[23] Moreels P, Perona P. Evaluation of features detectors and descriptors based on 3D objects [C]// Proceedings of 10th IEEE International Conference on Computer

Vision. Piscataway, NJ: IEEE, 2005: 800-807.

[24] Steger C. An unbiased detector of curvilinear structures [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1998, 20(3): 113-125.

[25] Mikolajczyk K. Affine covariant features [EB/OL]. [2004-01-01]. http://www.robots.ox.ac.uk/∼vgg/research/affine/.

[26] Mikolajczyk K, Schmid C. Scale & affine invariant interest point detectors [J]. International Journal of Computer Vision, 2004, 60(1): 63-86.

[27] Mikolajczyk K, Schmid C. An affine invariant interest point detector [C]// Proceedings of European Conference on Computer Vision. Berlin: Springer-Verlag,

2002: 128-142.

Improved Global Context Descriptor for Describing Interest Regions

Improved Global Context Descriptor for Describing Interest Regions

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 1

编辑推荐

Metrics

本文评价