How to make local image features more efficient and distinctive
How to make local image features more efficient and distinctive
- Author(s): C. Duan ; X. Meng ; C. Tu ; C. Yang
- DOI: 10.1049/iet-cvi:20070049
For access to this article, please select a purchase option:
Buy article PDF
Buy Knowledge Pack
IET members benefit from discounts to all IET publications and free access to E&T Magazine. If you are an IET member, log in to your account and the discounts will automatically be applied.
Thank you
Your recommendation has been sent to your librarian.
- Author(s): C. Duan 1 ; X. Meng 1 ; C. Tu 1 ; C. Yang 1
-
-
View affiliations
-
Affiliations:
1: School of Computer Science and Technology, Shandong University (Software-park Campus), Jinan, People's Republic of China
-
Affiliations:
1: School of Computer Science and Technology, Shandong University (Software-park Campus), Jinan, People's Republic of China
- Source:
Volume 2, Issue 3,
September 2008,
p.
178 – 189
DOI: 10.1049/iet-cvi:20070049 , Print ISSN 1751-9632, Online ISSN 1751-9640
- « Previous Article
- Table of contents
- Next Article »
A technique to construct efficient and distinctive descriptors for local image features is presented. The authors start with the scale invariant features detected and the gradient data of their neighbourhood patches in suitable size normalised and then apply independent component analysis (ICA) to obtain the independent components of the feature patches. The authors show how the ICA technique could be used to encode the salient aspects of the feature vectors because of the high-order statistical characteristics of both natural images and ICA. Comparisons are made between our descriptors and some state-of-the-art methods (e.g. scale invariant feature transform). Experimental results demonstrate that the proposed local feature descriptor is distinctive and with high matching speed.
Inspec keywords: independent component analysis; feature extraction; image matching
Other keywords:
Subjects: Other topics in statistics; Optical, image and video signal processing; Computer vision and image processing techniques; Other topics in statistics
References
-
-
1)
- A. Baumberg . (2000) Reliable feature matching across widely separated views.
-
2)
- Fergus, R., Perona, P., Zisserman, A.: `Object class recognition by unsupervised scale-invariant learning', Proc. Computer Vision and Pattern Recognition, June 2003.
-
3)
- W.T. Freeman , E.H. Adelson . The design and use of steerable filters. IEEE Trans. Pattern Anal. Mach. Intell. , 891 - 906
-
4)
- Matas, J., Chum, O., Urban, M., Pajdla, T.: `Robust wide baseline stereo from maximally stable external regions', Proc. 13th Conf. British Machine Vision, 2002, Cardiff, England, p. 384–393.
-
5)
- D.D. Lee , H.S. Seung . Learning the parts of objects by non-negative matrix factorization. Nature , 788 - 791
-
6)
- T. Tuytelaars , L. Van Gool . Matching widely separated views based on affine invariant regions. Int. J. Comput. Vis. , 59 , 61 - 85
-
7)
- Karhunen, J.: `Neural approaches to independent component analysis and source separation', Proc. 4th European Symp. Artificial Neural Networks (ESANN'96), April 1996, Bruges, Belgium, p. 249–266.
-
8)
- H.B. Barlow , C. Koch , J.L. Davis . (1994) What is the computational goal of the neocortex?, Large-scale neuronal theories of the brain.
-
9)
- J. Wang , G. Wiederhold . SIMPLIcity: semantics-sensitive integrated matching for picture libraries. IEEE Trans. Pattern Anal. Mach. Intell. , 8 , 1 - 17
-
10)
- J. Yao , W.K. Cham . 3D modeling and rendering from multiple wide-baseline images by match propagation. Signal Process. Image Commun. , 506 - 518
-
11)
- F. Jurie , C. Schmid . (2004) Scale-invariant shape features for recognition of object categories.
-
12)
- G. Carneiro , A. Jepson . (2003) Multi-scale phase-based local features.
-
13)
- W.E. Vinje , J.L. Gallant . Sparse coding and decorrelation in primary visual cortex during natural vision. Science , 1273 - 1276
-
14)
- A. Hyvarinen , E. Oja . Independent component analysis: algorithms and applications. Neural Netw. , 411 - 430
-
15)
- Lazebnik, S., Schmid, C., Ponce, J.: `Sparse texture representation using affine-invariant neighborhoods', Proc. Int. Conf. Computer Vision and Pattern Recognition, 2003, Madison, Wisconsin, USA.
-
16)
- Ke, Y., Sukthankar, R.: `PCA-SIFT: a more distinctive representation for local image descriptors', Proc. Conf. Computer Vision and Pattern Recognition, 2004, Washington, USA, p. 511–517.
-
17)
- B. Olshausen , D. Field . Emergence of simple-cell receptive field properties by learning a sparsecode fornatural images. Nature , 607 - 609
-
18)
- J. Karhunen , J. Joutsensalo . Generalization of principal component analysis, optimization problems and neural networks. Neural Netw. , 4 , 549 - 562
-
19)
- http://www.robots.ox.ac.uk/~vgg/research/affine, accessed February 2007.
-
20)
- K. Mikolajczyk , J. Matas . (2007) Improving descriptors for fast tree matching by optimal liner projection.
-
21)
- Mikolajczyk, K., Schmid, C.: `A performance evaluation of local descriptors', Proc. Computer Vision and Pattern Recognition, June 2003.
-
22)
- J.F. Cardoso , A. Souloumiac . Blind beamforming for non-Gaussian signals. IEE Proc. F , 6 , 771 - 774
-
23)
- L.M.J. Florack , B.M.T. Haar Romeny , J.J. Koenderink , M.A. Viergever . General intensity transformations and differential invariants. J. Math. Imaging Vis. , 171 - 187
-
24)
- MPEG-7 Visual Experimentation Model (XM), Version 12.0, ISO/IEC/JTC1/SC29/WG11, Doc. N4548, December 2001.
-
25)
- F. Mindru , T. Tuytelaars , L. Van Gool , T. Moons . Moment invariants for recognition under changing viewpoint and illumination. Comput. Vis. Image Underst. , 3 - 27
-
26)
- Mikolajczyk, K., Schmid, C.: `Indexing based on scale invariant interest points', Proc. Int. Conf. Computer Vision, July 2001, p. 525–531.
-
27)
- J. Cardoso . High-order contrasts for independent component analysis. Neural Comput. , 1 , 157 - 192
-
28)
- F. Rothganger , S. Lazebnik , C. Schmid , J. Ponce . 3D object modeling and recognition using local affine-invariant image descriptors and multi-view spatial constraints. Int. J. Comp. Vis. , 3 , 231 - 259
-
29)
- G. Hua , M. Brown , S. Winder . (2007) Discriminant embedding for local image descriptors.
-
30)
- Chen, H.T., Chang, H.W., Liu, T.L.: `Local discriminant embedding and its variants', Proc. IEEE Conf. Computer Vision and Pattern Recognition, June 2005, San Diego, CA, 2, p. 846–853.
-
31)
- E. Oja , J. Karhunen , M. Palaniswami . (1995) Signal separation by nonlinear Hebbian learning, Computational intelligence – a dynamic system perspective.
-
32)
- D. Lowe . Distinctive image features from scale-invariant keypoints, cascade filtering approach. Int. J. Comput. Vis. , 91 - 110
-
33)
- P. Comon . Independent component analysis – a new concept?. Signal Process. , 287 - 314
-
34)
- Schaffalitzky, F., Zisserman, A.: `Multi-view matching for unordered image sets', Proc. 7th European Conf. Computer Vision, 2002, Copenhagen, Denmark, p. 414–431.
-
35)
- K. Mikolajczyk , C. Schmid . Scale and affine invariant interest point detectors. Int. J. Comput. Vis. , 63 - 86
-
36)
- K. Mikolajczyk , T. Tuytelaars , C. Schmid . A comparison of affine region detectors. Int. J. Comput. Vis. , 43 - 72
-
37)
- Lowe, D.G.: `Object recognition from local scale-invariant features', Proc. Int. Conf. Computer Vision, 1999, p. 1150–1157.
-
38)
- A. Bell , T. Sejnowski . An information-maximization approach to blind separation and blind deconvolution. Neural Comput. , 1129 - 1159
-
1)