Browse > Article
http://dx.doi.org/10.4218/etrij.12.0111.0538

Enhanced SIFT Descriptor Based on Modified Discrete Gaussian-Hermite Moment  

Kang, Tae-Koo (Department of Electrical Engineering, Korea University)
Zhang, Huazhen (Department of Electrical Engineering, Korea University)
Kim, Dong W. (Department of Digital Electronics and Information, Inha Technical College)
Park, Gwi-Tae (Department of Electrical Engineering, Korea University)
Publication Information
ETRI Journal / v.34, no.4, 2012 , pp. 572-582 More about this Journal
Abstract
The discrete Gaussian-Hermite moment (DGHM) is a global feature representation method that can be applied to square images. We propose a modified DGHM (MDGHM) method and an MDGHM-based scale-invariant feature transform (MDGHM-SIFT) descriptor. In the MDGHM, we devise a movable mask to represent the local features of a non-square image. The complete set of non-square image features are then represented by the summation of all MDGHMs. We also propose to apply an accumulated MDGHM using multi-order derivatives to obtain distinguishable feature information in the third stage of the SIFT. Finally, we calculate an MDGHM-based magnitude and an MDGHM-based orientation using the accumulated MDGHM. We carry out experiments using the proposed method with six kinds of deformations. The results show that the proposed method can be applied to non-square images without any image truncation and that it significantly outperforms the matching accuracy of other SIFT algorithms.
Keywords
SIFT; modified discrete Gaussian-Hermite moments (MDGHM); local feature extraction;
Citations & Related Records

Times Cited By Web Of Science : 0  (Related Records In Web of Science)
연도 인용수 순위
  • Reference
1 L. Ma et al., "Local Intensity Variation Analysis for Iris Recognition," Pattern Recognition, vol. 37, no. 6, 2004, pp. 1287-1298.   DOI   ScienceOn
2 W. Shen and Y. Xiao, "Stereo Matching Based on Orthogonal Gaussian-Hermite Moments," Proc. SPIE Int. Symp. Multispectral Image Process. Pattern Recognition, 2009.
3 B. Yang and M. Dai, "Image Analysis by Gaussian-Hermite Moments," Signal Process., vol. 91, no. 10, 2011, pp. 2290-2303.   DOI   ScienceOn
4 L. Juan and O. Gwun, "A Comparison of SIFT, PCA-SIFT and SURF," Int. J. Image Process., vol. 3, no. 4, 2009, pp.143-152.
5 http://www.robots.ox.ac.uk/-vgg/research/affine
6 C.J. van Rijsbergen, Information Retrieval, Butterworth-Heinemann, London, UK, 1979.
7 D. Lisin et al., "Combining Local and Global Image Features for Object Class Recognition," IEEE Workshop Learning Computer Vision Pattern Recognition, 2005.
8 D.G. Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," Int. J. Computer Vision, vol. 60, 2004, pp. 91-110.   DOI
9 Y. Ke and R. Sukthankar, "PCA-SIFT: A More Distinctive Representation for Local Image Descriptors," Proc. Int. Conf. Computer Vision Pattern Recognition, 2004, pp. II: 506-513.
10 H. Bay, T. Tuytelaars, and L.V. Gool, "SURF: Speeded Up Robust Features," 9th European Conf. Computer Vision, 2006, pp. 404-417.
11 K. Mikolajczyk and C. Schmid, "A Performance Evaluation of Local Descriptors," IEEE Trans. Pattern Anal. Mach. Intell., vol. 27, 2003, pp. 1615-1630.
12 J. Shen, "Orthogonal Gaussian-Hermite Moments for Image Characterization," Proc. SPIE Intelligent Robots Computer Vision XVI, 1997, p. 224.
13 L. Wang, Y. Wu, and M. Dai, "Some Aspects of Gaussian-Hermite Moments in Image Analysis," Proc. Int. Conf. Natural Computation, 2007, p. 450.