An Improved PCA-SIFT Algorithm by Fuzzy K-Means for Image Matching

Abstract:

Image matching plays an important role in computer vision. The features extracted by SIFT algorithm have high stability invariant to scale, rotation and light, so it is the most popular algorithm for image matching. While SIFT algorithm also has its disadvantages of high dimensional data and time-consuming. To solve this problem, the traditional method employs PCA algorithm to reduce dimensionality of the descriptors. While PCA is a linear dimensionality reduction algorithm which means that it can only be used for linear distributed data. This paper employs the fuzzy K-means algorithm to improve it (referred to as FKPCA) and improved RANSAC algorithm to eliminate false matching points after matching with PCA-SIFT and FKPCA-SIFT. From the experimental results, compared with PCA-SIFT algorithm, it can be seen that FKPCA-SIFT can keep the high matching accuracy for image. Moreover, FKPCA-SIFT can also be applied to non-linear data to expand the scope of PCA-SIFT and provides a better reference platform for further research.

• Periodical: Applied Mechanics and Materials (Volumes 644-650)
• Pages: 4291-4296
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.644-650.4291
• Online since: September 2014
• Authors: Ning Li Zhang*, Yan Ma, Xiang Fen Zhang, Yan Lu Xu
• Keywords: FKPCA-SIFT Algorithm, Image Matching, Non-Linear Dimensionality Reduction RANSAC Algorithm, SIFT Algorithm

References

[1] LOWE D G in: Distinctive image features from scale-invariant keypoint, submited to International Journal of Computer Vision, Vol. 60(2004).

[2] David G. lowe in: Object recognition from local scale-invariant features, International Conference on Computer Vision, Corfu , Greece (1999).

DOI: 10.1109/iccv.1999.790410

[3] R. Fergus, P. Perona, and A. Zisserman in: Object class recognition by unsupervised scale-invariant learning , IEEE Computer Society Conference on Computer Vision and Pattern Recognition (2003).

DOI: 10.1109/cvpr.2003.1211479

[4] Qiu Wentao, Zhao Jian, Liu Jie in: Image matching combine SIFT with regional SSDA, International Conference on Control Engineering and Communication Technology (2012).

DOI: 10.1109/iccect.2012.78

[5] G. Sharma, S. Chaudhury, and J. Srivastava in: Bag-of-features kernel eigen spaces for classification, International Conference on Pattern Recognition (2008).

DOI: 10.1109/icpr.2008.4761240

[6] Feng Jia in: The Study and Improvement for SIFT Algorithm, submitted to Ji Lin University (2010).

[7] Xu Yongzhi，Hua Huichuan in: The Improvement for Three disadvantages of PCA Algorithm, submitted to Journal of Technology Management Research, Vol. 6 (2009).

[8] Kanungo T, Mount D M in: An efficient K-means clustering Algorithm: analysis and implementation. Volume 24 of IEEE Transaction on Pattern Analysis and Matching Intelligence (2002).

DOI: 10.1109/tpami.2002.1017616

[9] Li Lili in: Fuzzy C-means Clustering Algorithm and Its Application in Image Segmentation, submitted to Shandong Normal University (2009).

[10] Bhattacharya. P, Gavrilova. M in: Improving RANSAC feature matching with local topological information volume 29 of Voronoi Diagrams in Science and Engineering (ISVD) (2012).

DOI: 10.1109/isvd.2012.8