Image Segment Matching Using Affine- Invariant Regions

In this paper, a method for matching image segments using triangle-based (geometrical) regions is proposed. Triangular regions are formed from triples of vertex points obtained from a keypoint detector (SIFT). However, triangle regions are subject to noise and distortion around the edges and vertices (especially acute angles). Therefore, these triangles are expanded into parallelogramshaped regions. The extracted image segments inherit an important triangle property; the invariance to affine distortion. Given two images, matching corresponding regions is conducted by computing the relative affine matrix, rectifying one of the regions w.r.t. the other one, then calculating the similarity between the reference and rectified region. The experimental tests show the efficiency and robustness of the proposed algorithm against geometrical distortion.

Authors:

• Ibrahim El rube'

Keywords:

• Image matching
• key point detection
• affine invariant
• triangle-shaped segments.

References:

[1] N. S. Vassilieva ,"Content-based Image Retrieval Methods",
Programming and Computer Software, 2009, Vol. 35, No. 3, pp. 158-
180. ┬® Pleiades Publishing, Ltd., 2009.Original Russian Text ┬® N.S.
Vassilieva, 2009, published in Programmirovanie, 2009, Vol. 35, No. 3.
[2] Yang Gui, Xiaohu Zhang, and Yang Shang, SAR image segmentation
using MSER and improved spectral clustering , EURASIP Journal on
Advances in Signal Processing 2012, 2012:83.
[3] Jiguang Dai, Weidong Song and Jichao Zhang Remote Sensing Image
Matching via Harris Detector and Wavelet Domain, 18th International
Conference on Geoinformatics, 2010, pp. 1-4.
[4] M. Paradowski and A. 'Sluzek, "Detection of image fragments related
by affine transforms: Matching triangles and ellipses," in Proc.
International Conference on Information Science and Applications, vol.
1, 2010, pp.189-196
[5] Babbar, G., Punam Bajaj, AnuChawla, and Monika Gogna. 2010. A
comparative study of image matching algorithms, International Journal
of Information, Technology and Knowledge Management.July
December. 2(2): 337-339.
[6] Schenk, T., A. Krupnik, and Y. Postolov. 2000. Comparative study of
surface matching algorithms, International Archives of Photogrammetry
and Remote Sensing Vol. XXXIII, part 4B, Amsterdam 2000. p. 518-
524.
[7] Lowe, D.G. 1999. Object recognition from local scale-invariant features,
the proceedings of the seventh IEEE International Conference on
Computer Vision 1999. 2: 1150-1157.
[8] Mikolajczyk, K, and. C. Schmid. 2004. Scale and affine invariant
interest point detectors. International Journal of Computer Vision 60(1):
63-86.
[9] Lowe, D.G. 2004. Distintive image feature from scale-invariant
keypoints. International Journal of Computer Vision, 60(2): 91-110.
[10] Ke, Y., and R. Sukthankar. 2004. PCA-SIFT: A more distinctive
representation for local image descriptors. IEEE Computer Society
Conference on Computer Vision and Pattern Recognition (CVPR 04) -
2: 506-513.
[11] Bay, H., A. Ess, T. Tuytelaars, and L. Van Gool. 2006. Speeded-up
robust features (SURF). Computer Vision ECCV 2006, Vol. 3951.
Lecture Notes in Computer Science. p. 404-417.
[12] Juan, L., and O. Gwun. 2009. A comparison of SIFT, PCA-SIFT, and
SURF. International Journal of Image Processing (IJIP) 3(4): 143-
152.57
[13] Wassim Messaoudi, Imed Riadh Farah, Karim sahebettabâa, and Basel
Solaiman, Semantic Strategic Satellite Image Retrieval, 3rd
International Conference on Information and Communication
Technologies: From Theory to Applications, 2008. ICTTA 2008. pp. 1-6
[14] S. M. Zakariya, Rashid Ali and Nesar Ahmad, Combining Visual
Features of an Image at Different Precision Value of Unsupervised
Content Based Image Retrieval, IEEE International Conference on
Computational Intelligence and Computing Research (ICCIC), 2010,
pp. 1-4.
[15] J.M. Morel and G.Yu, ASIFT: A New Framework for Fully Affine
Invariant Image Comparison, SIAM Journal on Imaging Sciences, vol.
2, issue 2, 2009.
[16] Samer R. Saydam, Ibrahim El Rube, Amin A. Shoukry: Contourlet
Based Interest Points Detector. ICTAI (2) 2008: 509-513.