Qiang Tong, Terumasa Aoki



A Blur-Invariant Interest Point Detector Based on Moment Symmetry for Motion and Gaussian Blurred Image Matching

pdf PDF



Interest point detector is crucial to local feature-based image matching. However, lacking of robustness to strong blur is the fatal flaw of existing interest point detectors. As far as the authors know, all of the existing image matching methods fail to match a blurred image (caused by camera motion and out of focus, etc.) and a non-blurred image, even though blurred image matching is a critical task for many image/video applications. This article presents a blur-invariant interest point detector for blurred image matching. The proposed detector applies some blur-invariant image moments to detect a kind of special interest points from images. The special interest points are based on a new concept called Moment Symmetry (MS). These interest points are very robust to blur unlike traditional interest points based on corners or blobs. Experimental results show the proposed detector outperforms the state of the art interest point detectors for blurred image matching.



blur-invariant, local feature, moments, symmetry, interest point detector, image matching



[1] V. Ferrari, T. Tuytelaars, L. VanGool, Simultaneous object recognition and segmentation by image, in: ECCV (2004) 40–54.

[2] T. Tuytelaars, L. VanGool, Matching widely separated views based on affine invariant regions, IJCV 59 (1) (2004) 61–85.

[3] K. Mikolajczyk, C. Schmid, Indexing based on scale invariant interest points, in: ICCV (2001) 525–531.

[4] C. Schmid, R. Mohr, Local grayvalue invariants for image retrieval, PAMI 19 (5) (1997) 530– 534.

[5] D. Lowe, Distinctive image features from scaleinvariant keypoints, IJCV 60 (2) (2004) 91–110.

[6] H. Bay, T. Tuytelaars, L. VanGool, Surf: Speeded up robust features, in: ECCV (2006) 404–417.

[7] E. Rublee, et al, Orb: An efficient alternative to sift or surf, in: ICCV (2011) 2564–2571.

[8] S. Leutenegger, Y. Siegwart, Brisk: Binary robust invariant scalable keypoints, in: ICCV (2011) 2548–2555.

[9] J. Cai, H. Ji, C. Liu, Z. Shen, Blind motion deblurring using multiple images, J. Comput. Physics 228 (14) (2009) 5057–5071.

[10] C. Schuler, M. Hirsch, S. Harmeling, Learning to deblur, PAMI 38 (7) (2016) 1439–1451.

[11] Z. Hu, M. Yang, Good regions to deblur, in: ECCV (2012) 59–72.

[12] C. Harris, M. Stephens, A combined corner and edge detector, in: Alvey vision conference (1988) 10–14.

[13] K. Mikolajczyk, C. Schmid, Scale & affine invariant interest point detectors, IJCV 60 (1) (2004) 63–68.

[14] T. Lindeberg, Feature detection with automatic scale selection, IJCV 30 (2) (1998) 79–116.

[15] J. Matas, O. Chum, M. Urban, T. Pajdla, Robust wide baseline stereo from maximally stable extremal regions, in: BMVC (2002) 384–396.

[16] T. Kadir, M. Brady, Saliency, scale and image description, IJCV 45 (2) (2001) 83–105.

[17] J. Flusser, T. Suk, Degraded image analysis: an invariant approach, PAMI 20 (6) (1998) 590– 603.

[18] J. Flusser, et al, Recognition of images degraded by linear motion blur without restoration, in: Theoretical Foundations of Computer Vision (1996) 37–51.

[19] D. Shen, et al, Symmetry detection by generalized complex (gc) moments: a close-form solution, PAMI 21 (5) (1999) 466–476.

[20] M. Brown, D. Lowe, Invariant features from interest point groups, in: BMVC (2002) 656–665.

[21] http://www1.cs.columbia.edu/CAVE/software/ softlib/coil 20.php.

[22] K. Mikolajczyk, C. Schmid, A performance evaluation of local descriptors, PAMI 27 (10) (2004) 1615–1630.

[23] R. Khler, S. Harmeling, Recording and playback of camera shake: Benchmarking blind deconvolution with a real-world database, in: ECCV (2012) 27–40.

[24] Q. Tong, T. Aoki, A blur-invariant local feature for motion blurred image matching, in: International Conference on Digital Image Processing (2017) 181–187.

Cite this paper

Qiang Tong, Terumasa Aoki. (2017) A Blur-Invariant Interest Point Detector Based on Moment Symmetry for Motion and Gaussian Blurred Image Matching. International Journal of Signal Processing, 2, 96-106


Copyright © 2017 Author(s) retain the copyright of this article.
This article is published under the terms of the Creative Commons Attribution License 4.0