Journal of Advanced Navigation Technology (한국항행학회논문지)

The Korean Navigation Institute (한국항행학회)
권호 표지
DOI QR코드

DOI QR Code

Improving Matching Performance of SURF Using Color and Relative Position

위치와 색상 정보를 사용한 SURF 정합 성능 향상 기법

  • Lee, KyungSeung (School of Electrical Engineering, Korea University) ;
  • Kim, Daehoon (School of Electrical Engineering, Korea University) ;
  • Rho, Seungmin (Division of Information and Communication, Baekseok University) ;
  • Hwang, Eenjun (School of Electrical Engineering, Korea University)
  • 이경승 (고려대학교 전기전자전파 공학부) ;
  • 김대훈 (고려대학교 전기전자전파 공학부) ;
  • 노승민 (백석대학교 정보통신학부) ;
  • 황인준 (고려대학교 전기전자전파 공학부)
  • Received : 2012.03.21
  • Published : 2012.04.30
Download PDF
⟨ Previous Next ⟩

Abstract

SURF is a robust local invariant feature descriptor and has been used in many applications such as object recognition. Even though this algorithm has similar matching accuracy compared to the SIFT, which is another popular feature extraction algorithm, it has advantage in matching time. However, these descriptors do not consider relative location information of extracted interesting points to guarantee rotation invariance. Also, since they use gray image of original color image, they do not use the color information of images, either. In this paper, we propose a method for improving matching performance of SURF descriptor using the color and relative location information of interest points. The location information is built from the angles between the line connecting the centers of interest points and the orientation line constructed for the center of each interest points. For the color information, color histogram is constructed for the region of each interest point. We show the performance of our scheme through experiments.

SURF(Speeded Up Robust Features)는 다양한 상태 변화에 강인한 기술자 추출 방법으로 객체 인식과 같은 분야에서 유용하게 사용되는 알고리즘이다. 이 알고리즘은 대표적인 특징점 추출 알고리즘인 SIFT(Scale Invariant Feature Transform)와 비슷한 성능을 보이면서도 수행 시간이 훨씬 빠르다는 장점이 있다. 하지만 이러한 기술자들은 회전 불변한 특징 보장을 위해서, 추출한 특징점 간의 위치 정보를 고려하지 않는다. 또한, 원본 영상을 흑백 영상으로 변환하여 사용하기 때문에, 원본 이미지의 색상 정보도 이용하지 않는다. 본 논문에서는 특징점들 간의 상대적인 위치 정보 및 색상 정보를 이용하여 SURF 기술자의 정합 성능을 개선하는 방안을 제안한다. 상대적인 위치 정보는 특징점들의 중심을 연결하는 선분과 특징점 중심에서부터 생성되는 orientation 선분 사이의 각을 기반으로 한다. 색상 정보의 경우 각 특징점이 포함하고 있는 영역에 대해 color histogram을 생성하여 사용한다. 실험을 통하여 제안된 기법의 성능 개선을 보인다.

Keywords

References

  1. P. Schugerl, R. Sorchag, W. Bailer, and G.Thallinger, "Object re-detection using sift and mpeg-7 color descriptors", In International Workshop on Multimedia Content Analysis and Mining, pp.305-314, 2007
  2. Zhang, W., Yu, B., Zelinsky, G. J., & Samaras, D., "Object class recognition using multiple layer boosting with heterogeneous features", In CVPR'05, pp. 323-330, 2005
  3. Cheng Hongwei, Jiang Letian, Chen Xiaonming, Bao Jing, "Intergrated Color Balance Algorithm For Panoramic Image", American Journal of Engineering and Technology Research. 2011
  4. M. Brown, D. G. Lowe, "Unsupervised 3D Object Recognition and Reconstruction in Unordered Data sets", Proceeding of the Fifth International Conference on 3-D Digital Imaging and Modeling, pp.56-63, June 13-16, 2005.
  5. Liu, J., Hubbold, R., "Automatic camera calibration and scene reconstruction with scale-invariant features", In:ISVC, pp.558-568, 2006
  6. D.G.Lowe, "Object Recognition from Local Scale-Invariant Features," Proc. Seventh Int'l Conf. Computer Vision, 1150-1157(1999)
  7. D.G.Lowe, "Distinctive Image Features from Scale-Invariant Keypoints," Int'l J. Computer Vision, 60 (2), 91-110(2004) https://doi.org/10.1023/B:VISI.0000029664.99615.94
  8. Y. Ke, and R. Sukthankar, "PCA-SIFT: A More Distinctive Representation for Local Image Descriptors," Proc, Computer Vision and Pattern Recognition, 511-517(2004)
  9. Mikolajczyk, and K., S, chmid, C, "A performance evaluation of local descriptors", PAMI 27(10), 1615-1630(2005) https://doi.org/10.1109/TPAMI.2005.188
  10. Sarfraz S., and Hellwich O, "Head Pose Estimation in Face recognition across Pose Scenarios", Proceeding of VISAPP 2008, Int. conference on Computer Vision theory and Applications, Madeira, Portugal, 235-242(2008)
  11. H. Bay, T. Tuytelaars, and L. V. Gool, "SURF: Speeded up robust features," European Conference on Computer Vision, 404-417(2006)
  12. P.A. Viola, and M.J.Jones, "Rapid object detection using a boosted cascade of simple features", CVPR, (1), 511-518(2008)
  13. Gang Meng, Zhiguo Jiang, Danpei Zhao, "The Usage of Color Invariance in SURF" Proc. of SPIE(2009).
  14. Pen Fan, Aidong Men, Mengyang Chen, Bo Yang, "Color-Surf: A Surf Descriptor with Local Kernel Color Histograms", Proceeding of IC-NIDC, pp.726-730(2009)
  15. Hyunsup Yoon, Hwan-Ik Chung, Hernsoo Hahn, "SURF Algorithm with Color and Global Characteristics" Proceeding of ICCAS-SICE, pp.183-187 (2009)
  16. ALOI(Amsterdam Library of Object Images), http://staff.science.uva.nl/-aloi/

Cited by

  1. Matching and Geometric Correction of Multi-Resolution Satellite SAR Images Using SURF Technique vol.30, pp.4, 2014, https://doi.org/10.7780/kjrs.2014.30.4.2