Advertisement

Optimization of SURF Algorithm for Image Matching of Parts

  • Hongyan DuanEmail author
  • Xiaoyu Zhang
  • Wensi He
Conference paper
Part of the Transactions on Intelligent Welding Manufacturing book series (TRINWM)

Abstract

SURF algorithm, which is featured with high speed and good robustness, is a common algorithm for feature points detection. But this algorithm has such drawbacks as the separating capacity of its feature points descriptor is low and principal direction of feature points is not accurate, which can easily cause less image matching pairs and high mismatching ratio. Therefore, an improved SURF algorithm is proposed to increase matching pairs effectively and raise accuracy of matching. For the algorithm, two new-type feature sets are added, and 128-dimensional feature descriptor is established. The method of combining Euclidean distance with cosine similarity match is adopted to match feature points. Then RANSAC method is used to lower mismatching ratio, thus achieving robots’ parts-matching in the indoor environment. The experiment result shows that under the conditions of images rotating, zooming, blurring, lighting and view change, the improved algorithm has better robustness. Besides, its matching ratio and accuracy are higher than standard SURF algorithm.

Keywords

Image processing Improved SURF algorithm Image matching Cosine similarity RANSAC algorithm 

References

  1. 1.
    Ding NN, Liu YY, Zhang Y et al (2012) Fast image registration based on SURF-DAISY algorithm and randomized kd trees. J Optoelectron Laser 23(7):1395–1402Google Scholar
  2. 2.
    Lowe DG (2004) Distinctive image features from scale-invariant key points. Int J Comput Vis 60(2):91–110MathSciNetCrossRefGoogle Scholar
  3. 3.
    Wang M, Yang K, Hua XS et al (2010) Towards a relevant and diverse search of social images. IEEE Trans Multimed 12(8):829–842CrossRefGoogle Scholar
  4. 4.
    Bay H, Ess A, Tuytelaars T et al (2008) Speeded-up robust features. Comput Vis Image Underst 110(3):404–417CrossRefGoogle Scholar
  5. 5.
    Bauer J, Sünderhauf N, Protzel P (2007) Comparing several implementations of two recently published feature detectors. IFAC Proc Vol 40(15):143–148CrossRefGoogle Scholar
  6. 6.
    Lienhart R, Kuranov A, Pisarevsky V (2003) Empirical analysis of detection cascades of boosted classifiers for rapid object detection. Dagm 2781:297–304Google Scholar
  7. 7.
    Jia L, Fu W, Wen W et al (2013) Image matching based on improved sift algorithm. Chin J Sci Instrum 34(5):1107–1112Google Scholar
  8. 8.
    Yan ZG, Jiang JG, Guo D (2014) Image matching based on surf feature and delaunay triangular meshes. Acta Autom Sin 40(6):1216–1222zbMATHGoogle Scholar
  9. 9.
    Xie Y, Li X, Lu J et al (2010) Underwater images real-time registration method based on surf. J Comput-Aided Des Comput Graph 22(12):2215–2220Google Scholar
  10. 10.
    Fu W, Qin C, Liu J et al (2011) Matching and location of image object based on sift algorithm. Chin J Sci Instrum 32(1):163–169Google Scholar
  11. 11.
    Hu M, Chen J, Shi C (2015) Three-dimensional mapping based on SIFT and RANSAC for mobile robot. In: IEEE international conference on cyber technology in automation, control, and intelligent systems. IEEE, pp 139–144Google Scholar
  12. 12.
    Huang L, Chen C, Shen H et al (2015) Adaptive registration algorithm of color images based on surf. Measurement 66:118–124CrossRefGoogle Scholar

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  1. 1.College of Mechanical and Electrical EngineeringLanzhou University of TechnologyLanzhouChina

Personalised recommendations