Description-Based Ranking of Visual Instances: Feasibility Study for Keypoints | SpringerLink
Skip to main content
Springer Nature Link
Log in

Description-Based Ranking of Visual Instances: Feasibility Study for Keypoints

  • Conference paper
  • First Online:
Progress in Image Processing, Pattern Recognition and Communication Systems (CORES 2021, IP&C 2021, ACS 2021)

Part of the book series: Lecture Notes in Networks and Systems ((LNNS,volume 255))

  • 449 Accesses

Abstract

The paper introduces (and investigates) a novel methodology for improving performances of detection of visual objects (keypoints are selected as objects for the feasibility study). Using any (i.e. either hand-crafted or deep-learned) detector in conjunction with the selected descriptor, we rank the extracted keypoints using stability of their descriptors. Stability is defined by the magnitude of partial derivatives of the descriptor over parameters determining deformations of the original images. In practice, discrete approximations of the derivatives are used. We have preliminarily verified that by using the keypoints top-ranked by the proposed criterion (i.e. those with least-sensitive descriptors) instead of keypoints top-ranked by the standard prominence criteria, performances of matching (we primarily focus on precision) can be substantially improved. The results have been obtained using a popular benchmark set of images.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution

Subscribe and save

Springer+ Basic
¥17,985 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Chapter
JPY 3498
Price includes VAT (Japan)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
JPY 17159
Price includes VAT (Japan)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
JPY 21449
Price includes VAT (Japan)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    http://www.robots.ox.ac.uk/~vgg/research/affine/.

References

  1. Alahi, A., Ortiz, R., Vandergheynst, P.: Freak: fast retina keypoint. In: 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 510–517 (2012)

    Google Scholar 

  2. Alcantarilla, P.F., Bartoli, A., Davison, A.J.: Kaze features. In: Computer Vision—ECCV 2012, pp. 214–227 (2012)

    Google Scholar 

  3. Barroso-Laguna, A., Riba, E., Ponsa, D., Mikolajczyk, K.: Key.net: keypoint detection by handcrafted and learned cnn filters. In: Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV) (2019)

    Google Scholar 

  4. Bay, H., Ess, A., Tuytelaars, T., Van Gool, L.: Speeded-up robust features (surf). Comput. Vis. Image Underst. 110(3), 346–359 (2008)

    Article  Google Scholar 

  5. Clady, X., Ieng, S.H., Benosman, R.: Asynchronous event-based corner detection and matching. Neural Netw. 66, 91–106 (2015)

    Article  Google Scholar 

  6. Dai, Z., Huang, X., Chen, W., He, L., Zhang, H.: A comparison of CNN-based and hand-crafted keypoint descriptors. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 2399–2404 (2019)

    Google Scholar 

  7. Duan, L., Wu, C., Miao, J., Qing, L., Fu, Y.: Visual saliency detection by spatially weighted dissimilarity. In: CVPR 2011, pp. 473–480 (2011)

    Google Scholar 

  8. Harris, C., Stephens, M.: A combined corner and edge detector. In: Alvey Vision Conference, pp. 147–152 (1988)

    Google Scholar 

  9. Itti, L., Koch, C., Niebur, E.: A model of saliency-based visual attention for rapid scene analysis. IEEE Trans. Pattern Anal. Mach. Intell. 20(11), 1254–1259 (1998)

    Article  Google Scholar 

  10. Jiao, L., et al.: A survey of deep learning-based object detection. IEEE Access 7, 128837–128868 (2019)

    Article  Google Scholar 

  11. Komorowski, J., Czarnota, K., Trzcinski, T., Dabala, L., Lynen, S.: Interest point detectors stability evaluation on apolloscape dataset. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)

    Google Scholar 

  12. Leutenegger, S., Chli, M., Siegwart, R.Y.: Brisk: binary robust invariant scalable keypoints. In: 2011 International Conference on Computer Vision (ICCV), pp. 2548–2555 (2011)

    Google Scholar 

  13. Lowe, D.G.: Distinctive image features from scale-invariant keypoints. Int. J. Comput. Vis. 60(2), 91–110 (2004)

    Article  Google Scholar 

  14. Matas, J., Chum, O., Urban, M., Pajdla, T.: Robust wide baseline stereo from maximally stable extremal regions. In: British Machine Vision Conference, pp. 384–393 (2002)

    Google Scholar 

  15. Mikolajczyk, K., Schmid, C.: Scale and affine invariant interest point detectors. Int. J. Comput. Vis. 60, 63–86 (2004)

    Article  Google Scholar 

  16. Mikolajczyk, K., Schmid, C.: A performance evaluation of local descriptors. IEEE Trans. PAMI 27, 1615–1630 (2005)

    Article  Google Scholar 

  17. Mikolajczyk, K., et al.: A comparison of affine region detectors. Int. J. Comput. Vis. 65, 43–72 (2005)

    Article  Google Scholar 

  18. Nascimento, J.C., Marques, J.S.: Performance evaluation of object detection algorithms for video surveillance. IEEE Trans. Multimed. 8(4), 761–774 (2006)

    Article  Google Scholar 

  19. Ono, Y., Trulls, E., Fua, P., Kwang, M.Y.: LF-NET: learning local features from images. In: 32nd International Conference on Neural Information Processing (NIPS 2018), pp. 6237–6247 (2018)

    Google Scholar 

  20. Prasad, D.K.: Survey of the problem of object detection in real images. Int. J. Image Process. 6(6), 441–466 (2012)

    Google Scholar 

  21. Redmon, J., Farhadi, A.: Yolo9000: better, faster, stronger. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7263–7271 (2017)

    Google Scholar 

  22. Revaud, J., et al.: R2D2: repeatable and reliable detector and descriptor (2019). http://arxiv.org/abs/1906.06195

  23. Rosten, E., Drummond, T.: Machine learning for high-speed corner detection. In:Computer Vision—ECCV 2006, pp. 430–443 (2006)

    Google Scholar 

  24. Śluzek, A.: Descriptor-driven keypoint detection. In: 2018 Digital Image Computing:Techniques and Applications (DICTA), pp. 1–8 (2018)

    Google Scholar 

  25. Śluzek, A.: Improving performances of mser features in matching and retrievaltasks. LNCS (ECCV 2016 Workshops) 9915, pp. 759–770(2016)

    Google Scholar 

  26. Ullah, I., et al.: A brief survey of visual saliency detection. Multimed. Tools Appl. 79, 34605–34645 (2020)

    Article  Google Scholar 

  27. Yi, K.M., Fortuny, E.T., Lepetit, V., Fua, P.: Lift: learned invariant feature transform. In: Proceedings of the 14th European Conference on ECCV 2016), vol. 2, pp. 467–483 (2016)

    Google Scholar 

  28. Zhang, X., Yu, F.X., Karaman, S., Chang, S.: Learning discriminative and transformation covariant local feature detectors. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4923–4931 (2017)

    Google Scholar 

  29. Zheng, L., Yang, Y., Tian, Q.: Sift meets CNN: a decade survey of instance retrieval. IEEE Trans. PAMI 40(5), 1224–1244 (2018)

    Article  Google Scholar 

  30. Zou, Z., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: a survey (2019). http://arxiv.org/abs/1905.05055

Download references

Author information

Authors and Affiliations

  1. Institute of Information Technology, Warsaw University of Life Sciences-SGGW, Warsaw, Poland

    Andrzej Śluzek

Authors
  1. Andrzej Śluzek
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Andrzej Śluzek .

Editor information

Editors and Affiliations

  1. Institute of Computer Science and Telecommunications, University of Science and Technlogy, Bydgoszcz, Poland

    Michal Choraś

  2. Institute of Computer Science and Telecommunications, University of Science and Technology, Bydgoszcz, Poland

    Ryszard S. Choraś

  3. Faculty of Electronics, Wroclaw University of Science and Technology, Wrocław, Poland

    Marek Kurzyński

  4. Faculty of Electronics, Wroclaw University of Science and Technology, Wrocław, Poland

    Paweł Trajdos

  5. West Pomeranian University of Technology in Szczecin, Szczecin, Poland

    Jerzy Pejaś

  6. West Pomeranian University of Technology in Szczecin, Szczecin, Poland

    Tomasz Hyla

Rights and permissions

Reprints and permissions

Copyright information

© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Śluzek, A. (2022). Description-Based Ranking of Visual Instances: Feasibility Study for Keypoints. In: Choraś, M., Choraś, R.S., Kurzyński, M., Trajdos, P., Pejaś, J., Hyla, T. (eds) Progress in Image Processing, Pattern Recognition and Communication Systems. CORES IP&C ACS 2021 2021 2021. Lecture Notes in Networks and Systems, vol 255. Springer, Cham. https://doi.org/10.1007/978-3-030-81523-3_8

Download citation

Publish with us

Policies and ethics