Skip to main navigation menu Skip to main content Skip to site footer

Vol. 10 No. 2.0 (2021)
Scholar : National School of Leadership

Research Articles

Fuzzy Mathematical Technique to Bovine Feature Extraction and Identification

Published 2021-12-31

  • ANUSHA EDWIN

ANUSHA EDWIN
MAR IVANIOS COLLEGE

Abstract

A feature extractor which is rotation-invariant detector and descriptor, using fuzzy- SURF (Speeded-Up Robust Features) is presented. Fuzzy SURF approximates or even outperforms the schemes with respect to repeatability, distinctiveness, and robustness, which can be computed and compared much faster. Nose patterns are the asymmetrical features of the skin surface of bovine. The nose pattern can considered as a biometric identifier for bovine. This is done by relying on integral images for image convolutions; by building on the strengths of the leading existing detectors and descriptors (specifically, using a Hessian matrix-based measure for the detector, and a distribution-based descriptor); and by matching with fuzzy similarity measure. This leads to a combination of novel detection, description, and matching steps. The paper encompasses a detailed description of the detector and descriptor and then explores the effects of the most important parameters.

References

  1. P.A. Viola, M.J. Jones, “Rapid object detection using a boosted cascade of simple
  2. features”, in: CVPR, issue 1, 2001, pp. 511–518.
  3. P. Simard, L. Bottou, P. Haffner, Y. LeCun, “Boxlets: a fast convolution algorithm for
  4. signal processing and neural networks”, in: NIPS, 1998.
  5. K. Mikolajczyk, C. Schmid, “Indexing based on scale invariant interest points, in: ICCV”,
  6. vol. 1, 2001, pp. 525–531.
  7. T. Lindeberg, “Feature detection with automatic scale selection”, IJCV 30 (2) (1998)
  8. –116.
  9. J. J. Koenderink, “The structure of images”, Biological Cybernetics 50 (1984) 363–370.
  10. T. Lindeberg, “Scale-space for discrete signals”, PAMI 12 (3) (1990) 234–254.
  11. D. Lowe, “Distinctive image features from scale-invariant keypoints”, IJCV 60 (2) (2004)
  12. –110.
  13. A. Neubeck, L. Van Gool, “Efficient non-maximum suppression”, in: ICPR, 2006.
  14. M. Brown and D. Lowe, “Invariant features from interest point groups”, in: BMVC, 2002.
  15. H. Bay, B. Fasel and L. Van Gool, “Interactive museum guide: fast and robust recognition
  16. of museum objects”, in: Proceedings of the First International Workshop on Mobile
  17. Vision, May 2006.
  18. H. Bay, T. Tuytelaars, L. Van Gool, “SURF: speeded up robust features”, in: ECCV,