Impact of reduction in descriptor size on object detection and classification | Multimedia Tools and Applications Skip to main content
Springer Nature Link
Log in

Impact of reduction in descriptor size on object detection and classification

  • Published:
Multimedia Tools and Applications Aims and scope Submit manuscript

Abstract

Extraction of distinctive and robust features in image/video analysis and processing has attracted the attention of researchers in the recent years. Elimination of irrelevant and less important features reduces the computational complexity to a great extent at the cost of a very marginal reduction in accuracy. This paper presents a framework for dimensionality reduction of the binary features to obtain a low dimension feature vector for object detection. The process of identification and selection of the most relevant feature is performed in three steps: extraction of features using binary descriptors; Selection of best feature subset using Sequential Forward Selection (SFS) and Principal Component Analysis; classification using SVM classifier. The experimental results show that BRISK and LATCH descriptors perform better even when the dimensionality is reduced from 256, 128, and 64 to 32 bits with an acceptable classification accuracy and significant reduction in run time. However, there is slight decrease in the classification accuracy of LBP, FREAK, BRIEF, and ORB. A classification rate of 84.93% is obtained with LATCH descriptor for a descriptor size of 32 bits.

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

Access this article

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

Price includes VAT (Japan)

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

References

  1. Alahi A, Ortiz R, Vandergheynst P (2012) Freak: Fast retina keypoint. In Computer vision and pattern recognition (CVPR), 2012 IEEE conference on (p 510-517). IEEE

  2. Baccini A, Besse P, Falguerolles A (1996) A -norm PCA and a heuristic approach. Ordinal Symbol. Data Anal 359–368

  3. Blum AL, Langley P (1997) Selection of relevant features and examples in machine learning. Artif Intell 97(1):245–271

    Article  MathSciNet  Google Scholar 

  4. Calonder M, Lepetit V, Strecha C, Fua P (2010) Brief: Binary robust independent elementary features. Computer Vision–ECCV 2010:778–792

    Google Scholar 

  5. Chen Y, Yang M, Chen X, Liu B, Wang H, Wang S (2018) Sensorineural hearing loss detection via discrete wavelet transform and principal component analysis combined with generalized eigenvalue proximal support vector machine and Tikhonov regularization. Multimedia Tools and Applications 77(3):3775–3793

    Article  Google Scholar 

  6. de Silva V, Tenenbaum JB (2003) Global versus local methods in nonlinear dimensionality reduction. In: Advances in Neural Information Processing Systems, vol. 15, Cambridge, p 721-728

  7. Ghodsi A (2006) Dimensionality reduction a short tutorial. Department of Statistics and Actuarial Science, Univ. of Waterloo, Waterloo, pp 37–38

    Google Scholar 

  8. Gudigar A, Chokkadi S, Raghavendra U (2016) A review on automatic detection and recognition of traffic sign. Multimedia Tools and Applications 75(1):333–364

    Article  Google Scholar 

  9. He XF, Cai D, Yan SC, Zhang HJ (2005) Neighborhood preserving embedding. In: Proc. of ICCV05, p 1208-1213

  10. Howley T, Madden MG, O’Connell ML, Ryder AG (2006) The effect of principal component analysis on machine learning accuracy with high dimensional spectral data. In Applications and Innovations in Intelligent Systems XIII (pp. 209-222). Springer, London

  11. Hussain SU, Triggs W (2010) Feature sets and dimensionality reduction for visual object detection. In: BMVC 2010-British Machine Vision Conference (p 112-1). BMVA Press

  12. Izenman AJ (2013) Linear discriminant analysis. In: Modern multivariate statistical techniques (pp. 237-280). Springer, New York

    Google Scholar 

  13. Jain A, Zongker D (1997) Feature selection: Evaluation, application, and small sample performance. IEEE Trans Pattern Anal Mach Intell 19(2):153–158

    Article  Google Scholar 

  14. Jolliffe IT (2002) Principal component analysis, 2nd edn. Springer, Berlin

    MATH  Google Scholar 

  15. Kang K, Cao Y, Zhang J, Wang Z (2016) Salient object detection and classification for stereoscopic images. Multimedia Tools and Applications 75(3):1443–1457

    Article  Google Scholar 

  16. Ke Q, Kanade T (2005) Robust norm factorization in the presence of outliers and missing data by alternative convex programming. Proc Comput Vis Pattern Recogn Conf 739–737

  17. Keller S, Braun AC, Hinz S, Weinmann M (2016, August) Investigation of the impact of dimensionality reduction and feature selection on the classification of hyperspectral EnMAP data. In: Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), 2016 8th Workshop on. IEEE, p 1–5

  18. Koller D, Sahami M (1996) Toward optimal feature selection. Stanford InfoLab, Stanford

    Google Scholar 

  19. Kosmpoulos A, Paliouras G, Androutsopoulos I (2014) The effect of dimensionality reduction on large scale hierarchical classification. In: Kanoulas E. et al. (eds) Information Access Evaluation. Multilinguality, Multimodality, and Interaction. CLEF 2014. Lecture Notes in Computer Science, vol 8685. Springer, Cham

    Google Scholar 

  20. Kumar R, Chandra P, Hanmandlu M (2014) Rotational invariant fingerprint matching using local directional descriptors. International Journal of Computational Intelligence Studies 3(4):292–319

    Article  Google Scholar 

  21. Kumar R, Chandra P, Hanmandlu M (2016) A Robust Fingerprint Matching System Using Orientation Features. Journal of Information Processing Systems 12(1):83–99

    Google Scholar 

  22. Kumar R, Hanmandlu M, Chandra P (2014) An empirical evaluation of rotation invariance of LDP features for fingerprint matching using neural networks. International Journal of Computational Vision and Robotics 4(4):330–348

    Article  Google Scholar 

  23. Lafon S, Lee AB (2006) Diffusion maps and coarse-graining: A unified framework for dimensionality reduction, graph partitioning, and data set parameterization. In: IEEE Trans. PAMI 28(9):1393-1403

    Article  Google Scholar 

  24. Leutenegger S, Chli M, Siegwart RY (2011) BRISK: binary robust invariant scalable keypoints. In: Computer Vision (ICCV), 2011 IEEE International Conference on (p 2548–2555). IEEE

  25. Levi, G, Hassner T (2016) LATCH: learned arrangements of three patch codes. In: Applications of Computer Vision (WACV), 2016 IEEE Winter Conference on (p 1–9). IEEE

  26. Pietikäinen M, Hadid A, Zhao G, Ahonen T (2011) Local binary patterns for still images. Computer vision using local binary patterns, p 13-47

  27. Plastria F, De Bruyne S, Carrizosa E (2008) Dimensionality Reduction for Classification. In: Tang C, Ling CX, Zhou X, Cercone NJ, Li X (eds) Advanced Data Mining and Applications. ADMA 2008. Lecture Notes in Computer Science, vol 5139. Springer, Berlin, Heidelberg

    Google Scholar 

  28. Popelínský L (2000) Combining the principal components method with different learning algorithms. In: Proc. of ECML/PKDD IDDM Workshop (Integrating Aspects of Data Mining, Decision Support and Meta-Learning) 2001

  29. Rani R, Kumar R, Singh AP (2018) An empirical evaluation of translational and rotational invariance of descriptors and the classification of flower dataset. Pattern Anal Applic 21(1):1–18

    Article  MathSciNet  Google Scholar 

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

    Google Scholar 

  31. Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290:2323–2326

    Article  Google Scholar 

  32. Rublee E, Rabaud V, Konolige K, Bradski G (2011) ORB: an efficient alternative to SIFT or SURF. In: Computer Vision (ICCV), 2011 IEEE international conference on (p 2564-2571). IEEE

  33. Schölkopf B, Smola A, Müller K-R (1999) Kernel principal component analysis. In: Advances in Kernel methods – support vector learning. MIT Press, p 327–352

  34. Shlens J (2014) A tutorial on principal component analysis. arXiv preprint arXiv:1404.1100

  35. Sulic V, Perš J, Kristan M, Kovacic S (2010) Efficient dimensionality reduction using random projection. In: 15th Computer Vision Winter Workshop, 29–36, (Nov’eHrady, Czech Republic)

  36. Sun M, Han TX, He Z (2016) A classification leveraged object detector. arXiv preprint arXiv:1604.01841

  37. Tapu R, Mocanu B, Zaharia T (2017) A computer vision-based perception system for visually impaired. Multimedia Tools and Applications 76(9):11771–11807

    Article  Google Scholar 

  38. Tenenbaum JB, Silva VD, Langford JC (2000) A global geometric framework for nonlinear dimensionality reduction. Science 290:2319–2323

    Article  Google Scholar 

  39. Wang SH, Zhan TM, Chen Y, Zhang Y, Yang M, Lu HM, Phillips P (2016) Multiple sclerosis detection based on biorthogonal wavelet transform, RBF kernel principal component analysis, and logistic regression. IEEE Access 4:7567–7576

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. GGSIPU, Dwarka, New Delhi, India

    Ritu Rani, Amit Prakash Singh & Ravinder Kumar

Authors
  1. Ritu Rani
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Amit Prakash Singh
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Ravinder Kumar
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Ritu Rani.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Rani, R., Singh, A.P. & Kumar, R. Impact of reduction in descriptor size on object detection and classification. Multimed Tools Appl 78, 8965–8979 (2019). https://doi.org/10.1007/s11042-018-6911-7

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11042-018-6911-7

Keywords

Search

Navigation