Your browser does not support JavaScript!
http://iet.metastore.ingenta.com
1887

access icon free Analysis of reduced-set construction using image reconstruction from a HOG feature vector

© The Institution of Engineering and Technology
Received 07/09/2016, Accepted 18/08/2017, Revised 15/05/2017, Published 23/08/2017

Recently, several methods have been published that demonstrate how to reconstruct an image from a discriminative feature vector. This study explains that previous approaches minimising the histogram-of-oriented-gradient (HOG) feature error in the principal component analysis (PCA) domain of the learning database have a disadvantage in that they cannot reflect the different dynamic range of each PCA dimension, and proposes an improved method to exploit the eigenvalue as the weighting factor of each PCA dimension. Experimental results using pedestrian and vehicle image databases quantitatively show that the proposed method improves the quality of reconstructed images. Additionally, the proposed method is applied to the image reconstruction of the resultant support vectors (SVs) of reduced-set construction which showed the best performance among SV number reduction methods. As the resultant SVs of reduced-set construction are not corresponding to any image of the learning database, it is hard to analyse the problem and performance of the method. By observing the images of the resultant SVs, one potential problem regarding the database used is newly considered and the direction of further study can be established in order to address the problem.

Inspec keywords: principal component analysis; visual databases; support vector machines; feature extraction; vehicles; image reconstruction; pedestrians

Other keywords: SV number reduction methods; discriminative feature vector; PCA dimension weighting factor; image reconstruction; histogram-of-oriented-gradient feature error; learning database; pedestrian image databases; principal component analysis; reduced-set construction analysis; HOG feature vector; vehicle image databases; resultant support vectors

Subjects: Knowledge engineering techniques; Image recognition; Computer vision and image processing techniques; Other topics in statistics; Other topics in statistics; Spatial and pictorial databases; Traffic engineering computing

References

    1. 1)
      • 23. Turk, M., Pentland, A.: ‘Eigenfaces for recognition’, J. Cogn. Neurosci., 1991, 3, (1), pp. 71–86.
    2. 2)
      • 15. Parikh, D., Lawrence Zitnick, C.: ‘The role of features, algorithms and data in visual recognition’. 2010 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), San Francisco, CA, 13–18 June 2010, pp. 2328–2335.
    3. 3)
      • 4. Keerthi, S.S., Chapelle, O., DeCoste, D.: ‘Building support vector machines with reduced classifier complexity’, J. Mach. Learn. Res., 2006, 7, pp. 1493–1515.
    4. 4)
      • 5. Angiulli, F., Astorino, A.: ‘Scaling up support vector machines using nearest neighbor condensation’, IEEE Trans. Neural Netw., 2010, 21, (2), pp. 351–357.
    5. 5)
      • 6. Kobayashi, T., Otsu, N.: ‘Efficient reduction of support vectors in Kernel-based methods’. Proc. 16th IEEE ICIP, November 7–10, 2009, pp. 2077–2080.
    6. 6)
      • 19. Mathworks, Global Optimization Toolbox User's Guide, Sep. 2011.
    7. 7)
      • 30. Xiang, Y., Choi, W., Lin, Y., et al: ‘Data-driven 3D voxel patterns for object category recognition’. 2015 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Boston, MA, 7–12 June 2015, pp. 1903–1911.
    8. 8)
      • 34. Anton, H., Busby, R.C.: ‘Section 7.8 best approximation and least squares’, in ‘Contemporary linear algebra’ (John Wiley & Sons, Inc, 2003), pp. 393–403, ISBN 978-0-471-16362-6.
    9. 9)
      • 32. Li, B., Wu, T., Shu, S.-C.: ‘Integrating context and occlusion for car detection by hierarchical and-or model’. 13th European Conf. Computer Vision (ECCV), Zurich, Switzerland, September 6–12, 2014, pp. 652–667.
    10. 10)
      • 13. d'Angelo, E., Jacques, L., Alahi, A., et al: ‘From bits to images: inversion of local binary descriptors’, IEEE Trans. Pattern Anal. Mach. Intell., 2014, 36, (5), pp. 874–887.
    11. 11)
      • 7. Franc, V., Hlavac, V.: ‘STPRtool: statistical pattern recognition toolbox’. [Online]. Available: http://cmp.felk.cvut.cz/cmp/software/stprtool.
    12. 12)
      • 1. Lin, H.-J., Yeh, J.P.: ‘A hybrid optimization strategy for simplifying the solutions of support vector machines’, Pattern Recognit. Lett., 2010, 31, (7), pp. 563–571.
    13. 13)
      • 20. Munder, S., Gavrila, D.M.: ‘An experimental study on pedestrian classification’, IEEE Trans. Pattern Anal. Mach. Intell., 2006, 28, (11), pp. 1863–1868.
    14. 14)
      • 28. Object Detection Evaluation 2012. [Online], Available: http://www.cvlibs.net/datasets/kitti/eval_object.php.
    15. 15)
      • 25. HOGgles: Visualizing Object Detection Features. [Online]. Available: http://web.mit.edu/vondrick/ihog/.
    16. 16)
      • 24. Leo, X.: ‘Histogram of oriented gradients’. [Online]. Available: http://www.mathworks.com/matlabcentral/fileexchange/33863-histograms-of-oriente.
    17. 17)
      • 8. Geebelen, D., Suykens, J.A.K., Vandewalle, J.: ‘Reducing the number of support vectors of SVM classifiers using the smoothed separable case approximation’, IEEE Trans. Neural Netw. Learn. Syst., 2012, 23, (4), pp. 682–688.
    18. 18)
      • 22. Daimler Pedestrian Classification Benchmark Dataset. [Online]. Available: http://www.gavrila.com.
    19. 19)
      • 16. Tatu, A., Lauze, F., Nielsen, M., et al: ‘Exploring the representation capabilities of the HOG descriptor’. 2011 IEEE Int. Conf. Computer Vision Workshops (ICCV Workshops), Barcelona, 6–13 November 2011, pp. 1410–1417.
    20. 20)
      • 26. Sivaraman, S., Trivedi, M.M.: ‘Looking at vehicles on the roads: a survey of vision-based vehicle detection, tracking, and behavior analysis’, IEEE Trans. Intell. Transp. Syst., 2013, 14, (4), pp. 1773–1795.
    21. 21)
      • 18. Blanz, V., Vetter, T.: ‘A morphable model for the synthesis of 3D faces’. 26th Int. Conf. Computer Graphics and Interactive Techniques (SIGGRAPH'99), Los Angeles, CA, USA, 8–13 August 1999, pp. 187–194.
    22. 22)
      • 27. Geiger, A., Lenz, P., Urtasun, R.: ‘Are you ready for autonomous driving? The KITTI vision benchmark suite’. 2012 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Providence, RI, 16–21 June 2012, pp. 3354–3361.
    23. 23)
      • 14. Weinzaefel, P., Jégou, H., Pérez, P.: ‘Reconstructing an image from its local descriptors’. 2011 IEEE Conf. Computer Vision and Pattern Recognition (CVPR), Providence, RI, 20–25 June 2011, pp. 337–344.
    24. 24)
      • 9. Paisitkariangkrai, S., Shen, C., Zhang, J.: ‘Performance evaluation of local features in human classification and detection’, IET Comput. Vis., 2008, 2, (4), pp. 236–246.
    25. 25)
      • 12. Vondrick, C., Khosla, A., Malisiewicz, T., et al: ‘HOGgles: visualizing object detection features’. 2013 IEEE Int. Conf. Computer Vision (ICCV), Sydney, NSW, 1–8 December 2013, pp. 1–8.
    26. 26)
      • 36. Mohamed, A.-R., Hinton, G., Penn, G.: ‘Understanding how deep belief networks perform acoustic modeling’. 2012 IEEE Int. Conf. Acoustics, Speech and Signal Processing (ICASSP), Kyoto, Japan, 25–30 March 2012, pp. 4273–4276.
    27. 27)
      • 3. Jung, H.G., Kim, G.: ‘Support vector number reduction: survey and experimental evaluations’, IEEE Trans. Intell. Transp. Syst., 2014, 15, (2), pp. 463–476.
    28. 28)
      • 17. Šafarič, R., Rojko, A.: ‘3.3.12 advantages and disadvantages of genetic algorithms’, Intelligent Techniques in Mechatronics, 2006. [Online]. Available: http://www.ro.feri.uni-mb.si/predmeti/int_reg/Predavanja/Eng/3.Genetic%20algorithm/_18.html.
    29. 29)
      • 37. Parikh, D., Lawrence Zitnick, C.: ‘Human-debugging of machines’. Second Workshop on Computational Social Science and the Wisdom of Crowds, Sierra Nevada, Spain, 7 October 2011, pp. 1–5.
    30. 30)
      • 21. Jung, H.G., Kim, J.: ‘Constructing a pedestrian recognition system with a public open database, without the necessity of re-training: an experimental study’, Pattern Anal. Appl., 2010, 13, (2), pp. 223–233.
    31. 31)
      • 2. Burges, C.J.C.: ‘Simplified support vector decision rules’. Proc. 13th Int. Conf. Machine Learning, 1996, pp. 71–77.
    32. 32)
      • 31. Ohn-Bar, E., Trivedi, M.M.: ‘Learning to detect vehicles by clustering appearance patterns’, IEEE Trans. Intell. Transp. Syst., 2015, 16, (5), pp. 2511–2521.
    33. 33)
      • 33. Chang, C.-C., Lin, C.-J.: ‘LIBSVM: a library for support vector machines’, ACM Trans. Intell. Syst. Technol., 2011, 2, (3), pp. 27:1–27:27. [Online]. Available: http://www.csie.ntu.edu.tw/~cjlin/libsvm/.
    34. 34)
      • 10. Dalad, N., Triggs, B.: ‘Histograms of oriented gradients for human detection’. Proc. IEEE Comput. Soc. Conf. Computer Vision and Pattern Recognition, San Diego, CA, USA, June 25, 2005, vol. 1, pp. 886–893.
    35. 35)
      • 35. Zeiler, M.D., Fergus, R.: ‘Visualizing and understanding convolutional networks’. 13th European Conf. Computer Vision (ECCV), Zurich, Switzerland, September 6–12, 2014, pp. 818–833.
    36. 36)
      • 29. Pepik, B., Stark, M., Gehler, P., et al: ‘Multi-view and 3D deformable part models’, IEEE Trans. Pattern Anal. Mach. Intell., 2015, 37, (11), pp. 2232–2245.
    37. 37)
      • 11. Jung, H.G.: ‘Support vector number reduction by extending iterative preimage addition using genetic algorithm-based preimage estimation’, Pattern Recognit. Lett., 2016, 84, pp. 43–48.
http://iet.metastore.ingenta.com/content/journals/10.1049/iet-cvi.2016.0317
Loading

Related content

content/journals/10.1049/iet-cvi.2016.0317
pub_keyword,iet_inspecKeyword,pub_concept
6
6
Loading
Print this page
This is a required field
Please enter a valid email address