Analysis of single- and dual-dictionary strategies in pedestrian classification

Original Article
  • 38 Downloads

Abstract

Sparse coding has recently been a hot topic in visual tasks in image processing and computer vision. It has applications and brings benefits in reconstruction-like tasks and in classification-like tasks as well. However, regarding binary classification problems, there are several choices to learn and use dictionaries that have not been studied. In particular, how single-dictionary and dual-dictionary approaches compare in terms of classification performance is largely unexplored. We compare three single-dictionary strategies and two dual-dictionary strategies for the problem of pedestrian classification (“pedestrian” vs “background” images). In each of these five cases, images are represented as the sparse coefficients induced from the respective dictionaries, and these coefficients are the input to a regular classifier both for training and subsequent classification of novel unseen instances. Experimental results with the INRIA pedestrian dataset suggest, on the one hand, that dictionaries learned from only one of the classes, even from the background class, are enough for obtaining competitive good classification performance. On the other hand, while better performance is generally obtained when instances of both classes are used for dictionary learning, the representation induced by a single dictionary learned from a set of instances from both classes provides comparable or even superior performance over the representations induced by two dictionaries learned separately from the pedestrian and background classes.

Keywords

Dictionary learning Sparse representations Binary classification Pedestrian classification 

Notes

Acknowledgements

The collaboration of Á. Hernández-Górriz in an earlier stage of this work is acknowledged. This work is partly funded by the Spanish Ministerio de Economía, Industria y Competitividad (TIN2013-46522-P), and Generalitat Valenciana (PROMETEOII/2014/062).

References

  1. 1.
    Alfaro A, Mery D, Soto A (2016) Action recognition in video using sparse coding and relative features. In: Computer vision and pattern recognition (CVPR), pp 2688–2697Google Scholar
  2. 2.
    Boughorbel S, Jarray F, El-Anbari M (2017) Optimal classifier for imbalanced data using Matthews correlation coefficient metric. PLoS ONE 12(6):e0177678.  https://doi.org/10.1371/journal.pone.0177678 CrossRefGoogle Scholar
  3. 3.
    Bryt O, Elad M (2008) Compression of facial images using the K-SVD algorithm. J Vis Commun Image Represent 19(4):270–282CrossRefGoogle Scholar
  4. 4.
    Castrodad A, Sapiro G (2012) Sparse modeling of human actions from motion imagery. Int J Comput Vis (IJCV) 100(1):1–15CrossRefGoogle Scholar
  5. 5.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. In: Computer vision and pattern recognition (CVPR)Google Scholar
  6. 6.
    Deng W, Hu J, Guo J (2012) Extended SRC: undersampled face recognition via intraclass variant dictionary. IEEE Trans Pattern Anal Mach Intell (PAMI) 34(9):1864–1870CrossRefGoogle Scholar
  7. 7.
    Deng W, Hu J, Guo J (2013) In defense of sparsity based face recognition. In: Computer vision and pattern recognition (CVPR)Google Scholar
  8. 8.
    Elad M (2010) Sparse and redundant representations: from theory to applications in signal and image processing. Springer, BerlinCrossRefMATHGoogle Scholar
  9. 9.
    Elad M, Aharon M (2006) Image denoising via learned dictionaries and sparse representation. In: Computer vision and pattern recognition (CVPR)Google Scholar
  10. 10.
    Fadili MJ, Starck JL, Murtagh F (2009) Inpainting and zooming using sparse representations. Comput J 52:64–79CrossRefGoogle Scholar
  11. 11.
    Gao Y, Ma J, Yuille AL (2017) Semi-supervised sparse representation based classification for face recognition with insufficient labeled samples. IEEE Trans Image Process 26(5):2545–2560MathSciNetCrossRefGoogle Scholar
  12. 12.
    Hawe S, Seibert M, Kleinsteuber M (2013) Separable dictionary learning. In: Computer vision and pattern recognition (CVPR), pp 438–445Google Scholar
  13. 13.
    Howse J, Joshi P, Beyeler M (2016) OpenCV: Computer Vision Projects with Python. PacktGoogle Scholar
  14. 14.
    Hsieh SH, Lu CS, Pei SC (2014) 2D sparse dictionary learning via tensor decomposition. In: IEEE global conference on signal and information processing (GlobalSIP), pp 492–496Google Scholar
  15. 15.
    Hunter JD (2007) Matplotlib: a 2D graphics environment. Comput Sci Eng 9(3):90–95CrossRefGoogle Scholar
  16. 16.
    Jiang Z, Lin Z, Davis LS (2013) Label consistent K-SVD: learning a discriminative dictionary for recognition. IEEE Trans Pattern Anal Mach Intell (PAMI) 35(11):2651–2664CrossRefGoogle Scholar
  17. 17.
    Krishna Vinay G, Haque SM, Venkatesh Babu R, Ramakrishnan K (2012) Human detection using sparse representation. In: IEEE international conference on acoustics, speech and signal processing (ICASSP)Google Scholar
  18. 18.
    Liang F, Tang S, Zhang Y, Xu Z, Li J (2014) Pedestrian detection based on sparse coding and transfer learning. Mach Vis Appl (MVA) 25(7):1697–1709CrossRefGoogle Scholar
  19. 19.
    Liu W, Tao D, Cheng J, Tang Y (2014) Multiview Hessian discriminative sparse coding for image annotation. Comput Vis Image Underst (CVIU) 118(Supplement C):50–60CrossRefGoogle Scholar
  20. 20.
    Liu W, Liu H, Tao D, Wang Y, Lu K (2015) Multiview Hessian regularized logistic regression for action recognition. Sig Process 110:101–107CrossRefGoogle Scholar
  21. 21.
    Liu W, Zha ZJ, Wang Y, Lu K, Tao D (2016) \(p\)-Laplacian regularized sparse coding for human activity recognition. IEEE Trans Ind Electron 63(8):5120–5129Google Scholar
  22. 22.
    Liu Y, Lasang P, Siegel M, Sun Q (2016) Multi-sparse descriptor: a scale invariant feature for pedestrian detection. Neurocomputing 184:55–65CrossRefGoogle Scholar
  23. 23.
    Lou Y, Bertozzi AL, Soatto S (2011) Direct sparse deblurring. J Math Imaging Vis 39(1):1–12MathSciNetCrossRefMATHGoogle Scholar
  24. 24.
    Mairal J, Elad M, Sapiro G (2008) Sparse representation for color image restoration. IEEE Trans Image Process 17(1):53–69MathSciNetCrossRefMATHGoogle Scholar
  25. 25.
    Mairal J, Bach F, Ponce J, Sapiro G (2009) Online dictionary learning for sparse coding. In: International conference on machine learning (ICML)Google Scholar
  26. 26.
    Mairal J, Bach F, Ponce J, Sapiro G (2010) Online learning for matrix factorization and sparse coding. J Mach Learn Res 11:19–60MathSciNetMATHGoogle Scholar
  27. 27.
    Mairal J, Bach F, Ponce J (2012) Task-driven dictionary learning. IEEE Trans Pattern Anal Mach Intell (PAMI) 34(4):791–804CrossRefGoogle Scholar
  28. 28.
    Mairal J, Bach F, Ponce J (2014) Sparse modeling for image and vision processing. Found Trends Comput Graph Vis 8(2–3):85–283CrossRefMATHGoogle Scholar
  29. 29.
    Mallat S, Zhang Z (1993) Matching pursuits with time-frequency dictionaries. IEEE Trans Signal Process 41(12):3397–3415CrossRefMATHGoogle Scholar
  30. 30.
    Matthews BW (1975) Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochim Biophys Acta (BBA) Protein Struct 405(2):442–451CrossRefGoogle Scholar
  31. 31.
    Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay E (2011) Scikit-learn: machine learning in Python. J Mach Learn Res 12:2825–2830MathSciNetMATHGoogle Scholar
  32. 32.
    Ren X, Ramanan D (2013) Histograms of sparse codes for object detection. In: Computer vision and pattern recognition (CVPR)Google Scholar
  33. 33.
    Rigamonti R, Brown M, Lepetit V (2011) Are sparse representations really relevant for image classification? In: Computer vision and pattern recognition (CVPR)Google Scholar
  34. 34.
    Rubinstein R, Zibulevsky M, Elad M (2010) Double sparsity: learning sparse dictionaries for sparse signal approximation. IEEE Trans Signal Process 58(3):1553–1564MathSciNetCrossRefGoogle Scholar
  35. 35.
    Sahay A (2016) Data visualization, vol I. Business Expert Press, New YorkGoogle Scholar
  36. 36.
    Serra-Toro C, Hernández-Górriz Á, Traver VJ (2017) Strategies of dictionary usages for sparse representations for pedestrian classification. Pattern Recogn Image Anal IbPRIA 2017:96–103MathSciNetCrossRefGoogle Scholar
  37. 37.
    Shekhar S, Patel VM, Nguyen HV, Chellappa R (2015) Coupled projections for adaptation of dictionaries. IEEE Trans Image Process 24(10):2941–2954MathSciNetCrossRefGoogle Scholar
  38. 38.
    Shi Q, Eriksson A, van den Hengel A, Shen C (2011) Is face recognition really a compressive sensing problem? In: Computer vision and pattern recognition (CVPR)Google Scholar
  39. 39.
    Singh K, Vishwakarma DK, Walia GS (2017) Blind image deblurring via gradient orientation-based clustered coupled sparse dictionaries. Pattern Anal Appl (PAA).  https://doi.org/10.1007/s10044-017-0652-5
  40. 40.
    Sironi A, Tekin B, Rigamonti R, Lepetit V, Fua P (2015) Learning separable filters. IEEE Trans Pattern Anal Mach Intell (PAMI) 37(1):94–106CrossRefGoogle Scholar
  41. 41.
    Sivalingam R, Somasundaram G, Morellas V, Papanikolopoulos N, Lotfallah OA, Park Y (2010) Dictionary learning based object detection and counting in traffic scenes. In: International conference on distributed smart camerasGoogle Scholar
  42. 42.
    Spratling MW (2014) Classification using sparse representations: a biologically plausible approach. Biol Cybern 108(1):61–73MathSciNetCrossRefGoogle Scholar
  43. 43.
    Sulam J, Ophir B, Zibulevsky M, Elad M (2016) Trainlets: dictionary learning in high dimensions. IEEE Trans Signal Process 64(12):3180–3193MathSciNetCrossRefGoogle Scholar
  44. 44.
    Sun R, Zhang G, Yan X, Gao J (2016) Robust pedestrian classification based on hierarchical kernel sparse representation. Sensors 16(8):1296CrossRefGoogle Scholar
  45. 45.
    Wang W, Yan Y, Zhang L, Hong R, Sebe N (2016) Collaborative sparse coding for multiview action recognition. IEEE Multimedia 23(4):80–87CrossRefGoogle Scholar
  46. 46.
    Wilcoxon F (1945) Individual comparisons by ranking methods. Biom Bull 1(6):80–83CrossRefGoogle Scholar
  47. 47.
    Wright J et al (2009) Robust face recognition via sparse representation. IEEE Trans Pattern Anal Mach Intell (PAMI) 31(2):210–227CrossRefGoogle Scholar
  48. 48.
    Wright J et al (2010) Sparse representation for computer vision and pattern recognition. Proc IEEE 98(6):1031–1044CrossRefGoogle Scholar
  49. 49.
    Xie YF, Su SZ, Li SZ (2010) A pedestrian classification method based on transfer learning. In: 2010 International conference on image analysis and signal processing, pp 420–425Google Scholar
  50. 50.
    Xu R, Jiao J, Zhang B, Ye Q (2012) Pedestrian detection in images via cascaded \(L_1\)-norm minimization learning method. Pattern Recogn 45(7):2573–2583CrossRefGoogle Scholar
  51. 51.
    Yang J, Wright J, Huang TS, Ma Y (2010) Image super-resolution via sparse representation. IEEE Trans Image Process 19(11):2861–2873MathSciNetCrossRefMATHGoogle Scholar
  52. 52.
    Yang M, Zhang L, Feng X, Zhang D (2011) Fisher discrimination dictionary learning for sparse representation. In: International conference on computer vision (ICCV), pp 543–550Google Scholar
  53. 53.
    Yao T, Wang Z, Xie Z, Gao J, Feng DD (2017) Learning universal multiview dictionary for human action recognition. Pattern Recogn 64:236–244CrossRefGoogle Scholar
  54. 54.
    Zhang L, Zhou WD, Chang PC, Liu J, Yan Z, Wang T, Li FZ (2012) Kernel sparse representation-based classifier. IEEE Trans Signal Process 60(4):1684–1695MathSciNetCrossRefGoogle Scholar
  55. 55.
    Zheng J, Jiang Z, Chellappa R (2016) Cross-view action recognition via transferable dictionary learning. IEEE Trans Image Process 25(6):2542–2556MathSciNetCrossRefGoogle Scholar
  56. 56.
    Zheng M, Bu J, Chen C, Wang C, Zhang L, Qiu G, Cai D (2011) Graph regularized sparse coding for image representation. IEEE Trans Image Process 20(5):1327–1336MathSciNetCrossRefMATHGoogle Scholar
  57. 57.
    Zheng M, Bu J, Chen C (2014) Hessian sparse coding. Neurocomputing 123:247–254CrossRefGoogle Scholar
  58. 58.
    Zhu Q, Yeh M, Cheng K, Avidan S (2006) Fast human detection using a cascade of histograms of oriented gradients. In: Computer vision and pattern recognition (CVPR), pp 1491–1498Google Scholar
  59. 59.
    Zhu XX, Bamler R (2013) A sparse image fusion algorithm with application to pan-sharpening. IEEE Trans Geosci Remote Sens 51(5):2827–2836CrossRefGoogle Scholar

Copyright information

© Springer-Verlag London Ltd., part of Springer Nature 2018

Authors and Affiliations

  1. 1.Institute of New Imaging TechnologiesJaume-I UniversityCastellónSpain

Personalised recommendations