An ELM based local topology preserving hashing

  • Yang Liu
  • Lin FengEmail author
  • Shenglan Liu
  • Muxin Sun
Original Article


Hashing learning has become one of the most active research areas in computer vision and multimedia information retrieval with the explosively boosted data volume. Mainstream hashing methods adopt a two-stage hashing framework to realize hashing learning. That is, obtain low dimensional embedding and encode binary codes respectively. However, this kind of methods divides the dimensional reduction error and binary encoding loss apart, which is not beneficial to preserve the original data structure. Hence, we propose a local topology preserving hashing (LTPH) method to reduce the dimensional reduction error and binary encoding loss simultaneously. To clearly reveal the original data structure, Local Topology Preserving Embedding (LTPE) algorithm is proposed in this paper. LTPE utilizes the data similarity as well as the local geometry information to construct original data topology, which can effectively detect the original data structure. Nevertheless, LTPH is a transductive method, which is not suitable for large scale applications. Considering the outstanding global approximation ability and fast computation speed of Extreme Learning Machine (ELM), we propose an ELM based local topology preserving hashing (ELMLTPH) method to realize efficient hashing learning for large scale applications. With the facilitation of ELM, original data topology is effectively preserved to hamming space. Extensive image retrieval experiments are conducted on CIFAR, Caltech 101/256, Corel 10K and GIST-1M datasets, which demonstrate the superiority of ELMLTPH compared to several state-of-the-art hashing methods.


Hashing learning Extreme learning machine Topology preserving Large scale image retrieval 



This study was funded by National Natural Science Foundation of People’s Republic of China (61370200, 61672130, 61602082) and the Open Program of State Key Laboratory of Software Architecture, Item number SKLSAOP1701.

Compliance with ethical standards

Conflict of interest

Yang Liu, Lin Feng, Shenglan Liu and Muxin Sun declare that they have no conflict of interest.

Human and animals participants

This article does not contain any studies with human participants or animals performed by any of the authors.


  1. 1.
    Lin J, Yin J, Cai Z (2013) A secure and practical mechanism of outsourcing extreme learning machine in cloud computing. IEEE Intell Syst 28(6):35–38Google Scholar
  2. 2.
    Zhang D, Wang F, Si L (2011) Composite hashing with multiple information sources. In: Proceedings of the 34th international ACM SIGIR conference on research and development in information retrieval. ACM, Beijing, pp 225–234Google Scholar
  3. 3.
    Kong W, Li WJ, Guo M Manhattan hashing for large-scale image retrieval. In: Proceedings of the 35th international ACM SIGIR. ACM, Portland, pp 45–54Google Scholar
  4. 4.
    Zhong H, Miao C, Shen Z et al (2014) Comparing the learning effectiveness of BP, ELM, I-ELM, and SVM for corporate credit ratings. Neurocomputing 128:285–295CrossRefGoogle Scholar
  5. 5.
    Dridi A, Recupero DR (2017) Leveraging semantics for sentiment polarity detection in social media. Int J Mach Learn Cybern. (Early Access)CrossRefGoogle Scholar
  6. 6.
    Liu W, Wang J, Kumar S et al (2011) Hashing with graphs. In: Proceedings of the 28th international conference on machine learning (ICML-11), IMLS, Bellevue, pp 1–8Google Scholar
  7. 7.
    Gong Y, Lazebnik S, Gordo A (2013) Iterative quantization: a procrustean approach to learning binary codes for large-scale image retrieval. Pattern Anal Mach Intell IEEE Trans 35(12):2916–2929CrossRefGoogle Scholar
  8. 8.
    Gionis A, Indyk P, Motwani R (1999) Similarity search in high dimensions via hashing. VLDB 99(6):518–529Google Scholar
  9. 9.
    Datar M, Immorlica N, Indyk P et al (2004) Locality-sensitive hashing scheme based on p-stable distributions. In: Proceedings of the twentieth annual symposium on computational geometry. ACM, NewYork, pp 253–262Google Scholar
  10. 10.
    Raginsky M, Lazebnik S (2009) Locality-sensitive binary codes from shift-invariant kernels. In: Advances in Neural Information Processing Systems 22, NIPS, Vancouver, pp 1509–1517Google Scholar
  11. 11.
    Kulis B, Jain P, Grauman K (2009) Fast similarity search for learned metrics. Pattern Anal Mach Intell IEEE Trans 31(12):2143–2157CrossRefGoogle Scholar
  12. 12.
    Jin Z, Li C, Lin Y (2013) Density sensitive hashing. IEEE Trans Cybern 44(8):1362–1371CrossRefGoogle Scholar
  13. 13.
    Weiss Y, Torralba A, Fergus R (2009) Spectral hashing. Adv Neural Inform Process Syst, NIPS, Vancouver, pp 1753–1760Google Scholar
  14. 14.
    Wang J, Kumar S, Chang SF (2012) Semi-supervised hashing for large-scale search. Pattern Anal Mach Intell IEEE Trans 34(12):2393–2406CrossRefGoogle Scholar
  15. 15.
    Irie G, Li Z, Wu XM et al (2014) Locally linear hashing for extracting non-linear manifolds. In: Proceedings of the IEEE conference on computer vision and pattern recognition, IEEE, Columbus, pp 2115–2122Google Scholar
  16. 16.
    Liu Y, Bai X, Yang H (2015) Isometric mapping hashing. Graph-based representations in pattern recognition. Springer, New York, pp 325–334Google Scholar
  17. 17.
    Gui J, Liu T, Sun Z (2018) Fast supervised discrete hashing. IEEE Trans Pattern Anal Mach Intell 40(2):490–496CrossRefGoogle Scholar
  18. 18.
    Song J, Zhang H, Li X (2018) Self-supervised video hashing with hierarchical binary auto-encoder. IEEE Trans Image Process 27(7):3210–3221MathSciNetCrossRefGoogle Scholar
  19. 19.
    Zhao K, Lu H, Mei J (2014) Locality preserving hashing. AAAI, AAAI Press, Québec, pp 2874–2881Google Scholar
  20. 20.
    Yang L, Lin F, Shenglan L (2018) Global similarity preserving hashing. Soft Comput 22(7):2105–2120CrossRefGoogle Scholar
  21. 21.
    Ng WWY, Lv Y, Zeng Z (2017) Sequential conditional entropy maximization semi-supervised hashing for semantic image retrieval. Int J Mach Learn Cybern 8(2):571–586CrossRefGoogle Scholar
  22. 22.
    Zhang L, He Z, Liu Y (2017) Deep object recognition across domains based on adaptive extreme learning machine. Neurocomputing 239:194–203CrossRefGoogle Scholar
  23. 23.
    Zhang L, Zhang D (2017) Evolutionary cost-sensitive extreme learning machine. IEEE Trans Neural Netw Learn Syst 28(12):3045–3060MathSciNetCrossRefGoogle Scholar
  24. 24.
    Tang J, Deng C, Huang GB (2016) Extreme learning machine for multilayer perceptron. IEEE Trans Neural Netw Learn Syst 27(4):809–821MathSciNetCrossRefGoogle Scholar
  25. 25.
    Huang GB, Zhu QY, Siew CK (2005) Extreme learning machine: a new learning scheme of feedforward neural networks. In: Proceedinga of the IEEE International Joint Conference on Neural Networks, IEEE, Budapest, pp 985–990Google Scholar
  26. 26.
    Li MB, Huang GB, Saratchandran P (2005) Letters: fully complex extreme learning machine. Neurocomputing 68(1):306–314CrossRefGoogle Scholar
  27. 27.
    Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501CrossRefGoogle Scholar
  28. 28.
    Huang GB, Chen L, Siew CK (2006) Universal approximation using incremental constructive feedforward networks with random hidden nodes. IEEE Trans Neural Netw 17(4):879–892CrossRefGoogle Scholar
  29. 29.
    Chen L, Cui L, Huang R (2016) Bio-inspired neural network with application to license plate recognition: hysteretic ELM approach. Assembly Autom 36(2):172–178CrossRefGoogle Scholar
  30. 30.
    Liu S, Feng L, Liu Y, Wu J, Sun M, Wang W (2017) Robust discriminative extreme learning machine for relevance feedback in image retrieval. Multidimension Syst Signal Process 28(3):1071–1089CrossRefGoogle Scholar
  31. 31.
    Xizhao W, Weipeng C (2018) Non-iterative approaches in training feed-forward neural networks and their applications. Soft Comput.
  32. 32.
    Weipeng C, Zhong M, Xizhao W, Shubin C (2017) Improved bidirectional extreme learning machine based on enhanced random search. Memetic Comput.
  33. 33.
    Shixin Z, Xizhao W, Liying W (2017) Analysis on fast training speed of extreme learning machine and replacement policy. Int J Wireless Mobile Comput 13(4):314–322CrossRefGoogle Scholar
  34. 34.
    Shuxia L, Xizhao W, Guiqiang Z, Zhou X (2015) Effective algorithms of the Moore-Penrose inverse matrices for extreme learning machine. Intell Data Anal 19(4):743–760CrossRefGoogle Scholar
  35. 35.
    Huang GB (2014) An insight into extreme learning machines: random neurons, random features and kernels. Cogn Comput 6(3):376–390CrossRefGoogle Scholar
  36. 36.
    Huang GB, Chen L (2007) Letters: Convex incremental extreme learning machine. Neurocomputing 70(16):3056–3062CrossRefGoogle Scholar
  37. 37.
    Huang GB (2011) Extreme learning machines: a survey. Int J Mach Learn Cybern 2(2):107–122CrossRefGoogle Scholar
  38. 38.
    Wang X, Wang R, Chen X (2018) Discovering the relationship between generalization and uncertainty by incorporating complexity of classification. IEEE Trans Cybern 48(2):703–715CrossRefGoogle Scholar
  39. 39.
    Wang X, Zhang T, Wang R (2017) Non-iterative deep learning: incorporating restricted boltzmann machine into multilayer random weight neural networks. IEEE Trans Syst Man Cybern Syste. IEEE Early Access Articles)
  40. 40.
    Wang Z, Wang X (2018) A deep stochastic weight assignment network and its application to chess playing. J Parallel Distrib Computi 117:205–211CrossRefGoogle Scholar
  41. 41.
    Huang Z, Wang X (2018) Sensitivity of data matrix rank in non-iterative training. Neurocomputing 313:386–391CrossRefGoogle Scholar
  42. 42.
    Cao W, Wang X, Zhong M et al (2018) A review on neural networks with random weights. Neurocomputing 275:278–287CrossRefGoogle Scholar
  43. 43.
    Hong Z, Tsang EC, Wang X et al (2017) Monotonic classification extreme learning machine. Neurocomputing 225(C):205–213Google Scholar
  44. 44.
    Cao J, Chen T, Fan J (2014) Fast online learning algorithm for landmark recognition based on BoW framework. In: Industrial electronics and applications, IEEE, Hangzhou, pp 1163–1168Google Scholar
  45. 45.
    Huang G, Song S, Gupta JND (2014) Semi-supervised and unsupervised extreme learning machines. IEEE Trans Cybern 44(12):2405–2417CrossRefGoogle Scholar
  46. 46.
    Zhang R, Lan Y, Huang GB (2012) Universal approximation of extreme learning machine with adaptive growth of hidden nodes. IEEE Trans Neural Netw Learn Syst 23(2):365–371CrossRefGoogle Scholar
  47. 47.
    Iosifidis A, Tefas A, Pitas I (2013) Minimum class variance extreme learning machine for human action recognition. IEEE Trans Circuits Syst Video Technol 23(11):1968–1979CrossRefGoogle Scholar
  48. 48.
    Zhang L, Liu Y, Deng P (2017) Odor recognition in multiple E-nose systems with cross-domain discriminative subspace learning. IEEE Trans Instrum Measure 66(7):1679–1692CrossRefGoogle Scholar
  49. 49.
    Iosifidis A, Tefas A, Pitas I (2016) Graph embedded extreme learning machine. IEEE Trans Cybern 46(1):311–324CrossRefGoogle Scholar
  50. 50.
    Shen F, Shen C, Shi Q et al (2013) Inductive hashing on manifolds. In: Proceedings of the IEEE conference on computer vision and pattern recognition, IEEE, Portland, pp 1562–1569Google Scholar
  51. 51.
    Zhang P, Wee CY, Niethammer M, et al (2013) Large deformation image classification using generalized locality-constrained linear coding. In: International conference on medical image computing and computer-assisted intervention. Springer, Berlin, pp 292–299Google Scholar
  52. 52.
    Li J, Wang JZ (2003) Automatic linguistic indexing of pictures by a statistical modeling approach. Pattern Anal Mach Intell IEEE Trans 25(9):1075–1088CrossRefGoogle Scholar
  53. 53.
    Wang JZ, Li J, Wiederhold G (1999) SIMPLIcity: semantics-sensitive integrated matching for picture libraries. IEEE Trans Pattern Anal Mach Intell 23(9):171–193Google Scholar
  54. 54.
    Fei-Fei L, Fergus R, Perona P (2007) Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Comput Vis Image Underst 106(1):59–70CrossRefGoogle Scholar
  55. 55.
    Jegou H, Douze M, Schmid C (2011) Product quantization for nearest neighbor search. IEEE Trans Pattern Anal Mach Intell 33(1):117–128CrossRefGoogle Scholar
  56. 56.
    Wang H, Feng L, Zhang J (2016) Semantic discriminative metric learning for image similarity measurement. IEEE Trans Multimed 18(8):1579–1589CrossRefGoogle Scholar
  57. 57.
    Qiao H, Zhang P (2013) An explicit nonlinear mapping for manifold learning. IEEE Trans Cybern 43(1):51–63CrossRefGoogle Scholar
  58. 58.
    Qiao H, Peng J-G (2003) A reference model approach to stability analysis of neural networks. IEEE Trans Syst Man Cybern Part B Cybern 33(6):925–936CrossRefGoogle Scholar
  59. 59.
    Zhang L, Wang X, Huang GB et al (2018) Taste Recognition in E-Tongue Using Local Discriminant Preservation Projection. IEEE Trans Cybern. (IEEE Early Access Articles)
  60. 60.
    Oliva A, Torralba A (2001) Modeling the shape of the scene: a holistic representation of the spatial envelope. Int J Comput Vis 42(3):145–175CrossRefGoogle Scholar
  61. 61.
    Belkin M, Niyogi P (2003) Laplacian eigenmaps for dimensionality reduction and data representation. Neural Comput 15(6):1373–1396CrossRefGoogle Scholar
  62. 62.
    Izenman AJ (2013) Linear discriminant analysis. Modern multivariate statistical techniques. Springer, New York, pp 237–280CrossRefGoogle Scholar
  63. 63.
    Strecha C, Bronstein A, Bronstein M (2012) LDAHash: improved matching with smaller descriptors. IEEE Trans Pattern Anal Mach Intell 34(1):66–78CrossRefGoogle Scholar
  64. 64.
    Roweis ST, Saul LK (2000) Nonlinear dimensionality reduction by locally linear embedding. Science 290(5500):2323–2326CrossRefGoogle Scholar
  65. 65.
    Wen Z, Yin W (2013) A feasible method for optimization with orthogonality constraints. Math Program 142(1–2):397–434MathSciNetCrossRefGoogle Scholar
  66. 66.
    Wong TT, Yang NY (2017) Dependency analysis of accuracy estimates in k-fold cross validation. IEEE Trans Knowl Data Eng 29(11):2417–2427CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Faculty of Electronic Information and Electrical EngineeringDalian University of TechnologyDalianChina
  2. 2.School of Innovation and EntrepreneurshipDalian University of TechnologyDalianChina
  3. 3.State Key Laboratory of Software Architecture (Neusoft Corporation)ShenyangChina

Personalised recommendations