Multimedia Tools and Applications

, Volume 78, Issue 5, pp 6033–6047 | Cite as

Sparse coding based few learning instances for image retrieval

  • Hao Wu
  • Rongfang Bie
  • Junqi Guo
  • Xin Meng
  • Shenling WangEmail author


Hundreds of thousands of images that are widely used in different fields of modern life have appeared in recent years. The process of retrieving the target images from a big database has become a meaningful problem. As one of the classical techniques of computer vision, image retrieval could effectively solve the problem. However, in most cases, high-quality retrieval results are supported by a large number of learning instances. It not only occupies much computing resources but also wastes much human resource. Moreover, much time is wasted in the process of retrieval. To solve the abovementioned problems, we proposed a sparse coding based few learning instances model for retrieval. Concretely, cross-validation sparse coding representation, sparse coding based instance distance and improved KNN model are combined which directly contributes to build up the previous model. It could reduce the number of learning instances significantly through the selection of optimized learning instances while preserving the retrieval accuracy. At last, a database using a large number of images was set up. The experimental results using the database show our method’s superiority in preserving the quality of retrieval with the reduction of learning instances.


Image retrieval Cross-validation sparse coding representation Sparse coding based instance distance KNN AP value AUC value 



This research is sponsored by Fundamental Research Funds for the Central Universities (No.2016NT14), National Natural Science Foundation of China (No.61601033) and Beijing Advanced Innovation Center for Future Education (BJAICFE2016IR-004).


  1. 1.
    Alham NK et al (2011) A MapReduce-based distributed SVM algorithm for automatic image annotation. Comput Math Appl 62(7):2801–2811zbMATHCrossRefGoogle Scholar
  2. 2.
    Arbelaez P, Fowlkes C, Martin D (2007) The berkeley segmentation dataset and benchmark. see http://www.eecs.berkeley.Edu/Research/Projects/CS/vision/bsds
  3. 3.
    Arora S et al (2015) Simple, efficient, and neural algorithms for sparse coding. arXiv preprint arXiv:1503.00778Google Scholar
  4. 4.
    Bay H, Ess A, Tuytelaars T et al (2008) Speeded-up robust features (SURF) [J]. Comput Vis Image Underst 110(3):346–359CrossRefGoogle Scholar
  5. 5.
    Berens J, Finlayson GD, Qiu G (2000) Image indexing using compressed colour histograms [J]. IEEE Vision Image Signal Process 147(4):349–355CrossRefGoogle Scholar
  6. 6.
    Boughorbel S, Tarel J-P, Boujemaa N (2005) Generalized histogram intersection kernel for image recognition. IEEE International conference on image processing 2005. vol 3. IEEEGoogle Scholar
  7. 7.
    Bulò SR, Rabbi M, Pelillo M (2011) Content-based image retrieval with relevance feedback using random walks [J]. Pattern Recogn 44(9):2109–2122CrossRefGoogle Scholar
  8. 8.
    Celik C, Bilge HS (2017) Content based image retrieval with sparse representations and local feature descriptors: a comparative study [J]. Pattern Recogn 68:1–13CrossRefGoogle Scholar
  9. 9.
    Cui Z, Ge SS, Cao Z et al (2015) Analysis of different sparsity methods in constrained RBM for sparse representation in cognitive robotic perception [J]. J Intell Robot Syst 80(1):121–132CrossRefGoogle Scholar
  10. 10.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection [C]. Computer Vision and Pattern Recognition, 2005. CVPR 2005. IEEE computer society conference on IEEE, pp 886–893Google Scholar
  11. 11.
    Dimitrovski I, Kocev D, Loskovska S et al (2016) Improving bag-of-visual-words image retrieval with predictive clustering trees [J]. Inf Sci 329:851–865CrossRefGoogle Scholar
  12. 12.
    Griffin G, Holub A, Perona P (2007) Caltech-256 object category dataset. Technical Report, California Institute of Technology, PasadenaGoogle Scholar
  13. 13.
    Guo Y et al (2016) Deep learning for visual understanding: a review. Neurocomputing 187:27–48CrossRefGoogle Scholar
  14. 14.
    He Z, You X, Yuan Y (2009) Texture image retrieval based on non-tensor product wavelet filter banks [J]. Signal Process 89(8):1501–1510zbMATHCrossRefGoogle Scholar
  15. 15.
    He K, Zhang X, Ren S et al (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition [C]. In: European conference on computer vision. Springer, Cham, pp 346–361Google Scholar
  16. 16.
    Hinton GE, Osindero S, Teh Y-W (2006) A fast learning algorithm for deep belief nets. Neural Comput 18(7):1527–1554MathSciNetzbMATHCrossRefGoogle Scholar
  17. 17.
    Hsieh C-J et al (2008) A dual coordinate descent method for large-scale linear SVM. Proceedings of the 25th international conference on Machine learning. ACMGoogle Scholar
  18. 18.
    Joutou T, Yanai K (2009) A food image recognition system with multiple kernel learning. 2009 16th IEEE international conference on image processing (ICIP). IEEEGoogle Scholar
  19. 19.
    Kamath U, Shehu A, De Jong K (2010) Using evolutionary computation to improve svm classification. IEEE Congress on Evolutionary Computation. IEEEGoogle Scholar
  20. 20.
    Kramer O (2013) K-nearest neighbors. Dimensionality reduction with unsupervised nearest neighbors. Springer Berlin Heidelberg, pp 13–23zbMATHCrossRefGoogle Scholar
  21. 21.
    Krizhevsky A, Hinton G (2009) Learning multiple layers of features from tiny images. Technical Report, University of TorontoGoogle Scholar
  22. 22.
    Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems. CrossRefGoogle Scholar
  23. 23.
    Kundu MK, Chowdhury M (2015) Bulò S R. A graph-based relevance feedback mechanism in content-based image retrieval [J]. Knowl-Based Syst 73:254–264CrossRefGoogle Scholar
  24. 24.
    Lampert CH, Nickisch H, Harmeling S (2009) Learning to detect unseen object classes by between-class attribute transfer. In: Pro. IEEE Conference on Computer vision and pattern recognition, pp 951–958, IEEE, Miami, FLGoogle Scholar
  25. 25.
    Lazebnik S, Schmid C, Ponce J (2006) Beyond bags of features: spatial pyramid matching for recognizing natural scene categories. Computer Vision and Pattern Recogn, 2006 IEEE computer society conference on vol 2. IEEEGoogle Scholar
  26. 26.
    Li Y, Bie R, Zhang C et al (2017) Optimized learning instance-based image retrieval [J]. Multimed Tools Appl 76(15):16749–16766CrossRefGoogle Scholar
  27. 27.
    Lowe DG (2004) Distinctive image features from Scale-Invariant Keypoints [J]. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  28. 28.
    Lu X, Zheng X, Li X (2017) Latent semantic minimal hashing for image retrieval. IEEE Trans Image Process 26(1):355–368MathSciNetzbMATHCrossRefGoogle Scholar
  29. 29.
    Mairal J, Bach F, Ponce J (2014) Sparse Modeling for Image and Vision Processing [J]. Found Trends Comput Graph Vision 8(2):85–283zbMATHCrossRefGoogle Scholar
  30. 30.
    Moustakidis S et al (2012) SVM-based fuzzy decision trees for classification of high spatial resolution Remote Sens images. IEEE Trans Geosci Remote Sens 50(1):149–169CrossRefGoogle Scholar
  31. 31.
    Munajat MDE, Widyantoro DH, Munir R (2016) Road detection system based on RGB histogram filterization and boundary classifier [C]. International conference on advanced computer science and information systems. IEEE, pp 195–200Google Scholar
  32. 32.
    Ngiam J, Chen Z, Koh P W et al (2011) Learning deep energy models [C]. In: Proceedings of the 28th international conference on machine learning (ICML-11), Bellevue, WA, USA, pp 1105–1112Google Scholar
  33. 33.
    Ojala T, Pietikainen M, Harwood D (2002) Performance evaluation of texture measures with classification based on Kullback discrimination of distributions [C]. Iapr International Conference on Pattern Recognition, 1994. Vol. 1 - Conference A: Computer Vision & Image Processing. IEEE, vol 1, pp 582–585Google Scholar
  34. 34.
    Pal M, Foody GM (2010) Feature selection for classification of hyperspectral data by SVM [J]. IEEE Trans Geosci Remote Sens 48(5):2297–2307CrossRefGoogle Scholar
  35. 35.
    Perronnin F, Sánchez J, Mensink T (2010) Improving the fisher kernel for large-scale image classification [C]. In: European conference on computer vision. Springer, Berlin, Heidelberg, pp 143–156CrossRefGoogle Scholar
  36. 36.
    Poultney C, Chopra S, Cun YL (2006) Efficient learning of sparse representations with an energy-based model. In: Advances in neural information processing systems, Vancouver, BC, CanadaGoogle Scholar
  37. 37.
    Qi X, Han Y (2007) Incorporating multiple SVMs for automatic image annotation. Pattern Recogn 40(2):728–741MathSciNetzbMATHCrossRefGoogle Scholar
  38. 38.
    Radenović F, Tolias G, Chum O (2016) CNN image retrieval learns from BoW: unsupervised fine-tuning with hard examples [C]. European conference on computer vision. Springer, Cham pp 3–20CrossRefGoogle Scholar
  39. 39.
    Rui Y, Huang TS, Chang S-F (1999) Image retrieval: current techniques, promising directions, and open issues. J Vis Commun Image Represent 10(1):39–62CrossRefGoogle Scholar
  40. 40.
    Russell BC et al (2008) LabelMe: a database and web-based tool for image annotation. Int J Comput Vis 77(1–3):157–173CrossRefGoogle Scholar
  41. 41.
    Salakhutdinov R, Hinton GE (2009) Deep Boltzmann machines. In: International conference on artificial intelligence and statistics (AISTATS), vol 1Google Scholar
  42. 42.
    Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556Google Scholar
  43. 43.
    Smeulders AWM, Worring M, Santini S et al (2000) Content-based image retrieval at the end of the early years [J]. IEEE Trans Pattern Anal Mach Intell 22(12):1349–1380CrossRefGoogle Scholar
  44. 44.
    Szegedy C et al (2015) Going deeper with convolutions. Proc IEEE Conf Comput Vis Pattern RecognitGoogle Scholar
  45. 45.
    Tarabalka Y et al (2010) SVM-and MRF-based method for accurate classification of hyperspectral images. IEEE Geosci Remote Sens Lett 7(4):736–740CrossRefGoogle Scholar
  46. 46.
    Van Ginneken B, Koenderink JJ, Dana KJ (1999) Texture histograms as a function of irradiation and viewing direction [J]. Int J Comput Vis 31(2–3):169–184CrossRefGoogle Scholar
  47. 47.
    Vedaldi A, Zisserman A (2011) Image Classification Practical,
  48. 48.
    Wang G, Forsyth D, Hoiem D (2010) Comparative object similarity for improved recognition with few or no examples. In: IEEE conference on computer vision and pattern recognition, pp 3525–3532, IEEE, San Francisco, CAGoogle Scholar
  49. 49.
    Wu H, Miao Z, Wang Y et al (2015) Optimized recognition with few instances based on semantic distance [J]. Vis Comput 31(4):367–375CrossRefGoogle Scholar
  50. 50.
    Wu H et al (2015) Recognition improvement through the optimisation of learning instances. IET Comput Vis 9(3):419–427CrossRefGoogle Scholar
  51. 51.
    Xiaoqiang L, Chen Y, Li X (2018) Hierarchical recurrent neural hashing for image retrieval with hierarchical convolutional features. IEEE Trans Image Process 27(1):106–120MathSciNetzbMATHCrossRefGoogle Scholar
  52. 52.
    Yang J, Yu K, Gong Y et al (2009) Linear spatial pyramid matching using sparse coding for image classification [C]. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, Miami, pp 1794–1801Google Scholar
  53. 53.
    You X, Li Q, Tao D et al (2014) Local metric learning for exemplar-based object detection [J]. IEEE Trans Circuits Syst Video Technol 24(8):1265–1276CrossRefGoogle Scholar
  54. 54.
    Yu J et al (2015) Learning to rank using user clicks and visual features for image retrieval. IEEE Trans Cybern 45(4):767–779CrossRefGoogle Scholar
  55. 55.
    Zeiler MD, Fergus R (2014) Visualizing and understanding convolutional networks. European Conference on Computer Vision. Springer International PublishingGoogle Scholar

Copyright information

© Springer Science+Business Media, LLC, part of Springer Nature 2018

Authors and Affiliations

  • Hao Wu
    • 1
  • Rongfang Bie
    • 1
  • Junqi Guo
    • 1
  • Xin Meng
    • 2
  • Shenling Wang
    • 1
    Email author
  1. 1.College of Information Science and TechnologyBeijing Normal UniversityBeijingChina
  2. 2.Electric Power Planning & Engineering InstituteBeijingChina

Personalised recommendations