Research of commodity recommendation workflow based on LSH algorithm

  • Liu Dongsu 
  • Huo Chenhui 
  • Yan Hao 


This paper joins the image-matching module into the hybrid recommendation system and constructs its workflow, which fuses image features and hybrid recommendation algorithms to improve diversity of advice result. SIFT feature extracted was used as the standard of image matching, improved LSH algorithm based on p-stable distribution to implement image matching and searching module for high dimensional and huge image set, then redesigned the workflow of existing commodity recommendation system combined with the proposed image matching module. This paper proposed an improved LSH algorithm based on p-stable distribution to finish image searching and matching. The experiment proved that the algorithm has a certain degree of optimization to improve recall rate and error rate at the same time, through the matching time and the length of hash table shows that the algorithm optimizes the memory utilization and search efficiency. The extracted SIFT feature of images is the only foundation we used when comparing different images at present. In the following research, we can try to use a variety of image features as the basis for matching to improve the reliability of the matching results.


SIFT feature LSH algorithm Image matching Recommendation system 


  1. 1.
    Abdel-Hakim AE, Farag AA (2006) CSIFT: a SIFT descriptor with color invariant characteristics// computer vision and pattern recognition, 2006 I.E. computer society conference on. IEEE 2006:1978–1983Google Scholar
  2. 2.
    Andoni A, Razenshteyn I (2015) Optimal Data-Dependent Hashing for Approximate Near NeighborsGoogle Scholar
  3. 3.
    Bai JF, Ma Y, Li J et al (2011) Novel averaging window filter for SIFT in infrared face recognition. Chin Opt Lett 9(8):081002–081001CrossRefGoogle Scholar
  4. 4.
    Bay H, Ess A, Tuytelaars T et al (2008) Speeded-up robust features. Comput Vis Image Underst 110(3):404–417CrossRefGoogle Scholar
  5. 5.
    Boroş E, Roşca G, Iftene A (2010) Using SIFT method for global topological localization for indoor environments// 10th Workshop of the Cross-Language Evaluation Forum, Corfu, Greece, 6242: 277–282Google Scholar
  6. 6.
    Campos LMD, Fernández-Luna JM, Huete JF et al (2010) Combining content-based and collaborative recommendations: a hybrid approach based on Bayesian networks. Int J Approx Reason 51(7):785–799CrossRefGoogle Scholar
  7. 7.
    Melville P, Mooney RJ, Nagarajan R (2002) Content-boosted collaborative filtering for improved recommendations// Eighteenth National Conference on Artificial Intelligence 2002:187–192.Google Scholar
  8. 8.
    Cao YD, Liu YY, Jia X, et al (2016) Image spam filtering with improved LSH algorithm. Application Research of Computers 33(6):1693–1696Google Scholar
  9. 9.
    Cheung W, Hamarneh G (2009) n-SIFT: n-dimensional scale invariant feature transform. IEEE Trans Image Process A Publ IEEE Signal Processing Soc 18(9):2012Google Scholar
  10. 10.
    Datar M, Immorlica N, Indyk P et al (2004) Locality-sensitive hashing scheme based on p-stable distributions// twentieth symposium on computational geometry. ACM 2004:253–262MATHGoogle Scholar
  11. 11.
    Ding XM, Wang WY, Huang XD (2007) New method for detecting and tracking of moving target based on difference and invariant. Opt Precis Eng 15(4):570–576Google Scholar
  12. 12.
    Fu WP, Qin C, Liu J, etc (2011) Matching and location of image object based on SIFT algorithm. Chin J Sci Instrum, 32(1):163–169Google Scholar
  13. 13.
    Gong WG, Zhang X, Li ZH (2011) Image registration based on extended LSH. Opt Precis Eng 19(6):1375–1383CrossRefGoogle Scholar
  14. 14.
    Grabner M, Grabner H, Bischof H (2006) Fast approximated SIFT// Asian conference on computer vision. Springer-Verlag 2006:918–927Google Scholar
  15. 15.
    Indyk P (1998) Approximate nearest neighbors: towards removing the curse of dimensionality. Theor Comput 604-613(11):604–613MathSciNetMATHGoogle Scholar
  16. 16.
    Indyk P (2000) Stable distributions, pseudorandom generators, embeddings and data stream computation// foundations of computer science. Proceed Symp IEEE 2000:189Google Scholar
  17. 17.
    Junfeng B, Yong M, Jing L et al (2011) Novel averaging window filter for SIFT in infrared face recognition. Chin Opt Lett 9(8):081002–081002CrossRefGoogle Scholar
  18. 18.
    Ke Y, Sukthankar R (2004) PCA-SIFT: a more distinctive representation for local image descriptors// IEEE computer society conference on computer vision and pattern recognition. IEEE Comput Soc 2004:506–513Google Scholar
  19. 19.
    Kounalakis T, Triantafyllidis GA (2011) 3D scene’s object detection and recognition using depth layers and SIFT-based machine learning. 3d. Research 2(3):1–11Google Scholar
  20. 20.
    Lo TWR, Siebert JP (2009) Local feature extraction and matching on range images: 2.5D SIFT. Comput Vis Image Underst 113(12):1235–1250CrossRefGoogle Scholar
  21. 21.
    Lowe DG (2004) Distinctive image features from scale-invariant key-points. Int J Comput Vis 60(2):91–110CrossRefGoogle Scholar
  22. 22.
    Luo ST, Wang YL, Zhang Q (2005) Electronic image stabilizing algorithm for image tracking system on vehicle. Opt Precis Eng 13(1):95–103Google Scholar
  23. 23.
    Lv Q, Josephson W, Wang Z et al (2007) Multi-probe LSH: efficient indexing for high-dimensional similarity search// international conference on very large data bases. VLDB Endowment 2007:950–961Google Scholar
  24. 24.
    Shan KE, Wang BL, Huang XY (2010) An improved SIFT algorithm and its application in medical image registration. J Xiamen University 49(3):354–358Google Scholar
  25. 25.
    Su DL (2014) Research on personalized recommendation algorithm integrating image similarity and collaborative filtering. Dissertation, Soochow UniversityGoogle Scholar
  26. 26.
    Suzuki T, Amano Y, Hashizume T (2010) Vision based localization of a small UAV for generating a large mosaic image// Sice Conference 2010, Proceedings of. IEEE, 2010:2960–2964Google Scholar
  27. 27.
    The MIRFLICKR Retrieval Evaluation.
  28. 28.
    Wang XL (2008) Research on high-dimensional indexing technology in content-based image retrieval system. Dissertation, Huazhong University of Science and TechnologyGoogle Scholar
  29. 29.
    Wang HF, Liu SQ, Wang DB (2008) Video camera rotation compensation algorithm based on feature matching of sequence image frames. Opt Precis Eng 16(7):1330–1334Google Scholar
  30. 30.
    Xiong Y, Huimin MA (2010) Extraction and application of 3D object SIFT feature. J Image Graph 15(5):814–819Google Scholar
  31. 31.
    Xu JJ, Zhang Y, Zhang H (2015) Fast image registration algorithm based on improved Harris-SIFT descriptor. J Electron Meas Instrum 29(1):48–54MathSciNetGoogle Scholar
  32. 32.
    Yang Y (2015) Image recommendation system based on the image features obtained from deep learning. Dissertation, University of Electronic Science and Technology of ChinaGoogle Scholar
  33. 33.
    Zhang YJ (2005) Image Engineering. Tsinghua University Press, ChinaGoogle Scholar
  34. 34.
    Zhang LL, Chen LF (2014) A novel image retrieval method based on combinatorial improvement clustering of SIFT feature points. J Dalian Univ Technol 54(4):477–481Google Scholar
  35. 35.
    Zhao WC, Dong RX, Wang Q (2017) Research on face recognition algorithm with multi-scale analysis fusing SIFT. J Gansu Sci 29(4):32–36 47Google Scholar
  36. 36.
    Zhu PX (2013) Research of content-based commercial product image retrieval and recommendation system. Dissertation, South China University of TechnologyGoogle Scholar

Copyright information

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

Authors and Affiliations

  1. 1.School of Economics and ManagementXidian UniversityXi’anChina

Personalised recommendations