Very Large-Scale Image Retrieval Based on Local Features

  • Chang-Qing Yin
  • Wei Mao
  • Wei Jiang
Part of the Communications in Computer and Information Science book series (CCIS, volume 304)


Traditional image retrieval technology is pixel sensitive and with low fault tolerance. To overcome this deficiency, a novel method for large-scale image retrieval is proposed in this paper, which is especially suitable for images with kinds of interferences, such as rotation, pixel lost, watermarks, etc. First, local features of images are extracted to build a visual dictionary with weight, which is a new data structure developed from bag-of-words. In the retrieval process, we look up all the features extracted from the target image in the dictionary and create a single list of weight to get the result. We demonstrate the effectiveness of our approach using a coral image set and online image set on eBay.


image retrieval interference visual dictionary with weight 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    Farquhar, J., Szedmak, S., Meng, H., Shawe-Taylor, J.: Improving “Bag-of-keypoints” image categorization. University of Southampton (2005)Google Scholar
  2. 2.
    Jegou, H., Douze, M., Schmid, C.: On the Burstiness of Visual Elements. In: IEEE Conference on Computer Version and Recognition, Miami, FL, USA, pp. 1169–1176 (2009)Google Scholar
  3. 3.
    Edward, R., Drummond, T.: Fusing Points and Lines for High Performance Tracking. In: ICCV, pp. 1508–1515 (2005)Google Scholar
  4. 4.
    Edward, R., Drummond, T.: Machine Learning for High-speed Corner Detection. In: Machine Learning, pp. 1–14 (2006)Google Scholar
  5. 5.
    Lowe, D.: Object Recognition from Scale-invariant Features. In: ICCV, pp. 1150–1157 (1999)Google Scholar
  6. 6.
    Leutenegger, S., Margarita, C., Roland, Y.: Siegwart. BRISK: Binary Robust Invariant Scalable Keypoints. In: ICCV (2011)Google Scholar
  7. 7.
    Anna, B., Andrew, Z., Xavier, M.: Image Classification using Random Forests and Ferns. In: ICCV, pp. 1–8 (2007)Google Scholar
  8. 8.
    Ethan, R., Vincent, R., Kurt, K., Gary, B.: ORB: an Efficient Alternative to SIFT or SURF. In: ICCV (2011)Google Scholar
  9. 9.
    Muja, M., Lowe, D.: Fast Approximate Nearest Neighbours with Automatic Algorithm Configuration. In: 4th International Conference on Computer Vision Theory and Applications, pp. 331–340. Springer, France (2009)Google Scholar
  10. 10.
    Csurka, G., Bray, C., Dance, C., Fan, L.: Visual Categorization with Bags of Keypoints. In: Proc. of ECCV Workshop on Statistical Learning in Computer Vision. Czech Republic, Prague (2004)Google Scholar
  11. 11.
    Kekre, H.B., Dhirendra, M.: Digital Image Search & Retrieval using FFT Sectors of Color Images. International Journal on Computer Science and Engineering, 368–372 (2010)Google Scholar
  12. 12.
    Bian, W., Tao, D.C.: Biased Discriminant Euclidean Embedding for Content-Based Image Retrieval. IEEE Transactions on Image Processing, 545–554 (2010)Google Scholar
  13. 13.
    Perronnin, F., Liu, Y., Sanchez, J.: Large-scale Image Retrieval with Compressed Fisher Vectors. In: Computer Vision and Pattern Recognition (CVPR), pp. 3384–3391 (2010)Google Scholar
  14. 14.
    Douze, M., Ramisa, A., Schmid, C.: Combining Attributes and Fisher Vectors for Efficient Image Retrieval. In: Computer Vision and Pattern Recognition (CVPR), pp. 754–752 (2011)Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2012

Authors and Affiliations

  • Chang-Qing Yin
    • 1
    • 2
  • Wei Mao
    • 1
    • 2
  • Wei Jiang
    • 1
    • 2
  1. 1.Tongji UniversityShanghaiChina
  2. 2.IBM (China) Co. LimitedShanghaiChina

Personalised recommendations