Abstract
Traditional landmark recognition methods work by using local image features, k-means vector quantization and classifiers like SVM to recognize landmarks. However, the inefficient codebook learning by k-means constraints the possibility of using high-dimensional feature spaces, large numbers of image descriptors and large codebooks which are needed for good results. In this paper we introduce a fast unsupervised codebook learning - Extremely Random Projection Forest (ERPF), which is an ensemble of random projection tree with randomly splitting direction. We evaluate our approach on two public datasets and ERPF significantly outperforms other spatial tree methods and k-means.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Hao, Q., Cai, R., Li, Z., Zhang, L., Pang, Y., Wu, F.: 3d visual phrases for landmark recognition. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 3594–3601 (2012)
Li, Y., Crandall, D.J., Huttenlocher, D.P.: Landmark classification in large-scale image collections. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1957–1964 (2009)
Zheng, Y.-T., Zhao, M., Song, Y., Adam, H., Buddemeier, U., Bissacco, A., Brucher, F., Chua, T.-S., Neven, H.: Tour the world: building a web-scale landmark recognition engine. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1085–1092 (2009)
Lowe, D.G.: Distinctive image features from scale invariant keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
Bay, H., Tuytelaars, T., Van Gool, L.: SURF: Speeded up robust features. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006, Part I. LNCS, vol. 3951, pp. 404–417. Springer, Heidelberg (2006)
Heinly, J., Dunn, E., Frahm, J.-M.: Comparative evaluation of binary features. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012, Part II. LNCS, vol. 7573, pp. 759–773. Springer, Heidelberg (2012)
Csurka, G., Dance, C., Fan, L., Willamowski, J., Bray, C.: Visual categorization with bags of keypoints. In: Int. Workshop on Statistical Learning in Computer Vision, ECCV, vol. 1, p. 22 (2004)
Perronnin, F., Dance, C., Csurka, G., Bressan, M.: Adapted vocabularies for generic visual categorization. In: Leonardis, A., Bischof, H., Pinz, A. (eds.) ECCV 2006. LNCS, vol. 3954, pp. 464–475. Springer, Heidelberg (2006)
Jurie, F., Triggs, B.: Creating efficient codebooks for visual recognition. In: International Conference on Computer Vision, vol. 1, pp. 604–610 (2005)
Nister, D., Stewenius, H.: Scalable recognition with a vocabulary tree. In: IEEE International Conference on Computer Vision and Pattern Recognition, vol. 2, pp. 2161–2168 (2006)
Freund, Y., Dasgupta, S., Kabra, M., Verma, N.: Learning the structure of manifolds using random projections. In: Advances in Neural Information Processing Systems, pp. 473–480 (2007)
Cao, Z., Yin, Q., Tang, X., Sun, J.: Face recognition with learning-based descriptor. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2707–2714 (2010)
McFee, B., Lanckriet, G.R.G.: Large-scale music similarity search with spatial trees. In: International Society for Music Information Retrieval, pp. 55–60 (2011)
Breiman, L.: Random forests. Machine Learning 45(1), 5–32 (2001)
Ji, R., Duan, L.-Y., Chen, J., Yang, S., Huang, T., Yao, H., Gao, W.: Pkubench: a context rich mobile visual search benchmark. In: International Conference on Image Processing, pp. 2545–2548 (2011)
Chen, D.M., Baatz, G., Koser, K., Tsai, S.S., Vedantham, R., Pylvanainen, T., Roimela, K., Chen, X., Bach, J., Pollefeys, M.: City-scale landmark identification on mobile devices. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 737–744 (2011)
Li, Y., Snavely, N., Huttenlocher, D.P.: Location recognition using prioritized feature matching. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 791–804 (2010)
Bergamo, A., Sinha, S.N., Torresani, L.: Leveraging structure from motion to learn discriminative codebooks for scalable landmark classification. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 763–770 (2013)
Fritz, G., Seifert, C., Paletta, L.: A mobile vision system for urban detection with informative local descriptors. In: International Conference on Computer Vision Systems, p. 30 (2006)
Cai, H., Yan, F., Mikolajczyk, K.: Learning weights for codebook in image classification and retrieval. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2320–2327 (2010)
Perronnin, F., Dance, C.: Fisher kernels on visual vocabularies for image categorization. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 1–8 (2007)
Dasgupta, S., Freund, Y.: Random projection trees for vector quantization. IEEE Trans. Information Theory 55(7), 3229–3242 (2009)
Arandjelovic, R., Zisserman, A.: Three things everyone should know to improve object retrieval. In: IEEE International Conference on Computer Vision and Pattern Recognition, pp. 2911–2918 (2012)
Bentley, J.L.: Multidimensional binary search trees used for associative searching. Communications of the ACM 18(9), 509–517 (1975)
Fan, R.-E., Chang, K.-W., Hsieh, C.-J., Wang, X.R., Lin, C.-J.: Liblinear: A library for large linear classification. The Journal of Machine Learning Research 9, 1871–1874 (2008)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2014 Springer International Publishing Switzerland
About this paper
Cite this paper
Guo, Y., Lu, W. (2014). Extremely Fast Unsupervised Codebook Learning for Landmark Recognition. In: Ali, M., Pan, JS., Chen, SM., Horng, MF. (eds) Modern Advances in Applied Intelligence. IEA/AIE 2014. Lecture Notes in Computer Science(), vol 8481. Springer, Cham. https://doi.org/10.1007/978-3-319-07455-9_38
Download citation
DOI: https://doi.org/10.1007/978-3-319-07455-9_38
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-07454-2
Online ISBN: 978-3-319-07455-9
eBook Packages: Computer ScienceComputer Science (R0)