Abstract
The Bag-of-visual-words (BOW) has recently become a popular representation to describe image content. Each image is represented by the frequency histogram of visual words obtained by assigning each key point of the image to the closest visual word. Overall, codebook is constructed via K-means clustering. In this paper we have used unsupervised neural network algorithm, to overcome some weaknesses of K-means; the standard Self Organizing Map SOM. We evaluated our method on two public datasets. Results exceed the current state-of-art retrieval performance with the baseline BOW on Holidays dataset, with less performance on the Kentucky dataset, however. We experimentally show that the proposed soft-weighting approach shows significant improvement over the baseline BOW with a small codebook size.
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
Jsasutani, E., Yamada, A.: The mpeg-7 color layout descriptor: A compact image feature description for high-speed image/vide segment retrieval. In: Proceedings of the Image Processing (2001)
Swain, M.J., Ballard, D.H.: Color Indexing. International Journal of Computer Vision 7(1), 11–32 (1991)
Lowe, D.: Distinctive image features from scale invariant keypoints. International Journal Computer Vision (IJCV) 60(2), 91–110 (2004)
Sivic, J., Zisserman, A.: Video Google: A text retrieval approach to object matching in videos. In: Proc. ICCV (2003)
Ke, Y., Sukthankar, R.: PCA-SIFT: A More Distinctive Representation for Local Image Descriptors. In: Proc. Conf. Computer Vision and Pattern Recognition, pp. 511–517 (2004)
Nistér, D., Stewénius, H.: Scalable recognition with a vocabulary tree. In: CVPR, June 17-22, vol. 2 (2006)
Lepetit, V., Lagger, P., Fua, P.: Randomized trees for realtimekeypoint recognition. In: Proc. CVPR (June 2005)
Macqueen, J.B.: Some methods of classification and analysis of multivariate observations. In: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, pp. 281–297 (1967)
Jegou, H., Douze, M., Schmid, C.: Hamming embedding and weak geometric consistency for large scale image search. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008, Part I. LNCS, vol. 5302, pp. 304–317. Springer, Heidelberg (2008)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Object retrieval with large vocabularies and fast spatial matching. In: Proc. CVPR (2007)
Jegou, H., Douze, M.: INRIA Holidays dataset (2008), http://lear.inrialpes.fr/people/jegou/data.php
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: IEEE CVPR (2006)
Zhang, J., Marszalek, M., Lazebnik, S., Schmid, C.: Local features and kernels for classification of texture and object categories: An in-depth study. In INRIA Technical Report RR-5737 (2005)
Kohonen, T.: The Self-Organizing Map. Proceedings of the IEEE 78, 1464–1480 (1990)
Tsai, S., Chen, D., Takacs, G., Chandrasekhar, V., Vedantham, R., Grzeszczuk, R., Girod, B.: Fast geometric re-ranking for image-based retrieval. In: Int. Conf. on Image Processing, Hong Kong (September 2010)
Zhang, Y., Jia, Z., Chen, T.: Image retrieval with geometry-preserving visual phrases. In: Proc. IEEE Conf. on Computer Vision and Pattern Recognition (2011)
Hare, J.S., Samangooei, S., Lewis, P.H.: Efficient clustering and quantisation of SIFT features: exploiting characteristics of the SIFT descriptor and interest region detectors under image inversion. In: ICMR 2011, p. 2 (2011)
Philbin, J., Chum, O., Isard, M., Sivic, J., Zisserman, A.: Lost in quantization: improving particular object retrieval in large scale image databases. In: CVPR, June 23-28 (2008)
Ben Chikha, S., Marzouki, K.: Making Standard SOM Invariant to the Initial Conditions. In: Cabestany, J., Sandoval, F., Prieto, A., Corchado, J.M. (eds.) IWANN 2009, Part I. LNCS, vol. 5517, pp. 204–211. Springer, Heidelberg (2009)
Jegou, H., Douze, M., Schmid, C.: Improving Bag-of-Features for Large Scale Image Search. International Journal of Computer Vision 87(3), 316–336 (2010)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2013 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Elleuch, Z., Marzouki, K. (2013). Optimization of BOW Using Self Organizing Map Artificial Neural Network in Similar Images Retrieval Systems. In: Sanches, J.M., Micó, L., Cardoso, J.S. (eds) Pattern Recognition and Image Analysis. IbPRIA 2013. Lecture Notes in Computer Science, vol 7887. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-38628-2_39
Download citation
DOI: https://doi.org/10.1007/978-3-642-38628-2_39
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-38627-5
Online ISBN: 978-3-642-38628-2
eBook Packages: Computer ScienceComputer Science (R0)