Abstract
Bag of Visual Words is one of the most widely used approaches for representing images for object categorization; however, it has several drawbacks. In this paper, we propose three properties and their corresponding quantitative evaluation measures to assess the ability of a visual word to represent and discriminate an object class. Additionally, we also introduce two methods for ranking and filtering visual vocabularies and a soft weighting method for BoW image representation. Experiments conducted on the Caltech-101 dataset showed the improvement introduced by our proposals, which obtained the best classification results for the highest compression rates when compared with a state-of-the-art mutual information based method for feature selection.
Chapter PDF
Similar content being viewed by others
References
Kesorn, K., Poslad, S.: An enhanced bag-of-visual word vector space model to represent visual content in athletics images. IEEE Transactions on Multimedia 14(1), 211–222 (2012)
Lopez-Sastre, R., Tuytelaars, T., Acevedo-Rodriguez, F., Maldonado-Bascon, S.: Towards a more discriminative and semantic visual vocabulary. Computer Vision and Image Understanding 115(3), 415–425 (2011)
Jiu, M., Wolf, C., Garcia, C., Baskurt, A.: Supervised learning and codebook optimization for bag of words models. Cognitive Computation 4, 409–419 (2012)
Chang, L., Duarte, M.M., Sucar, L.E., Morales, E.F.: A bayesian approach for object classification based on clusters of sift local features. Expert Systems with Applications 39, 1679–1686 (2012)
Jiang, Y.G., Ngo, C.W., Yang, J.: Towards optimal bag-of-features for object categorization and semantic video retrieval. In: CVIR, pp. 494–501. ACM (2007)
Zhang, Y., Wu, J., Cai, J.: Compact representation for image classification: To choose or to compress? In: CVPR 2014 (2014)
Jégou, H., Douze, M., Schmid, C.: Product quantization for nearest neighbor search. IEEE Pattern Analysis and Machine Intellingence 33(1), 117–128 (2011)
Gong, Y., Kumar, S., Rowley, H.A., Lazebnik, S.: Learning binary codes for high-dimensional data using bilinear projections. In: CVPR 2013 (2013)
Fei-Fei, L., Fergus, R., Perona, P.: Learning generative visual models from few training examples: An incremental bayesian approach tested on 101 object categories. Comput. Vis. Image Underst. 106(1), 59–70 (2007)
Emerson, P.: The original borda count and partial voting. Social Choice and Welfare 40(2), 353–358 (2013)
Moulin, C., Barat, C., Ducottet, C.: Fusion of tf.idf weighted bag of visual features for image classification. In: Qunot, G. (ed.) CBMI, pp. 1–6. IEEE (2010)
Bosch, A., Zisserman, A., Munoz, X.: Image classification using random forests and ferns. In: ICCV, vol. 23(1), pp. 1–8 (2007)
Elkan, C.: Using the triangle inequality to accelerate k-means. In: Fawcett, T., Mishra, N., (eds.) ICML, pp. 147–153. AAAI Press (2003)
Vedaldi, A., Zisserman, A.: Efficient additive kernels via explicit feature maps. Pattern Analysis and Machine Intellingence 34(3) (2011)
Lazebnik, S., Schmid, C., Ponce, J.: Beyond bags of features: Spatial pyramid matching for recognizing natural scene categories. In: CVPR, pp. 2169–2178 (2006)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Chang, L., Pérez-Suárez, A., Rodríguez-Collada, M., Hernández-Palancar, J., Arias-Estrada, M., Sucar, L.E. (2015). Assessing the Distinctiveness and Representativeness of Visual Vocabularies. In: Pardo, A., Kittler, J. (eds) Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications. CIARP 2015. Lecture Notes in Computer Science(), vol 9423. Springer, Cham. https://doi.org/10.1007/978-3-319-25751-8_40
Download citation
DOI: https://doi.org/10.1007/978-3-319-25751-8_40
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-25750-1
Online ISBN: 978-3-319-25751-8
eBook Packages: Computer ScienceComputer Science (R0)
