Abstract
Object recognition from images is traditionally based on a large training set of previously annotated images which is impractical for some applications. Also, most methods use only local or global features. Due to the nature of objects some features are better suited for some objects, so researchers have recently combined both types of features to improve the recognition performance. This approach, however, is not sufficient for the recognition of generic objects which can take a wide variety of appearances. In this paper, we propose a novel object recognition system that: (i) uses a small set of images obtained from the Web, (ii) induces a set of models for each object to deal with polymorphism, and (iii) optimizes the contribution of local and global features to deal with different types of objects. We performed tests with both generic and specific objects, and compared the proposed approach against base classifiers and state-of-the-art systems with very promising results.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsPreview
Unable to display preview. Download preview PDF.
References
The Semantic Robot Vision Challenge (2011), http://www.semantic-robot-vision-challenge.org/
Bunescu, R.C., Mooney, R.J.: Multiple Instance Learning for Sparse Positive Bags. In: 24th International Conference on Machine Learning (ICML 2007), pp. 105–112. ACM (2007)
Chang, L., Duarte, M., Sucar, L., Morales, E.: A Bayesian Approach for Object Classification Based on Clusters of SIFT Local Features. Expert Systems With Applications 39(2), 1679–1686 (2012)
Fergus, R., Fei-Fei, L., Perona, P., Zisserman, A.: Learning Object Categories from Google”s Image Search. In: 10th IEEE International Conference on Computer Vision (ICCV 2005), vol. 2, pp. 1816–1823. IEEE (2005)
Gabor, D.: Theory of Communication. Journal of the Institution of Electrical Engineers-Part III: Radio and Communication Engineering 93(26), 429–441 (1946)
Grimson, W., Huttenlocher, D.: On the Sensitivity of the Hough Transform for Object Recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence 12(3), 255–274 (1990)
Ji, Y., Idrissi, K., Baskurt, A.: Object Categorization Using Boosting Within Hierarchical Bayesian Model. In: 16th IEEE International Conference on Image Processing (ICIP 2009), pp. 317–320. IEEE (2009)
Lisin, D., Mattar, M., Blaschko, M., Learned-Miller, E., Benfield, M.: Combining Local and Global Image Features for Object Class Recognition. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2005) - Workshops, vol. 03, pp. 47–54. IEEE (2005)
Lowe, D.: Distinctive Image Features from Scale-Invariant Keypoints. International Journal of Computer Vision 60(2), 91–110 (2004)
Manshor, N., Rajeswari, M., Ramachandram, D.: Multi-Feature Based Object Class Recognition. In: International Conference on Digital Image Processing (ICDIP 2009), pp. 324–329. IEEE (2009)
Meger, D., Muja, M., Helmer, S., Gupta, A., Gamroth, C., Hoffman, T., Baumann, M., Southey, T., Fazli, P., Wohlkinger, W., Viswanathan, P., Little, J., Lowe, D., Orwell, J.: Curious George – An Integrated Visual Search Platform. In: Canadian Conf. on Computer and Robot Vision (CRV 2010), pp. 107–114. IEEE (2010)
Mikolajczyk, K., Schmid, C.: A Performance Evaluation of Local Descriptors. IEEE Transactions on Pattern Analysis & Machine Intelligence 27(10), 1615–1630 (2005)
Ozuysal, M., Calonder, M., Lepetit, V., Fua, P.: Fast Keypoint Recognition Using Random Ferns. IEEE Transactions on Pattern Analysis and Machine Intelligence 32(3), 448–461 (2010)
Pereira, R., Lopes, L.S.: Learning Visual Object Categories with Global Descriptors and Local Features. In: Lopes, L.S., Lau, N., Mariano, P., Rocha, L.M. (eds.) EPIA 2009. LNCS, vol. 5816, pp. 225–236. Springer, Heidelberg (2009)
Rothganger, F., Lazebnik, S., Schmid, C., Ponce, J.: 3D Object Modeling and Recognition Using Affine-Invariant Patches and Multi-View Spatial Constraints. In: IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR 2003), vol. 2, pp. 272–277. IEEE (2003)
Schroff, F., Criminisi, A., Zisserman, A.: Harvesting Image Databases from the Web. In: 11th International Conference on Computer Vision (ICCV 2007), pp. 1–8. IEEE (2007)
Vijayanarasimhan, S., Grauman, K.: Keywords to Visual Categories – Multiple-Instance Learning for Weakly Supervised Object Categorization. In: IEEE Conf. on Computer Vision and Pattern Recognition (CVPR 2008), pp. 1–8. IEEE (2008)
Wang, Y., Hou, Z., Leman, K., Pham, N.T., Chua, T.W., Chang, R.: Combination of Local and Global Features for Near-Duplicate Detection. In: Lee, K.T., et al. (eds.) MMM 2011 Part I. LNCS, vol. 6523, pp. 328–338. Springer, Heidelberg (2011)
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2012 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Navarrete, D.J., Morales, E.F., Sucar, L.E. (2012). Unsupervised Learning of Visual Object Recognition Models. In: Pavón, J., Duque-Méndez, N.D., Fuentes-Fernández, R. (eds) Advances in Artificial Intelligence – IBERAMIA 2012. IBERAMIA 2012. Lecture Notes in Computer Science(), vol 7637. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-642-34654-5_52
Download citation
DOI: https://doi.org/10.1007/978-3-642-34654-5_52
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-642-34653-8
Online ISBN: 978-3-642-34654-5
eBook Packages: Computer ScienceComputer Science (R0)