An Improved Vehicle Logo Recognition Using a Classifier Ensemble Based on Pattern Tensor Representation and Decomposition
- 143 Downloads
The paper presents a vehicle logo recognition system based on novel combination of tensor based feature extraction and ensemble of tensor subspace classifiers. Each originally two-dimensional vehicle logotype is transformed to a three-dimensional feature tensor applying the extended structural tensor method. All such exemplary logo-tensors which correspond to a single class are stacked to form a 4D logo-class-tensor. Decomposing each 4D logo-class-tensor into the orthogonal tensor subspace allows classification of unknown logotypes. The proposed system allows reliable vehicle logo recognition in real conditions as shown by experiments.
KeywordsVehicle Logo Recognition Tensor Subspace Classification Extended Structural Tensor Higher Order Singular Value Decomposition
Unable to display preview. Download preview PDF.
- 1.Bigün, J., Granlund, G. H., Wiklund, J., “Multidimensional Orientation Estimation with Applications to Texture Analysis and Optical Flow,” IEEE PAMI, 13, 8, pp. 775–790, 1991.Google Scholar
- 2.Brox, T., Boomgaard van den, R., Lauze, F., Weijer van de, J., Weickert, J., Mrázek, P., Kornprobst, P., “Adaptive Structure Tensors and their Applications, in Visualization and Processing of Tensor Fields (Weickert, J., Hagen, H. ed.), Springer, pp. 17–47, 2006.Google Scholar
- 3.Bugaj, M., Cyganek, B., “GPU Based Computation of the Structural Tensor for Real-Time Figure Detection,” in Proc. of the 20th International Conference on Computer Graphics, Visualization and Computer Vision (WSCG’12), Czech Republic, 2012.Google Scholar
- 4.Cyganek, B., Object Detection and Recognition in Digital Images: Theory and Practice, Wiley, 2013.Google Scholar
- 5.Cyganek, B., “Object Recognition with the Higher-Order Singular Value Decomposition of the Multi-Dimensional Prototype Tensors,” 3rd Computer Science On-line Conference (CSOC 2014). Advances in Intelligent Systems and Computing, Springer, pp. 395–405, 2014.Google Scholar
- 6.Cyganek, B., Woźniak, M., “Vehicle Logo Recognition with an Ensemble of Classifiers,” ACIIDS 2014, Part II, LNAI 8398 (Nguyen, N. T. et al. eds.), pp. 117–126, 2014.Google Scholar
- 7.Dai, S., Huang, H., Gao, Z., “Vehicle-logo recognition method based on Tchebichef moment invariants and SVM,” Software Engineering, WCSE’09, pp. 18–21, 2009.Google Scholar
- 8.Jähne, B., Digital Image Processing (6th edition), Springer-Verlag, 2005.Google Scholar
- 10.Ki, Y., Baik, D., “Vehicle-classification algorithm for single-loop detectors using neural networks,” Vehicular Technology, IEEE Transactions on, 55, 6, pp. 1704–1711, 2006.Google Scholar
- 11.Kolda, T. G., Bader, B. W., “Tensor Decompositions and Applications,” SIAM Review, pp. 455–500, 2008.Google Scholar
- 12.Krawczyk, B., Woźniak, M., Herrera, F., “On the Usefulness of One-Class Classifier Ensembles for Decomposition of Multi-Class Problems,” Elsevier Pattern Recognition, doi: 10.1016/j.patcog.2015.06.001, 2015.
- 13.Krawczyk, B., “One-class classifier ensemble pruning and weighting with firefly algorithm,” Neurocomputing, 150, Elsevier, pp. 490–500, 2015.Google Scholar
- 14.Lathauwer, de L., “Signal Processing Based on Multilinear Algebra,” Ph. D. dissertation, Katholieke Universiteit Leuven, 1997.Google Scholar
- 16.Leys, C., Ley, C., Klein, O., Bernard, P., Licata, L., “Detecting outliers: Do not use standard deviation around the mean, use absolute deviation around the median,” Journal of Experimental Social Psychology, 49, 4, pp. 764–766, July 2013.Google Scholar
- 17.Medialab LPR database, http://www.medialab.ntua.gr/research/LPRdatabas. html, 2015.
- 18.Petrovic, V. S., Cootes, T. F., “Analysis of features for rigid structure vehicle type recognition,” in Proc. BMVC, 2004.Google Scholar
- 19.Psyllos, A. P., Anagnostopoulos, C.-N. E., Kayafas, E., “Vehicle logo recognition using a sift-based enhanced matching scheme,” IEEE ITS, 11, 2, pp. 322–328, 2010.Google Scholar
- 20.Psyllos, A., Anagnostopoulos, C., Kayafas, E., “Vehicle model recognition from frontal view image measurements,” Computer Standards & Interfaces, 33, 2, pp. 142–151, 2011.Google Scholar
- 21.Psyllos, A., Anagnostopoulos, C.-N., Kayafas, E., “M-SIFT: A new method for Vehicle Logo Recognition, 2012 IEEE International Conference on Vehicular Electronics and Safety, Istanbul, Turkey, 2012.Google Scholar
- 23.Sulehria, H., Zhang, Y., “Vehicle logo recognition using mathematical morphology,” Proc. of the 6th WSEAS Intl Conf. on Telecommunications and Informatics, 2007.Google Scholar
- 24.Turk, M., Pentland, A., “Eigenfaces for recognition,” Journal of Cognitive Neuroscience, 3, 1, pp. 71–86, 1991.Google Scholar
- 25.Luis-García, R., Deriche, R., Rousson, M., Alberola-López, C., “Tensor Processing for Texture and Colour Segmentation,” LNCS, 3540, pp. 1117–1127, 2005.Google Scholar
- 26.Meyer, C.D., Matrix Analysis and Applied Linear Algebra, SIAM, 2000.Google Scholar
- 27.Perona, P., Malik, J., “Scale-Space and Edge Detection Using Anisotropic Diffusion,” IEEE Transactions on Pattern Analysis and Machine Intelligence, 12, 7, pp. 629–639, July 1990.Google Scholar
- 28.Sapiro, G., Geometric Partial Differential Equations and Image Analysis, Cambridge University Press, 2001.Google Scholar
- 29.Woźniak, M., Grana, M, Corchado, E., “A survey of multiple classifier systems as hybrid systems,” Information Fusion, 16, pp. 3–17, March 2014.Google Scholar