The combination of differential evolution and color attention for object recognition

ABSTRACT

Color attention algorithm can improve the accuracy of object recognition significantly. In the algorithm, there are 3 parameters related to bin number of color features and shape features and the weight between color and shape, need to be set. Whether the parameters are set correctly or not poses a great impact on the accuracy of object recognition. However, searching suitable values in the parameters space related to color attention algorithm is a NP-hard problem and the parameters of the algorithm are set manually in recent research through which the right values are not guaranteed to be found. Recently, bio-inspired computing gains much attention for its advantages in complex optimization problems and differential evolution outperforms most other bio-inspired computing algorithms in divergence and stability in optimization problems. When taking the accuracy of object recognition as a fitness function, increasing the accuracy of object recognition is then an optimization problem to find the largest accuracy in parameter spaces. Therefore, we design the structure of the agent of differential evolution and take the classification accuracy with support vector machine algorithm as a fitness function. Then we use differential evolution to search the parameters space and find some suitable parameters for color attention algorithm successfully. Our experimental evaluation demonstrates that the accuracy of object recognition increases greatly with the right parameters.

References

1. Chang, C.-C. and Lin, C.-J., 2011. LIBSVM: A Library for Support Vector Machines. Acm Transactions on Intelligent Systems and Technology 2, 3 (2011). DOI= http://dx.doi.org/10.1145/1961189.1961199.
2. Li, H., Wei, Y., Li, L., and Yuan, Y., 2012. Similarity learning for object recognition based on derived kernel. Neurocomputing 83(Apr 15), 110--120. DOI= http://dx.doi.Org/10.1016/i.neucom.2011.12.005.
3. Linde, O. and Lindeberg, T., 2012. Composed complex-cue histograms: An investigation of the information content in receptive field based image descriptors for object recognition. Computer Vision and Image Understanding 116, 4 (Apr), 538--560. DOI= http://dx.doi.Org/10.1016/i.cviu.2011.12.003.
4. Liu, B., Wang, L., and Jin, Y.-H., 2007. Advances in differential evolution. Control and Decision 22, 7, 721.
5. Liu, Y.-H., Lee, A. J. T., and Chang, F., 2012. Object recognition using discriminative parts. Computer Vision and Image Understanding 116, 7 (Jul), 854--867. DOI= http://dx.doi.Org/10.1016/i.cviu.2012.03.007.
6. Nanni, L. and Lumini, A., 2013. Heterogeneous bag-of-features for object/scene recognition. Applied Soft Computing 13, 4 (Apr), 2171--2178. DOI= http://dx.doi.Org/10.1016/i.asoc.2012.12.013.
7. Shahbaz Khan, F., Van De Weher, J., and Vanrell, M., 2009. Top-down color attention for object recognition. In Computer Vision, 2009 IEEE 12th International Conference on IEEE, 979--986.
8. Storn, R. and Price, K., 1997. Differential evolution--a simple and efficient heuristic for global optimization over continuous spaces. Journal of global optimization 11, 4, 341--359.
9. Van De Sande, K. E. A., Gevers, T., and Snoek, C. G. M., 2010. Evaluating Color Descriptors for Object and Scene Recognition. Ieee Transactions on Pattern Analysis and Machine Intelligence 32, 9 (Sep), 1582--1596. DOI= http://dx.doi.org/10.1109/tpami.2009.154.
10. Van De Weder, J. and Schmid, C., 2006. Coloring local feature extraction. In Computer Vision - Eccv 2006, Pt 2, Proceedings, A. Leonardis, H. Bischof and A. Pinz Eds., 334--348.
11. Zou, J., Liu, C.-C., Zhang, Y., and Lu, G.-F., 2013. Object recognition using Gabor co-occurrence similarity. Pattern Recognition 46, 1 (Jan), 434--448. DOI= http://dx.doi.Org/10.1016/j.patcog.2012.06.018.

Index Terms

• Computing methodologies

  • Artificial intelligence

    • Computer vision

      • Computer vision problems

        • Object recognition