Performance Evaluation of Image Filtering for Classification and Retrieval

Falk Schubert, Krystian Mikolajczyk

Abstract

Much research effort in the literature is focused on improving feature extraction methods to boost the performance in various computer vision applications. This is mostly achieved by tailoring feature extraction methods to specific tasks. For instance, for the task of object detection often new features are designed that are even more robust to natural variations of a certain object class and yet discriminative enough to achieve high precision. This focus led to a vast amount of different feature extraction methods with more or less consistent performance across different applications. Instead of fine-tuning or re-designing new features to further increase performance we want to motivate the use of image filters for pre-processing. We therefore present a performance evaluation of numerous existing image enhancement techniques which help to increase performance of already well-known feature extraction methods. We investigate the impact of such image enhancement or filtering techniques on two state-of-the-art image classification and retrieval approaches. For classification we evaluate using a standard Pascal VOC dataset. For retrieval we provide a new challenging dataset. We find that gradient-based interest-point detectors and descriptors such as SIFT or HOG can benefit from enhancement methods and lead to improved performance.

References

  1. Everingham, M., Van Gool, L., Williams, C. K. I., Winn, J., and Zisserman, A. (2010). The pascal visual object classes (voc) challenge. IJCV.
  2. Farbman, Z., Fattal, R., Lischinski, D., and Szeliski, R. (2008). Edge-preserving decompositions for multiscale tone and detail manipulation. SIGGRAPH.
  3. Fattal, R., Lischinski, D., and Werman, M. (2002). Gradient domain high dynamic range compression. In SIGGRAPH.
  4. Gross, R. and Brajovic, V. (2003). An image preprocessing algorithm for illumination invariant face recognition. In AVBPA.
  5. Heseltine, T., Pears, N. E., and Austin, J. (2002). Evaluation of image pre-processing techniques for eigenface based face recognition. ICIG.
  6. Horváth, A. (2011). http://log69.com/aaphoto en.html .
  7. Huang, B. Q., Zhang, Y. B., and Kechadi, M. T. (2007). Preprocessing techniques for online handwriting recognition. In ISDA.
  8. Jain, R. and Doermann, D. (2012). Logo retrieval in document images. Document Analysis Systems, IAPR International Workshop on, 0:135-139.
  9. Jégou, H., Douze, M., and Schmid, C. (2008). Hamming embedding and weak geometric consistency for large scale image search. In ECCV.
  10. Kalantidis, Y., Pueyo, L., and Trevisiol, M. (2011). Scalable triangulation-based logo recognition. ICMR.
  11. Kumar, M., Murthy, P., and Kumar, P. (2011). Performance evaluation of different image filtering algorithms using image quality assessment. IJCA.
  12. Lazebnik, S., Schmid, C., and Ponce, J. (2006). Beyond bags of features: Spatial pyramid matching for recognizing natural scenes and categories. CVPR.
  13. Philbin, J. (2010). Scalable Object Retrieval in Very Large Image Collections. PhD thesis, University of Oxford.
  14. Sivic, J. and Zisserman, A. (2003). Video Google: A text retrieval approach to object matching in videos. In ICCV.
  15. Tomasi, C. and Manduchi, R. (1998). Bilateral filtering for gray and color images. In ICCV.
  16. Yan, F., Kittler, J., Mikolajczyk, K., and Tahir, A. (2012). Non-sparse multiple kernel fisher discriminant analysis. JMLR.
Download


Paper Citation


in Harvard Style

Schubert F. and Mikolajczyk K. (2013). Performance Evaluation of Image Filtering for Classification and Retrieval . In Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8565-41-9, pages 485-491. DOI: 10.5220/0004333104850491


in Bibtex Style

@conference{icpram13,
author={Falk Schubert and Krystian Mikolajczyk},
title={Performance Evaluation of Image Filtering for Classification and Retrieval},
booktitle={Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2013},
pages={485-491},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0004333104850491},
isbn={978-989-8565-41-9},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 2nd International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - Performance Evaluation of Image Filtering for Classification and Retrieval
SN - 978-989-8565-41-9
AU - Schubert F.
AU - Mikolajczyk K.
PY - 2013
SP - 485
EP - 491
DO - 10.5220/0004333104850491