Speeding Up Local Patch Dissimilarity
There are many patch-based techniques used in image processing, but most of them are heavy to compute with current machines. A dissimilarity measure for images based on patches, inspired from rank distance, called Local Patch Dissimilarity (LPD), was recently introduced. It has very promising results in optical character recognition, but, as other patch-based methods, it is computationally heavy.
This work aims at showing that LPD can be improved in terms of efficiency. Several ways of optimizing the LPD algorithm are presented, such as using a hash table to store precomputed patch distances or skipping the comparison of overlapping patches. Another way to avoid the problem of the higher computational time on large sets of images is to turn to local learning methods.
Several experiments are conducted on two datasets using both standard machine learning methods and local learning methods. All methods are based on LPD. The obtained results come to support the fact that LPD is a very good dissimilarity measure for images. In this paper, LPD is also used with success for classifying images other than handwritten digits.
Keywordsimage dissimilarity image classification handwritten digit recognition patches patch-based technique
- 5.Conaire, C.O., O’Connor, N.E., Smeaton, A.F.: An Improved Spatiogram Similarity Measure for Robust Object Localisation. In: ICASSP, pp. 1069–1072 (2007)Google Scholar
- 6.Deselaers, T., Keyser, D., Ney, H.: Discriminative Training for Object Recognition using Image Patches. In: CVPR, pp. 157–162 (2005)Google Scholar
- 8.Efros, A.A., Freeman, W.T.: Image quilting for texture synthesis and transfer. In: SIGGRAPH 2001, pp. 341–346. ACM (2001)Google Scholar
- 9.Guo, G., Dyer, C.R.: Patch-based Image Correlation with Rapid Filtering. In: CVPR (2007)Google Scholar
- 10.Lazebnik, S., Schmid, C., Ponce, J.: A Maximum Entropy Framework for Part-Based Texture and Object Recognition. In: ICCV, pp. 832–838 (2005)Google Scholar
- 12.Lowe, D.G.: Object Recognition from Local Scale-Invariant Features. In: ICCV, vol. 2, pp. 1150–1157. IEEE Computer Society, Washington, DC (1999)Google Scholar
- 13.Shawe-Taylor, J., Cristianini, N.: Kernel Methods for Pattern Analysis. Cambridge University Press (2004)Google Scholar
- 14.Simard, P., LeCun, Y., Denker, J.S., Victorri, B.: Transformation Invariance in Pattern Recognition, Tangent Distance and Tangent Propagation. Neural Networks: Tricks of the Trade (1996)Google Scholar
- 15.Vapnik, V.: Estimation of dependencies based on empirical data (Information Science and Statistics), 2nd edn. Springer (2006)Google Scholar
- 16.Wilder, K.J.: Decision tree algorithms for handwritten digit recognition. Electronic Doctoral Dissertations for UMass Amherst (January 1998), http://scholarworks.umass.edu/dissertations/AAI9823791
- 17.Xie, J., Zhang, L., You, J., Zhang, D.: Texture classification via patch-based sparse texton learning. In: ICIP, Hong Kong, China, pp. 2737–2740 (2010)Google Scholar