Performance Evaluation of Robust Matching Measures

This paper is aimed at evaluating the performances of differ ent measures which have been proposed in literature for robust matching. In particular, classical matc hing metrics typically employed for this task are considered together with specific approaches aiming at achi eving robustness. The main aspects assessed by the proposed evaluation are robustness with respect to phot metric distortions, noise and occluded patterns. Specific datasets have been used for testing, which provide a very challenging framework for what concerns the considered disturbance factors and can also serve as tes tbed for evaluation of future robust visual correspondence measures.

[1]  William J. Christmas,et al.  Orientation Correlation , 2002, BMVC.

[2]  Ramin Zabih,et al.  Non-parametric Local Transforms for Computing Visual Correspondence , 1994, ECCV.

[3]  Daniel Scharstein,et al.  Matching images by comparing their gradient fields , 1994, Proceedings of 12th International Conference on Pattern Recognition.

[4]  Shree K. Nayar,et al.  Ordinal Measures for Image Correspondence , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Yutaka Satoh,et al.  Using selective correlation coefficient for robust image registration , 2003, Pattern Recognit..

[6]  J. Crowley,et al.  Experimental Comparison of Correlation Techniques , 2007 .

[7]  Jan Flusser,et al.  Image registration methods: a survey , 2003, Image Vis. Comput..

[8]  Peter Seitz,et al.  Using Local Orientational Information As Image Primitive For Robust Object Recognition , 1989, Other Conferences.

[9]  Farhan Ullah,et al.  Orientation Code Matching for Robust Object Search , 2001 .

[10]  Alain Crouzil,et al.  Dense matching using correlation: new measures that are robust near occlusions , 2003, BMVC.

[11]  Andrea Giachetti,et al.  Matching techniques to compute image motion , 2000, Image Vis. Comput..

[12]  Jun Shen,et al.  An optimal linear operator for step edge detection , 1992, CVGIP Graph. Model. Image Process..

[13]  Federico Tombari,et al.  A robust measure for visual correspondence , 2007, 14th International Conference on Image Analysis and Processing (ICIAP 2007).

[14]  Alain Crouzil,et al.  A new correlation criterion based on gradient fields similarity , 1996, Proceedings of 13th International Conference on Pattern Recognition.