Name
Abstract | ||
|---|---|---|
A fast pattern matching scheme termed matching by tone mapping (MTM) is introduced which allows matching under nonlinear tone mappings. We show that, when tone mapping is approximated by a piecewise constant/linear function, a fast computational scheme is possible requiring computational time similar to the fast implementation of normalized cross correlation (NCC). In fact, the MTM measure can be viewed as a generalization of the NCC for nonlinear mappings and actually reduces to NCC when mappings are restricted to be linear. We empirically show that the MTM is highly discriminative and robust to noise with comparable performance capability to that of the well performing mutual information, but on par with NCC in terms of computation time. |
Year | DOI | Venue |
|---|---|---|
2014 | 10.1109/TPAMI.2013.138 | IEEE Trans. Pattern Anal. Mach. Intell. |
Keywords | Field | DocType |
photometric invariant template matching,computational time,linear function,fast computational scheme,nonlinear tone mapping,nonlinear mapping,fast pattern,computation time,tone mapping,mtm measure,fast implementation,structural similarity,correlation,photometry,vectors,template matching,histograms,mathematical model,convolution,pattern matching,approximation theory | Template matching,Cross-correlation,Pattern recognition,Computer science,Convolution,Approximation theory,Tone mapping,Mutual information,Artificial intelligence,Pattern matching,Piecewise | Journal |
Volume | Issue | ISSN |
36 | 2 | 1939-3539 |
Citations | PageRank | References |
12 | 0.57 | 14 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yacov Hel-Or | 1 | 461 | 40.74 |
| Hagit Zabrodsky Hel-Or | 2 | 371 | 28.19 |
| Eyal David | 3 | 30 | 1.68 |