Log-polar transform-based wavelet-modified maximum average correlation height filter for distortion-invariant target recognition

In this paper, we report a log-polar transform-based filter for in-plane rotation and scale-invariant target recognition. The log-polar transform is a known space-invariant image representation used in several image vision systems to eliminate the effects of scale and rotation in an image. In case of in-plane rotation invariance, peaks shift horizontally, while in case of scale invariance, peaks shift vertically. For full out-of-plane rotation-invariance (0–360°), log-polar transformed images are used to train the wavelet-modified maximum average correlation height (WaveMACH) filter. Correlation peak height and peak-to-sidelobe ratio have been calculated as metrics of goodness of the log-polar transform-based WaveMACH filter. This filter would reduce the memory requirement for filter storage in a practical system. Simulation results have been presented.