Invariance in Template Matching

This paper introduces variations on the template matching theme that extend its usefulness by providing invariance to mean intensity-level variations, certain geometric transformations and partial obscura-tions of the target object in the image. First order statistics of the pixel by pixel diierences between the template and the image are used as a match measure in order to provide invariance to mean intensity-level diierences. It is shown how scale and translation in-variance can be achieved by using the Fourier-Mellin transform. Rotation invariance is achieved by pre-processing with a polar coordinate transform before using a modiied Fourier-Mellin transform. Tessel-lated sub-templates are used to ignore the innuence of obscurations on an otherwise matching object when calculating the match measure.