Application of target recognition algorithm based on log-polar transformation for imaging guidance

Image matching is often used in target recognition for imaging guidance, but the scale change and rotation of target make this ineffective. Aiming at this question, we introduce a novel recognition algorithm based on log-polar transformation, which provides an invariant representation of the object's rotation and scaling. Collecting the distance axis projection, this algorithm not only work well when the target has the scale change or rotation, but also has the low operation cost. Indeed the validity of this method is verified in the paper.