An image feature point matching algorithm based on fixed scale feature transformation

Aiming at high complexity and computationally of scale invariant feature transform operator, an image feature matching algorithm based on fixed scale group scale invariant feature transform operator was brought out. It utilized fixed scale group to reduce certain amount of computation in the extraction and matching process of image feature points without affect correctness of final result. Simulation results show the feature points extracted by fixed scale transform operator has good stability in case of image translation, rotation, affine transformation and perspective transform. The correct rate is also higher. When the scale group is 4, the robustness trend of algorithm good and has not too much useless computation, which can be applied in various image process systems.