Fast matching algorithm based on moment feature of image
Kaifeng Sun · Control theory & applications · 2010
To deal with the large amount of computation of moments during matching, we propose a novel fast matchingalgorithm based on moment invariants. This algorithm utilizes the computational characteristic of moments and sets tensum-tables to reduce the computational complexity of moments during matching. With the proposed algorithm, lower ordermoments of each sub-image can be determined by using only a few additive and multiplicative operations, which shortensthe matching time greatly. Meanwhile, the proposed algorithm computes moment features directly from the gray value ofimage and the result is accurate and independent from the matching precision. Simulation results illustrate the effectivenessof the proposed algorithm.