Application of MRF to Depth Information Estimation of Micro Image Defocus

For the problem of depth information estimation of micro vision image,a defocus characteristic parameter model based on Markov random field(MRF)is presented,which converts the depth information estimation problem of defocus characteristics into the optimization problem of energy function.With iterated conditional mode(ICM)algorithm applied to fulfill optimization and least squares estimate(LSE)algorithm employed to estimate the parameters of initial point,performance of the ICM algorithm is improved and the result of the algorithm is prevented from getting into local optimum.The experiments and simulations prove that the model and algorithm are effective and feasible.