We propose a noise robust two-step phase shifting algorithm for the evaluation of random and unknown phase step. In this algorithm, the phase within a small size two-dimensional window around a user selected pixel in an interferogram is approximated as a quadratic surface. The problem of quadratic phase fitting parameter estimation is formulated as a state space analysis performed using the extended Kalman filter. The phase step is evaluated from the estimated parameters and subsequently the interferogram phase distribution is obtained. Simulation and experimental results are demonstrated.