Robust extraction of features in a severely defocused image is the fundamental problem of a phase-difference autofocusing system. In order to solve this problem, a multi-resolution feature extraction algorithm is proposed. Given the extracted features, the proposed auto-focusing system can provide the ideal focusing position using phase correlation matching. Since the proposed system accurately estimates the phase difference in the out-of-focus blurred image under low illumination, it can provide fast, robust auto focusing.