Scale Invariant Feature Transform (SIFT) is a very powerful technique for image registration. While SIFT descriptors accurately extract invariant image characteristics around keypoints, the commonly used matching approach for registration is overly simplified, because it completely ignores the geometric information among descriptors. In this paper, we formulate keypoint matching as a global optimization problem and provide a suboptimum solution using belief propagation. Experimental results show significant improvement over previous approaches.
- belief networks
- image matching
- image registration
- belief propagation
- invariant image characteristics
- scale invariant feature transform