MIFT: A Mirror Reflection Invariant Feature Descriptor

Abstract. In this paper, we present a mirror reflection invariant de-scriptor which is inspired from SIFT. While preserving tolerance to scale, rotation and even affine transformation, the proposed descriptor, MIFT, is also invariant to mirror reflection. We analyze the structure of MIFT and show how MIFT outperforms SIFT in the context of mirror reflec-tion while performs as well as SIFT when there is no mirror reflection. The performance evaluation is demonstrated on natural images such as reflection on the water, non-rigid symmetric objects viewed from differ-ent sides, and reflection in the mirror. Based on MIFT, applications to image search and symmetry axis detection for planar symmetric objects are also shown.