Affine Differential Invariants for Invariant Feature Point Detection
This work addresses the problem of achieving affine invariance in feature detection for computer vision applications, representing an incremental advancement over existing Euclidean methods.
The paper tackled the limitation of Euclidean-invariant feature detectors by developing an affine-invariant detector based on differential invariants using the equivariant method of moving frames, and also computed fundamental equi-affine invariants for 3D image volumes.
Image feature points are detected as pixels which locally maximize a detector function, two commonly used examples of which are the (Euclidean) image gradient and the Harris-Stephens corner detector. A major limitation of these feature detectors are that they are only Euclidean-invariant. In this work we demonstrate the application of a 2D affine-invariant image feature point detector based on differential invariants as derived through the equivariant method of moving frames. The fundamental equi-affine differential invariants for 3D image volumes are also computed.