A convolutional approach to reflection symmetry
This work addresses symmetry detection in computer vision, offering a parameter-centered approach that is incremental in improving computational efficiency for known object sizes.
The paper tackles reflection symmetry detection in 2D by introducing a convolutional method based on complex-valued wavelet convolutions, which outperforms the best algorithm on the CVPR 2013 Symmetry Detection Competition Database for single-symmetry cases.
We present a convolutional approach to reflection symmetry detection in 2D. Our model, built on the products of complex-valued wavelet convolutions, simplifies previous edge-based pairwise methods. Being parameter-centered, as opposed to feature-centered, it has certain computational advantages when the object sizes are known a priori, as demonstrated in an ellipse detection application. The method outperforms the best-performing algorithm on the CVPR 2013 Symmetry Detection Competition Database in the single-symmetry case. Code and a new database for 2D symmetry detection is available.