Universal Joint Image Clustering and Registration using Partition Information
This addresses the challenge of aligning and grouping images simultaneously, which is incremental as it builds on information-theoretic methods for registration.
The paper tackles the problem of jointly clustering and registering multiple images by developing algorithms based on multivariate information functionals, proving asymptotic optimality for pairwise registration and consistency for joint clustering-registration, with order-optimal scaling for limited-resolution images.
We consider the problem of universal joint clustering and registration of images and define algorithms using multivariate information functionals. We first study registering two images using maximum mutual information and prove its asymptotic optimality. We then show the shortcomings of pairwise registration in multi-image registration, and design an asymptotically optimal algorithm based on multiinformation. Further, we define a novel multivariate information functional to perform joint clustering and registration of images, and prove consistency of the algorithm. Finally, we consider registration and clustering of numerous limited-resolution images, defining algorithms that are order-optimal in scaling of number of pixels in each image with the number of images.