We present an approach for unsupervised alignment of an ensemble of images called congealing. Our algorithm is based on image registration using the mutual information measure as a cost function. The cost function is optimized by a standard gradient descent method in a multiresolution scheme. As opposed to other congealing methods, which use the SSD measure, the mutual information measure is better suited as a similarity measure for registering images since no prior assumptions on the relation of intensities between images are required. We present alignment results on the MNIST handwritten digit database and on facial images obtained from the CVL database.
Fields of Expertise
- Information, Communication & Computing
Storer, M., Urschler, M., & Bischof, H. (2010). Intensity-Based Congealing for Unsupervised Joint Image Alignment. In 20th International IEEE Conference on Pattern Recognition (ICPR) (pp. 1473-1476). Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/ICPR.2010.364