Given an ensemble with multiple object classes, the authors propose an approach to solve two problems automatically and simultaneously, image alignment and clustering.
Joint alignment for an image ensemble can rectify images in the spatial domain such that the aligned images are as similar to each other as possible. This important technology has been applied to various object classes and medical applications; however, previous approaches to joint alignment work on an ensemble of a single object class. In the authors’ approach, both the alignment parameters and clustering parameters are formulated into a unified objective function, whose optimization leads to an unsupervised joint estimation approach. It is further extended to semi-supervised simultaneous estimation where a few labeled images are provided. Extensive experiments on diverse real-world databases demonstrated the capabilities of the authors’ work on this challenging problem. (Publisher abstract provided)
Similar Publications
- Developing and validating an emotion recognition test for policing
- Face Finder: Filtering a Large Face Database using Scars, Marks and Tattoos
- Population-level Effects on Crime of Recovering Firearms from Armed Prohibited Persons: Intention-to-treat Analysis of a Pragmatic Cluster-randomised Trial in California Cities