GLAMpoints: Greedily Learned Accurate Match points
This work addresses the specific problem of improving feature matching for medical imaging, particularly in ophthalmology, by introducing a domain-optimized detector, though it is incremental as it builds on CNN-based approaches.
The paper tackles the problem of feature point detection in challenging retinal slitlamp images, where classical methods fail due to low quality and insufficient features, and shows that GLAMpoints significantly outperforms both classical and state-of-the-art CNN-based methods in matching and registration quality.
We introduce a novel CNN-based feature point detector - GLAMpoints - learned in a semi-supervised manner. Our detector extracts repeatable, stable interest points with a dense coverage, specifically designed to maximize the correct matching in a specific domain, which is in contrast to conventional techniques that optimize indirect metrics. In this paper, we apply our method on challenging retinal slitlamp images, for which classical detectors yield unsatisfactory results due to low image quality and insufficient amount of low-level features. We show that GLAMpoints significantly outperforms classical detectors as well as state-of-the-art CNN-based methods in matching and registration quality for retinal images. Our method can also be extended to other domains, such as natural images. Training code and model weights are available at https://github.com/PruneTruong/GLAMpoints_pytorch.