Performance Analysis of Cone Detection Algorithms
Letizia Mariotti, Nicholas Devaney

TL;DR
This paper compares the performance of cone detection algorithms using simulated retinal images, demonstrating that image up-sampling improves accuracy and analyzing the impact of noise on parameter estimation.
Contribution
It introduces a simulation technique for realistic cone mosaic images and compares three algorithms using FROC curves, highlighting the benefits of up-sampling.
Findings
Performance improves with image up-sampling.
Estimated regularity is highly sensitive to noise.
Simulated images enable rigorous algorithm comparison.
Abstract
Many algorithms have been proposed to help clinicians evaluate cone density and spacing, as these may be related to the onset of retinal diseases. However, there has been no rigorous comparison of the performance of these algorithms. In addition, the performance of such algorithms is typically determined by comparison with human observers. Here we propose a technique to simulate realistic images of the cone mosaic. We use the simulated images to test the performance of two popular cone detection algorithms and we introduce an algorithm which is used by astronomers to detect stars in astronomical images. We use Free Response Operating Characteristic (FROC) curves to evaluate and compare the performance of the three algorithms. This allows us to optimize the performance of each algorithm. We observe that performance is significantly enhanced by up-sampling the images. We investigate the…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
