An unsupervised algorithm for detecting good continuation in Dot Patterns
Resumen:
In this article we describe an algorithm for the automatic detection of perceptually relevant configurations of `good continuation' of points in 2D point patterns. The algorithm is based on the `a contrario' detection theory and on the assumption that `good continuation' of points are locally quasi-symmetric. The algorithm has only one critical parameter, which controls the number of false detections.
| 2017 | |
|
Good continuation Gestalt Dots Non-accidentalness Local symmetry |
|
| Inglés | |
| Universidad de la República | |
| COLIBRI | |
| http://hdl.handle.net/20.500.12008/8904 | |
| Acceso abierto | |
| Licencia Creative Commons Atribución – No Comercial – Sin Derivadas (CC BY-NC-SA 4.0) |
| Sumario: | In this article we describe an algorithm for the automatic detection of perceptually relevant configurations of `good continuation' of points in 2D point patterns. The algorithm is based on the `a contrario' detection theory and on the assumption that `good continuation' of points are locally quasi-symmetric. The algorithm has only one critical parameter, which controls the number of false detections. |
|---|
