Artículo de revista
A fast probabilistic model for hypothesis rejection in SIFT-based object recognition
Fecha
2006Registro en:
PROGRESS IN PATTERN RECOGNITION, IMAGE ANALYSIS AND APPLICATIONS, PROCEEDINGS Book Series: LECTURE NOTES IN COMPUTER SCIENCE Volume: 4225 Pages: 696-705 Published: 2006
0302-9743
Autor
Loncomilla, Patricio
Ruiz del Solar, Javier
Institución
Resumen
This paper proposes an improvement over the traditional SIFT-based object recognition methodology proposed by Lowe [3]. This improvement corresponds to a fast probabilistic model for hypothesis rejection (affine solution verification stage), which allows a large reduction in the number of false positives. The new probabilistic model is evaluated in an object recognition task using a database of 100 pairs of images.