DAcImPro: A novel database of acquired image projections and its application to object recognition
Résumé
Projector-camera systems are designed to improve the projection qual-
ity by comparing original images with their captured projections, which is usually
complicated due to high photometric and geometric variations. Many research
works address this problem using their own test data which makes it extremely
difficult to compare different proposals. This paper has two main contributions.
Firstly, we introduce a new database of image projections that, covering photo-
metric and geometric conditions and providing data for ground-truth computa-
tion, can serve to evaluate different algorithms in projector-camera systems. Sec-
ondly, a new object recognition scenario from acquired projections is presented,
which could be of a great interest in such domains, as home video projections and
public presentations. We show that the task is more challenging than the classical
recognition problem and thus requires additional pre-processing, such as color
compensation or projection area selection