A probabilistic 3D object recognition algorithm is presented. In order to g
uide the recognition process the probability that match hypotheses between
image features and model features are correct is computed. A model is devel
oped which uses the probabilistic peaking effect of measured angles and rat
ios of lengths by tracing iso-angle and iso-ratio curves on the viewing sph
ere. The model also accounts for various types of uncertainty in the input
such as incomplete and inexact edge detection. For each match hypothesis th
e pose of the object and the pose uncertainty which is due to the uncertain
ty in vertex position are recovered. This is used to find sets of hypothese
s which reinforce each other by matching features of the same object with c
ompatible uncertainty regions. A probabilistic expression is used to rank t
hese hypothesis sets. The hypothesis sets with the highest rank are output.
The algorithm has been fully implemented, and tested on real images.