Robust hypothesis verification for model based object reconition using gaussian error model

摘要

The use of hypothesis verification is reurrent in the model based recognition iteraature. Small sets of features forming slaient grupos are paired with model featurees. poses can be h6ypothesised from this small set of eature-to-feature correspondences. he verification of the pose consists in measuring how much model features transformed by the computed pose coincide with image features. When data involved in the initial pairing are noisy the pose is inaccurate and the verification is a difficult problem.