Exploring Reliability for Automatic Identity Verification with Statistical Shape Models

One of the drawbacks of statistical shape models is their occasional failure to converge. Although visually this fact is usually easy to assess there is not, in general, an automatic way to detect the failure. In this work we introduce a generic reliability measure for statistical shape models. It is based on a probabilistic framework and uses information extracted by the model itself during the matching process. The proposed method was validated with two variants of Active Shape Models by working with facial images. The experimental results showed a high correlation between the segmentation accuracy and the estimated reliability.