Reliable Reference Areas for 3D Smiling Facial Model Alignment: Posed vs Natural Smile Expressions.

Abstract

To evaluate the reliability of various reference areas for digital alignment between 3D resting and smiling facial models. 3D posed and natural smiling faces of 33 adults were registered to the respective neutral faces, using six matching strategies with different reference matching surfaces: nose (N), nose + central forehead (NFc), nose + whole forehead (NFw), nose + chin (NC), nose + central forehead + chin (NFcC), and nose + whole forehead + chin (NFwC). The positional discrepancies of the registered images were measured at the left and right pupil centers. Two-way ANOVA and post hoc multiple pairwise t test with Bonferroni correction (α = .05) were used to evaluate the measurements. As a result, the use of larger reference areas increases the trueness of image-matching, whereas there was no statistically significant difference between the matching strategies within the same smiling type. Meanwhile, the image registration of posed smiles resulted in fewer positional disparities than the natural smiles with significant differences observed for the registration using the NC and NFcC surface-based matching areas at the right pupil (P = .030 and .026, respectively). The findings of this study suggest that the reference surface areas and smiling types have some impact on the accuracy of 3D smiling facial image alignments. Large and evenly distributed matching surfaces are recommended for posed smiles, whereas caution should be taken when using the chin area as a reference surface for matching natural smile facial images.