| 摘要 |
Techniques for generating a distorted template for a given facial image are provided. First, at least one facial feature point from a given facial image is selected. The selected facial feature has location information associated therewith. A representation of a region proximate to the selected facial feature point is then generated. Next, the location information associated with the selected facial feature point and/or the representation of the region proximate to the selected facial feature point are distorted. A distorted template is then formed, wherein the distorted template comprises the distorted location information associated with the selected facial feature point and/or the distorted representation of the region proximate to the selected facial feature point.
|
