Learning deformable shape manifolds

We propose an approach to shape detection of highly deformable shapes in images via manifold learning with regression. Our method does not require shape key points be defined at high contrast image regions, nor do we need an initial estimate of the shape. We only require sufficient representative training data and a rough initial estimate of the object position and scale. We demonstrate the method for face shape learning, and provide a comparison to nonlinear Active Appearance Model. Our method is extremely accurate, to nearly pixel precision and is capable of accurately detecting the shape of faces undergoing extreme expression changes. The technique is robust to occlusions such as glasses and gives reasonable results for extremely degraded image resolutions.

► We achieve state of the art performance on face shape detection. ► The method is non-iterative. ► No sliding window allows for efficient function evaluation. ► It does not require strong shape contours or high resolution. ► A shape model gives reasonable estimates in the case of large occlusions.