Facial Image Deformation Based on Landmark Detection
This is an incremental improvement for applications in image editing or entertainment, focusing on enhancing authenticity in facial modifications.
The paper tackles facial image deformation for tasks like eye expansion and nose/mouth/cheek shrinking using a 106-point landmark detector, finding that Rigid Deformation yields the best quality despite being the slowest method.
In this work, we use facial landmarks to make the deformation for facial images more authentic. The deformation includes the expansion of eyes and the shrinking of noses, mouths, and cheeks. An advanced 106-point facial landmark detector is utilized to provide control points for deformation. Bilinear interpolation is used in the expansion and Moving Least Squares methods (MLS) including Affine Deformation, Similarity Deformation and Rigid Deformation are used in the shrinking. We compare the running time as well as the quality of deformed images using different MLS methods. The experimental results show that the Rigid Deformation which can keep other parts of the images unchanged performs better even if it takes the longest time.