Facial Image Deformation Based on Landmark Detection

TL;DR

This paper presents a facial image deformation technique using landmark detection, employing MLS methods for realistic modifications like enlarging eyes and shrinking facial features, with Rigid Deformation providing the best quality.

Contribution

It introduces a novel combination of landmark detection and MLS methods for authentic facial image deformation, emphasizing the effectiveness of Rigid Deformation.

Findings

Rigid Deformation yields the highest quality deformed images.

Rigid Deformation maintains unchanged parts better than other MLS methods.

Rigid Deformation has the longest processing time among the methods.

Abstract

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.