Bas-relief Generation from Face Photograph Based on Facial Feature Detection
Hai Thien To, Bong-Soo Sohn · International Conference on Human-Computer Interaction · 2016
In this paper, we propose a method that creates bas-relief surfaces by brightness dark-parts on the face in the photograph. The proposed approach includes two phases: firstly, we detect the special-parts on the face, then the second phase determines the dark-parts and adjusts the brightness of image. By this way, we detected face parts which combine with the knowledge of the Equations of Lines to make the nose part will not be sunk suddenly in 3d environment and make them look like realistically. We called the proposed method is abEL (adjust brightness by the Equations of Lines). Additionally, we use some image processing techniques (such as the morphological opening-closing by reconstruction with suitable thresholds to invert color of the hair part and the other parts which are outside of the face).By this way, using this technique is not only make eyebrows brighter, but also make the whites of the eyes more darker which make the photograph becomes better.