The goal of this thesis is to use machine learning methods for datasets of scanned faces and to create a program that allows to explore and edit faces represented as triangle meshes with a number of controls. Firstly we had to reduce dimension of triangle meshes by PCA and then we tried to predict shape of meshes according to physical properties like weight, height, age and BMI. The modeled faces can be used in animation or games.

Indiana University-Purdue University Indianapolis (IUPUI) / This thesis explores a data driven machine learning based solution for Facial reconstruction from three dimensional (3D) skull shape for recognizing or identifying unknown subjects during forensic investigation. With over 8000 unidentified bodies during the past 3 decades, facial reconstruction of disintegrated bodies in helping with identification has been a critical issue for forensic practitioners. Historically, clay modelling has been used for facial reconstruction that not only requires an expert in the field but also demands a substantial amount of time for modelling, even after acquiring the skull model. Such manual reconstruction typically takes from a month to over 3 months of time and effort. The solution presented in this thesis uses 3D Cone Beam Computed Tomography (CBCT) data collected from many people to build a model of the relationship of facial skin to skull bone over a dense set of locations on the face. It then uses this skin-to-bone relationship model learned from the data to reconstruct the predicted face model from a skull shape of an unknown subject. The thesis also extends the algorithm in a way that could help modify the reconstructed face model interactively to account for the effects of age or weight. This uses the predicted face model as a starting point and creates different hypotheses of the facial appearances for different physical attributes. Attributes like age and body mass index (BMI) are used to show the physical facial appearance changes with the help of a tool we constructed. This could improve the identification process. The thesis also presents a methods designed for testing and validating the facial reconstruction algorithm.

Processes of biological changes of organism over time distinctly manifest themselves in a face morphology. The present study age changes are observed as shape and size changes of transversal dates of surface 3D virtual models of faces of 443 women and men (22-88 years old) devided into six age groups in decade. Differences in faces among each age group with respect to the sex were investigated and a sexual dimorphism and its gradual progress with the age using methods of geometric morphometrics (coherent point drift - dense correspondence algorithm, principal component analysis, per vertex t-test, shell-to-shell deviation). A significant difference among age categories was observedd both in shape as well as in form of the face. The faces of women and men were becoming wider with age and convexity was decreasing at the same time. A decline of the whole forehead and of the profile of the men's nose was observed, whereas the women's foreheadwas getting bevel due to the decline of the top part and a profile of the nose wasn't changed with the age. On contrary, the men's chin was unvarying with the age, while the women's chin was sliding out foward. There was observed a distinct decline in the front part of a upper jaw with the both sex. It was found out that after the seventh life decade the face gets...

<p>This thesis explores a data driven machine learning based solution for Facial reconstruction from three dimensional (3D) skull shape for recognizing or identifying unknown subjects during forensic investigation. With over 8000 unidentified bodies during the past 3 decades, facial reconstruction of disintegrated bodies in helping with identification has been a critical issue for forensic practitioners. Historically, clay modelling has been used for facial reconstruction that not only requires an expert in the field but also demands a substantial amount of time for modelling, even after acquiring the skull model. Such manual reconstruction typically takes from a month to over 3 months of time and effort. The solution presented in this thesis uses 3D Cone Beam Computed Tomography (CBCT) data collected from many people to build a model of the relationship of facial skin to skull bone over a dense set of locations on the face. It then uses this skin-to-bone relationship model learned from the data to reconstruct the predicted face model from a skull shape of an unknown subject. The thesis also extends the algorithm in a way that could help modify the reconstructed face model interactively to account for the effects of age or weight. This uses the predicted face model as a starting point and creates different hypotheses of the facial appearances for different physical attributes. Attributes like age and body mass index (BMI) are used to show the physical facial appearance changes with the help of a tool we constructed. This could improve the identification process. The thesis also presents a methods designed for testing and validating the facial reconstruction algorithm. <br></p>

This study is based on evaluative longitudinal data of facial development in a group of children from 6 to 12 years. The research used three-dimensional models of the faces of 18 girls and 15 boys that were scanned at yearly intervals. These models were used to follow development of the face and its particular areas including analysis of variability (PCA). Developmental changes were observed for each gender separately as well as for the development of sexual dimorphism. Results were visualized by using superimposed color maps of average faces of a particular age group and maps depicting the statistically significant differences in individual areas. The presented data exhibited growth in the face of both genders, while slightly bigger changes in the form of the face were observed in the boys' samples. For girls and boys the most intensive growth was found in the direction of the width and height of the entire face and the nose, especially in the direction of length. These changes took place throughout the whole studied period of growth, yet more intensive growth was evident for girls beginning at age 10 years and for boys from 11 years onward. Shape changes also occurred with age for both genders: the face gradually narrowed, the cheeks flattened and a more retruded position of the forehead...