A well balanced and harmonious soft tissue profile is an important consideration in orthodontic diagnosis and treatment planning. The purpose of this study was to determine the soft tissue profile norms in Tswana subjects, compare the results with those of other ethnic groups and develop soft tissue “norms” or standards which may be useful as guides for diagnosis and treatment planning for Tswana orthodontic patients in South Africa. 420 subjects between the ages of 15-20 were randomly selected from their schools at no criteria. 102 Tswana (52 female and 50 male) and 50 non-Tswana subjects (25 female and 25 male) were selected according to criteria. The subjects were selected for excellence of occlusion, balanced facial proportion, complete dentition (third molars disregarded) dental Class I occlusion with normal overbite and overjet, minimal spacing or crowding, no history of orthodontic treatment and no gross caries. Various orthodontic analyses were used to measure and determine soft tissue facial profiles in both Tswana and non-Tswana subjects. Results were analysed statistically to determine the differences in facial profiles between Tswana and non-Tswana subjects and compare these to Caucasian and African-American norms. The results indicate that Tswana subjects had a flatter profile than non-Tswana subjects whose facial profiles were fuller. The study also indicates that the facial profile values established for Caucasian subjects are not applicable to Tswana and African-American subjects. The findings of the present study showed that when planning orthodontic treatment for Tswana subjects it may be useful to perhaps take into account some measurements which may be more appropriate. Copyright / Dissertation (MSc(Odont))--University of Pretoria, 2010. / Orthodontics / unrestricted

The purpose of this research was to enhance the methods towards the development of an efficient three dimensional face recognition system. More specifically, one of our aims was to investigate how the use of curvature of the diagonal profiles, extracted from 3D facial geometry models can help the neutral face recognition processes. Another aim was to use a gender classifier employed on 3D facial geometry in order to reduce the search space of the database on which facial recognition is performed. 3D facial geometry with facial expression possesses considerable challenges when it comes face recognition as identified by the communities involved in face recognition research. Thus, one aim of this study was to investigate the effects of the curvature-based method in face recognition under expression variations. Another aim was to develop techniques that can discriminate both expression-sensitive and expression-insensitive regions for ii face recognition based on non-neutral face geometry models. In the case of neutral face recognition, we developed a gender classification method using support vector machines based on the measurements of area and volume of selected regions of the face. This method reduced the search range of a database initially for a given image and hence reduces the computational time. Subsequently, in the characterisation of the face images, a minimum feature set of diagonal profiles, which we call T shape profiles, containing diacritic information were determined and extracted to characterise face models. We then used a method based on computing curvatures of selected facial regions to describe this feature set. In addition to the neutral face recognition, to solve the problem arising from data with facial expressions, initially, the curvature-based T shape profiles were employed and investigated for this purpose. For this purpose, the feature sets of the expression-invariant and expression-variant regions were determined respectively and described by geodesic distances and Euclidean distances. By using regression models the correlations between expressions and neutral feature sets were identified. This enabled us to discriminate expression-variant features and there was a gain in face recognition rate. The results of the study have indicated that our proposed curvature-based recognition, 3D gender classification of facial geometry and analysis of facial expressions, was capable of undertaking face recognition using a minimum set of features improving efficiency and computation.

The purpose of this research was to enhance the methods towards the development of an efficient three dimensional face recognition system. More specifically, one of our aims was to investigate how the use of curvature of the diagonal profiles, extracted from 3D facial geometry models can help the neutral face recognition processes. Another aim was to use a gender classifier employed on 3D facial geometry in order to reduce the search space of the database on which facial recognition is performed. 3D facial geometry with facial expression possesses considerable challenges when it comes face recognition as identified by the communities involved in face recognition research. Thus, one aim of this study was to investigate the effects of the curvature-based method in face recognition under expression variations. Another aim was to develop techniques that can discriminate both expression-sensitive and expression-insensitive regions for ii face recognition based on non-neutral face geometry models. In the case of neutral face recognition, we developed a gender classification method using support vector machines based on the measurements of area and volume of selected regions of the face. This method reduced the search range of a database initially for a given image and hence reduces the computational time. Subsequently, in the characterisation of the face images, a minimum feature set of diagonal profiles, which we call T shape profiles, containing diacritic information were determined and extracted to characterise face models. We then used a method based on computing curvatures of selected facial regions to describe this feature set. In addition to the neutral face recognition, to solve the problem arising from data with facial expressions, initially, the curvature-based T shape profiles were employed and investigated for this purpose. For this purpose, the feature sets of the expression-invariant and expression-variant regions were determined respectively and described by geodesic distances and Euclidean distances. By using regression models the correlations between expressions and neutral feature sets were identified. This enabled us to discriminate expression-variant features and there was a gain in face recognition rate. The results of the study have indicated that our proposed curvature-based recognition, 3D gender classification of facial geometry and analysis of facial expressions, was capable of undertaking face recognition using a minimum set of features improving efficiency and computation.

Após a análise subjetiva utilizando fotografias de perfil de 540 indivíduos, selecionou-se 120 indivíduos adultos jovens (60 do gênero masculino e 60 do feminino), leucodermas, com perfil facial harmonioso, equilíbrio do terço inferior da face e selamento labial passivo, com o objetivo de estabelecer parâmetros cefalométricos para avaliar a estética facial e analisar as correlações entre referências anteroposteriores do tecido tegumentar da face. Utilizando telerradiografias dos indivíduos selecionados, foram desenhadas estruturas anatômicas de interesse e traçada a linha vertical passando pelo ponto sela (LSv) e linhas horizontais verdadeiras passando pelos pontos PRT (ponto de referência da fronte), Pn, A, Ls, Li, B e Pg. Os valores médios cefalométricos obtidos para o gênero masculino e feminino e o total da amostra foram submetidos aos testes estatísticos. As medidas cefalométricas avaliadas mostraram-se maiores no gênero masculino do que no feminino. No gênero masculino, todas as medidas cefalométricas do terço médio e inferior apresentaram correlação positiva estatisticamente significativa com a referência do terço superior da face e todas as correlações mostraram-se valores maiores que no feminino. No gênero feminino, não foram observadas correlações diretas estatisticamente significativas para as medidas Sv-B (p = 0,107) e Sv-Pg (p = 0,091). As fórmulas para a previsibilidade dos valores de Sv - Pn, Sv - A, Sv - Ls, Sv - Li, Sv - B e Sv - Pg para o gênero masculino e o feminino em função da medida Sv-PRT mostraram-se igual para ambos os gêneros, necessitando ser acrescido um valor compensatório a cada medida para os homens. / After subjective analysis of profile photographs of 540 individuals, 120 young adults (60 males and 60 females), leucodermas, with balanced facial profile, equilibrium of the lower facial third and passive lip sealing, in order to establish cephalometrics parameters for facial esthetics and evaluate the correlation between anteroposterior references of facial soft tissues. By using lateral radiographies of the selected individuals, anatomic structures of interesting were drawn, and the true vertical line passing through Sela point (LSv) and true horizontal lines passing through points PRT (reference point of the forehead), Pn, A, Ls, Li, B e Pg. The cephalometric average values which were calculated for masculine, feminine genders and the total of sample were evaluated by statics tests. The cephalometric measures analyzed showed high values to the masculine gender in comparing to the feminine gender. In the masculine gender, all the cephalometric measures of the middle and lower facial third presented positive correlation statistically significant to the reference of the superior facial third and all correlations were higher than female measures. In the feminine gender, direct correlations statistically significant for Sv-B (p = 0,107) e Sv-Pg (p = 0,091) measures. The formulas for the prevision of the values of Sv - Pn, Sv - A, Sv - Ls, Sv - Li, Sv - B e Sv - Pg dimensions for males and females individuals in function of Sv-PRT showed similar in both genders, needing to be added a specific value for each measures for males individuals.

Após a análise subjetiva utilizando fotografias de perfil de 540 indivíduos, selecionou-se 120 indivíduos adultos jovens (60 do gênero masculino e 60 do feminino), leucodermas, com perfil facial harmonioso, equilíbrio do terço inferior da face e selamento labial passivo, com o objetivo de estabelecer parâmetros cefalométricos para avaliar a estética facial e analisar as correlações entre referências anteroposteriores do tecido tegumentar da face. Utilizando telerradiografias dos indivíduos selecionados, foram desenhadas estruturas anatômicas de interesse e traçada a linha vertical passando pelo ponto sela (LSv) e linhas horizontais verdadeiras passando pelos pontos PRT (ponto de referência da fronte), Pn, A, Ls, Li, B e Pg. Os valores médios cefalométricos obtidos para o gênero masculino e feminino e o total da amostra foram submetidos aos testes estatísticos. As medidas cefalométricas avaliadas mostraram-se maiores no gênero masculino do que no feminino. No gênero masculino, todas as medidas cefalométricas do terço médio e inferior apresentaram correlação positiva estatisticamente significativa com a referência do terço superior da face e todas as correlações mostraram-se valores maiores que no feminino. No gênero feminino, não foram observadas correlações diretas estatisticamente significativas para as medidas Sv-B (p = 0,107) e Sv-Pg (p = 0,091). As fórmulas para a previsibilidade dos valores de Sv - Pn, Sv - A, Sv - Ls, Sv - Li, Sv - B e Sv - Pg para o gênero masculino e o feminino em função da medida Sv-PRT mostraram-se igual para ambos os gêneros, necessitando ser acrescido um valor compensatório a cada medida para os homens. / After subjective analysis of profile photographs of 540 individuals, 120 young adults (60 males and 60 females), leucodermas, with balanced facial profile, equilibrium of the lower facial third and passive lip sealing, in order to establish cephalometrics parameters for facial esthetics and evaluate the correlation between anteroposterior references of facial soft tissues. By using lateral radiographies of the selected individuals, anatomic structures of interesting were drawn, and the true vertical line passing through Sela point (LSv) and true horizontal lines passing through points PRT (reference point of the forehead), Pn, A, Ls, Li, B e Pg. The cephalometric average values which were calculated for masculine, feminine genders and the total of sample were evaluated by statics tests. The cephalometric measures analyzed showed high values to the masculine gender in comparing to the feminine gender. In the masculine gender, all the cephalometric measures of the middle and lower facial third presented positive correlation statistically significant to the reference of the superior facial third and all correlations were higher than female measures. In the feminine gender, direct correlations statistically significant for Sv-B (p = 0,107) e Sv-Pg (p = 0,091) measures. The formulas for the prevision of the values of Sv - Pn, Sv - A, Sv - Ls, Sv - Li, Sv - B e Sv - Pg dimensions for males and females individuals in function of Sv-PRT showed similar in both genders, needing to be added a specific value for each measures for males individuals.