Random Gabor based templates for facial expression recognition in images with facial occlusion

Robust facial expression recognition (FER) under occluded face conditions is challenging. It requires robust algorithms of feature extraction and investigations into the effects of different types of occlusion on the recognition performance to gain insight. Previous FER studies in this area have been limited. They have spanned recovery strategies for loss of local texture information and testing limited to only a few types of occlusion and predominantly a matched train-test strategy. This paper proposes a robust approach that employs a Monte Carlo algorithm to extract a set of Gabor based part-face templates from gallery images and converts these templates into template match distance features. The resulting feature vectors are robust to occlusion because occluded parts are covered by some but not all of the random templates. The method is evaluated using facial images with occluded regions around the eyes and the mouth, randomly placed occlusion patches of different sizes, and near-realistic occlusion of eyes with clear and solid glasses. Both matched and mis-matched train and test strategies are adopted to analyze the effects of such occlusion. Overall recognition performance and the performance for each facial expression are investigated. Experimental results on the Cohn-Kanade and JAFFE databases demonstrate the high robustness and fast processing speed of our approach, and provide useful insight into the effects of occlusion on FER. The results on the parameter sensitivity demonstrate a certain level of robustness of the approach to changes in the orientation and scale of Gabor filters, the size of templates, and occlusions ratios. Performance comparisons with previous approaches show that the proposed method is more robust to occlusion with lower reductions in accuracy from occlusion of eyes or mouth.

Facial Feature Tracking and Occlusion Recovery in American Sign Language

Facial features play an important role in expressing grammatical information in signed languages, including American Sign Language(ASL). Gestures such as raising or furrowing the eyebrows are key indicators of constructions such as yes-no questions. Periodic head movements (nods and shakes) are also an essential part of the expression of syntactic information, such as negation (associated with a side-to-side headshake). Therefore, identification of these facial gestures is essential to sign language recognition. One problem with detection of such grammatical indicators is occlusion recovery. If the signer's hand blocks his/her eyebrows during production of a sign, it becomes difficult to track the eyebrows. We have developed a system to detect such grammatical markers in ASL that recovers promptly from occlusion. Our system detects and tracks evolving templates of facial features, which are based on an anthropometric face model, and interprets the geometric relationships of these templates to identify grammatical markers. It was tested on a variety of ASL sentences signed by various Deaf native signers and detected facial gestures used to express grammatical information, such as raised and furrowed eyebrows as well as headshakes.

Facial type measurements influence on transverse dimensions of normal occlusion arches

Objective – To correlate facial type measurements of Caucasian individuals with transverse dimensions of normal occlusion arches. Methods – Twenty-one pairs of dental models were selected according to the following inclusion criteria: presence of all permanent teeth from 1 st molar to 1 st molar; normal occlusion; no prosthetic crowns; no previous orthodontic treatment and 2 mm or less of crow- dings or spacings. The cephalometric measurements of lateral cephalometric X-ray of the same individuals were taken and tabulat ed. To evaluate the repetition of arch measurements, paired Student’s t-test and Pearson's correlation coefficient were used. The r elationship between the measurements was analysed by using the Pearson’s correlation. Results – The repetition of the measurements showed high correlation and no systematic error. In the comparison between the measurements, a moderate negative correlation was observed b et- ween facial axis angle and the measurements Upper and Lower 6-6, whereas a positive correlation was observed between dentition height and the latter. Conclusion – It was observed a negative correlation between facial axis angle and upper and lower inter-molar distance as well as a positive correlation between dentition height and upper and lower inter-molar distance.

Toward a more robust facial expression recognition in occluded images using randomly sampled Gabor based templates

Occlusion is a big challenge for facial expression recognition (FER) in real-world situations. Previous FER efforts to address occlusion suffer from loss of appearance features and are largely limited to a few occlusion types and single testing strategy. This paper presents a robust approach for FER in occluded images and addresses these issues. A set of Gabor based templates is extracted from images in the gallery using a Monte Carlo algorithm. These templates are converted into distance features using template matching. The resulting feature vectors are robust to occlusion. Occluded eyes and mouth regions and randomly places occlusion patches are used for testing. Two testing strategies analyze the effects of these occlusions on the overall recognition performance as well as each facial expression. Experimental results on the Cohn-Kanade database confirm the high robustness of our approach and provide useful insights about the effects of occlusion on FER. Performance is also compared with previous approaches.

Robust facial feature extraction and matching

Automated feature extraction and correspondence determination is an extremely important problem in the face recognition community as it often forms the foundation of the normalisation and database construction phases of many recognition and verification systems. This paper presents a completely automatic feature extraction system based upon a modified volume descriptor. These features form a stable descriptor for faces and are utilised in a reversible jump Markov chain Monte Carlo correspondence algorithm to automatically determine correspondences which exist between faces. The developed system is invariant to changes in pose and occlusion and results indicate that it is also robust to minor face deformations which may be present with variations in expression.

Towards spontaneous facial expression recognition in real-world video

Facial expression is an important channel of human social communication. Facial expression recognition (FER) aims to perceive and understand emotional states of humans based on information in the face. Building robust and high performance FER systems that can work in real-world video is still a challenging task, due to the various unpredictable facial variations and complicated exterior environmental conditions, as well as the difficulty of choosing a suitable type of feature descriptor for extracting discriminative facial information. Facial variations caused by factors such as pose, age, gender, race and occlusion, can exert profound influence on the robustness, while a suitable feature descriptor largely determines the performance. Most present attention on FER has been paid to addressing variations in pose and illumination. No approach has been reported on handling face localization errors and relatively few on overcoming facial occlusions, although the significant impact of these two variations on the performance has been proved and highlighted in many previous studies. Many texture and geometric features have been previously proposed for FER. However, few comparison studies have been conducted to explore the performance differences between different features and examine the performance improvement arisen from fusion of texture and geometry, especially on data with spontaneous emotions. The majority of existing approaches are evaluated on databases with posed or induced facial expressions collected in laboratory environments, whereas little attention has been paid on recognizing naturalistic facial expressions on real-world data. This thesis investigates techniques for building robust and high performance FER systems based on a number of established feature sets. It comprises of contributions towards three main objectives: (1) Robustness to face localization errors and facial occlusions. An approach is proposed to handle face localization errors and facial occlusions using Gabor based templates. Template extraction algorithms are designed to collect a pool of local template features and template matching is then performed to covert these templates into distances, which are robust to localization errors and occlusions. (2) Improvement of performance through feature comparison, selection and fusion. A comparative framework is presented to compare the performance between different features and different feature selection algorithms, and examine the performance improvement arising from fusion of texture and geometry. The framework is evaluated for both discrete and dimensional expression recognition on spontaneous data. (3) Evaluation of performance in the context of real-world applications. A system is selected and applied into discriminating posed versus spontaneous expressions and recognizing naturalistic facial expressions. A database is collected from real-world recordings and is used to explore feature differences between standard database images and real-world images, as well as between real-world images and real-world video frames. The performance evaluations are based on the JAFFE, CK, Feedtum, NVIE, Semaine and self-collected QUT databases. The results demonstrate high robustness of the proposed approach to the simulated localization errors and occlusions. Texture and geometry have different contributions to the performance of discrete and dimensional expression recognition, as well as posed versus spontaneous emotion discrimination. These investigations provide useful insights into enhancing robustness and achieving high performance of FER systems, and putting them into real-world applications.

Avaliação da alteração do plano oclusal em cirurgias ortognáticas combinadas com utilização de fixação interna rígida em pacientes com padrão facial de Classe II

OBJETIVO: avaliar a estabilidade de cirurgias bimaxilares com fixação interna rígida, na qual promoveu-se uma rotação anti-horária da mandíbula e conseqüente redução do ângulo do plano oclusal. METODOLOGIA: foram estudados 15 pacientes com padrão facial de Classe II e deficiência mandibular. Os movimentos cirúrgicos foram avaliados por meio de medidas lineares e angulares realizadas no programa CefX, obtidas de telerradiografias cefalométricas em norma lateral em três diferentes tempos: (T0) pré-operatório, (T1) pós-operatório imediato e (T2) pós-operatório de no mínimo 6 meses. RESULTADOS E CONCLUSÕES: os resultados demonstraram que a cirurgia bimaxilar promove mudanças faciais significativas e, principalmente, que a rotação anti-horária da mandíbula com redução do ângulo do plano oclusal mostrou-se estatisticamente estável, sendo uma opção confiável em cirurgias de pacientes com padrão facial de Classe II com deficiência mandibular.

Análise fotogramétrica e subjetiva do perfil facial de indivíduos com oclusão normal

OBJETIVO: avaliar o perfil facial em fotografias de jovens brasileiros leucodermas com oclusão normal. METODOLOGIA: 58 fotografias de perfil de 23 jovens do gênero masculino e 35 do feminino, com idade média de 16,03 ± 2,04 anos, que apresentavam 4 das 6 chaves de oclusão de Andrews. As fotografias foram julgadas por 21 alunos e 2 professores de pós-graduação. Também foi feita fotogrametria dos integrantes da amostra. RESULTADOS E CONCLUSÕES: verificou-se que a oclusão normal natural não foi indicativa de beleza do perfil facial, visto que 28% dos perfis avaliados foram classificados como desagradáveis. Dentre as medidas pesquisadas para os grupos de perfis agradáveis, aceitáveis e desagradáveis, verificou-se que poucas foram as que se apresentaram estatisticamente diferentes, chamando a atenção para o fato que, isoladamente, as medidas fotogramétricas do perfil facial não poderiam indicar beleza do perfil.

Determinação da relação central. Estudo sobre as posições laterais da mandíbula, em relação à linha mediana facial, em função de dois métodos para esta determinação.

The authors studied the lateral positional desviations of the mandible, in relation to the facial median line in 30 (thirty) full edentulous patients, with the purpose to verify the influence of the unstrained guided (chinpoint guidance) and deglutition methods for the determination of centric relation. According the results obtained they conclude that the unstrained guided method produced a mandibular lateral desviation with a mean value of the 0.752 mm and in the deglutition method the mean value observed was 1.109 mm. The statistical analysis of the results revealed for the unstrained guided method a proportion of the points to the right and left of the median line not statistically significant, while for the deglutition method the difference was statistically significant at a level of 5%.

Divine proportions and facial esthetics after manipulation of frontal photographs.

AIM: To investigate the relationship between divine proportion and facial esthetics in frontal photographs as well as whether any of the 4 ratios for manipulation provide more favorable facial esthetics. MATERIAL AND METHODS: The sample comprised 20 frontal photographs of Caucasian individuals (11 males and 9 females). The photographs were digitized and stored on a compact disk. A photometric analysis was created with 7 facial segments that were measured on Image Tool software and 4 ratios between 2 facial segments calculated using Microsoft Excel. This manipulation led to 5 different photographs of the same individual: one photograph with no manipulation and the others with 1 of the ratios manipulated in the Deformer 2.0 to very close or equal to 1.618. Thereafter, the 5 photographs of all individuals were evaluated by 12 examiners. The examiners selected those photographs that were esthetically more pleasant. CONCLUSION: After evaluation, a chi-square test revealed a relationship between divine proportion and facial esthetics. Among the ratios selected, R1 and R2 provided more favorable facial esthetics.

Orthognathic Surgery in the Young Cleft Patient: Preliminary Study on Subsequent Facial Growth

Purpose: This study evaluated the long-term effects of orthognathic surgery on subsequent growth of the maxillomandibular complex in the young cleft patient. Patients and Methods: We evaluated 12 young cleft patients (9 male and 3 female patients), with a mean age of 12 years 6 months (range, 9 years 8 months to 15 years 4 months), who underwent Le Fort I osteotomies, with maxillary advancement, expansion, and/or downgrafting, by use of autogenous bone or hydroxyapatite grafts, when indicated, for maxillary stabilization. Five patients had concomitant osteotomies of the mandibular ramus. All patients had presurgical and postsurgical orthodontic treatment to control the occlusion. Radiographs taken at initial evaluation (T1) and presurgery (T2) were compared to establish the facial growth vector before surgery, whereas radiographs taken immediately postsurgery (T3) and at longest follow-up (T4) were used to determine postsurgical growth. Each patient's lateral cephalograms were traced, and 16 landmarks were identified and used to compute 11 measurements describing presurgical and postsurgical growth. Results: Before surgery, all patients had relatively normal growth. After surgery, cephalograms showed statistically significant growth changes from T3 to T4, with the maxillary depth decreasing by -3.3° ± 1.8°, Sella-nasion-point A by -3.3° ± 1.8°, and point A-nasion-point B by -3.6° ± 2.8°. The angulation of the maxillary incisors increased by 9.2° ± 11.7°. Of 12 patients, 11 showed disproportionate postsurgical jaw growth. Maxillary growth occurred predominantly in a vertical vector with no anteroposterior growth, even though most patients had shown anteroposterior growth before surgery. The distance increased in the linear measurement from nasion to gnathion by 10.3 ± 7.9 mm. Four of 5 patients operated on during the mixed dentition phase had teeth that erupted through the cleft area. A variable impairment of postoperative growth was seen with the 2 types of grafting material used. No significant difference was noted in the effect on growth in patients with unilateral clefts versus those with bilateral clefts. The presence of a pharyngeal flap was noted to adversely affect growth, whereas simultaneous mandibular surgery did not. After surgery, 11 of 12 patients tended toward a Class III end-on occlusal relation. Conclusions: Orthognathic surgery may be performed on growing cleft patients when mandated by psychological and/or functional concerns. The surgeon must be cognizant of the adverse postsurgical growth outcomes when performing orthognathic surgery on growing cleft patients with the possibility for further surgery requirements. Performing maxillary osteotomies on cleft patients would be more predictable after completion of facial growth. © 2008 American Association of Oral and Maxillofacial Surgeons.

Avaliação dos contatos oclusais em próteses provisórias unitárias implantossuportadas confeccionadas com e sem arco facial

To assess the number of occlusal contacts achieved in temporal prostheses mounted in a semi-adjusted articulator using the facial arch and the Camper plane. Ten patients treated in a private clinic were selected to be rehabilitated with prostheses in previously placed single implants. For each patient two temporal prostheses were designed obtained under different conditions: (1) model mounting using facial arch and (2) Camper plane mounting. Prostheses were made and adjusted in the laboratory and placed only by an operator. The occlusal contacts achieved in each condition were photographed being assessed and quantified by a second professional not involved with the mounting conditions. Results obtained were analyzed by Mann-Whitney test with a 5 % significance level. There was not a statistically difference between the number of occlusal contacts when prostheses were made with facial arch or Camper plane (p= 0.113). The temporal dental prosthesis confection for single implants, semi-adjusted articulator using the Camper plane, not differ very much from the facial arch use, according to the number of resulting occlusal contacts.

Changes in facial morphology after adenotonsillectomy in mouth-breathing children

Background. Morphological and dentofacial alterations have been attributed to impaired respiratory function. Objective. To examine the influence of mouth breathing (MB) on children facial morphology before and after adenoidectomy or adenotonsillectomy. Methods. Thirty-three MB children who restored nasal breathing (NB) after surgery and 22 NB children were evaluated. Both groups were submitted to lateral cephalometry, at time 1 (T1) before and at time 2 (T2) 28months on average postoperatively. Results. Comparison between the MB and NB groups at T1 showed that mouth breathers had higher inclination of the mandibular plane; more obtuse gonial angle; dolichofacial morphology; and a decrease in the total and inferior posterior facial heights. Twenty-eight months after the MB surgical intervention, they still presented a dolichofacial morphologic pattern. During this period, MB altered the face growth direction and decreased their mandible plane inclination, with reduction in the SN.GoGn, PP.MP, SNGn, and ArGo.GoMe parameters as well as an increase in BaN.PtGn. Conclusion. After the MB rehabilitation, children between 3 and 6years old presented significant normalization in the mandibular growth direction, a decrease in the mandible inclination, and an increase in the posterior facial height. Instead, they still persisted with a dolichofacial pattern when compared with nasal breathers. © 2011 The Authors. International Journal of Paediatric Dentistry © 2011 BSPD, IAPD and Blackwell Publishing Ltd.

New approaches to dental occlusion: A literature update

Because the study of occlusion is a basic area in dentistry, its components, physiology and integration with the stomatognathic system (SS) have been the subject of interest in the scientific literature. However, the focus given to this issue has changed substantially. Currently, new approaches have been proposed in order to update concepts and to demonstrate the full integration and functionality of this system within the human body. With this approach, the authors proposed the following literature review aimed at gathering recent papers (published from 2000 to 2010) with innovative study design, methodology and/or results. The authors' intention is to show the main trends in the study of occlusion and the SS. The literature review was conducted in the PubMed database, using initially the term dental occlusion as a key-word. As items of interest were found, papers were grouped by categories according to their main subject matter. Forty-seven articles were selected and the main categories obtained were: 1. functional magnetic resonance imaging (fMRI); 2. brain activation; 3. masticatory/occlusal function; 4. body function and physical performance; 5. osseoperception; 6. finite element models; and 7. occlusion and pain. Observing the current literature, the authors found that recent studies present different methodologies for the study of occlusion. These studies have allowed scientists to obtain detailed information about the physiology of occlusion and the SS, as well as about its integration in the body. Research in this area should be continued in order to clarify, in detail, the role of each component of the SS and its interaction with human physiology. © 2012 by CHROMA, Inc.