Optimal metric selection for improved multi-pose face recognition with group information

We address the limitation of sparse representation based classification with group information for multi-pose face recognition. First, we observe that the key issue of such classification problem lies in the choice of the metric norm of the residual vectors, which represent the fitness of each class. Then we point out that limitation of the current sparse representation classification algorithms is the wrong choice of the ℓ2 norm, which does not match with data statistics as these residual values may be considerably non-Gaussian. We propose an explicit but effective solution using ℓp norm and explain theoretically and numerically why such metric norm would be able to suppress outliers and thus can significantly improve classification performance comparable to the state-of-arts algorithms on some challenging datasets

Semi-supervised classification based on subspace sparse representation

Graph plays an important role in graph-based semi-supervised classification. However, due to noisy and redundant features in high-dimensional data, it is not a trivial job to construct a well-structured graph on high-dimensional samples. In this paper, we take advantage of sparse representation in random subspaces for graph construction and propose a method called Semi-Supervised Classification based on Subspace Sparse Representation, SSC-SSR in short. SSC-SSR first generates several random subspaces from the original space and then seeks sparse representation coefficients in these subspaces. Next, it trains semi-supervised linear classifiers on graphs that are constructed by these coefficients. Finally, it combines these classifiers into an ensemble classifier by minimizing a linear regression problem. Unlike traditional graph-based semi-supervised classification methods, the graphs of SSC-SSR are data-driven instead of man-made in advance. Empirical study on face images classification tasks demonstrates that SSC-SSR not only has superior recognition performance with respect to competitive methods, but also has wide ranges of effective input parameters.

Sparse representation with multi-manifold analysis for texture classification from few training images

Texture classification is one of the most important tasks in computer vision field and it has been extensively investigated in the last several decades. Previous texture classification methods mainly used the template matching based methods such as Support Vector Machine and k-Nearest-Neighbour for classification. Given enough training images the state-of-the-art texture classification methods could achieve very high classification accuracies on some benchmark databases. However, when the number of training images is limited, which usually happens in real-world applications because of the high cost of obtaining labelled data, the classification accuracies of those state-of-the-art methods would deteriorate due to the overfitting effect. In this paper we aim to develop a novel framework that could correctly classify textural images with only a small number of training images. By taking into account the repetition and sparsity property of textures we propose a sparse representation based multi-manifold analysis framework for texture classification from few training images. A set of new training samples are generated from each training image by a scale and spatial pyramid, and then the training samples belonging to each class are modelled by a manifold based on sparse representation. We learn a dictionary of sparse representation and a projection matrix for each class and classify the test images based on the projected reconstruction errors. The framework provides a more compact model than the template matching based texture classification methods, and mitigates the overfitting effect. Experimental results show that the proposed method could achieve reasonably high generalization capability even with as few as 3 training images, and significantly outperforms the state-of-the-art texture classification approaches on three benchmark datasets. © 2014 Elsevier B.V. All rights reserved.

A conceptual classification of parents’ attributions of the role of food advertising in children’s diets

Background : High levels of child obesity are triggering growing concerns about the prevalence and effects of food advertising targeted at children. Efforts to address this advertising are confounded by the expanding repertoire of media and promotional techniques used to reach and attract children. The present study explored parents’ views on food marketing and the strategies parents employ when attempting to ameliorate its effects. As part of an online survey of Australian parents’ attitudes towards a range of food advertisements, respondents were invited to provide additional comment in an open-ended question. The question was optional and asked “Are there any other comments you would like to make?”. One in five of the survey respondents (18%; n = 235) elected to answer this question by discussing their views on food advertising and children’s diets. The responses were imported into NVivo10 for coding and analysis. A grounded approach was used to draw meaning from the data and develop a proposed conceptual classification of parents’ attributions relating to food advertising and its consequences.

Results : The majority of responses related to the negative perceived effects of unhealthy food advertising on children’s diets, with few respondents considering such advertisements to be innocuous. The responses were classified into four conceptual categories reflecting differing attitudes to advertising (negative to neutral) and varying levels of locus of control (low to high). The typical characteristics of parents allocated to the four categories exhibited variation according to weight status, television viewing habits, education level, and family size. The largest number of responses was coded to the category characterized by a negative attitude toward food advertising and a low locus of control. Parents in this category were more likely than others to be overweight/obese and heavy television viewers. Parents in the negative attitude to advertising and high locus of control category nominated a variety of parenting practices that could form the basis of parent education interventions.

Conclusions : The results suggest that many Australian parents may feel disempowered in the face of high levels of advertising for unhealthy foods. The current voluntary regulatory code appears to be inadequate in scope and coverage to address this situation.

Mixed-norm sparse representation for multi view face recognition

Face recognition with multiple views is a challenging research problem. Most of the existing works have focused on extracting shared information among multiple views to improve recognition. However, when the pose variation is too large or missing, 'shared information' may not be properly extracted, leading to poor recognition results. In this paper, we propose a novel method for face recognition with multiple view images to overcome the large pose variation and missing pose issue. By introducing a novel mixed norm, the proposed method automatically selects candidates from the gallery to best represent a group of highly correlated face images in a query set to improve classification accuracy. This mixed norm combines the advantages of both sparse representation based classification (SRC) and joint sparse representation based classification (JSRC). A trade off between the ℓ1-norm from SRC and ℓ2,1-norm from JSRC is introduced to achieve this goal. Due to this property, the proposed method decreases the influence when a face image is unseen and has large pose variation in the recognition process. And when some face images with a certain degree of unseen pose variation appear, this mixed norm will find an optimal representation for these query images based on the shared information induced from multiple views. Moreover, we also address an open problem in robust sparse representation and classification which is using ℓ1-norm on the loss function to achieve a robust solution. To solve this formulation, we derive a simple, yet provably convergent algorithm based on the powerful alternative directions method of multipliers (ADMM) framework. We provide extensive comparisons which demonstrate that our method outperforms other state-of-the-arts algorithms on CMU-PIE, Yale B and Multi-PIE databases for multi-view face recognition.

Proposta para classificação, segundo a severidade, dos indivíduos portadores de más oclusões do Padrão Face Longa

OBJETIVO: o presente estudo teve como objetivo propor um método para classificação, segundo a severidade, dos indivíduos Padrão Face Longa, avaliando sua confiabilidade e reprodutibilidade. METODOLOGIA: foram utilizadas fotografias faciais (frontal, perfil e frontal sorrindo) de 125 crianças Padrão Face Longa (54 do gênero feminino e 71 do gênero masculino), selecionadas apenas considerando-se a morfologia facial, com idades entre 10 anos e 6 meses e 15 anos e 2 meses. As fotografias foram avaliadas, separadamente, por três examinadores, sendo reavaliadas após três semanas, em uma nova disposição aleatória. Os indivíduos foram graduados em três subtipos, de acordo com a severidade: moderado, médio e severo. Para avaliar as concordâncias intra e interexaminadores, foi utilizada a estatística Kappa (k). RESULTADOS: na avaliação intra-examinador, todos os examinadores obtiveram concordâncias substanciais, com o valor de Kappa variando de 0,64 a 0,66, havendo em todos os examinadores 80% ou mais de concordância. Quando comparadas as avaliações interexaminadores, as freqüências de concordância diminuíram, variando de 67,2% a 70,4%. A partir dos valores de Kappa, que variaram de 0,41 a 0,46, a interpretação foi considerada moderada. CONCLUSÕES: com base nesses resultados, o método foi considerado aplicável, com necessidade de complemento de informações provenientes de outros exames rotineiramente aplicados em Ortodontia. A aplicação clínica será demonstrada com intuito de evidenciar os níveis diferentes de severidade das más oclusões do Padrão Face Longa e as características do protocolo de tratamento recomendado.

Correlation between maxillary central incisor form and face form in 4 racial groups

Objectives: the purpose of this study was to evaluate the correlation between central incisor form and face form in 4 racial groups and to investigate if there was agreement among experts in categorizing the central incisor forms. Method and Materials: A total of 160 subjects (40 whites, 40 mulattos, 40 blacks, and 40 Asians) ranging from 18 to 33 years of age were selected. Digital photographic records were made, 1 full-face and 1 intraoral view of the maxillary right central incisor. The outline tracings of the tooth and face images were obtained using Adobe Photoshop 5.0 software. The outline tracings were printed in distinct transparencies, and 3 prosthodontists determined if there was correspondence between the tooth and the face forms by superimposition of the transparencies. If there was disagreement among the prosthodontists' evaluations, the prevalent decision was considered. The experts also classified the central incisor forms into square, ovoid, tapering, or combination at 2 different sessions. At the first session, no instructions were given. At the second session, the prosthodontists were instructed to follow Williams' method of classification. Results: A correspondence between tooth and face forms was found in 23.75% of all cases. Agreement on the tooth form classifications among the prosthodontists occurred in 30.62% of all cases at the first session and 24.37% at the second session. Conclusion: There is not a highly defined correlation between central incisor form and face form in any racial group studied. In addition, the experts were not in fair agreement in categorizing tooth forms.

Improving face recognition with multispectral fusion and support vector machines

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Relationship between the morphology of the maxillary central incisor and horizontal and vertical measurements of the face

Purpose: In order to assist in the selection of artificial teeth for complete dentures, this study aimed to assess the relationship between horizontal and vertical measurements of the face and the morphology of the maxillary central incisor. Materials and Methods: This was a study of 50 plaster casts and 100 teleradiographs - 50 in lateral norm and 50 in frontal norm, belonging to 50 individuals, Caucasian, with a naturally optimal occlusion, matching at least four of the six keys of Andrews. Images of the upper central incisors were obtained by scanning the plaster casts (three-dimensional) and subjectively classified by three examiners as oval, triangular or quadrangular. Facial measures (vertical and horizontal) were defined by means of teleradiographs. In order to check inter-examiner agreement on the classification of central incisor, the Kappa test was used. To verify whether data had normal distribution, the Kolmogorov-Smirnov test was used ( P > 0.2) was used. One-way analysis of variance was employed to assess the association between variables (P > 0.05). Results: When vertical measurements were compared with the three incisor shapes, there was no statistically significant difference (P > 0.05): Triangular (0.54), oval (0.63) and quadrangular (0.51). Similarly, no difference (P > 0.05) was found for facial width (139.08, 143.37, 141.65), maxillary width (76.68, 78.99, 76.91) and mandibular width (103.47, 105.50, 103.11). Conclusions: The majority of cases showed that horizontal and vertical measurements of the face cannot be used as a reference for determining the morphology of the maxillary central incisor crown. It is relevant to analyze and compare other morphological structures to improve the oral health-related quality of life for the conventional denture wearer.

Improving gender classification accuracy in the wild

[EN]In this paper, we focus on gender recognition in challenging large scale scenarios. Firstly, we review the literature results achieved for the problem in large datasets, and select the currently hardest dataset: The Images of Groups. Secondly, we study the extraction of features from the face and its local context to improve the recognition accuracy. Diff erent descriptors, resolutions and classfii ers are studied, overcoming previous literature results, reaching an accuracy of 89.8%.

Identification of problems in functioning of people with sleep disorders in a clinical setting using the International Classification of Functioning Disability and Health (ICF) Checklist

We conducted an explorative, cross-sectional, multi-centre study in order to identify the most common problems of people with any kind of (primary) sleep disorder in a clinical setting using the International Classification of Functioning, Disability and Health (ICF) as a frame of reference. Data were collected from patients using a structured face-to-face interview of 45-60 min duration. A case record form for health professionals containing the extended ICF Checklist, sociodemographic variables and disease-specific variables was used. The study centres collected data of 99 individuals with sleep disorders. The identified categories include 48 (32%) for body functions, 13 (9%) body structures, 55 (37%) activities and participation and 32 (22%) for environmental factors. 'Sleep functions' (100%) and 'energy and drive functions', respectively, (85%) were the most severely impaired second-level categories of body functions followed by 'attention functions' (78%) and 'temperament and personality functions' (77%). With regard to the component activities and participation, patients felt most restricted in the categories of 'watching' (e.g. TV) (82%), 'recreation and leisure' (75%) and 'carrying out daily routine' (74%). Within the component environmental factors the categories 'support of immediate family', 'health services, systems and policies' and 'products or substances for personal consumption [medication]' were the most important facilitators; 'time-related changes', 'light' and 'climate' were the most important barriers. The study identified a large variety of functional problems reflecting the complexity of sleep disorders. The ICF has the potential to provide a comprehensive framework for the description of functional health in individuals with sleep disorders in a clinical setting.

Evaluation of an integrated system for classification, assessment and comparison of services for long-term care in Europe: the eDESDE-LTC study

Background: The harmonization of European health systems brings with it a need for tools to allow the standardized collection of information about medical care. A common coding system and standards for the description of services are needed to allow local data to be incorporated into evidence-informed policy, and to permit equity and mobility to be assessed. The aim of this project has been to design such a classification and a related tool for the coding of services for Long Term Care (DESDE-LTC), based on the European Service Mapping Schedule (ESMS). Methods: The development of DESDE-LTC followed an iterative process using nominal groups in 6 European countries. 54 researchers and stakeholders in health and social services contributed to this process. In order to classify services, we use the minimal organization unit or “Basic Stable Input of Care” (BSIC), coded by its principal function or “Main Type of Care” (MTC). The evaluation of the tool included an analysis of feasibility, consistency, ontology, inter-rater reliability, Boolean Factor Analysis, and a preliminary impact analysis (screening, scoping and appraisal). Results: DESDE-LTC includes an alpha-numerical coding system, a glossary and an assessment instrument for mapping and counting LTC. It shows high feasibility, consistency, inter-rater reliability and face, content and construct validity. DESDE-LTC is ontologically consistent. It is regarded by experts as useful and relevant for evidence-informed decision making. Conclusion: DESDE-LTC contributes to establishing a common terminology, taxonomy and coding of LTC services in a European context, and a standard procedure for data collection and international comparison.

AVALIAÇÃO DO PADRÃO ESQUELÉTICO VERTICAL DA FACE NA OCLUSÃO NORMAL NATURAL E NAS MALOCLUSÕES DE ANGLE, E SUA CORRELAÇÃO COM A SÍNFISE MANDIBULAR

O propósito deste estudo foi avaliar cefalometricamente, o padrão esquelético vertical da face em indivíduos com oclusão normal natural e nas diferentes maloclusões e sua correlação com a sínfise mandibular, além de avaliar a presença de dimorfismo sexual. A amostra foi composta de 200 telerradiografias cefalométricas, divididas quanto ao tipo de oclusão, em cinco grupos: grupo A, com pacientes portadores de oclusão normal natural e grupos B, C, D e E, com pacientes portadores de maloclusões, sendo cada grupo, dividido igualmente quanto ao sexo e apresentando idade média entre 13 e 16 anos. A amostra foi classificada em 3 padrões morfológicos verticais da face, de acordo com o índice da altura facial (FHR), proposto por SIRIWAT & JARABAK ou Quociente de Jarabak, em: Hiperdivergente, Neutro e Hipodivergente. Foi utilizada a variável GoMe.VT, da análise de VIGORITO, para avaliar a inclinação da sínfise e sua correlação com os padrões verticais faciais. Após a coleta de dados e da avaliação dos testes estatísticos; qui-quadrado, teste t de Student e da correlação de Pearson, concluiu-se que, o padrão Hipodivergente em todos os pacientes estudados foi o mais frequente, com 70%, sendo que a maior frequência deste padrão foi encontrado na maloclusão Classe II, divisão 2, com 87.5%, existindo outras prevalências de alguns padrões em diferentes classes de oclusões. Foi encontrada uma correlação positiva entre a inclinação da sínfise mandibular e o quociente de Jarabak apenas para a maloclusão Classe I e maloclusão Classe III. Não houve diferença estatisticamente significante entre os sexos e a classificação da morfologia quando comparados os cinco grupos, porém, quando os grupos foram analisados separadamente, foram encontradas diferenças significantes entre os sexos.

Avaliação de medidas craniofaciais angulares e lineares em relação à quantidade de crescimento da face

A identificação dos padrões morfológicos da face é de extrema importância para a elaboração do diagnóstico ortodôntico e conseqüente plano de tratamento. Sendo assim, esta pesquisa teve como objetivo avaliar as relações entre as medidas lineares N-ENA, ENA-Pog e N-Pog, as medidas angulares N.OPI.ENA, ENA.OPI.Pog e N.OPI.Pog, e o índice VERT de acordo com a classificação proposta por RICKETTS. O material de estudo foi constituído de 700 telerradiografias, em norma lateral, de indivíduos brasileiros, leucodermas, de ambos os gêneros (318 do gênero masculino e 382 do gênero feminino), apresentando idade média de 16,66 anos. Das 700 telerradiografias foram constituídos quatro grupos de acordo com a oclusão. O primeiro grupo foi constituído de indivíduos com oclusão normal natural segundo ANDREWS, sendo observadas, clinicamente, quatro das seis chaves de oclusão. Os demais grupos se constituíram de indivíduos com más-oclusões de Classe I, II e III segundo ANGLE, sem relato de tratamento ortodôntico anterior. Após a análise estatística para a avaliação das medidas lineares N-ENA, ENA-Pog e N-Pog, e medidas angulares N.OPI.ENA, ENA.OPI.Pog e N.OPI.Pog, em relação ao índice VERT, evidenciou um aumento progressivo das medidas pesquisadas em relação aos seis padrões faciais determinados pelo índice VERT, mostrando um aumento destas medidas conforme se vai do padrão braquifacial severo para o padrão dolicofacial severo.

An integrative approach to face and expression recognition from 3D scans

Biometrics is afield of study which pursues the association of a person's identity with his/her physiological or behavioral characteristics.^ As one aspect of biometrics, face recognition has attracted special attention because it is a natural and noninvasive means to identify individuals. Most of the previous studies in face recognition are based on two-dimensional (2D) intensity images. Face recognition based on 2D intensity images, however, is sensitive to environment illumination and subject orientation changes, affecting the recognition results. With the development of three-dimensional (3D) scanners, 3D face recognition is being explored as an alternative to the traditional 2D methods for face recognition.^ This dissertation proposes a method in which the expression and the identity of a face are determined in an integrated fashion from 3D scans. In this framework, there is a front end expression recognition module which sorts the incoming 3D face according to the expression detected in the 3D scans. Then, scans with neutral expressions are processed by a corresponding 3D neutral face recognition module. Alternatively, if a scan displays a non-neutral expression, e.g., a smiling expression, it will be routed to an appropriate specialized recognition module for smiling face recognition.^ The expression recognition method proposed in this dissertation is innovative in that it uses information from 3D scans to perform the classification task. A smiling face recognition module was developed, based on the statistical modeling of the variance between faces with neutral expression and faces with a smiling expression.^ The proposed expression and face recognition framework was tested with a database containing 120 3D scans from 30 subjects (Half are neutral faces and half are smiling faces). It is shown that the proposed framework achieves a recognition rate 10% higher than attempting the identification with only the neutral face recognition module.^