Face recognition based on PCA and multi-degree of freedom neurons

An algorithm of PCA face recognition based on Multi-degree of Freedom Neurons theory is proposed, which based on the sample sets' topological character in the feature space which is different from "classification". Compare with the traditional PCA+NN algorithm, experiments prove its efficiency.

Gender Classification via Lips: Static and Dynamic Features

Automatic gender classification has many security and commercial applications. Various modalities have been investigated for gender classification with face-based classification being the most popular. In some real-world scenarios the face may be partially occluded. In these circumstances a classification based on individual parts of the face known as local features must be adopted. We investigate gender classification using lip movements. We show for the first time that important gender specific information can be obtained from the way in which a person moves their lips during speech. Furthermore our study indicates that the lip dynamics during speech provide greater gender discriminative information than simply lip appearance. We also show that the lip dynamics and appearance contain complementary gender information such that a model which captures both traits gives the highest overall classification result. We use Discrete Cosine Transform based features and Gaussian Mixture Modelling to model lip appearance and dynamics and employ the XM2VTS database for our experiments. Our experiments show that a model which captures lip dynamics along with appearance can improve gender classification rates by between 16-21% compared to models of only lip appearance.

Reorganização dos ajustes posturais antecipatórios do tibial anterior e do solear no início da marcha, em pacientes com AVE, face a uma intervenção de fisioterapia baseada no conceito de Bobath

Introdução: os APA´s ocorrem imediatamente antes do movimento e preparam-no tornando-o mais harmonioso e eficiente. Os pacientes com lesão do SNC apresentam frequentemente alterações no sistema de controlo postural interferindo significativamente nas suas AVD´s, como no início da marcha. Objetivo: descrever as alterações no tempo de ativação e sequência de ativação muscular do TA e do SOL no início da marcha em pacientes com AVE, face a uma intervenção em fisioterapia. Metodologia: A avaliação realizou-se antes e após um programa de intervenção, segundo a abordagem do Conceito de Bobath, através da electromiografia, plataforma de forças e máquina fotográfica para a avaliação do tempo de ativação muscular do tibial anterior e do solear no início da marcha. Recorreu-se também à Classificação Internacional de Funcionalidade e à Fulg-Mayer Assessment of Motor Recovery after Stroke. Resultados: Obteve-se uma diminuição dos valores registados pela EMG nos tempos de ativação muscular do TA e do SOL bilateralmente, e alterações na sequência de ativação. Verificaram-se modificações nos resultados da Classificação Internacional de Funcionalidade e da Fulg-Mayer Assessment of Motor Recovery after Stroke. Conclusão: O programa de intervenção segundo o Conceito de Bobath, induziu mudanças nos tempos de ativação muscular e na sequência de ativação dos músculos TA e SOL no início da marcha em pacientes com AVE.

Face Recognition using Probabilistic Neural Networks

In this paper we address the problem of face detection and recognition of grey scale frontal view images. We propose a face recognition system based on probabilistic neural networks (PNN) architecture. The system is implemented using voronoi/ delaunay tessellations and template matching. Images are segmented successfully into homogeneous regions by virtue of voronoi diagram properties. Face verification is achieved using matching scores computed by correlating edge gradients of reference images. The advantage of classification using PNN models is its short training time. The correlation based template matching guarantees good classification results

Face Recognition using Probabilistic Neural Networks

n this paper we address the problem of face detection and recognition of grey scale frontal view images. We propose a face recognition system based on probabilistic neural networks (PNN) architecture. The system is implemented using voronoi/ delaunay tessellations and template matching. Images are segmented successfully into homogeneous regions by virtue of voronoi diagram properties. Face verification is achieved using matching scores computed by correlating edge gradients of reference images. The advantage of classification using PNN models is its short training time. The correlation based template matching guarantees good classification results.

Rotation Invariant Real-time Face Detection and Recognition System

In this report, a face recognition system that is capable of detecting and recognizing frontal and rotated faces was developed. Two face recognition methods focusing on the aspect of pose invariance are presented and evaluated - the whole face approach and the component-based approach. The main challenge of this project is to develop a system that is able to identify faces under different viewing angles in realtime. The development of such a system will enhance the capability and robustness of current face recognition technology. The whole-face approach recognizes faces by classifying a single feature vector consisting of the gray values of the whole face image. The component-based approach first locates the facial components and extracts them. These components are normalized and combined into a single feature vector for classification. The Support Vector Machine (SVM) is used as the classifier for both approaches. Extensive tests with respect to the robustness against pose changes are performed on a database that includes faces rotated up to about 40 degrees in depth. The component-based approach clearly outperforms the whole-face approach on all tests. Although this approach isproven to be more reliable, it is still too slow for real-time applications. That is the reason why a real-time face recognition system using the whole-face approach is implemented to recognize people in color video sequences.

Example Based Learning for View-Based Human Face Detection

We present an example-based learning approach for locating vertical frontal views of human faces in complex scenes. The technique models the distribution of human face patterns by means of a few view-based "face'' and "non-face'' prototype clusters. At each image location, the local pattern is matched against the distribution-based model, and a trained classifier determines, based on the local difference measurements, whether or not a human face exists at the current image location. We provide an analysis that helps identify the critical components of our system.

Feature Selection for Face Detection

We present a new method to select features for a face detection system using Support Vector Machines (SVMs). In the first step we reduce the dimensionality of the input space by projecting the data into a subset of eigenvectors. The dimension of the subset is determined by a classification criterion based on minimizing a bound on the expected error probability of an SVM. In the second step we select features from the SVM feature space by removing those that have low contributions to the decision function of the SVM.

A new approach to the classification of mammographic masses and normal breast tissue

A new approach to mammographic mass detection is presented in this paper. Although different algorithms have been proposed for such a task, most of them are application dependent. In contrast, our approach makes use of a kindred topic in computer vision adapted to our particular problem. In this sense, we translate the eigenfaces approach for face detection/classification problems to a mass detection. Two different databases were used to show the robustness of the approach. The first one consisted on a set of 160 regions of interest (RoIs) extracted from the MIAS database, being 40 of them with confirmed masses and the rest normal tissue. The second set of RoIs was extracted from the DDSM database, and contained 196 RoIs containing masses and 392 with normal, but suspicious regions. Initial results demonstrate the feasibility of using such approach with performances comparable to other algorithms, with the advantage of being a more general, simple and cost-effective approach

As atitudes dos professores face à inclusão de alunos com deficiência : o contacto com a deficiência

RESUMO: Actualmente as práticas de exclusão evoluíram para uma perspectiva de inclusão, assim como para a consciencialização dos direitos e deveres de cada um, como forma de dar resposta à sociedade heterogénea existente. A visão baseada nos sistemas de identificação e classificação dos sujeitos em várias categorias de deficiências era algo muito usual, mas que foi abolida, dando assim lugar ao conceito de Necessidades Educativas Especiais, com uma óptica mais abrangente, tendo em conta o contexto em que o sujeito está envolvido (Nunes, 2000). As atitudes dos professores face aos alunos com deficiência têm melhorado significativamente (Ribeiro, 1999), no entanto o processo de inclusão destas crianças no ensino regular não está isento de problemas. Neste sentido, e para que este desafio seja ultrapassado com sucesso, torna-se essencial que os professores modifiquem as suas atitudes e passem a desempenhar um papel mais activo nas suas funções, devendo para isso, começar por adaptar o currículo, e posteriormente repensar as suas estratégias e métodos de trabalho, como forma a responder às necessidades de todos os alunos (Ainscow, 1997). O objectivo principal deste estudo é verificar se o contacto com a deficiência (a nível da experiência no ensino, formação inicial e contacto na infância/juventude), por parte dos professores, influencia as suas atitudes em relação à formação necessária para a inclusão de alunos com deficiência, bem como às vantagens que esta representa para esses mesmos alunos. A amostra foi constituída por 672 professores do ensino regular, todos estão actualmente no activo e leccionam níveis de ensino do Pré-Escolar ao Ensino Secundário, de Norte a Sul do país. (N = 482 do género feminino e N =190 do género masculino). O instrumento de avaliação aplicado foi o questionário APIAD – Atitude dos Professores face à Inclusão de Alunos com Deficiência (Leitão, 2011). Concluiu-se que a experiência no ensino de alunos com deficiência influencia significativamente a atitude dos professores face à formação necessária (deficiência motora: p<0,001; deficiência auditiva: p<0,001; deficiência visual: p<0,001; deficiência mental: p=0,004) e face às vantagens da inclusão para os alunos com deficiência (deficiência motora: p=0,005; deficiência auditiva: p<0,001; deficiência visual: p<0,001; deficiência mental: p=0,022). No que se refere ao contacto com pessoas com deficiência durante a formação inicial, concluiu-se que existem diferenças significativas na atitude dos professores face às vantagens da inclusão para os alunos com deficiência (deficiência motora: p<0,001; deficiência auditiva: p<0,001; deficiência visual: p<0,001; deficiência mental: p<0,001). No entanto, no que respeita à formação, a atitude dos professores não difere, independentemente de terem tido esse contacto (deficiência motora: p=0,393; deficiência auditiva: p=0,456; deficiência visual: p=0,055; deficiência mental: p=0,342). Relativamente ao contacto com pessoas com deficiência durante a infância/juventude conclui-se que não existem diferenças na atitude dos professores em relação à formação necessária (deficiência motora: p=0,893; deficiência auditiva: p=0,667; deficiência visual: p=0,459; deficiência mental: p=0,918). Por sua vez, no que respeita às vantagens da inclusão para os alunos com deficiência, esta variável só influencia significativamente a atitude dos professores no caso da deficiência visual (deficiência motora: p=0,154; deficiência auditiva: p=0,100; deficiência visual: p=0,045; deficiência mental: p=0,149). ABSTRACT: Currently the exclusionary practices evolved to an inclusion perspective, as well as the awareness of rights and duties of each one as a way to reply to the existing heterogeneous society. The vision-based systems for identification and classification of subjects into various categories of disabilities was very unusual, but it was abolished, giving way to the concept of Special Educational Needs, with a broader perspective, considering the context in which the subject is involved (Nunes, 2000). The teachers attitude face to the students with disabilities have improved significantly (Ribeiro, 1999), however the process of inclusion of these children in regular education isn't exempt of problems. In this direction and so this challenge is exceeded successfully, it is essential that teachers change their attitudes and start to perform a more active role in their functions, and to do so, start by adapting the curriculum and then rethink their strategies and working methods, in order to meet the needs of all students (Ainscow, 1997). The main purpose of this study is to verify that the contact with the disability (educational level of experience, initial formation and contact in childhood/youth), among teachers, influences their attitudes towards the needed formation for the inclusion of students with disabilities as well as the benefits that this represents for them. The sample consisted by 672 regular educational teachers, all currently in employment and teaching from Preschool to High school, from North to South. (N = 482 females and N = 190 males). The evaluation instrument used was the survey APIAD - Teachers attitude towards the inclusion of students with disabilities (Leitão, 2011). It was concluded that the experience in teaching students with disabilities influences significantly the teachers attitude faced to the necessary formation (motor disability: p<0,001; hearing impairment: p<0,001; visual impairment: p<0,001; mental disability: p=0,004) and faced to the inclusion benefits for students with disabilities (motor disability: p=0,005; hearing impairment: p<0,001; visual impairment: p<0,001; mental disability: p=0,022).Concerning to the contact with people with disabilities during the initial formation, it was concluded that there are significant differences in the teachers attitude face to the inclusion benefits for students with disabilities (motor disability: p<0,001; hearing impairment: p<0,001; visual impairment: p<0,001; mental disability: p<0,001). In relation to the formation, the teachers attitude is the same, regardless of whether or not they have had such contact (motor disability: p=0,393; hearing impairment: p=0,456; visual impairment: p=0,055; mental disability: p=0,342). Regarding to the contact with people with disabilities during childhood/youth, it was concluded that there is no difference in the teachers attitude in relation to the formation needed (motor disability: p=0,893; hearing impairment: p=0,667; visual impairment: p=0,459; mental disability: p=0,918). On the other way, regarding to the inclusion benefits for students with disabilities, this influences significantly the teachers attitude just in the visual impairment. (motor disability: p=0,154; hearing impairment: p=0,100; visual impairment: p=0,045; mental disability: p=0,149).

Face verification using Gabor wavelets and AdaBoost

This paper presents a new face verification algorithm based on Gabor wavelets and AdaBoost. In the algorithm, faces are represented by Gabor wavelet features generated by Gabor wavelet transform. Gabor wavelets with 5 scales and 8 orientations are chosen to form a family of Gabor wavelets. By convolving face images with these 40 Gabor wavelets, the original images are transformed into magnitude response images of Gabor wavelet features. The AdaBoost algorithm selects a small set of significant features from the pool of the Gabor wavelet features. Each feature is the basis for a weak classifier which is trained with face images taken from the XM2VTS database. The feature with the lowest classification error is selected in each iteration of the AdaBoost operation. We also address issues regarding computational costs in feature selection with AdaBoost. A support vector machine (SVM) is trained with examples of 20 features, and the results have shown a low false positive rate and a low classification error rate in face verification.

Robust learning of discriminative projection for multicategory classification on the Stiefel manifold

Learning a robust projection with a small number of training samples is still a challenging problem in face recognition, especially when the unseen faces have extreme variation in pose, illumination, and facial expression. To address this problem, we propose a framework formulated under statistical learning theory that facilitates robust learning of a discriminative projection. Dimensionality reduction using the projection matrix is combined with a linear classifier in the regularized framework of lasso regression. The projection matrix in conjunction with the classifier parameters are then found by solving an optimization problem over the Stiefel manifold. The experimental results on standard face databases suggest that the proposed method outperforms some recent regularized techniques when the number of training samples is small.

Face recognition using kernel ridge regression

In this paper, we present novel ridge regression (RR) and kernel ridge regression (KRR) techniques for multivariate labels and apply the methods to the problem of face recognition. Motivated by the fact that the regular simplex vertices are separate points with highest degree of symmetry, we choose such vertices as the targets for the distinct individuals in recognition and apply RR or KRR to map the training face images into a face subspace where the training images from each individual will locate near their individual targets. We identify the new face image by mapping it into this face subspace and comparing its distance to all individual targets. An efficient cross-validation algorithm is also provided for selecting the regularization and kernel parameters. Experiments were conducted on two face databases and the results demonstrate that the proposed algorithm significantly outperforms the three popular linear face recognition techniques (Eigenfaces, Fisherfaces and Laplacianfaces) and also performs comparably with the recently developed Orthogonal Laplacianfaces with the advantage of computational speed. Experimental results also demonstrate that KRR outperforms RR as expected since KRR can utilize the nonlinear structure of the face images. Although we concentrate on face recognition in this paper, the proposed method is general and may be applied for general multi-category classification problems.

A fast kernel dimension reduction algorithm with applications to face recognition

This paper presents a novel dimensionality reduction algorithm for kernel based classification. In the feature space, the proposed algorithm maximizes the ratio of the squared between-class distance and the sum of the within-class variances of the training samples for a given reduced dimension. This algorithm has lower complexity than the recently reported kernel dimension reduction(KDR) for supervised learning. We conducted several simulations with large training datasets, which demonstrate that the proposed algorithm has similar performance or is marginally better compared with KDR whilst having the advantage of computational efficiency. Further, we applied the proposed dimension reduction algorithm to face recognition in which the number of training samples is very small. This proposed face recognition approach based on the new algorithm outperforms the eigenface approach based on the principle component analysis (PCA), when the training data is complete, that is, representative of the whole dataset.

Application of the DCT energy histogram for face recognition

In this paper, we investigate the face recognition problem via energy histogram of the DCT coefficients. Several issues related to the recognition performance are discussed, In particular the issue of histogram bin sizes and feature sets. In addition, we propose a technique for selecting the classification threshold incrementally. Experimentation was conducted on the Yale face database and results indicated that the threshold obtained via the proposed technique provides a balanced recognition in term of precision and recall. Furthermore, it demonstrated that the energy histogram algorithm outperformed the well-known Eigenface algorithm.