Η παρούσα διπλωματική εργασία αναφέρεται σε ένα αυτόματο σύστημα αναγνώρισης με χρήση της ομιλίας, και πιο συγκεκριμένα σε ένα σύστημα αναγνώρισης φύλου μέσω ομιλίας. Αναλύεται η δομή του, περιγράφεται η λειτουργία του και δίνονται οι λεπτομέρειες κάθε τμήματος του. Αρχικά, η εργασία επικεντρώνεται στην προεπεξεργασία του σήματος ομιλίας και στην εξαγωγή των κατάλληλων παραμέτρων, οι οποίες θα μπορέσουν να χαρακτηρίσουν κάθε φύλο. Στη συνέχεια, περιγράφεται η διαδικασία ταξινόμησης του συστήματος, οι αλγόριθμοι που χρησιμοποιούνται και στο τέλος παρουσιάζονται τα ποσοστά επιτυχίας. Τα αποτελέσματα υποδεικνύουν και το βέλτιστο σύνολο παραμέτρων ομιλίας για αξιόπιστη αναγνώριση φύλου. / The purpose of this diploma thesis is the study of a gender recognition system based on speech. More specifically the system’s structure is analyzed, its functions are described and details regarding every single part are given. We focus on the preprocessing of the speech signal and the definition of the appropriate parameters that characterize every gender. Moreover, the methods, which are used for classification during the experimental setup, are described and be presented with their results. These results also suggest the optimized speech parameters appropriate for reliable gender recognition.

Yes / Automatic gender classification has become a topic of great interest to the visual computing research community in recent times. This is due to the fact that computer-based automatic gender recognition has multiple applications including, but not limited to, face perception, age, ethnicity, identity analysis, video surveillance and smart human computer interaction. In this paper, we discuss a machine learning approach for efficient identification of gender purely from the dynamics of a person’s smile. Thus, we show that the complex dynamics of a smile on someone’s face bear much relation to the person’s gender. To do this, we first formulate a computational framework that captures the dynamic characteristics of a smile. Our dynamic framework measures changes in the face during a smile using a set of spatial features on the overall face, the area of the mouth, the geometric flow around prominent parts of the face and a set of intrinsic features based on the dynamic geometry of the face. This enables us to extract 210 distinct dynamic smile parameters which form as the contributing features for machine learning. For machine classification, we have utilised both the Support Vector Machine and the k-Nearest Neighbour algorithms. To verify the accuracy of our approach, we have tested our algorithms on two databases, namely the CK+ and the MUG, consisting of a total of 109 subjects. As a result, using the k-NN algorithm, along with tenfold cross validation, for example, we achieve an accurate gender classification rate of over 85%. Hence, through the methodology we present here, we establish proof of the existence of strong indicators of gender dimorphism, purely in the dynamics of a person’s smile.

No / This chapter is concerned with the discussion of a computational framework to aid with gender classification in an automated fashion using the dynamics of a smile. The computational smile dynamics framework we discuss here uses the spatio-temporal changes on the face during a smile. Specifically, it uses a set of spatial and temporal features on the overall face. These include the changes in the area of the mouth, the geometric flow around facial features and a set of intrinsic features over the face. These features are explicitly derived from the dynamics of the smile. Based on it, a number of distinct dynamic smile parameters can be extracted which can then be fed to a machine learning algorithm for gender classification.

The Finnish legislation on legal gender recognition includes a prerequisite of being infertile. This practice not only differs from the legislation of the other Nordic countries but has also been found to be a violation of articles from human rights conventions. The practice has been found to be incompatible with the picture of Finland as a progressive Nordic country and it indeed creates an inconsistency between the regime of Nordic countries. The aim of the thesis is to analyze this problem from a governmental perspective and to find factors that could explain the difference between these countries. Theories of governmentality and governing gender will be applied in the analysis with the help of discourse analysis. From the perspective of the regime of Nordic countries, it is possible that the legislation in Finland would be developed into the same direction in the following years.

Germany´s government voted recently on a new legislation on gender recognition, which should replace the Transexuellengesetz. The Selbstbestimmungsgesetz presents a significant shift from the medicalised approach to a self-identification process, which through a more simplified procedures replaces invasive medical examinations. Through a qualitative content analysis and the lens of Judith Butler´s “Gender Trouble”, this research analyses the recent developments to capture progressions and prevailing challenges. The findings demonstrate the significant shift of the new legislation which acknowledges the autonomy and agency of adult individuals to self-determine their gender identity, which also emphasises the evolving acceptance of diverse gender identities. However, the analysis presents limitations where the law lacks clarifications or enforcement mechanisms to ensure legal protection for gender non-conforming people. Especially, aspects regarding a clear non-discrimination law, the inclusion of the house rights, age limits for minors, and more clear recognition of gender identities beyond the binary system are presenting possibilities for mistreatment.

[EN] Deep Learning is a new area of Machine Learning research which aims to create computational models that learn several representations of the data using deep architectures. These methods have become very popular over the last few years due to the remarkable results obtained in speech recognition, visual object recognition, object detection, natural language processing, etc. The goal of this thesis is to present some contributions to the Deep Learning framework, particularly focused on computer vision problems dealing with images. These contributions can be summarized in two novel methods proposed: a new regularization technique for Restricted Boltzmann Machines called Mask Selective Regularization (MSR), and a powerful discriminative network called Local Deep Neural Network (Local-DNN). On the one hand, the MSR method is based on taking advantage of the benefits of the L2 and the L1 regularizations techniques. Both regularizations are applied dynamically on the parameters of the RBM according to the state of the model during training and the topology of the input space. On the other hand, the Local-DNN model is based on two key concepts: local features and deep architectures. Similar to the convolutional networks, the Local-DNN model learns from local regions in the input image using a deep neural network. The network aims to classify each local feature according to the label of the sample to which it belongs, and all of these local contributions are taken into account during testing using a simple voting scheme. The methods proposed throughout the thesis have been evaluated in several experiments using various image datasets. The results obtained show the great performance of these approaches, particularly on gender recognition using face images, where the Local-DNN improves other state-of-the-art results. / [ES] El Aprendizaje Profundo (Deep Learning en inglés) es una nueva área dentro del campo del Aprendizaje Automático que pretende crear modelos computacionales que aprendan varias representaciones de los datos utilizando arquitecturas profundas. Este tipo de métodos ha ganado mucha popularidad durante los últimos años debido a los impresionantes resultados obtenidos en diferentes tareas como el reconocimiento automático del habla, el reconocimiento y la detección automática de objetos, el procesamiento de lenguajes naturales, etc. El principal objetivo de esta tesis es aportar una serie de contribuciones realizadas dentro del marco del Aprendizaje Profundo, particularmente enfocadas a problemas relacionados con la visión por computador. Estas contribuciones se resumen en dos novedosos métodos: una nueva técnica de regularización para Restricted Boltzmann Machines llamada Mask Selective Regularization (MSR), y una potente red neuronal discriminativa llamada Local Deep Neural Network (Local-DNN). Por una lado, el método MSR se basa en aprovechar las ventajas de las técnicas de regularización clásicas basadas en las normas L2 y L1. Ambas regularizaciones se aplican sobre los parámetros de la RBM teniendo en cuenta el estado del modelo durante el entrenamiento y la topología de los datos de entrada. Por otro lado, El modelo Local-DNN se basa en dos conceptos fundamentales: características locales y arquitecturas profundas. De forma similar a las redes convolucionales, Local-DNN restringe el aprendizaje a regiones locales de la imagen de entrada. La red neuronal pretende clasificar cada característica local con la etiqueta de la imagen a la que pertenece, y, finalmente, todas estas contribuciones se tienen en cuenta utilizando un sencillo sistema de votación durante la predicción. Los métodos propuestos a lo largo de la tesis han sido ampliamente evaluados en varios experimentos utilizando distintas bases de datos, principalmente en problemas de visión por computador. Los resultados obtenidos muestran el buen funcionamiento de dichos métodos, y sirven para validar las estrategias planteadas. Entre ellos, destacan los resultados obtenidos aplicando el modelo Local-DNN al problema del reconocimiento de género utilizando imágenes faciales, donde se han mejorado los resultados publicados del estado del arte. / [CA] L'Aprenentatge Profund (Deep Learning en anglès) és una nova àrea dins el camp de l'Aprenentatge Automàtic que pretén crear models computacionals que aprenguen diverses representacions de les dades utilitzant arquitectures profundes. Aquest tipus de mètodes ha guanyat molta popularitat durant els últims anys a causa dels impressionants resultats obtinguts en diverses tasques com el reconeixement automàtic de la parla, el reconeixement i la detecció automàtica d'objectes, el processament de llenguatges naturals, etc. El principal objectiu d'aquesta tesi és aportar una sèrie de contribucions realitzades dins del marc de l'Aprenentatge Profund, particularment enfocades a problemes relacionats amb la visió per computador. Aquestes contribucions es resumeixen en dos nous mètodes: una nova tècnica de regularització per Restricted Boltzmann Machines anomenada Mask Selective Regularization (MSR), i una potent xarxa neuronal discriminativa anomenada Local Deep Neural Network ( Local-DNN). D'una banda, el mètode MSR es basa en aprofitar els avantatges de les tècniques de regularització clàssiques basades en les normes L2 i L1. Les dues regularitzacions s'apliquen sobre els paràmetres de la RBM tenint en compte l'estat del model durant l'entrenament i la topologia de les dades d'entrada. D'altra banda, el model Local-DNN es basa en dos conceptes fonamentals: característiques locals i arquitectures profundes. De forma similar a les xarxes convolucionals, Local-DNN restringeix l'aprenentatge a regions locals de la imatge d'entrada. La xarxa neuronal pretén classificar cada característica local amb l'etiqueta de la imatge a la qual pertany, i, finalment, totes aquestes contribucions es fusionen durant la predicció utilitzant un senzill sistema de votació. Els mètodes proposats al llarg de la tesi han estat àmpliament avaluats en diversos experiments utilitzant diferents bases de dades, principalment en problemes de visió per computador. Els resultats obtinguts mostren el bon funcionament d'aquests mètodes, i serveixen per validar les estratègies plantejades. Entre d'ells, destaquen els resultats obtinguts aplicant el model Local-DNN al problema del reconeixement de gènere utilitzant imatges facials, on s'han millorat els resultats publicats de l'estat de l'art. / Mansanet Sandín, J. (2016). Contributions to Deep Learning Models [Tesis doctoral]. Universitat Politècnica de València. https://doi.org/10.4995/Thesis/10251/61296

Observers can identify gender based on individual gait styles visually. Existing research showed that gender differences in gait kinematics mainly occur in the frontal and transverse planes and are influenced by various factors. This study adds to the existing work by analysing the kinematic features that distinguish gait styles influenced by gender and gait speeds. 29 females and 33 males without gait disorders took part in this study. A wireless IMU-based sensor system was used to collect 3D kinematic data at 60 Hz on a 15 m walkway at three different gait speeds. Statistical analysis was based on discrete parameters, principal component analysis (PCA), and support vector machines (SVM). Dissimilarities due to different gait speeds were analysed in transverse and frontal planes for the upper body and in the sagittal plane for the upper and lower body (p < 0.001 and Cohen’s d > 0.8). In joint angles (knees; transversal plane), segment orientation angles (upper body; frontal plane) and segment position (upper body; sagittal and frontal plane), statistically significant differences (p < 0.001 and Cohen’s d > 0.8) were observed for gender.Good classification accuracies for joint angles, segment orientation and segment positions of 97-100 % between gait speed and 77-87 % between gender groups were found. In this study, gender had less influence on gait kinematics than gait speed.:1. Introduction 2. Methods 3. Results 4. Discussion

The purpose of this dissertation was to provide knowledge of how issues of social work policy and practice are being raised in the responses to the Scottish Government’s public consultation ‘Review of the Gender Recognition Act 2004’ from 2017. Further, the purpose was to understand how sex and gender were described in the responses, and how these descriptions may relate to concepts of power and discourse in regards to social work practice. The dissertation is based on the 32 opposing organisational responses to the public consultation. The material was processed through a qualitative content analysis, generating ten categories that this dissertation labels as (1) sex as a biological reality, (2) on the post-structuralist view of gender, (3) gender mainstreaming, (4) the magnitude of the decision and regret,(5) diagnosis criteria as a quality assurer for trans care, (6) trans people without gender affirming surgery, (7) the challenge for professionals, (8) biological males, single-sex spaces and the risk for exploitation, (9) cis women’s rights and (10) cis women’s vulnerability. The categories were later condensed into three themes labelled as (1) understanding gender identities and self-declaration, (2) the shift towards self-declaration and (3) the threat to cis women. The themes and categories were analysed through the theoretical framework of Judith Butler’s queer theory. The analysis was followed by a discussion that integrated the theoretical framework with previous research, aiming to enhance the applicability of the findings to the dissertation's purpose and the future of social work research. The findings of the dissertations show that the opposing organisation’s often described sex and gender using biological essentialist discourse, perceiving sex and gender as an innate biological feature that cannot be changed. Further, the findings show little mention of issues of social work in the organisation's responses to the public consultation. Drawing from previous research, the dissertation critiques this by arguing that civil society organisations should pay attention to discourse around legal gender recognition and its implications for the shaping of social work since they are key stakeholders for the development of social work policy and practice. / Syftet med denna uppsats var att bidra till kunskap om hur frågor kring socialt arbete lyfts fram i remissvaren till den skotska regeringens remiss ‘Review of the Gender Recognition Act 2004’ från 2017. Syftet var vidare att förstå hur begreppen kön och genus beskrivs i remissvaren, samt hur dessa beskrivningar relaterar till begreppen diskurs och makt i förhållande till socialt arbete. Uppsatsen baseras på 32 remissvar från de organisationer som motsatte sig den skotska regeringens syn på juridisk könstillhörighet. Materialet bearbetades genom en kvalitativ innehållsanalys vilket genererade tio kategorier som i denna uppsats benämns (1) kön som en biologisk verklighet, (2) om den poststrukturalistiska synen på genus, (3) genus-mainstreaming, (4) beslutets magnitud och ånger, (5) diagnoskriterier som kvalitetsgaranti för transvård, (6) transpersoner utan könsbekräftande kirurgi, (7) utmaningen för yrkesverksamma, (8) biologiska män, separatistiska utrymmen och risken för exploatering, (9) ciskvinnors rättigheter och (10) ciskvinnors sårbarhet. Kategorierna kondenserades sedan till tre teman som i denna uppsats benämns (1) förståelsen av könsidentiteter ochsjälvbestämmande, (2) övergången till självbestämmande och (3) fara för ciskvinnor. Temana och kategorierna analyserades med hjälp av Judith Butlers queerteori. Analysen följdes av en diskussion som integrerade det teoretiska ramverket med tidigare forskning, med avsikten att öka tillämpbarheten av resultaten för uppsatsens syfte och den framtida forskningen inom socialt arbete. Uppsatsens resultat visar att organisationerna ofta beskrev kön och genus med hjälp av en könsdeterministisk diskurs, som förstår kön och genus som inneboende biologiska egenskaper som inte kan förändras. Resultatet visar vidare att frågor kring socialt arbete lyfts fram i låg utsträckning i organisationernas remissvar. Uppsatsen kritiserar detta genom att argumentera för att civilsamhällesorganisationer bör uppmärksamma remissen simplikationer för utformningen av socialt arbete i relation till frågan om juridisk könstillhörighet eftersom civilsamhällesorganisationer är viktiga aktörer för utvecklingen av socialt arbete.

Les progrès récents des réseaux de neurones artificiels (plus connus sous le nom d'apprentissage profond) ont permis d'améliorer l’état de l’art dans plusieurs domaines de la vision par ordinateur. Dans cette thèse, nous étudions des techniques d'apprentissage profond dans le cadre de l’analyse du genre et de l’âge à partir du visage humain. En particulier, deux problèmes complémentaires sont considérés : (1) la prédiction du genre et de l’âge, et (2) la synthèse et l’édition du genre et de l’âge.D’abord, nous effectuons une étude détaillée qui permet d’établir une liste de principes pour la conception et l’apprentissage des réseaux de neurones convolutifs (CNNs) pour la classification du genre et l’estimation de l’âge. Ainsi, nous obtenons les CNNs les plus performants de l’état de l’art. De plus, ces modèles nous ont permis de remporter une compétition internationale sur l’estimation de l’âge apparent. Nos meilleurs CNNs obtiennent une précision moyenne de 98.7% pour la classification du genre et une erreur moyenne de 4.26 ans pour l’estimation de l’âge sur un corpus interne particulièrement difficile.Ensuite, afin d’adresser le problème de la synthèse et de l’édition d’images de visages, nous concevons un modèle nommé GA-cGAN : le premier réseau de neurones génératif adversaire (GAN) qui produit des visages synthétiques réalistes avec le genre et l’âge souhaités. Enfin, nous proposons une nouvelle méthode permettant d’employer GA-cGAN pour le changement du genre et de l’âge tout en préservant l’identité dans les images synthétiques. Cette méthode permet d'améliorer la précision d’un logiciel sur étagère de vérification faciale en présence d’écarts d’âges importants. / The recent progress in artificial neural networks (rebranded as deep learning) has significantly boosted the state-of-the-art in numerous domains of computer vision. In this PhD study, we explore how deep learning techniques can help in the analysis of gender and age from a human face. In particular, two complementary problem settings are considered: (1) gender/age prediction from given face images, and (2) synthesis and editing of human faces with the required gender/age attributes.Firstly, we conduct a comprehensive study which results in an empirical formulation of a set of principles for optimal design and training of gender recognition and age estimation Convolutional Neural Networks (CNNs). As a result, we obtain the state-of-the-art CNNs for gender/age prediction according to the three most popular benchmarks, and win an international competition on apparent age estimation. On a very challenging internal dataset, our best models reach 98.7% of gender classification accuracy and an average age estimation error of 4.26 years.In order to address the problem of synthesis and editing of human faces, we design and train GA-cGAN, the first Generative Adversarial Network (GAN) which can generate synthetic faces of high visual fidelity within required gender and age categories. Moreover, we propose a novel method which allows employing GA-cGAN for gender swapping and aging/rejuvenation without losing the original identity in synthetic faces. Finally, in order to show the practical interest of the designed face editing method, we apply it to improve the accuracy of an off-the-shelf face verification software in a cross-age evaluation scenario.