|
|
Symmetry of triangle meshes
Vévoda, Petr ; Pelikán, Josef (advisor) ; Krajíček, Václav (referee)
Triangle meshes belong to methods of storing a surface of a threedimensional object in computer memory. A human face can be represented this way too. Findings about symmetry of faces are valuable for a variety of fields of study such as anthropology, medicine, criminalistics or psychology. For computing an approximate plane of symmetry of a face we have proposed an algorithm based on a gradient method, which minimizes distance between its mesh and its symmetric image over a set of all planes. However, it is possible to apply this algorithm to an arbitrary mesh and use its landmarks too. We have integrated the implementation covering also results visualization into Morphome3cs project focused on computations in anthropology.
|
|
|
Changes in preferences for heterozygosity in MHC genes across the menstrual cycle
Ptáčková, Kateřina ; Havlíček, Jan (advisor) ; Janotová, Kateřina (referee)
5 Abstract Products of major histocompatibility complex (MHC) plays key role in immune system of vertebrates. Prior studies on different vertebrate species show, that heterozygosity in MHC genes is linked to more efficient immune system and preferred in mate choice. Results of human studies are ambivalent, which can be due to the effect of some modulating factors like reproductive status. Therefore, our aim was to test heterozygosity related preferences in faces, odor and voice across menstrual cycle. Our sample consisted of 51 men and 52 women, from which 23 used hormonal contraception and 29 had natural cycle. They were genotyped in -A, -B and -DR alleles. All odor stimuli, face photos and voice records were rated on seven-point scale in both follicular and luteal phase. Repeated measures ANOVA was used for the analysis. Changes in ratings across the menstrual cycle and heterozygosity were most discernible on voice ratings. Voices of homozygous males were rated more attractive than voices of heterozygous males especially in follicular phase. Similar shift to higher ratings in follicular phase was manifested in ratings of homozygous male faces, but the difference between homozygous males and heterozygous males was not significant. Women with natural cycle also rated voices higher in their follicular phase...
|
|
| |
|
|
Qualitative analysis of laic personality description on the basis of facial morphology
Souhrada, Jan ; Pivoňková, Věra (advisor) ; Poláčková Šolcová, Iva (referee)
This study examines spontanneous, laic personality ratings of face in comparison to following questionnaires: 16 PF, EPQ-R, NEO-PI-R. We've focused on how people spontaneously rate personality from face in relation to traits which are examined by said questionnaires. We tried to discover which traits are part of questionnaires but not included qualiative ratings and vice versa which traits can be found in laic descriptions but not in questionnaires. We used data from previous studies which provided us with two independent data, self-reports and ratings of facial photographs. Ratings were sorted out and compared to questionnaires. Most of the traits from qualiative data were also included in NEO-PI-R, specifically 90,4% of traits from self-reports and 82,90% of peer reports. 16 PF covered 88% and 77,81% of traits, EPQ-R 86% and 75,94% respectively. The least covered factor overall was Self-Reliance (16 PF) which included only 0,4% of all traits from self-reports. We have not found any factor which would be completely neglected in qualiatitve descriptions. Atractivity and physical traits were one of the main traits among those left unclassified. As with atractivity itself there was wide range of traits that we are unsure of how much personality relevant they actually are. Among unclassified traits...
|
|
| |
|
|
Influence of external and internal factors on senescent changes of human face
Žigová, Dominika ; Velemínská, Jana (advisor) ; Kožejová Jaklová, Lenka (referee)
Aging is responsible for characteristic human facial changes. The purpose of this thesis is to identify and discuss possible factors that affect facial aging, which involves bone remodelling caused by progressive resorption of craniofacial bones. During the life, muscles become weaker as a result of muscle aging and activity, which leads to atrophy. In addition, their attachment to bones changes because of a decline in bone mass. Skin elasticity reduces with age, thus wrinkles are formed, skin colour changes and blood flow is impaired. Sun exposure is one of the extrinsic factors that have a significant effect on the facial senescent changes as it daily influences human skin by decreasing skin water content and impairing structures of collagen, elastin, and vessels. Smoking causes ischemia and wrinkles. Chronic skin diseases appear due to alcohol abuse, increased stress and air pollution. Sleep deficiency and low relative humidity environment contribute to skin dehydration and dryness. Skin can be protected and maintained youthful for longer by having a healthy diet. Aside from extrinsic factors, senescent facial changes are also influenced by various genes, a hormonal change, and bone remodelling. Nowadays, people age more slowly because of medical progress, better health care, new findings, and...
|
|
|
Generating Faces with Generative Adversarial Networks
Konečný, Daniel ; Herout, Adam (referee) ; Kolář, Martin (advisor)
Cílem této práce je generování barevných obrázků obličejů z náhodně určených vysokodimenzionálních vektorů pomocí generativních neuronových sítí. Dále se zabývá analýzou vstupních vektorů na základě příznaků obličejů z nich vygenerovaných. Je provedena implementace generativní neuronové sítě pro generování obrázků ručně psaných číslic, poté dalších dvou sítí pro generování obrázků obličejů. Vygenerované obrázky zobrazují věrohodně vypadající obličeje, lidské oko je však dokáže odlišit od fotek reálných osob. Analýza jednotlivých dimenzí vektorů je provedena pomocí Studentova t-testu. Dále jsou vstupní vektory promítnuty do podprostorů pomocí lineární diskriminační analýzy a jsou nalezeny rozdělovací hranice mezi třídami příznaků. Analýza generovaných dat dokazuje, že ovlivněním vstupního vektoru je možné docílit generování obrázku obličeje s požadovanými příznaky s pravděpodobností až 80 %. Hlavním výsledkem této práce je model generativní neuronové sítě určené pro generování obrázků obličejů. Dalším přínosem je nástroj pro generování obrázků obličejů na základě vybraných příznaků.
|
|
|
Smartphone Game Using Recognition of Face Features
Skoták, Jiří ; Szőke, Igor (referee) ; Herout, Adam (advisor)
This master's thesis focuses on smartphone game for iOS, which uses recognition of face features and other information, which can be obtained from a smartphone's camera and sensors. This work describes a few approaches for real-time face detection and then introduces and compares possibilities for such task on iOS. Moreover, the thesis contains a draft of the final game and its levels. The game showcases various technologies in its levels such as object detection, processing an image color and others. Finally, the thesis introduces the final form of the game that is released and available on the App Store.
|
|
|
Biometric Gateway Using Camera to Identify People
Jelen, Vilém ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
Biometric gateways are used to quickly and accurately identify people. Of the biometric characteristics, iris, face and fingerprints are commonly used. By combining them, better identification results can be achieved. The aim of this thesis is to create such a biometric gateway together with the control application. A combination of iris of both eyes and face is used, which is captured by cameras from three angles to increase accuracy. Neural networks are used to detect and extract face features. Iris recognition is realized using Daugman's algorithm.
|
|
|
Descriptor for Identification of a Person by the Face
Coufal, Tomáš ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Thesis provides an overview and discussion of current findings in the field of biometrics. In particular, it focuses on facial recognition subject. Special attention is payed to convolutional neural networks and capsule networks. Thesis then lists current approaches and state-of-the-art implementations. Based on these findings it provides insight into engineering a very own solution based of CapsNet architecture. Moreover, thesis discussed advantages and capabilitied of capsule neural networks for identification of a person by its face.
|
guest ::
