Search

The healthcare systems are facing a multitude of challenges in the modern world, including the aging population, a shortage of medical personnel, and regional barriers such as low population density and long distances. On the other hand, real-time video analysis based on computer vision and artificial intelligence approaches are being proposed as important future tools for assisting healthcare professionals. Despite the numerous advances in computer vision-based healthcare and medical diagnosis methods, the practical implementation of these techniques as embedded or remote solutions remains a challenge. This doctoral thesis aims to contribute to this effort by leveraging the advancements in computer vision and artificial intelligence to improve the unobtrusive and unsupervised acquisition of remote biosignals extracted from videos. The focus of this thesis is on improving the reliability and accuracy of remote photoplethysmography (rPPG) and remote ballistography (rBSG) techniques, as captured through camera-based embedded and distributed devices and remote video connections. The extracted biosignals are then analyzed to enable assistive diagnosis, prioritizing applications such as stress assessment, depression detection, and respiratory disease monitoring. The challenges and complexities of implementing computer vision in healthcare, including the integration of the methods in a distributed architecture and the impact of network and computational constraints in the application, are carefully considered and evaluated. The findings of this work are anticipated to enhance the quality of healthcare and patient outcomes while also contributing to the advancement of a more sustainable and accessible healthcare system., Tiivistelmä Terveydenhuollon toteutus on nykyään yhä hankalampaa, kun väestö ikääntyy ja lääkintähenkilökuntaa puuttuu. Lisäksi alueellisesti on omia haasteitaan kuten alhainen väestötiheys tai pitkät etäisyydet. Toisaalta tietokonenäköön ja tekoälyyn perustuva reaaliaikainen videoanalyysi voi olla tärkeä työkalu terveydenhuollon ammattilaisille tulevaisuudessa. Näiden tekniikoiden käytännön toteutus upotettuina tai etäratkaisuina on edelleen haastavaa, vaikka tietokonenäköön perustuva terveydenhuolto ja lääketieteelliset diagnoosimenetelmät ovatkin ottaneet lukuisia edistysaskelia. Tämä väitöskirja pyrkii edistämään tätä työtä hyödyntämällä tietokonenäön ja tekoälyn edistysaskeleita parantaakseen etäbiosignaalien huomaamatonta ja valvomatonta hankintaa videokuvasta. Väitöskirjan painopiste on etäfotopletysmografian (rPPG) ja etäballistografian (rBSG) tekniikoiden luotettavuuden ja tarkkuuden parantamisessa upotetuilla ja hajautetuilla kameralaitteilla sekä etävideoyhteyksillä. Näitä biosignaaleja analysoidaan ja tuotetaan avustava diagnoosi, missä painopisteenä ovat sovellukset kuten stressin arviointi, masennuksen havaitseminen ja hengityselinten sairauksien seuranta. Tietokonenäön soveltamisen haasteet ja monimutkaisuudet terveydenhuollossa, mukaan lukien menetelmien integrointi hajautettuun arkkitehtuuriin sekä verkon ja laskennallisten rajoitusten vaikutus sovellukseen, otetaan huolellisesti huomioon ja arvioidaan. Tämän työn tulosten odotetaan parantavan terveydenhuollon laatua ja potilastuloksia sekä edistävän kestävämmän ja saavutettavamman terveydenhuoltojärjestelmän kehitystä.

The field of fine-grained semantic segmentation for a person's face and head, which includes identifying facial parts and head components, has made significant progress in recent years. However, this task remains challenging due to the difficulty of considering ambiguous occlusions and large pose variations. To address these difficulties, we propose a new framework called Mask-FPAN. Our framework includes a de-occlusion module that learns to parse occluded faces in a semi-supervised manner, taking into account face landmark localization, face occlusion estimations, and detected head poses. Additionally, we improve the robustness of 2D face parsing by combining a 3D morphable face model with the UV GAN. We also introduce two new datasets, named FaceOccMask-HQ and CelebAMaskOcc-HQ, to aid in face parsing work. Our proposed Mask-FPAN framework successfully addresses the challenge of face parsing in the wild and achieves significant performance improvements, with a mIoU increase from 0.7353 to 0.9013 compared to the current state-of-the-art on challenging face datasets.

The field of fine-grained semantic segmentation for a person's face and head, which includes identifying facial parts and head components, has made significant progress in recent years. However, this task remains challenging due to the difficulty of considering ambiguous occlusions and large pose variations. To address these difficulties, we propose a new framework called Mask-FPAN. Our framework includes a de-occlusion module that learns to parse occluded faces in a semi-supervised manner, taking into account face landmark localization, face occlusion estimations, and detected head poses. Additionally, we improve the robustness of 2D face parsing by combining a 3D morphable face model with the UV GAN. We also introduce two new datasets, named FaceOccMask-HQ and CelebAMaskOcc-HQ, to aid in face parsing work. Our proposed Mask-FPAN framework successfully addresses the challenge of face parsing in the wild and achieves significant performance improvements, with a mIoU increase from 0.7353 to 0.9013 compared to the current state-of-the-art on challenging face datasets.

Machines that interact with humans can do so better if they can also visually understand us, but they have limited resources to do so. The main topic of this dissertation is contrasting the use of resources by machine vision systems against the accuracy obtained by them. This thesis focuses on reducing the need for data, memory, and computation in real-world machine vision systems, applied to human observation and face analysis. This dissertation tackles annotation effort by exploring how weakly-supervised object/person detectors can be improved. Findings show that prior knowledge about objects' bounds in images helps the detector learn the spatial extent of objects using only weak image-level labels. The proposed implementation enables single-shot detection, thus improving computational efficiency of this data-efficient method. The thesis also demonstrates how prior knowledge about eye locations can be used to reduce the computational burden of gaze tracking: non-vital parts of the input image can be discarded without losing accuracy. Additionally, the thesis finds how a priori known geometrical relations can be exploited to project gaze onto a screen with little human annotation effort. Findings of this dissertation further suggest that spatial structures in images can be exploited for improving efficiency of vision tasks. The proposed solution allows for learning detection of facial occlusions and anomalies from only a few examples. Results also indicate that this solution can be used as a loss function for unsupervised pre-training of neural networks when resources are constrained. Lastly, this thesis showcases how prior know-how about blood-flow physiology in faces can be applied in a camera-based vital signs estimator. Even when data is available, this hand-crafted method performs better than deep learning methods — both in terms of accuracy and efficiency. At the same time, the results also reveal the pitfalls of as, Pattern Recognition and Bioinformatics

Objective: We explore state of the art machine learning based tools for automatic facial and linguistic affect analysis to allow easier, faster, and more precise quantification and annotation of children’s verbal and non-verbal affective expressions in psychodynamic child psychotherapy. Method: The sample included 53 Turkish children: 41 with internalizing, externalizing and comorbid problems; 12 in the non-clinical range. We collected audio and video recordings of 148 sessions, which were manually transcribed. Independent raters coded children’s expressions of pleasure, anger, sadness and anxiety using the Children’s Play Therapy Instrument (CPTI). Automatic facial and linguistic affect analysis modalities were adapted, developed, and combined in a system that predicts affect. Statistical regression methods (linear and polynomial regression) and machine learning techniques (deep learning, support vector regression and extreme learning machine) were used for predicting CPTI affect dimensions. Results: Experimental results show significant associations between automated affect predictions and CPTI affect dimensions with small to medium effect sizes. Fusion of facial and linguistic features work best for pleasure predictions; however, for other affect predictions linguistic analyses outperform facial analyses. External validity analyses partially support anger and pleasure predictions. Discussion: The system enables retrieving affective expressions of children, but needs improvement for precision.

Deep learning (DL) models have been successfully applied in video-based affective computing, allowing to recognize emotions and mood, or to estimate the intensity of pain or stress based on facial expressions. Despite the advances with state-of-the-art DL models for spatio-temporal recognition of facial expressions associated with depression, some challenges remain in the cost-effective application of 3D-CNNs: (1) 3D convolutions employ structures with fixed temporal depth that decreases the potential to extract discriminative representations due to the usually small difference of spatio-temporal variations along different depression levels; and (2) the computationally complexity of these models with consequent susceptibility to overfitting. To address these challenges, we propose a novel DL architecture called the Maximization and Differentiation Network (MDN) in order to effectively represent facial expression variations that are relevant for depression assessment. The MDN operates without 3D convolutions, by exploring multiscale temporal information using a maximization block that captures smooth facial variations, and a difference block to encode sudden facial variations. Extensive experiments using our proposed MDN result in improved performance while reducing the number of parameters by more than 3 when compared with 3D-ResNet models. Our model also outperforms other 3D models and achieves state-of-the-art results for depression detection. Code available at: https://github.com/wheidima/MDN.

Recently, deep learning models have been successfully employed in video-based affective computing applications. One key application is automatic depression recognition from facial expressions. State-of-the-art approaches to recognize depression typically explore spatial and temporal information individually, by using convolutional neural networks (CNNs) to analyze appearance information, and then by either mapping feature variations or averaging the depression level over video frames. This approach has limitations to represent dynamic information that can help to discriminate between depression levels. In contrast, 3D CNN-based models can directly encode the spatio-temporal relationships, although these models rely on fixed-range temporal information and single receptive field. This approach limits the ability to capture facial expression variations with diverse ranges, and the exploitation of diverse facial areas. In this paper, a novel 3D CNN architecture the Multiscale Spatiotemporal Network (MSN) is introduced to effectively represent facial information related to depressive behaviours. The basic structure of the model is composed of parallel convolutional layers with different temporal depths and sizes of receptive field, which allows the MSN to explore a wide range of spatio-temporal variations in facial expressions. Experimental results on two benchmark datasets show that our MSN is effective, outperforming state-of-the-art methods in automatic depression recognition.

This paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image. To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected and characterized directly from the image via a simple and effective parametric model, determining several features such as location, orientation, width, and height. With these ingredients, we propose to minimize a photometric error to retrieve the final detailed 3D map, which is initialized by current techniques based on deep learning. In contrast with other approaches, we only require estimating a depth parameter, making our approach fast and intuitive. Extensive experimental evaluation is presented in a wide variety of synthetic and real images, including different skin properties and facial expressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles., Peer Reviewed, Postprint (author's final draft)

This paper introduces a method to obtain a detailed 3D reconstruction of facial skin from a single RGB image. To this end, we propose the exclusive use of an input image without requiring any information about the observed material nor training data to model the wrinkle properties. They are detected and characterized directly from the image via a simple and effective parametric model, determining several features such as location, orientation, width, and height. With these ingredients, we propose to minimize a photometric error to retrieve the final detailed 3D map, which is initialized by current techniques based on deep learning. In contrast with other approaches, we only require estimating a depth parameter, making our approach fast and intuitive. Extensive experimental evaluation is presented in a wide variety of synthetic and real images, including different skin properties and facial expressions. In all cases, our method outperforms the current approaches regarding 3D reconstruction accuracy, providing striking results for both large and fine wrinkles.

Context: When playing a co-operative game, being aware of your collaborators (where they are playing, what they are doing, the abilities they have, etc.) is essential for achieving the game's goals. This led to the definition of Gamespace Awareness in order to guide in the identification of the awareness needs in the form of a compilation of the awareness elements that a co-operative game should feature. Objective: Gamespace Awareness does not establish how much awareness information players must be provided with. This constitutes the main motivation for this work: to assess the impact of different levels of Gamespace Awareness elements on a co-operative game. Method: A multiplayer action game was developed that supports three different awareness configurations, each one featuring different awareness levels (high, medium and low). The impact of these awareness levels was measured as regards game score, time, players’ happiness while playing, enjoyment and perceived usefulness. Several techniques such as subjective surveys and facial expression analysis were used to measure these factors. Results: The analysis of the results shows that the higher the awareness, the better the game score. However, the highest level of player happiness was not achieved with the most awareness-enabled configuration; we found that the players’ enjoyment depends not only on their awareness level but also on their expertise level. Finally, the awareness elements related to the present and the future were the most useful, as could be expected in a multiplayer action game. Conclusions: The results showed that the medium level awareness obtained the best results. We therefore concluded that a certain level of awareness is necessary, but that excessive awareness could negatively affect the game experience.

Enhancing facial images captured under different lighting conditions is an important challenge and a crucial component in the automatic face recognition systems. This work tackles illumination variation challenge by proposing a new face image enhancement approach based on Fuzzy theory. The proposed Fuzzy reasoning model generates an adaptive enhancement which corrects and improves non-uniform illumination and low contrasts. The FRM approach has been assessed using four blind-reference image quality metrics supported by visual assessment. A comparison to six state-of-the-art methods has also been provided. Experiments are performed on four public data sets, namely Extended Yale-B, Mobio, FERET and Carnegie Mellon University Pose, Illumination, and Expression, showing very interesting results achieved by our approach.

Automatic kinship verification from facial images is a relatively new and challenging research problem in computer vision. It consists in automatically determining whether two persons have a biological kin relation by examining their facial attributes. In this work, we compare the performance of humans and machines in kinship verification tasks. We investigate the state-of-the-art methods in automatic kinship verification from facial images, comparing their performance with the one obtained by asking humans to complete an equivalent task using a crowdsourcing system. Our results show that machines can consistently beat humans in kinship classification tasks in both images and videos. In addition, we study the limitations of currently available kinship databases and analyzing their possible impact in kinship verification experiment and this type of comparison.

Automatic medical diagnosis is an emerging center of interest in computer vision as it provides unobtrusive objective information on a patient’s condition. The face, as a mirror of health status, can reveal symptomatic indications of specific diseases. Thus, the detection of facial abnormalities or atypical features is at upmost importance when it comes to medical diagnostics. This survey aims to give an overview of the recent developments in medical diagnostics from facial images based on computer vision methods. Various approaches have been considered to assess facial symptoms and to eventually provide further help to the practitioners. However, the developed tools are still seldom used in clinical practice, since their reliability is still a concern due to the lack of clinical validation of the methodologies and their inadequate applicability. Nonetheless, efforts are being made to provide robust solutions suitable for healthcare environments, by dealing with practical issues such as real-time assessment or patients positioning. This survey provides an updated collection of the most relevant and innovative solutions in facial images analysis. The findings show that with the help of computer vision methods, over 30 medical conditions can be preliminarily diagnosed from the automatic detection of some of their symptoms. Furthermore, future perspectives, such as the need for interdisciplinary collaboration and collecting publicly available databases, are highlighted.

Context: When playing a co-operative game, being aware of your collaborators (where they are playing, what they are doing, the abilities they have, etc.) is essential for achieving the game's goals. This led to the definition of Gamespace Awareness in order to guide in the identification of the awareness needs in the form of a compilation of the awareness elements that a co-operative game should feature. Objective: Gamespace Awareness does not establish how much awareness information players must be provided with. This constitutes the main motivation for this work: to assess the impact of different levels of Gamespace Awareness elements on a co-operative game. Method: A multiplayer action game was developed that supports three different awareness configurations, each one featuring different awareness levels (high, medium and low). The impact of these awareness levels was measured as regards game score, time, players’ happiness while playing, enjoyment and perceived usefulness. Several techniques such as subjective surveys and facial expression analysis were used to measure these factors. Results: The analysis of the results shows that the higher the awareness, the better the game score. However, the highest level of player happiness was not achieved with the most awareness-enabled configuration; we found that the players’ enjoyment depends not only on their awareness level but also on their expertise level. Finally, the awareness elements related to the present and the future were the most useful, as could be expected in a multiplayer action game. Conclusions: The results showed that the medium level awareness obtained the best results. We therefore concluded that a certain level of awareness is necessary, but that excessive awareness could negatively affect the game experience.

Deep learning methods are able to automatically discover better representations of the data to improve the performance of the classifiers. However, in computer vision tasks, such as the gender recognition problem, sometimes it is difficult to directly learn from the entire image. In this work we propose a new model called Local Deep Neural Network (Local-DNN), which is based on two key concepts: local features and deep architectures. The model learns from small overlapping regions in the visual field using discriminative feed forward networks with several layers. We evaluate our approach on two well-known gender benchmarks, showing that our Local-DNN outperforms other deep learning methods also evaluated and obtains state-of-the-art results in both benchmarks. (C) 2015 Elsevier B.V. All rights reserved.

Deep learning methods are able to automatically discover better representations of the data to improve the performance of the classifiers. However, in computer vision tasks, such as the gender recognition problem, sometimes it is difficult to directly learn from the entire image. In this work we propose a new model called Local Deep Neural Network (Local-DNN), which is based on two key concepts: local features and deep architectures. The model learns from small overlapping regions in the visual field using discriminative feed forward networks with several layers. We evaluate our approach on two well-known gender benchmarks, showing that our Local-DNN outperforms other deep learning methods also evaluated and obtains state-of-the-art results in both benchmarks. (C) 2015 Elsevier B.V. All rights reserved.

Humans are not sensitive to variations in facial appearance and are capable of performing face analysis tasks reliably under realistic conditions when compared with current computer-based face analysis techniques. This can be partly explained by the ability of humans to make effective use of previously encountered known faces for both internal representation and processing. This thesis focuses on establishing computational models to account for the cognitive findings related to internal face representation and two fundamental perception processes (distinctiveness and familiarity), and developing novel methods based on the models for face analysis. Specifically, a set of reference samples that may or may not contain any labeling information and any instance of the person whose face is under consideration are proposed to model previously encountered faces. The non-negative matrix factorization which affords part-based representation is extended to learn reusable local facial patterns for representation from the reference set. Computational models are developed for locating distinctive areas and measuring familiarity of faces with respect to the reference set. By employing the proposed face representation, distinctiveness and familiarity models, novel schemes are developed to recognize faces from single sample per person and estimate ages and head poses of faces.

Humans are not sensitive to variations in facial appearance and are capable of performing face analysis tasks reliably under realistic conditions when compared with current computer-based face analysis techniques. This can be partly explained by the ability of humans to make effective use of previously encountered known faces for both internal representation and processing. This thesis focuses on establishing computational models to account for the cognitive findings related to internal face representation and two fundamental perception processes (distinctiveness and familiarity), and developing novel methods based on the models for face analysis. Specifically, a set of reference samples that may or may not contain any labeling information and any instance of the person whose face is under consideration are proposed to model previously encountered faces. The non-negative matrix factorization which affords part-based representation is extended to learn reusable local facial patterns for representation from the reference set. Computational models are developed for locating distinctive areas and measuring familiarity of faces with respect to the reference set. By employing the proposed face representation, distinctiveness and familiarity models, novel schemes are developed to recognize faces from single sample per person and estimate ages and head poses of faces.

Humans are not sensitive to variations in facial appearance and are capable of performing face analysis tasks reliably under realistic conditions when compared with current computer-based face analysis techniques. This can be partly explained by the ability of humans to make effective use of previously encountered known faces for both internal representation and processing. This thesis focuses on establishing computational models to account for the cognitive findings related to internal face representation and two fundamental perception processes (distinctiveness and familiarity), and developing novel methods based on the models for face analysis. Specifically, a set of reference samples that may or may not contain any labeling information and any instance of the person whose face is under consideration are proposed to model previously encountered faces. The non-negative matrix factorization which affords part-based representation is extended to learn reusable local facial patterns for representation from the reference set. Computational models are developed for locating distinctive areas and measuring familiarity of faces with respect to the reference set. By employing the proposed face representation, distinctiveness and familiarity models, novel schemes are developed to recognize faces from single sample per person and estimate ages and head poses of faces.

A statistical analysis of shapes of facial surfaces can play an important role in biometric authentication and other face-related applications. The main difficulty in developing such an analysis comes from the lack of a canonical system to represent and compare all facial surfaces. This paper suggests a specific, yet natural, coordinate system on facial surfaces, that enables comparisons of their shapes. Here a facial surface is represented as an indexed collection of closed curves, called facial curves, that are level curves of a surface distance function from the tip of the nose. Defining the space of all such representations of face, this paper studies its differential geometry and endows it with a Riemannian metric. It presents numerical techniques for computing geodesic paths between facial surfaces in that space. This Riemannian framework is then used to: (i) compute distances between faces to quantify differences in their shapes, (ii) find optimal deformations between faces, and (iii) define and compute average of a given set of faces. Experimental results generated using laser-scanned faces are presented to demonstrate these ideas.

This paper presents a statistical study of facial expressions. It shows how the result can be used to develop a high-level realistic automated framework for real-time facial expression synthesis, compliant with MPEG-4 Facial Animation (FA) spcifications.

Tato práce se zabývá možnými přístupy k 3D rekonstrukci obličeje z 2D snímku. Jsou zde popsány způsoby analýzy vstupního snímku, jako lokalizace obličeje a obličejových rysů, ze kterých rekonstrukce vychází. Dále je čtenář detailněji seznámen s modifikačním modelem, který je základem většiny zmíněných metod, jeho vytvořením z databáze statistických dat a použitím při rekonstrukci. Obsahem je také popis implementace algoritmu využívajícího tento model., This work deals with procedures that enables you reconstruct 3D face from a 2D picture. It describes ways to analyze an input picture, such as a face and facial features localization, on which this reconstruction builds. A reader is getting into a morphable model, its creation from static database data and and its usage on a reconstruction, more detailed later on, this morphable model is a building block of mentioned methods. This work contains also an algorithm implementation based on this model.

Tato práce se zabývá možnými přístupy k 3D rekonstrukci obličeje z 2D snímku. Jsou zde popsány způsoby analýzy vstupního snímku, jako lokalizace obličeje a obličejových rysů, ze kterých rekonstrukce vychází. Dále je čtenář detailněji seznámen s modifikačním modelem, který je základem většiny zmíněných metod, jeho vytvořením z databáze statistických dat a použitím při rekonstrukci. Obsahem je také popis implementace algoritmu využívajícího tento model., This work deals with procedures that enables you reconstruct 3D face from a 2D picture. It describes ways to analyze an input picture, such as a face and facial features localization, on which this reconstruction builds. A reader is getting into a morphable model, its creation from static database data and and its usage on a reconstruction, more detailed later on, this morphable model is a building block of mentioned methods. This work contains also an algorithm implementation based on this model.

Tato práce se zabývá možnými přístupy k 3D rekonstrukci obličeje z 2D snímku. Jsou zde popsány způsoby analýzy vstupního snímku, jako lokalizace obličeje a obličejových rysů, ze kterých rekonstrukce vychází. Dále je čtenář detailněji seznámen s modifikačním modelem, který je základem většiny zmíněných metod, jeho vytvořením z databáze statistických dat a použitím při rekonstrukci. Obsahem je také popis implementace algoritmu využívajícího tento model., This work deals with procedures that enables you reconstruct 3D face from a 2D picture. It describes ways to analyze an input picture, such as a face and facial features localization, on which this reconstruction builds. A reader is getting into a morphable model, its creation from static database data and and its usage on a reconstruction, more detailed later on, this morphable model is a building block of mentioned methods. This work contains also an algorithm implementation based on this model.

Tato práce se zabývá možnými přístupy k 3D rekonstrukci obličeje z 2D snímku. Jsou zde popsány způsoby analýzy vstupního snímku, jako lokalizace obličeje a obličejových rysů, ze kterých rekonstrukce vychází. Dále je čtenář detailněji seznámen s modifikačním modelem, který je základem většiny zmíněných metod, jeho vytvořením z databáze statistických dat a použitím při rekonstrukci. Obsahem je také popis implementace algoritmu využívajícího tento model., This work deals with procedures that enables you reconstruct 3D face from a 2D picture. It describes ways to analyze an input picture, such as a face and facial features localization, on which this reconstruction builds. A reader is getting into a morphable model, its creation from static database data and and its usage on a reconstruction, more detailed later on, this morphable model is a building block of mentioned methods. This work contains also an algorithm implementation based on this model.

Tato práce se zabývá možnými přístupy k 3D rekonstrukci obličeje z 2D snímku. Jsou zde popsány způsoby analýzy vstupního snímku, jako lokalizace obličeje a obličejových rysů, ze kterých rekonstrukce vychází. Dále je čtenář detailněji seznámen s modifikačním modelem, který je základem většiny zmíněných metod, jeho vytvořením z databáze statistických dat a použitím při rekonstrukci. Obsahem je také popis implementace algoritmu využívajícího tento model., This work deals with procedures that enables you reconstruct 3D face from a 2D picture. It describes ways to analyze an input picture, such as a face and facial features localization, on which this reconstruction builds. A reader is getting into a morphable model, its creation from static database data and and its usage on a reconstruction, more detailed later on, this morphable model is a building block of mentioned methods. This work contains also an algorithm implementation based on this model.

Tato práce se zabývá možnými přístupy k 3D rekonstrukci obličeje z 2D snímku. Jsou zde popsány způsoby analýzy vstupního snímku, jako lokalizace obličeje a obličejových rysů, ze kterých rekonstrukce vychází. Dále je čtenář detailněji seznámen s modifikačním modelem, který je základem většiny zmíněných metod, jeho vytvořením z databáze statistických dat a použitím při rekonstrukci. Obsahem je také popis implementace algoritmu využívajícího tento model., This work deals with procedures that enables you reconstruct 3D face from a 2D picture. It describes ways to analyze an input picture, such as a face and facial features localization, on which this reconstruction builds. A reader is getting into a morphable model, its creation from static database data and and its usage on a reconstruction, more detailed later on, this morphable model is a building block of mentioned methods. This work contains also an algorithm implementation based on this model.