|
|
Anthropometric Evaluation of Generated Face Images
Mikyšek, Jakub ; Rydlo, Štěpán (referee) ; Goldmann, Tomáš (advisor)
This work is focused on comparing artificially generated faces with real images by analyzing key facial landmarks and measuring the proportions between these landmarks. It also explores areas related to artificial neural networks, focusing on GANs that can generate artificially generated facial images. It explores their process, architecture and available models. The aim of the work is to evaluate how artificially generated images differ from real ones, and to find out in which proportions the difference is the largest.
|
|
|
Smart Fitness Assistent
Matějka, Martin ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
The thesis addresses the issue of determining repetitions and measuring the performance of athletes in public fitness centers. It proposes a combination of software and hardware capable of providing feedback to fitness center users. The process of developing software and hardware for data measurement and evaluation is outlined. These results are processed almost immediately after the completion of the exercise and can be presented to the user immediately. The presented combination of technologies offers a new way of monitoring and improving performance in the fitness environment from the perspective of the fitness center.
|
|
|
Detection of Nudity in an Image Data
Pešková, Daniela ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Zameranie tejto práce je vytvorenie nástroja schopného detekovať nahotu v obrazových dátach. To je dosiahnuté natrénovaním modelu na detekciu inkriminovaných častí tela a vytvorením algoritmu schopného detekovať pokožku. Výsledné nástroje môžu byť použité pre automatickú detekciu nahoty v obrázkoch. Prvá časť práce sa zameriava na teóriu neurónových sietí a počítačového videnia so zameraním na detekciu pokožky. Druhá časť hovorí o prístupe zvolenom pre vytvorenie datasetu, procese tvorby a trénovania modelu schopného detekovať nahotu v obraze, ako aj o algoritmickom prístupe.
|
|
|
Algorithm for Facial Image Quality Estimation
Husár, Tomáš ; Sakin, Martin (referee) ; Goldmann, Tomáš (advisor)
The precision of face recognition algorithms is heavily influenced by the quality of input images. The aim of the work is to evaluate the quality of face images using a convolutional neural network. The data on which the testing was carried out were created by various degradations of photos from the CelebA dataset. The resulting application determines the quality of images based on the predicted probabilities of individual degradations.
|
|
|
Tracking People in Video Captured from a Drone
Lukáč, Jakub ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Práca rieši možnosť zaznamenávať pozíciu osôb v zázname z kamery drona a určovať ich polohu. Absolútna pozícia sledovanej osoby je odvodená vzhľadom k pozícii kamery, teda vzhľadom k umiestneniu drona vybaveného príslušnými senzormi. Zistené dáta sú po ich spracovaní vykreslené ako príslušné cesty v grafe. Práca si ďalej dáva za cieľ využiť dostupné riešenia čiastkových problémov: detekcia osôb v obraze, identifikácia jednotlivých osôb v čase, určenie vzdialenosti objektu od kamery, spracovanie potrebných senzorových dát. Následne využiť preskúmané metódy a navrhnúť riešenie, ktoré bude v reálnom čase pracovať na uvedenom probléme. Implementačná časť spočíva vo využití akcelerátoru Intel NCS v spojení s Raspberry Pi priamo ako súčasť drona. Výsledný systém je schopný generovať výstup o polohe detekovaných osôb v zábere kamery a príslušne ho prezentovať.
|
|
|
Analysis of Facial Development Based on Anthropometric Properties
Oravec, Dávid ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
This bachelor thesis deals with anthropometry of human face, anthropometric landmarks, which are used to determine the distances and various relations between them. Our body is aging and consequently the position of anthropometric points is changing. The aim of this work is to determine anthropometric landmarks from photo of the human face and then to analyze the given face and how it develops over time. The model for facial landmark detection was trained and selected points which will be used to determine facial indices were chosen. Indices are used to find out how the face is evolving over time. Based on experiments we observe how the faces of men and women are changing over time.
|
|
|
Algorithmic Solution for Determining the Age of a Person Based on 2D Photography Using Artificial Intelligence
Bednář, Pavel ; Goldmann, Tomáš (referee) ; Drahanský, Martin (advisor)
Automated person's age estimation from a facial image is one of the challenges in the field of artificial intelligence and machine learning. Age estimation is often a non-trivial complexity for a person, unlike other biological characteristics such as determining gender or race. Information about an individual's age is very important for certain situations. For example, when committing an offense or crime, the amount of the sentence is co-determined by age. This information can also be used in the analysis of customers of a commercial entity and the subsequent adjustment of the offer. The aim of this work is to be able to extract his age from a photograph of a human face. The algorithm consists of two modules. If the first module says that the person is under 14 years old, the image will go to the second module. Furthermore, another version of the algorithm is proposed with an added module focused on selected facial features. In all modules transformations are performed on the image and their results are averaged. Finally, the algorithm is evaluated on standard datasets for age estimation and compared with state-of-the-art methods in this area.
|
|
| |
|
|
Perimeter Monitoring and Intrusion Detection Based on Camera Surveillance
Goldmann, Tomáš ; Drahanský, Martin (referee) ; Orság, Filip (advisor)
This bachelor thesis contains a description of the basic system for perimeter monitoring. The main part of the thesis introduces the methods of computer vision suitable for detection and classification of objects. Furthermore, I devised an algorithm based on background subtraction which uses a Histogram of Oriented Gradients for description of objects and an SVM classifier for their classification. The final part of the thesis consists of a comparison of the descriptor based on the Histogram of Oriented Gradients and the SIFT descriptor and an evaluation of precision of the detection algorithm.
|
|
|
Embedded Device for Robotic Arm Control
Kyzlink, Jiří ; Goldmann, Tomáš (referee) ; Orság, Filip (advisor)
This diploma thesis deals with a design and implementation of an embedded device (module), used to control a robotic manipulator. The module instructs servomotors of the manipulator to move according to the commands received via USB interface. The module consists of two double-sided printed circuit boards. The first one allows connection to the CAN bus, redundant and thus reliable power supply for servomotors as well as the whole module. The second board, compute oriented one, embeds powerful microcontroller used to communicate with the servomotors and to solve the kinematics tasks. As a part of the thesis a graphical user interface as well as a web-oriented interface were developed. Both interfaces allow full control of the manipulator. All the communicating buses, tools and methods used during the design and implementation phases of the work are described in the thesis. Finally, measurements proved improvement of the motion smoothness and response times in several orders of magnitude in comparison to the previous system.
|
guest ::
