|
|
Detecting Presentation Attacks Using Face Spoofing
Homola, Tomáš ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Face detection is one of the most important and widespread methods of verifying a person's identity. However, this method also raises concerns about privacy and security. It is important to be aware of the dangers it brings and constantly develop the necessary means to protect against them. This thesis aims to explain the issue of face spoofing, the threat that arises from a successful attacker's attempt at spoofing, and the detection of these spoofs using algorithms.
|
|
|
Počítačová hra s umělou inteligencí
Ludrovan, Tomáš ; Goldmann, Tomáš (referee) ; Orság, Filip (advisor)
This thesis focuses on the development of multiplayer computer game and the examination of possibilites of using artificial intelligence for implementing entities controlled by the computer. The game code is written in C++ programming language and uses SDL2 library for user input and screen output. Besides others, some of the commonly used artificial intelligence algorithms are described here, which are used by the game either directly or as a modified version.
|
|
|
A Reduced Neural Network for Classifying the Presence of People in an Image
Stanček, Rastislav ; Rydlo, Štěpán (referee) ; Goldmann, Tomáš (advisor)
Táto práca sa zameriava na tému počítačového videnia, presnejšie, na binárnu klasifikáciu prítomnosti ľudí v obrazových dátach. Cieľom tejto práce je vytvoriť redukovanú neurónovú sieť s využitím metódy knowledge distillation. Klasifikácia a detekcia objektov je výpočtovo náročná operácia. Študentský model vytvorený pomocou knowledge distillation vykazuje ekvivalentnú presnosť, pričom je menší a má vyššiu inferenčnú rýchlosť v porovnaní s učiteľským modelom. Takýto model môže byť interdisciplinárne všestranný a to predovšetkým na koncových zariadeniach, ktoré majú relatívne slabé výpočtové schopnosti.
|
|
|
Palm liveness detection and identification
Kala, Adam ; Goldmann, Tomáš (referee) ; Sakin, Martin (advisor)
This bachelor's thesis is focused on the detection of liveness of the human hand and its identification from multispectral images. The main goal of the work is the recognition of a living hand and its forgeries based on the information we have obtained, the finding of minutiae for palm identification and their use. The work describes techniques for cropping the area of interest, extracting characteristic features from the palm, and subsequent detection of liveness and identification of the person. Liveness detection success reached over 90% and person identification with a False Acceptance Rate (FAR) of less than 2% for selected datasets.
|
|
|
Person Recognition Based on Anthropometric Proportions
Šimún, Samuel ; Semerád, Lukáš (referee) ; Goldmann, Tomáš (advisor)
This bachelor thesis focuses on the potential use of biometrics and machine learning. It discusses in detail anthropometric characteristics, their evolution and the potential of using these characteristics for person identification. It analyzes the potential uses of machine learning and what technologies exist for extracting a person's pose from an image for outputting the pose in the second dimension and in the third dimension. Also, the thesis describes and implements specific methods that use anthropometric features for person identification.
|
|
|
Application for Person Authentication Based on Retinal Images
Moncz, Oliver ; Goldmann, Tomáš (referee) ; Kavetskyi, Andrii (advisor)
This paper deals with the problem of authentication of people based on retinal images. The main objective is to design an algorithm that can match the retinal image with the registered images in the database. The outcome is the determination of identity with a degree of certainty. Another goal was to create an application that allows to perform the mentioned operations through a simple graphical user interface. Lastly, the results are evaluated and compared with existing solutions. The proposed authentication system achieved an average accuracy of 72.46 % for the DRIVE and STARE datasets, and 78.9 % for the FIRE dataset.
|
|
|
An Application for Analyzing the Resilience of Facial Recognition Algorithms against a Deepfake Image
Kučík, Adam ; Pleško, Filip (referee) ; Goldmann, Tomáš (advisor)
This thesis focuses on creating an application capable of determing whether a given image is deepfake or not. The application is created by using the convolutional neural network vgg-net. Part of the work is to create a Siamese neural network and test if it is suitable for detecting deepfake images. Several configurations of vgg16 and vgg19 networks are created within the thesis. Each configuration contain tables with the success rates of individual models agains our created deepfake dataset. The thesis also includes a section where we discuss deepfake algorithms that are open-source and describe the work with them. The entire application is implemented in Python using the TensorFlow library.
|
|
|
Laser Line Profilometry
Kugler, Jan ; Goldmann, Tomáš (referee) ; Malaník, Petr (advisor)
Profilometr je zařízení sloužící k měření geometrie povrchu. Liší se ve velikosti, přesnosti a rychlosti měření, a ceně. Účelem této práce je vytvořit software knihovnu a uživatelskou aplikaci pro jednoduchý systém složený z kamery a laseru, jehož úkolem bude měřit opotřebení vnitřního povrchu tankových hlavní. Je vypracován matematický popis tohoto systému který knihovna využívá pro určení polohy měřeného povrchu v prostoru. Výsledná knihovna obsahuje nástroje pro identifikaci rysů povrchu. Demonstrační aplikace umožňuje zároveň sledovat snímaný povrch, zpracovaný obraz, i výsledný profil povrchu.
|
|
|
The impact of facial expressions on 3D face recognition.
Kováč, Peter ; Goldmann, Tomáš (referee) ; Pleško, Filip (advisor)
Bakalárska práca "Vplyv výrazov tváre na rozpoznávanie tváre v 3D" sa zameriava na štúdium vplyvu výrazov tváre na presnosť rozpoznávania tváre v 3D. Prvé kapitoly skúmajú rôzne techniky 3D modelovania a ich využitie vrátane 3D morfovateľných modelov (3DMM), modelov blendshape a metód založených na neurónových sieťach ako FLAME (Faces Learned with an Articulated Model and Expressions). Práca následne predstavuje nový prístup k rekonštrukcii 3D modelov tvárí z 2D obrázkov a navrhuje hodnotiaci rámec na meranie vplyvu zmien výrazov tváre na rozpoznávanie tváre v 3D. Experimentálne výsledky ukazujú, ako rôzne výrazy, ako napríklad hnev, radosť a strach, ovplyvňujú presnosť rozpoznávania. Zistenia tejto práce prispievajú k hlbšiemu pochopeniu úlohy výrazov tváre v rozpoznávaní tváre v 3D a navrhujú možné zlepšenia na zvýšenie presnosti rozpoznávacích systémov.
|
|
|
Application for Automatic Evaluation of the Fidelity of the Generated Facial Image
Šotola, Jiří ; Semerád, Lukáš (referee) ; Goldmann, Tomáš (advisor)
This work focuses on the design and implementation of an application for verifying the fidelity of a synthetically generated images, which, due to the vastness of this topic, is aimed at verifying the similarity of the facial features of the original image and the image generated from it. For this application, a Gen_Verifier model is developed based on Siamese networks, which uses the contrastive loss. This model was trained and tested on the LFW dataset, where it reached an accuracy of 91 %. The StarGAN model is used to test the generated images, which generated facial images with changes in hair color, gender and age. The resulting testing on the generated images showed that the StarGAN model produces faces that are similar in 87.53 % cases.
|
guest ::
RSS feed.