|
|
Face Recognition
Kopřiva, Adam ; Hradiš, Michal (referee) ; Chmelař, Petr (advisor)
This master's thesis considers methods of face recognition. There are described methods with different approachs: knowledge-based methods, feature invariant approaches, template matching methods and appearance-based methods. This master's thesis is focused particulary on template matching method and statistical methods like a principal component analysis (PCA) and linear discriminant analysis (LDA). There are described in detail template matching methods like active shape models (ASM) and active appearance models (AAM).
|
|
|
Deep Neural Networks for Reinforcement Learning
Ludvík, Tomáš ; Bambušek, Daniel (referee) ; Hradiš, Michal (advisor)
The aim of this thesis is to use deep neural networks for task in reinforcement learning. I use my modification of 2D game Tuxánci for the purposes of the test environment. This modification provides the possibility of using the game as an environment for machine learning. Subsequently, Iam solving the task of learning the agent by using reinforcement learning with the Double DQN algorithm.
|
|
|
Game with Hand Gesture Control
Kartous, Petr ; Zemčík, Pavel (referee) ; Hradiš, Michal (advisor)
This work is focused on controlling the game by using hand gestures. The main part of the work is image segmentation and detection of the hand in picture. For the segmentation of the image are used techniques of skin detection and the background subtraction with adaptive model of the background. Also the methods of mathematical morphology to eliminate the noise from the image and the appropriate methods for transferring images of gestures to characteristic gestures in numerical form are mentioned. In the context of the work was a simple car race game created which is controlled by hand gestures. At the end there was a testing carried out to identify the advantages and disadvantages of used methods of image segmentation and to detect the used hand gestures. There were also several sets of gestures tested by which the game is controlled. The two sets which came out of the test most successfully are applicable depending on the quality of the hand gesture recognition.
|
|
|
Application of Mean Normalized Stochastic Gradient Descent for Speech Recognition
Klusáček, Jan ; Hradiš, Michal (referee) ; Pešán, Jan (advisor)
Umělé neuronové sítě jsou v posledních letech na vzestupu. Jednou z možných optimalizačních technik je mean-normalized stochastic gradient descent, který navrhli Wiesler a spol. [1]. Tato práce dále vysvětluje a zkoumá tuto metodu na problému klasifikace fonémů. Ne všechny závěry Wieslera a spol. byly potvrzeny. Mean-normalized SGD je vhodné použít pouze pokud je síť dostatečně velká, nepříliš hluboká a pracuje-li se sigmoidou jako nelineárním prvkem. V ostatních případech mean-normalized SGD mírně zhoršuje výkon neuronové sítě. Proto nemůže být doporučena jako obecná optimalizační technika. [1] Simon Wiesler, Alexander Richard, Ralf Schluter, and Hermann Ney. Mean-normalized stochastic gradient for large-scale deep learning. In Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pages 180{184. IEEE, 2014.
|
|
|
Generating Faces with Conditional Generative Adversarial Networks
Venkrbec, Tomáš ; Hradiš, Michal (referee) ; Kolář, Martin (advisor)
The main goal of this thesis is to implement and compare models based on various architectures of conditional generative adversarial networks. Their main purpose is to conditionally generate realistic looking human faces with selected features. Results from models using DCGAN, WGAN-GP and ProGAN architectures were compared. Models were implemented using Tensorflow library and were trained on Flickr-Faces-HQ dataset. Across all used architectures, I managed to train models capable of generating realistic human faces, with an option to select age and gender.
|
|
|
Shared Experience in Reinforcement Learning
Mojžíš, Radek ; Šůstek, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this thesis is to use methods of transfer learning for training neural network on a reinforcement learning tasks. As test environment, I am using old 2D console games, such as space invaders or phoenix. I am testing the impact of re-purposing already trained models for different environments. Next I use methods for domain feature transfer. Lastly i focus on the topic of multi-task learning. From the results we can gain insight into possibilities of using transfer learning for reinforcement learning algorithms.
|
|
|
Gesture Recognition
Svoboda, Tomáš ; Mlích, Jozef (referee) ; Hradiš, Michal (advisor)
This Bachelor's thesis is engaged in recognition hand gestures. The advantages and disavantages of various color models for skin color detection are discussed here. Skin is detected by look-up table. Look-up table is created from histogram of skin color and optional from Gaussian distribution, whose parameters are estimated from histogram. Hidden Markov models are used for gesture classification. The HTK toolkit have been used for working with the models. Own decoder of Hidden Markov models based on Viterbi algorithm was created for real-time gesture recognition. Several experiments were accomplished with data sets for 4 gestures. The results of the experiments are very good.
|
|
|
Apparent Personality Analysis from Video
Čigáš, Patrik ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This bachelor thesis deals with experiments with systems for apparent personality analysis from video, and compares accuracy of these systems. Systems from the experiments are created by linear regression and convolutional neural networks. Experiments compare accuracy of linear regressors processing visual and audial modality of video. On spectograms made from audial modality of video, thesis evaluates results of convolutional neural networks with varying number of convolutional and fully connected layers nad subsequently compares accuracy of regression solution and classification solution of the problem. For visual modality of video the thesis compares information values of gaze movement and face landmarks movement. System processing face landmarks movement reaches the best results in the experiments.
|
|
|
Object Detection Using Kinect
Řehánek, Martin ; Hradiš, Michal (referee) ; Španěl, Michal (advisor)
With the release of the Kinect device new possibilities appeared, allowing a simple use of image depth in image processing. The aim of this thesis is to propose a method for object detection and recognition in a depth map. Well known method Bag of Words and a descriptor based on Spin Image method are used for the object recognition. The Spin Image method is one of several existing approaches to depth map which are described in this thesis. Detection of object in picture is ensured by the sliding window technique. That is improved and speeded up by utilization of the depth information.
|
|
|
Image Compression with Neural Networks
Teuer, Lukáš ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This document describes image compression using different types of neural networks. Features of neural networks like convolutional and recurrent networks are also discussed here. The document contains detailed description of various neural network architectures and their inner workings. In addition, experiments are carried out on various neural network structures and parameters in order to find the most appropriate properties for image compression. Also, there are proposed new concepts for image compression using neural networks that are also immediately tested. Finally, a network of the best concepts and parts discovered during experimentation is designed.
|
guest ::
