|
|
Deep Learning for Facial Recognition in Video
Stratil, Jan ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This bachelor's thesis deals with facial recognition in video using deep neural networks. This task is split into 2 parts. The first part deals with training network that produces compact feature vector which represents the face identity from a video frame. The second part deals with training aggregation network that aggregates those feature vectors into one. This aggregation is fast and it has shown that its results are better than naive pooling methods. Results are tested on the LFW dataset, where it achieves 92.8% accuracy and on the YTF dataset, where the accuracy is 84.06%.
|
|
|
Deep Learning for Medical Image Analysis
Trávníčková, Kateřina ; Hradiš, Michal (referee) ; Španěl, Michal (advisor)
This bachelor thesis deals with medical volume data analysis using convolutional neural networks. The input of the analysis is a CT scan of human limbs and the output are segmented countours of long bones, humerus and tibia. The goal of this work is to find suitable convolutional neural network settings to achieve the best possible analysis output while the area under the Precision-Recall curve is used as the precision metric. The best accuracy reaches almost 88 % (0.8778 AUC). The implementation is based on Caffe framework, or python caffe module.
|
|
|
Video Enhancement Using Convolutional Networks
Skácel, David ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
Convolutional neural networks (CNN) represent a state-of-the-art approach to non-trivial image processing tasks, including compression artifacts reduction and image super-resolution. As some research groups nowadays show, these networks can also be leveraged to perform such tasks on real-world video data, resulting in video spatial super-resolution and more. The main goal of this work is to determine whether these nets can be adjusted to perform temporal super-resolution of real-world video data. I utilize the aforementioned neural net architectures in this paper to do so. As I show, given that the input videos are of reasonable quality, these nets are capable of double-image interpolation up to a certain level, where the output image is usable for temporal upsampling. Although the presented results are promising, I encourage more research to be done on this topic.
|
|
|
Detection of Graffiti Tags in Image
Pavlica, Jan ; Hradiš, Michal (referee) ; Špaňhel, Jakub (advisor)
The thesis is focused on the possible utilization of current methods in the area of computer vision with the purpose of automatic detection of graffiti tags in the image. Graffiti tagsare the most common expression of graffiti, which serves as the author’s signature. In the thesis, state-of-the-art detection systems were tested; the most effective one is the Single Shot MultiBox Detector. The result has reached 75.7% AP.
|
|
|
Parallel Deep Learning
Šlampa, Ondřej ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
Aim of this thesis is to propose how to evaluate favourableness of parallel deep learning. In this thesis I analyze parallel deep learning and I focus on its length. I take into account gradient computation length and weight transportation length. Result of this thesis is proposal of equations, which can estimate the speedup on multiple workers. These equations can be used to determine ideal number of workers for training.
|
|
|
Disparity Map Estimation from Stereo Image
Tábi, Roman ; Maršík, Lukáš (referee) ; Španěl, Michal (advisor)
The master thesis focuses on disparity map estimation using convolutional neural network. It discusses the problem of using convolutional neural networks for image comparison and disparity computation from stereo image as well as existing approaches of solutions for given problem. It also proposes and implements system that consists of convolutional neural network that measures the similarity between two image patches, and filtering and smoothing methods to improve the result disparity map. Experiments and results show, that the most quality disparity maps are computed using CNN on input patches with the size of 9x9 pixels combined with matching cost agregation and correction algorithm and bilateral filter.
|
|
|
Mushroom Detection and Recognition in Natural Environment
Steinhauser, Dominik ; Juránek, Roman (referee) ; Špaňhel, Jakub (advisor)
In this thesis is handled the problem of mushroom detection and recognition in natural environment. Convolutional neural networks are used. The beginning of this thesis is dedicated to the theory of neural networks. Further is solved the problem of object detection and classification. Using neural network trained for classification is solved also the task of localization. Results of trained CNNs are analised.
|
|
|
Computer Aided Recognization and Classification of Coat of Arms
Vídeňský, František ; Kočí, Radek (referee) ; Zbořil, František (advisor)
This master thesis describes the design and development of the system for detection and recognition of whole coat of arms as well as each heraldic parts. In the thesis are presented methods of computer vision for segmentation and detection of an object and selected methods that are the most suitable. Most of the heraldic parts are segmented using a convolution neural networks and the rest using active contours. The Histogram of the gradient method was selected for coats of arms detection in an image. For training and functionality verification is used my own data set. The resulting system can serve as an auxiliary tool used in auxiliary sciences of history.
|
|
|
Deep neural networks and their application for economic data processing
Witzany, Tomáš ; Mrázová, Iveta (advisor) ; Křen, Tomáš (referee)
Title: Deep neural networks and their application for economic data processing Author: Bc. Tomáš Witzany Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: Doc. RNDr. Iveta Mrázová, CSc., Department of Theoretical Com- puter Science and Mathematical Logic Abstract: Analysis of macroeconomic time-series is key for the informed decisions of national policy makers. Economic analysis has a rich history, however when considering modeling non-linear dependencies there are many unresolved issues in this field. One of the possible tools for time-series analysis are machine learn- ing methods. Of these methods, neural networks are one of the commonly used methods to model non-linear dependencies. This work studies different types of deep neural networks and their applicability for different analysis tasks, including GDP prediction and country classification. The studied models include multi- layered neural networks, LSTM networks, convolutional networks and Kohonen maps. Historical data of the macroeconomic development across over 190 differ- ent countries over the past fifty years is presented and analysed. This data is then used to train various models using the mentioned machine learning methods. To run the experiments we used the services of the computer center MetaCentrum....
|
|
|
Neural networks for automatic speaker, language, and sex identification
Do, Ngoc ; Jurčíček, Filip (advisor) ; Peterek, Nino (referee)
Title: Neural networks for automatic speaker, language, and sex identifica- tion Author: Bich-Ngoc Do Department: Institute of Formal and Applied Linguistics Supervisor: Ing. Mgr. Filip Jurek, Ph.D., Institute of Formal and Applied Linguistics and Dr. Marco Wiering, Faculty of Mathematics and Natural Sciences, University of Groningen Abstract: Speaker recognition is a challenging task and has applications in many areas, such as access control or forensic science. On the other hand, in recent years, deep learning paradigm and its branch, deep neural networks have emerged as powerful machine learning techniques and achieved state-of- the-art in many fields of natural language processing and speech technology. Therefore, the aim of this work is to explore the capability of a deep neural network model, recurrent neural networks, in speaker recognition. Our pro- posed systems are evaluated on TIMIT corpus using speaker identification task. In comparison with other systems in the same test conditions, our systems could not surpass reference ones due to the sparsity of validation data. In general, our experiments show that the best system configuration is a combination of MFCCs with their dynamic features and a recurrent neural network model. We also experiment recurrent neural networks and convo- lutional neural...
|
guest ::
