|
|
Face parameterization using videosequence
Lieskovský, Pavol ; Mekyska, Jiří (referee) ; Rajnoha, Martin (advisor)
This work deals with the problem of face parameterization from the video of a speaking person and estimating Parkinson’s disease and the progress of its symptoms based on face parameters. It describes the syntax and function of the program that was created within this work and solves the problem of face parameterization. The program formats the processed data into a time series of parameters in JSON format. From these data, a dataset was created, based on which artificial intelligence models were trained to predict Parkinson’s disease and the progress of its symptoms. The process of model training and their results are documented within this work.
|
|
|
Dataset generation for specific cases of face recognition
Kolmačka, Tomáš ; Kolařík, Martin (referee) ; Rajnoha, Martin (advisor)
The diploma thesis deals with current problems of person identification and deep learning. Furthermore, the work deals mainly with obtaining quality and diverse data that are used to train deep learning with convolutional neural networks for face recognition. There is very little public access to such data, so the practical part focuses on creating the MakeHuman plugin that will generate a database of random face images. It is possible to generate faces according to five different scenarios in which purely random faces or faces where the same can be seen with modifications such as different hair, beard, hat, glasses and more are created. The scenarios also allow you to generate faces with some expressions or faces as they age. You can set some parameters that give the appearance of the resulting database in the plugin. This can include face images from different angles of rotation, zooming and lighting.
|
|
|
Prototype Verification of Modification of Evolutionary Algorithm
Švestka, Marek ; Rajnoha, Martin (referee) ; Šeda, Pavel (advisor)
This thesis is about evolutionary algorithms with a concrete solution for an Aircraft Landing Problem. The goal is to create a genetic algorithm for this task resolution, apply selected modifications and compare all outputs. The program runs with different selection methods which are further reviewed. Input data are taken from Operations research library for this task. The outcome of this thesis gives a closer look to evolutionary programming and it’s problem resolution.
|
|
| |
|
|
Realtime Pedestrian Recognition Using Siamese
Network
Rajnoha, Martin
Image similarity measuring has many various applications. Pedestrian recognition is one of them and for the security purposes it is basically required to run in real-time. This paper proposes a deep Siamese neural network architecture for pedestrian recognition that achieves 70.28% accuracy on the test set containing 20 persons. Prediction of the model is fast enough for real-time processing.
|
|
|
Warehouse Modeling Using Graphical User Interface
Rajnoha, Martin
This paper describes a new algorithm which enable efficient conversion of graphical representation of warehouse into graph theory representation and consequently accelerates estimation for route costs. The proposed algorithm computes route distances between any place in warehouses and does so significantly faster than traditional approaches. For this purpose an algorithm based on Breadth first search, image processing “skeletonization” and Dijkstra algorithm was proposed. Using the proposed algorithm it is possible to search routes in a warehouse effectively and fast using precomputed routing table. Searching time is approximately hundreds of microseconds using routing table and even it is independent on size of warehouse instead of using Dijkstra algorithm.
|
|
|
Object tracking in video
Boszorád, Matej ; Přinosil, Jiří (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis deals with the issue of tracking multiple objects in a video, specifically focusing on non-learning algorithms. The first chapter represents the theoretical part of the thesis, in which some of the often used tracking methods are described, such as mean-shift, scale-invariant object transformation, Kalman filter, particle filter and Gabor wavelet transformation. These algorithms are broken down by properties they use for proper tracking. The chapter also contains section assignment problem, which is mainly concerned with Hungarian algorithm. The next part describes options of merging multiple tracking methods that are broken down by construction type into parallel, cascade, weighted and discriminatory with example for each one. Moreover there is described adaptability of the tracking system. Bellow are described problems which may occur during tracking and possible solutions to them. This section consists of a solution of image noise, changes in illumination, appearance and extinction of an object, focusing mainly on solving the problem of object occlusion. Within the practical part is created algorithm composed of different types of tracking, the results of which are then compared with selected tracking systems from the multiple object tracking benchmark. The practical part includes the tools used and the explanation of the design, in which the main classes and methods used for the tracking are explained. Besides that, this section describes parallel merging and tracking adaptability . The results of the thesis contain a comparison of the use of tracking techniques separately and together. To compare the results, videos for pedestrian tracking and face tracking were used. This thesis was based on the assumption that merging multiple monitoring systems will help with the improvement of the tracking, which was confirmed by the results.
|
|
|
Computational tasks for Parallel data processing course
Horečný, Peter ; Rajnoha, Martin (referee) ; Mašek, Jan (advisor)
The goal of this thesis was to create laboratory excercises for subject „Parallel data processing“, which will introduce options and capabilities of Apache Spark technology to the students. The excercises focus on work with basic operations and data preprocessing, work with concepts and algorithms of machine learning. By following the instructions, the students will solve real world situations problems by using algorithms for linear regression, classification, clustering and frequent patterns. This will show them the real usage and advantages of Spark. As an input data, there will be databases of czech and slovak companies with a lot of information provided, which need to be prepared, filtered and sorted for next processing in the first excercise. The students will also get known with functional programming, because the are not whole programs in excercises, but just the pieces of instructions, which are not repeated in the following excercises. They will get a comprehensive overview about possibilities of Spark by getting over all the excercices.
|
|
|
Protection of sensitive data contained in images
Mezina, Anzhelika ; Rajnoha, Martin (referee) ; Burget, Radim (advisor)
Tato bakalářská práce je zaměřena na využití hlubokého učení v bezpečnostním problému úniku citlivých informací ve formě obrazových dat. Pokusem o vyřešení tohoto problému bylo použití Single Shot Multibox Detectoru (SSD) a plně propojené sítě, poslední je mnohem rychlejší než jiné metody a může být použitá v praxi, kde je potřeba velmi rychlé analýzy příchozí a odchozí informace, například analýzy provozu sítě. V první části práce jsou popsané metody, které mohou být použité pro detekci klíčových slov. Druhá část obsahuje popis experimentu a dosažených výsledků pro dva modely neuronových sítí: Single Shot Multibox Detector a plně propojené sítě. Druhý model dosahuje uspokojivých vlastností jak z pohledu času zpracování tak i přesnosti a lze jej použít v praxi.
|
|
|
Image similarity measuring using deep learning
Štarha, Dominik ; Šeda, Pavel (referee) ; Rajnoha, Martin (advisor)
This master´s thesis deals with the reseach of technologies using deep learning method, being able to use when processing image data. Specific focus of the work is to evaluate the suitability and effectiveness of deep learning when comparing two image input data. The first – theoretical – part consists of the introduction to neural networks and deep learning. Also, it contains a description of available methods, their benefits and principles, used for processing image data. The second - practical - part of the thesis contains a proposal a appropriate model of Siamese networks to solve the problem of comparing two input image data and evaluating their similarity. The output of this work is an evaluation of several possible model configurations and highlighting the best-performing model parameters.
|
guest ::
