|
|
License Plate Detection and Recognition for Traffic Analysis
Černá, Tereza ; Hradiš, Michal (referee) ; Herout, Adam (advisor)
This thesis describes the design and development of a system for detection and recognition of license plates. The work is divided into three basic parts: licence plates detection, finding of character positions and optical character recognition. To fullfill the goal of this work, a new dataset was taken. It contains 2814 license plates used for training classifiers and 2620 plates to evaluate the success rate of the system. Cascade Classifier was used to train detector of licence plates, which has success rate up to 97.8 %. After that, pozitions of individual characters were searched in detected pozitions of licence plates. If there was no character found, detected pozition was not the licence plate. Success rate of licence plates detection with all the characters found is up to 88.5 %. Character recognition is performed by SVM classifier. The system detects successfully with no errors up to 97.7 % of all licence plates.
|
|
|
Flight Game for Android
Šabata, David ; Kajan, Rudolf (referee) ; Herout, Adam (advisor)
This work deals with flight game development on Android platform. Firstly the possibilities of native development and development using Libgdx library will be discussed. Then flight mechanics of a real aircraft and simplified mechanics used in flight games will be explained. The work will also summarize current trends in mobile flight game controls and will propose a new control method based on touch input. Using this method a flight game will be designed and implemented. In the end of this work the process of testing and publishing will discussed, as well as possibilities of further development.
|
|
|
User Interface for Management of Digital Lectures
Koštialik, Daniel ; Szőke, Igor (referee) ; Herout, Adam (advisor)
The aim of the thesis is to design and program user interface for administration of digital lectures and their accompanying materials. The fundament of my approach creates network structure of individual videos that are related with each other with ability to look through them. The application allows user to create its own video lists and work with them like with real bookmarks on a notice board. Trials on the target group prove that it brings new view on arrangement and video watching. The main contribution of the thesis is that designed interface provides better utilisation of video lectures and thus makes the process of learning more efficient.
|
|
|
Explainable Convolutional Neural Networks
Kamenický, Daniel ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The aim of this work was to compare several methods for visualizing the features of each class on the input pixel layer of the CNN. Each method uses a different algorithm, based on gradients, to compute the resulting values. Using the implementation of each method, the resultant values of the methods are obtained by using the equation of energy concentration. The resultant values are presented in tables and graphs from which the success rate of the result of the work can be read. The difference between the methods and comparison of their results can be read from the work. This makes it possible to get an overview of gradient based visualization methods.
|
|
|
Texture-Based Image Segmentation
Pasáček, Václav ; Herout, Adam (referee) ; Španěl, Michal (advisor)
Image segmentation is an important step in image processing. A traditional way how to segment an image is a texture-based segmentation that uses texture features to describe image texture. In this work, Local Binary Patterns (LBP) are used for image texture representation. Texture feature is a histogram of occurences of LBP codes in a small image window. The work also aims to comparison of results of various modifications of Local Binary Patterns and their usability in the image segmentation which is done by unsupervised clustering of texture features. The Fuzzy C-Means algorithm is finally used for the clustering in this work.
|
|
|
Photos with Timestamp
Mlejnek, Matěj ; Herout, Adam (referee) ; Zemčík, Pavel (advisor)
This thesis describes the design and implementation of a system for creating timestamps for photos in groups. It deals with the ways the group timestamp of multiple photos can be verified all at once. The whole system can be split into four parts. The first part is a mobile application, in which photos are taken by the user. The second part is the server on which photos are backed up and which relays the photos to a server that makes group timestamps. The third part is the server itself that creates the timestamps. The fourth part consists of user tools for retrospectively checking the existence of a valid group timestamp.
|
|
|
Mobile App for Sharing Safety Information on a Trip
Gabaj, Dominik ; Tomešek, Jan (referee) ; Herout, Adam (advisor)
The aim of this bachelor thesis is to create a mobile application which would help people during the travel by sharing of their information. It enables to create a trip itinerary and its subsequent sharing with another users for the control and safety of the person. The application has two types of users. The first type of users are the ones, who actually participate in the trip and give information about themselves. The second type are users who use shared information of the trip for the safety and control of their relatives or friends. They can watch the location of these people at the particular moment. The application is designed and implemented for the Androit operation system. It uses Google's Firebase technology, which allows sharing datas between users in real time. In individual chapters is approximated the theory of mobile application development, evaluation of competing application and the description of implementation.
|
|
|
Convolutional Networks for Document Layout Analysis
Endrych, David ; Herout, Adam (referee) ; Kodym, Oldřich (advisor)
The goal of this thesis is to create a tool for analyzig the page layouts of text documents. The problem is solved by convolution neural networks. The architecture chosen in this thesis is the U-Net architecture. The cross entropy error function with weight map is used for train the network model. Paragraph regions are obtained throught connected component analysis. Experiments are evaluated using the Symmetric Best Dice object metric. Experiments have shown that it is better to use all paragraph edges than to focus only on vertical paragraph edges. In addition, experiments show that batche sampling strategies and adaptive resolution help to improve analysis results. The experiments also describe the application of separators, which is useful in analyzing multi-column documents.
|
|
|
Mobile System for Customer Feedback Collection
Kadlubiec, Jakub ; Szőke, Igor (referee) ; Herout, Adam (advisor)
Práce se zabývá popisem tvorby mobilního systému pro monitoring zákaznické spokojenosti a sběr zpětné vazby od návštěvníků v restauracích s názvem Huerate. Komplexně jsou popsané všechny fáze vývoje systému. První část práce se zabývá analýzou existujících řešení a stavem na trhu. Následně jsou na základně komunikace s majiteli restaurací sestaveny požadavky na systém. Nakonec se práce věnuje samotnému návrhu systému, jeho implementaci a nasazení v restauracích. Systém Huerate běží jako webová aplikace a je dostupný na adrese http://huerate.cz.
|
|
|
Intuitive Drawing on the Android Platform
Appl, Martin ; Kajan, Rudolf (referee) ; Herout, Adam (advisor)
This master's thesis deals with design and implementation of finger painting application for mobile devices with Android operating system. Main focus is on well designed, intuitive and friendly user interface. Solved problems are spline interpolation of points, zoom and pinch with transformation matrices, extensive history for action reversal and few basic tools.
|
guest ::
