|
|
Segmentation of images with leaves of woody species
Valchová, Ivana ; Suk, Tomáš (advisor) ; Křivánek, Jaroslav (referee)
The thesis focuses on segmentation of images with leaves of woody species. The aim was to investigate existing image segmentation methods, choose suitable method for given data and implement it. The chosen method should segment existing datasets, photographs from cameras as well as photographs from lower-quality mobile phones. Inputs are scanned leaves and photographs of various quality. The thesis summarizes the general methods of image segmentation and describes own algorithm that gives us the best results. Based on the histogram, the algorithm decides whether the input is of sufficient quality and can be segmented by Otsu algorithm or is not and should be segmented using GrowCut algorithm. Next, the image is improved by morphological closing and holes filling. Finally, only the largest object is left. Results are illustrated using generated output images. Powered by TCPDF (www.tcpdf.org)
|
|
|
Segmentation of images with leaves of woody species
Valchová, Ivana ; Suk, Tomáš (advisor) ; Blažek, Jan (referee)
The thesis focuses on segmentation of images with leaves of woody species. The main aim was to investigate existing image segmentation methods, choose suitable method for given data and implement it. Inputs are scanned leaves and photographs of various quality. The thesis summarizes the general methods of image segmentation and describes algorithm that gives us the best results. Based on the histogram, the algorithm decides whether the input is of sufficient quality and can be segmented by Otsu algorithm or is not and should be segmented using GrowCut algorithm. Next, the image is improved by morphological closing and holes filling. Finally, only the largest object is left. Results are illustrated using generated output images. Powered by TCPDF (www.tcpdf.org)
|
|
|
Morphology Characteristics of Simple Leaves
Křečková, Jana ; Novotný, Petr (advisor) ; Teodoridis, Vasilis (referee)
This bachelor thesis treats morphology characteristics of simple leaf. It works with recognized methods of leaf morphology stated within Ellis et al. (2009). The goal of this thesis was to evaluate use of this methods for describing leaves of recent species of Central Europe. The second goal was to organize morphology characteristics of chosen leaves. First part of the thesis treats theoretical leaf morphology, discusses different approaches of defining certain leaf characteristics and contains drawings of selected characteristics. The second part of the thesis contains main description of chosen sample using methods within Ellis et al. (2009). It describes sample selection, its processing and recognition of partial characteristics. Final descriptions are organized to charts according to aforementioned methods and listed as Appendix A. Special attention was dedicated to clarity, explicitness and applicability of morphology characteristics. This part of the thesis also treats difficulties and surprises arising through defining morphology characteristics. Key words: morphology, leaf, leaf morphology, simple leaf.
|
|
| |
|
|
Visibility Determination in 3D Maze
Hodes, Vít ; Pečiva, Jan (referee) ; Polok, Lukáš (advisor)
This work is about solving the visibility problem in the environment of simple 3D maze by means of BSP tree and PVS computation between leaves. It contains description of key algorithms and processes for achieving this goal. In the core of this work were all of the implemented ways of drawing measured and mutually compared. At the end are outlined next possible steps in development and evaluating achieved results.
|
|
| |
|
|
System for Support of Dynamic Data Structures Learning
Trávníček, Jiří ; Grulich, Lukáš (referee) ; Křena, Bohuslav (advisor)
The main objective of this work is to design and implement an application that can be used as an aid for the education of programming essentials. Particularly, the attention focuses on the domain of dynamic data structures. The target application will be implemented with the use of web technologies so that it can be run in an ordinary WWW browser. First of all, a brief introduction recapitulates the data structures to be covered. Then the work summarizes the usable technologies available within the web browsers with the focus on the particular technology (which is DHTML) that will become the target platform. The most significant part of this work then discusses the design of the final application. This rather theoretical part is then followed by the description of the practical implementation. A short user manual is also included.
|
|
|
Practical Efficiency of Containers
Halámka, Jan ; Letko, Zdeněk (referee) ; Holík, Lukáš (advisor)
This thesis is about theorethical and practical comparrison of following data containers: vector, deque, list, hash table, avl-tree, rb-tree, splay-tree, sg-tree, treap, B-tree, binomial heap, fibonacci heap, rope and skiplist while implementing sets. Asymptotic, amortized and average-case complexity for each of those structures are noted, as well as details about their implementation and description of how are they stored in computer memory. There was also created a set of tests for comparrison purposes, its results are also part of this paper.
|
|
|
Tree Code Decoding Methods
Zamazal, Zdeněk ; Lambertová, Petra (referee) ; Němec, Karel (advisor)
This thesis deals with applying knowledge of data channel coding and concerns about possibilities of tree codes decoding. It describes several decoding methods and inquires their ins and outs. Basic knowledge of theory of information is necessary, it is presumed that reader is familiar with convolutional codes and coder definitions. Criterions for choosing decoding method are introduced and lightely described. A decoder is designed using method choosed by denoted criterions. Implementation of the decoder, using Matlab Simulink enviroment, has taken part in the thesis. Function of the decoder is verified in simulation.
|
|
|
Administration of development documetation over WWW II
Gregárek, Ondřej ; Sysel, Petr (referee) ; Balík, Miroslav (advisor)
Document server is a web application controllable by way of web browser. It is meant to serve for the management of development documentation. The application is divided to the four basic parts: Requirements, Products, Tests and Test Run. The section Requirements serves for inserting requirements for products. Product is produced on the basis of these needs and registered in part Products. Test setting is created in the part Tests according to requirements from the part Requirements. Particular products are then tested. The part Test Run registers records of these tests. These are parts of the application: management of users, connecting supplements to records, printing and exportation of data to different formats, saving history of records, filtration and sorting of entries, etc. All the data is saved in the database MySQL. The application is written in scripting language PHP. Data is presented by template system Smarty. The output is in language XHTML. Cascading style CSS is used to formatting. This work describes development of the application. First it is dealing with the proposal of the database, connection and structure of particular tables. The function of the programme is explained in detail at the same time, which is essential for the correct proposal of the database. The application is based on the database. The selected structure of files and relations of scripts to library functions are shown. The template system and the interface for access of the programme to the database are explained. The most attention is paid to the description of solving important functions of the application, i.e. listing of records, their pagination, filtration, sorting and operation with them: saving, browsing, copying, confirmation and work with history, category and problems by upkeep of consistent tree and export of data to various formats. It is always outlined the problem, the idea of solving and the description of appropriate scripts. Samples of source code are also included for better understanding of complicated algorithms.
|
guest ::
