|
|
Deep Learning for Image Recognition
Kozel, Michal ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
Neural networks are currently state-of-the-art technology for speech, image and other recognition tasks. This thesis describes basis properties of neural networks and their learning. The aim of this thesis was to extend Caffe framework with new learning methods and compare their performance on Cifar10 dataset. Namely RMSPROP and normalized SGD
|
|
|
Automatic Text Recognition for Robots
Hartman, Zdeněk ; Materna, Zdeněk (referee) ; Španěl, Michal (advisor)
This bachelor thesis describe module design for text detection and recognition for use in robotic systems. To detect charters is used Stroke Width transform, which is applied on the input edge image. In the output image after Stroke Width transform are found connected components. For letter grouping into a words is used Hough transform, which is applied on the created binary image. This image contains points, which corresponding positions of found connected components. To recognize signs in detected areas is used Tesseract library. Before recognition detected areas are extracted and rotated into a horizontal position. This proposed detector can detect even rotated text. Accuracy of detection of the text is 75% above the test set "informační tabule".
|
|
|
Web Portal for Private Family Equipment Rental
Spilka, David ; Španěl, Michal (referee) ; Beran, Vítězslav (advisor)
This thesis deals with design and implementation of web portal called Private family equipment rental. The portal allows users to offer things that they are willing to borrow to other users within groups. Of course, users can also view items offered by other users and can also ask to borrow these things. The system is implemented mainly using PHP Nette framework, jQuery library and Twitter Bootstrap framework.
|
|
|
Robot Control with Voice Commands
Hájek, Pavel ; Kapinus, Michal (referee) ; Španěl, Michal (advisor)
This bachelor's thesis describes design and development of a robot voice control application aiming at platform PR2. It explains the procecess of voice recognition and describes the robot operating system as a target platform. The application uses library Sphinx-4 to translate speech to text, which is than published in ROS. In the end, the set of tests is described. Tests discovered, that the best way to control robot with a few simple commands is developing own grammar.
|
|
|
Script Language for Image Processing
Crlík, Radek ; Španěl, Michal (referee) ; Zemčík, Pavel (advisor)
This bachelor thesis deals with capabilities of scripting languages and their types. Specifically with design of one such language suitable for image processing. The goal was to create a language small enough, but easy to use. One of the requirement was to utilize OpenCV library, for which the resulting code would be as short as possible. First part deals with descriptions of scripting languages, their main philosophy and options of language processing by the computer. Second part contains description of the designed language. Last part documents achieved goals and possible ways how to extend the language even further.
|
|
|
Automatic Content-Based Image Categorization
Němec, Ladislav ; Španěl, Michal (referee) ; Veľas, Martin (advisor)
This thesis deals with automatic content-based image classification. The main goal of this work is implementation of application which is able to perform this task automatically. The solution consists of variable system using local image features extraction and visual vocabulary built by k-means method. Bag Of Words representation is used as a global feature describing each image. Support Vector Machines - the final component of this system - perform the classification based on this representation. In the last chapter, the results of this experimental system are presented.
|
|
|
Semi-Automatic Image Segmentation
Horák, Jan ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This work describes design and implementation of a tool for creating photomontages. The tool is based on methods of semi-automatic image segmentation. Work outlines problems of segmentation of image data and benefits of interaction with the user. It analyzes different approaches to interactive image segmentation, explains their principles and shows their positive and negative aspects. It also presents advantages and disadvantages of currently used photo-editing applications. Proposes application for creating photomontages which consists of two steps: Extraction of an object from picture and insertion of it into another picture. The first step uses the method of semi-automatic segmentation GrabCut based on the graph theory. The work also includes comparison between application and other applications in which it is possible to create a photomontage, and application tests done by users.
|
|
|
Mobile Application Supporting Management of Traffic Constructions
Obořil, Radek ; Španěl, Michal (referee) ; Herout, Adam (advisor)
This thesis deals with development of an application supporting management of traffic constructions. The resulting solution consists of a mobile application and a server application. The mobile application allows users to document progress of a construction using integrated camera, maps and GPS, and send collected data to the server. The server application includes a web service for client-server communication, and a web application for database management and processing of the collected data. Apart from the design and implementation, the features and technologies of mobile devices utilized by the application are discussed. The thesis also reviews current most significant mobile platforms and analyses concepts and technologies of cross-platform development, especially Xamarin and MvvmCross, which were used for development of the above-mentioned application.
|
|
|
Tabletop Object Detection
Varga, Tomáš ; Zemčík, Pavel (referee) ; Španěl, Michal (advisor)
This work describes the issue of tabletop object detection in point cloud. Point cloud is recorded with Kinect sensor. Designed solution uses algorithm RANSAC for plane detection, algorithm Euclidean clustering for segmentation and ICP algorithm for object detection. Algorithm ICP is modified and mainly it can detect rotational symetric objects and objects without any transformation against it's models. The final package is build on platform ROS. The achieved results with own dataset are good despite of the limited functionality of the detector.
|
|
|
Advanced Image Edge Detection
Mezírka, Martin ; Bařina, David (referee) ; Španěl, Michal (advisor)
The goal of this work is to investigate options how to apply trainable edge detection algorithm Structured forest for fast edge detection to information extraction from historici maps and medical images. For the work, annotated dataset was created and the detektor was tested on it. Structured forest achieved better results on map data, compared with classical detectors. Success rate of finding edges of bones was similar at both approaches. Aim of the work is focused on comparing different image annotation styles, experiments with dataset, including determining parameters and evaluation of the methods.
|
guest ::
RSS feed.