|
|
Application for Searching for Fitness Buddies (Android)
Kalous, Filip ; Behúň, Kamil (referee) ; Herout, Adam (advisor)
This thesis is concerned with the development of a application for smartphones. It's purpose will be to help find sports partners, no matter the sport activity, although it is aimed mainly on weight lifting activities in fitness centres. The development of the application for Android operation system and implementation of the server part made with the help of Ruby on Rails framework is analyzed in the thesis. In practice the application should enable its users to find a suitable sports partner anywhere and anytime.
|
|
|
Application Control Using User Hand and Fingertips Gestures
Břenek, Martin ; Behúň, Kamil (referee) ; Beran, Vítězslav (advisor)
This bachelor's thesis deals with creating the user interface element, which is used to control application by user hand and fingertips gesture. The text discuss the basics of computer vision and image segmentation principles. The thesis also focuses on analysis of task and solution design, describes implementation details, including used tools and includes test results of final solution.
|
|
|
Counting of People Passing Through a Door Using a Stationary Camera
Tichý, Ľuboš ; Behúň, Kamil (referee) ; Sochor, Jakub (advisor)
This bachelor thesis deals with counting of people passing through a door. It may be used in case, when we need to know, how many people there are in monitored room. The first part is a description of existing methods of counting people and the second part deals with used computer vision methods. Proposed system can count people, including distinguishing their motion direction. The last part contains an evaluation of the system.
|
|
| |
|
|
Optical Character Recognition Using Convolutional Networks
Csóka, Pavel ; Behúň, Kamil (referee) ; Hradiš, Michal (advisor)
This thesis aims at creation of new datasets for text recognition machine learning tasks and experiments with convolutional neural networks on these datasets. It describes architecture of convolutional nets, difficulties of recognizing text from photographs and contemporary works using these networks. Next, creation of annotation, using Tesseract OCR, for dataset comprised from photos of document pages, taken by mobile phones, named Mobile Page Photos. From this dataset two additional are created by cropping characters out of its photos formatted as Street View House Numbers dataset. Dataset Mobile Nice Page Photos Characters contains readable characters and Mobile Page Photos Characters adds hardly readable and unreadable ones. Three models of convolutional nets are created and used for text recognition experiments on these datasets, which are also used for estimation of annotation error.
|
|
|
Application for Searching for Fitness Buddies (iOS)
Plšek, Dominik ; Behúň, Kamil (referee) ; Herout, Adam (advisor)
Many successful projects are based on mobile applications using geographic position of the user and shared economy, mostly in transport market. These principles can be used in other fields of human life as well. As part of my thesis, I focused on applying these methods to the fitness market. A considerable part of potential customers is discouraged from exercising regularly by the fact that they do not have anyone to share these activities with. The purpose of the thesis is to create a mulitplatform mobile application Gymber which helps users searching for a partner or a trainer for running, weight-lifting or other desired fitness activity. Gymber allows users to share and respond to offers for fitness activity, displays a feed of appropriate places for these activities, informs users about places' opening hours, special events and news. The thesis also describes topics about user interface design, iOS application implementation and designing backend API for supporting other mobile platforms, too.
|
|
|
Evaluation of Object Detection in Image
Černošek, Bedřich ; Behúň, Kamil (referee) ; Zemčík, Pavel (advisor)
The main goal of this bachelor's thesis was to propose the evaluation method of object detection. Result of this work was to create a program which performs the evaluation of object detection on suitable data sample and intuitively displays result to user. The task was to propose suitable experiments and dataset for proving correctness of evaluation. Part of this work was to find optimal parameters for face detection and optimal photo preprocessing before the face detection.
|
|
|
Panoramic Photo Creation
Dospiva, Filip ; Sochor, Jakub (referee) ; Behúň, Kamil (advisor)
This thesis contains a comparison of approaches to implementation of the panoramic photos. There are analyzed partial steps to create panoramas and access methods that are used for these steps. There is a preview of the methods and schedules their advantages and disadvantages. Also included is a comparison of these methods and evaluation of their usability.
|
|
|
Head Pose Estimation from Photography
Szentandrási, Tamás ; Juránek, Roman (referee) ; Behúň, Kamil (advisor)
The aim of this work is to propose and implement a head pose estimation system using Random Forests, with photographic input. This work uses a version on Random Forests with using Fisher Linear Discriminant Analysis for node splits. It also uses a number of tools to achieve this goal, the OpenCV library, SQLiteCpp library, and the aflw database. This work created an accurate head pose estimation system reusable for future Computer Vision tasks.
|
|
|
Application for the Camera Image Editing for Android
Bělehrádek, Stanislav ; Szentandrási, István (referee) ; Behúň, Kamil (advisor)
In this thesis I dealt with creation of application for editing image from camera. Apliacation is for operating system Android. Aim was to study possibilities of image editing and of creating applications for platform Android. And next aim was to use discovered informations to develop application. Problem was solved by creating of framework for platform Android for image editing. This framework was used for develope application. Framework provides visual components useful for creation application GUI. Created application provides extra feature to create a custom effect by composition of filters from OpenCV library. Output is Android application and poster demonstrating the application. Next output is framework making development of applications for image editing easier. Framework contains also documentation with description of framework and instructions for use.
|
guest ::
