|
|
Face detection in image
Pospíšil, Lukáš ; Harabiš, Vratislav (referee) ; Mézl, Martin (advisor)
The main puprose of this paper is to introduce some of algorithms used in face detection in images. This paper focuses on face detection by using a skin-color based segmentation that is computed in three color spectrums (RGB,YCbCr and HSV). This paper also includes software for face detection in pictures and videos.
|
|
|
Face detection in image
Kubalová, Eva ; Odstrčilík, Jan (referee) ; Mézl, Martin (advisor)
The bachelor thesis deals with the face detection in the picture, detection methods analysis and application of these methods in daily life. Chosen approach for detection, the segmentation based on the skin color, is realized and tested in MATLAB programming environment. In the thesis three different methods for face detection are described and samples of discovering and highlighting of the face characteristics, eyes and mouth, are presented. In addition, the evaluation of successfulness of particular methods is provided. The last part of the thesis contains simple user interface for the operation of the designed algorithms.
|
|
|
Analysis of Parking Availability
Stránský, Václav ; Rozman, Jaroslav (referee) ; Marvan, Aleš (advisor)
This thesis deals with an analysis of parking availability. The task is to determine the occupancy of predefined parking places in the sequence of color images acquired by a fixed camera. The thesis describes the design, implementation, and testing of three utilized methods for car detection, i.e. background modelling, edge detection, and histogram comparison. These methods are combined in order to obtain a more robust and accurate solution. The proposed system has been successfully tested on several real scenarios.
|
|
|
Detection of Objects on Belt Conveyer
Láník, Aleš ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
In this master thesis, object's detection in image and tracking these objects in temporal area will be presented. First, theoretical background of the image's preprocessing, image filtration, the foreground extraction, and many others various image's features will be described. Next, design and implementation of detector will be processed. This part of my master thesis containes mainly information about detection of objects on belt conveyer Finally,results, conclusion and many supplementary data such as a photography camera's location will be shown.
|
|
|
Image segmentation based on relief
Gros, Jan ; Špiřík, Jan (referee) ; Křupka, Aleš (advisor)
The aim of this labor is to introduce the technique of image segmentation by flooding relief of landscape (watershed method). There are described some methods of image segmentation and explained the basic operations of the images, from which the morphological operations are used for watershed segmentation. Part of this labor is a short passage that deals with the use of some image filters for image preprocessing. The result of previous knowledge is presentation of segmentation algorithm designed by Lee Vincent and Pierre Soille. The next section describes the algorithm implementation in Java, contents and function of each class module and implementation using RapidMiner. The last section presents the results of the segmentation with created module using the test images without and with the use of some selected filters to reduce oversegmentation and improve the resulting segmentation.
|
|
|
Photo conversion to black and white
Pieger, Matúš ; Boštík, Ondřej (referee) ; Richter, Miloslav (advisor)
This bachelor's thesis describes the designing of algorithms for detection, processing and conversion of desired objects from input color images to grayscale or black and white domain. The input images are divided into two groups, where the first group consists of sudoku images and other brain puzzles. The second group contains images of paper documents. The thesis analyses imperfections of input images and their effect on the building and functionality of each of the programs. Subsequently, it looks for solutions of a reliable detection of desired objects and correction of their geometric distortions. For a better readability and toner saving when printing the output images respectively, the thesis gives answers as to how to erase unwanted shadows and in which way is it possible to perform bit depth reduction to a chosen number.
|
|
| |
|
|
Photo conversion to black and white
Pieger, Matúš ; Boštík, Ondřej (referee) ; Richter, Miloslav (advisor)
This bachelor's thesis describes the designing of algorithms for detection, processing and conversion of desired objects from input color images to grayscale or black and white domain. The input images are divided into two groups, where the first group consists of sudoku images and other brain puzzles. The second group contains images of paper documents. The thesis analyses imperfections of input images and their effect on the building and functionality of each of the programs. Subsequently, it looks for solutions of a reliable detection of desired objects and correction of their geometric distortions. For a better readability and toner saving when printing the output images respectively, the thesis gives answers as to how to erase unwanted shadows and in which way is it possible to perform bit depth reduction to a chosen number.
|
|
|
Vectorization of line-based images
Hadrava, Jan ; Pelikán, Josef (advisor) ; Novotný, Jiří (referee)
Some creators prefer working with pen and paper while creating graphic art. It is desirable to digitize a draft (scan it, photograph) and edit it on a computer afterwards. It is useful to convert an image to a vector format - to vectorize it. Vector representation of images gives us good quality in any zoom level and enables easier editing compared to a raster workflow. Each element is represented as a curve, or as a filled area defined by its outline. Line-based images may be edited very conveniently and efficiently. Contemporary vectorization tools usually search for connected areas. Some of them are also freely available. There exist significantly fewer programs which represent output graphics using lines, these programs are usually very expensive. This work proposes a vectorization algorithm and implements freely distributable program which represents vector image using lines. After initial pre-processing of input raster image its morphological skeleton is found (still in raster). A skeleton is then traced and converted into a vector form set of Bézier curves. An image is smoothed and exported to a required vector graphics format. Quality of an outcome is in many aspects comparable with quality of vectorization tools available to the author. Powered by TCPDF (www.tcpdf.org)
|
|
|
Face detection in image
Kubalová, Eva ; Odstrčilík, Jan (referee) ; Mézl, Martin (advisor)
The bachelor thesis deals with the face detection in the picture, detection methods analysis and application of these methods in daily life. Chosen approach for detection, the segmentation based on the skin color, is realized and tested in MATLAB programming environment. In the thesis three different methods for face detection are described and samples of discovering and highlighting of the face characteristics, eyes and mouth, are presented. In addition, the evaluation of successfulness of particular methods is provided. The last part of the thesis contains simple user interface for the operation of the designed algorithms.
|
guest ::
