|
|
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.
|
|
|
Digital image analysis of mitotic chromosomes
Danielová, Tereza ; Provazník, Ivo (referee) ; Škutková, Helena (advisor)
This master’s thesis is focused on digital image analysis of mitotic chromosomes. It deals with the design of the processing of digital images - from image preprocessing to clasification of each chromosomes, including testing on a set of images. This work introduces used cytogenetic methods, that are used to visualize chromosomes. In its practical part describes morphology operations and clasification procedure. Classification of the chomosomes was divided into 5 groups (A-G). All algorithms were created in the MATLAB program.
|
|
| |
|
|
Segmentation of optic disc in retinal image data
Juráček, Radek ; Mézl, Martin (referee) ; Odstrčilík, Jan (advisor)
This bachelor thesis is focused on the algorithm of automatic detection of the optical disk in retinal images. It briefly describes the anatomy of the human eye and the principles of scanning the ocular background. The following describes the optical disk segmentation methods. Selected methods are implemented in MATLAB and optimized using a genetic algorithm. A total of five methods were introduced and optimized on the HRF dataset and two experimental datasets.
|
|
|
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.
|
|
|
Quality Check of Text in Forms
Moravec, Zbyněk ; Juránek, Roman (referee) ; Zemčík, Pavel (advisor)
Purpose of this thesis is the quality check of correct button text display on photographed monitors. These photographs contain a variety of image distortions which complicates the following image graphic element recognition. This paper outlines several possibilities to detect buttons on forms and further elaborates on the implemented detection based on contour shapes description. After buttons are found, their defects are detected subsequently. Additionally, this thesis describes an automatic identification of picture with the highest quality for documentation purposes.
|
|
|
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)
|
|
|
Processing of Images of Petri Dishes
Adámek, Jakub ; Hradiš, Michal (referee) ; Zemčík, Pavel (advisor)
This master thesis deals with image processing of Petri dishes. The first part is about terms and procedures in laboratory practice. The following part is about devices and algorithms for image analysis of Petri dishes. The second part is about draft and implementation of own colony counting application, which was developed in cooperation with the microbiological laboratory. The application is developed for mobile devices running Android OS. The master thesis also includes the design and creation of two lighting units, which uses as an accessory for better results in the analysis of Petri dishes. In conclusion are presented results, compared lighting units and various types of mobile devices, on which the application was tested.
|
|
|
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.
|
|
|
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.
|
guest ::
