bibtype D - Thesis
ARLID 0486992
utime 20240103215640.8
mtime 20180221235959.9
title (primary) (eng) Selected Application Areas of Image Processing: Image Forensics and Medical Imaging
publisher
place Praha
name Czech Technical University in Prague
pub_time 2017
specification
page_count 153 s.
media_type P
keyword Image Processing
keyword Image Forensics
keyword Medical Imaging
keyword forgery detection
keyword capsule endoscopy
keyword videokymography
author (primary)
ARLID cav_un_auth*0283562
name1 Novozámský
name2 Adam
full_dept (cz) Zpracování obrazové informace
full_dept (eng) Department of Image Processing
department (cz) ZOI
department (eng) ZOI
institution UTIA-B
full_dept Department of Image Processing
fullinstit Ústav teorie informace a automatizace AV ČR, v. v. i.
source
url http://library.utia.cas.cz/separaty/2017/ZOI/novozamsky-0486992.pdf
cas_special
project
ARLID cav_un_auth*0273814
project_id VG20102013064
agency GA MV
project
ARLID cav_un_auth*0273813
project_id VF20102012010
agency GA MV
project
ARLID cav_un_auth*0292615
project_id GA13-28462S
agency GA ČR
project
ARLID cav_un_auth*0322186
project_id TA04010877
agency GA TA ČR
country CZ
project
ARLID cav_un_auth*0358496
project_id NT/13477-4/2012
agency GA MZd
country CZ
project
ARLID cav_un_auth*0314467
project_id GA15-16928S
agency GA ČR
abstract (eng) This dissertation deals with analysis of forensic and medical image data, two fields that use advanced methods in \emph{Image Processing}. The Thesis introduces the issue first and then describes the six attached papers with the author's contribution. The first paper presents several methods of forensic analysis of images and videos. These were designed to help in real-life practice to assess the credibility and origin of the data.\nOne way to confuse these methods is to display the forged image on the monitor and then take another photo of it. The second paper focuses on detecting such photos. It tries to find the periodicity caused by the LCD monitor grid in the image. The third conference paper solves the problem of determining the number of reference images to construct a high-performance fingerprint sensor. The fourth paper introduces a new procedure for detecting copy-move in pictures. The most common technique of counterfeiting is to copy part of the image and transfer it to another area. In this manner, it is possible to completely change the information that the image carries. The other two papers focus on the analysis of medical image data. The fifth paper introduces a new way of displaying bleeding spots in the small intestine, and the last paper describes the detection of vibration features of the vocal cords from videokymographic images.
RIV JD
FORD0 20000
FORD1 20200
FORD2 20205
reportyear 2018
habilitation
degree Ph.D.
institution Fakulta jaderná a fyzikálně inženýrská ČVUT / Ústav teorie a informace AV ČR v.v.i
place Břehová 7, 115 19 Praha 1 / Pod Vodárenskou věží 4, 182 08 Praha 8
year 2017
dates 20.2.2018
num_of_auth 1
inst_support RVO:67985556
permalink http://hdl.handle.net/11104/0282541
confidential S
arlyear 2017
mrcbU10 2017
mrcbU10 Praha Czech Technical University in Prague