|
|
Person's identification by means of bipedal locomotion
Krzyžanek, Jakub ; Richter, Miloslav (referee) ; Horák, Karel (advisor)
The aim of this thesis is to recognize a walking person in a sequence of images by defining his or her reference points to compare the course of their movement and then to identify the scanned person. Methods „k-means“ and „mean shift“ are used to obtain the silhouette of the person. However “environment model estimation” method is used here before those mentioned above. It is a type of a difference method and it helps to specify the scanning area and shortens the time of segmentation. During the search for the reference points the thesis focuses on three areas: the centre of the head and both ankle joints. Those points are later determined on the previous image sequence and compared with the real locations of the centre of the head and ankle joints marked by the user. The thesis also focuses on comparing the movement courses of those points and tries to identify the people whose walks are being scanned. Problematic situations which occurred during the whole process are analyzed in the end. The result of the thesis is an algorithm which can locate a moving person in an image sequence (video) and determine the reference points (centre of the head and ankles) to compare them and identify the scanned person.
|
|
|
Retinal biometry for human recognition
Sikorová, Eva ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
This master thesis deals with recognition of a person by comparing symptom sets extracted from images of the retinal vessels pattern. The first part includes the insight into biometric issues, the punctual analysis of human identification using retina images, and especially the literature research of methods of extraction and comparison. In the practical part there were realized algorithms for human identification with the method of nearest neighbor search (NS), translation, template matching (TM) and extended NS and TM including more symptoms, for which MATLAB program was used. The thesis includes testing of suggested programs on the biometric database of symptomatic vectors with the following evaluation.
|
|
|
Human recognition on thermal images
Jančuš, Rastislav ; Babinec, Tomáš (referee) ; Petyovský, Petr (advisor)
This half-yearly project includes basic briefing about thermovision technics and color models. Analyses functions and concepts for correct settings thermal camera on create images, which are included people. This work contains acquaintance with thermal camera EasIR-4, which was created database testing images, and with software Guide IrAnalyser shipped with this camera. The third part this project includes process about creating color models of skin and algorithm for identification people in thermal images, which emanate from human temperature and color skin. This algorithm is realized in program Matlab.
|
|
|
Human line-up in criminal proceedings
Dvořák, Marek ; Pelc, Vladimír (advisor) ; Heranová, Simona (referee)
The submitted diploma thesis deals with one of the special methods of the taking of evidence in criminal proceedings known as human recognition or line up. This method is specified in the current legal regulation of section 104b, Act No. 141/1961 Coll., Criminal Procedure Code. Particular attention is paid to the general definition of human recognition "in natura". However, some less common ways of execution of this method are also mentioned, such as blank line up occurring in some foreign jurisdictions (especially in Poland). Further attention is then focused on possible significant defects during the process of recognition with its legal consequences. The whole issue is even more complicated when we take into account that recognition as a criminal method is essentially unrepeatable. The thesis analyses foreign researches carried out in some countries, especially in the United States of America. Attention is then focused also on legal regulation of line-up (parade) in England and Wales, because these countries use one of the most modern methods in the world, such as video parade or CCTV. The question of the obligation to passively pass the recognition is also mentioned. Legislation does not deal with many of important questions and details so it's necessary to build on case law and opinions of criminal law...
|
|
|
Human recognition on thermal images
Jančuš, Rastislav ; Babinec, Tomáš (referee) ; Petyovský, Petr (advisor)
This half-yearly project includes basic briefing about thermovision technics and color models. Analyses functions and concepts for correct settings thermal camera on create images, which are included people. This work contains acquaintance with thermal camera EasIR-4, which was created database testing images, and with software Guide IrAnalyser shipped with this camera. The third part this project includes process about creating color models of skin and algorithm for identification people in thermal images, which emanate from human temperature and color skin. This algorithm is realized in program Matlab.
|
|
|
Human Recognition by Finger Veins
Lisák, Peter ; Drahanský, Martin (referee) ; Dvořák, Radim (advisor)
The master's thesis deals with biometric systems, especially these based on human recognition by finger veins. It describes some development principles of the new biometric system. It proposes some new approaches to the comparison of finger vein patterns and their fast identification in sizable databases. Verification is based on templates comparison by similarity and distance measures with proposed alignment approaches. The proposed method of identification is based on the combination of clustering and genetic algorithm. The second option is using the indexing tree structure and searching by range query.
|
|
|
Retinal biometry for human recognition
Sikorová, Eva ; Kolář, Radim (referee) ; Odstrčilík, Jan (advisor)
This master thesis deals with recognition of a person by comparing symptom sets extracted from images of the retinal vessels pattern. The first part includes the insight into biometric issues, the punctual analysis of human identification using retina images, and especially the literature research of methods of extraction and comparison. In the practical part there were realized algorithms for human identification with the method of nearest neighbor search (NS), translation, template matching (TM) and extended NS and TM including more symptoms, for which MATLAB program was used. The thesis includes testing of suggested programs on the biometric database of symptomatic vectors with the following evaluation.
|
|
|
Person's identification by means of bipedal locomotion
Krzyžanek, Jakub ; Richter, Miloslav (referee) ; Horák, Karel (advisor)
The aim of this thesis is to recognize a walking person in a sequence of images by defining his or her reference points to compare the course of their movement and then to identify the scanned person. Methods „k-means“ and „mean shift“ are used to obtain the silhouette of the person. However “environment model estimation” method is used here before those mentioned above. It is a type of a difference method and it helps to specify the scanning area and shortens the time of segmentation. During the search for the reference points the thesis focuses on three areas: the centre of the head and both ankle joints. Those points are later determined on the previous image sequence and compared with the real locations of the centre of the head and ankle joints marked by the user. The thesis also focuses on comparing the movement courses of those points and tries to identify the people whose walks are being scanned. Problematic situations which occurred during the whole process are analyzed in the end. The result of the thesis is an algorithm which can locate a moving person in an image sequence (video) and determine the reference points (centre of the head and ankles) to compare them and identify the scanned person.
|
|
|
Retinal Biometry for Human Recognition
Sikorová, E.
This paper deals with recognition of a person by comparing symptom sets extracted from images of the retinal vessels pattern. In the practical part there were realized algorithms for human identification with the method of nearest neighbor search (NS), extended NS including more symptoms and template matching, for which MATLAB program was used. The work includes testing of suggested programs on the biometric database of symptomatic vectors with the following evaluation.
|
guest ::
