|
|
Pupil and iris center detection
Prosser, Jan ; Chmelík, Jiří (referee) ; Kolář, Radim (advisor)
This thesis is aimed at image processing to obtain informations about the center of pupil and iris,the pupillar and limbic boundary from grayscale images of the eye. An introduction describes general research in topic of pupil, iris and changes in size of pupil. There are mentioned articles dealing with the detection of the center of pupil and iris. These articles were used as an inspiration for proposal of detection methods used in this work. The introduction ends with description of designed approaches of detection of parameters of pupil and iris in images of CASIA-Iris-Interval database. The second, practical part of this work, is dedicated to description of acquisition system, which was compiled to obtain proper images of eye. Individual analysis of methods used to obtain parameters of pupil and iris follows after that. There are two methods of detection of center of pupil and pupillar boundary, one method determines center of iris and limbic boundary. Last method detects centers and boundaries of pupil and iris at one time. The end of this work is dedicated to analysis of results of designed methods. Analysis includes score of successfulness of detection, statistical analysis, discussion of changes in pupillary diameter depending on the light conditions and changes in position of center of pupil during constriction and dilatation of pupil.
|
|
|
Retinal image registration using phase correlation
Prosser, Jan ; Harabiš, Vratislav (referee) ; Kolář, Radim (advisor)
This master’s thesis is aimed at registration of frames of retinal fundus video using phase corre- lation. An introduction describes general research in topic of retinal fundus, eye movements, diff erent approaches for image registration, phase correlation and examples of phase corre- lation applications. The second, practical part of master’s thesis, is dedicated to description of the proposed algorithm for registration of frames of retinal fundus video. The description of the proposed algorithm is divided into three parts. First two parts describe how frames of retinal fundus video are rated in terms of suitability for registration. Third part describes image registration algorithm itself. In conclusion, the accuracy of algorithm and computational time are evaluated.
|
|
|
Retinal image registration using phase correlation
Prosser, Jan ; Harabiš, Vratislav (referee) ; Kolář, Radim (advisor)
This master’s thesis is aimed at registration of frames of retinal fundus video using phase corre- lation. An introduction describes general research in topic of retinal fundus, eye movements, diff erent approaches for image registration, phase correlation and examples of phase corre- lation applications. The second, practical part of master’s thesis, is dedicated to description of the proposed algorithm for registration of frames of retinal fundus video. The description of the proposed algorithm is divided into three parts. First two parts describe how frames of retinal fundus video are rated in terms of suitability for registration. Third part describes image registration algorithm itself. In conclusion, the accuracy of algorithm and computational time are evaluated.
|
|
|
Pupil and iris center detection
Prosser, Jan ; Chmelík, Jiří (referee) ; Kolář, Radim (advisor)
This thesis is aimed at image processing to obtain informations about the center of pupil and iris,the pupillar and limbic boundary from grayscale images of the eye. An introduction describes general research in topic of pupil, iris and changes in size of pupil. There are mentioned articles dealing with the detection of the center of pupil and iris. These articles were used as an inspiration for proposal of detection methods used in this work. The introduction ends with description of designed approaches of detection of parameters of pupil and iris in images of CASIA-Iris-Interval database. The second, practical part of this work, is dedicated to description of acquisition system, which was compiled to obtain proper images of eye. Individual analysis of methods used to obtain parameters of pupil and iris follows after that. There are two methods of detection of center of pupil and pupillar boundary, one method determines center of iris and limbic boundary. Last method detects centers and boundaries of pupil and iris at one time. The end of this work is dedicated to analysis of results of designed methods. Analysis includes score of successfulness of detection, statistical analysis, discussion of changes in pupillary diameter depending on the light conditions and changes in position of center of pupil during constriction and dilatation of pupil.
|
guest ::
