|
|
Automatic Photography Categorization
Matuszek, Martin ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis deal with choosing methods, design and implementation of application, which is able of automatic categorization photos based on its content into predetermined groups. Main steps of categorization are described in greater detail. Finding and description of interesting points in image is implemented using SURF, creation of visual dictionary by k-means, mapping on the words through kd-tree structure. Own evaluation is made for categorization. It is described, how the selected steps were implemented with OpenCV and Qt libraries. And the results of runs of application with different settings are shown. And efforts to improve outcome, when the application can categorize right, but success is variable.
|
|
|
Pulse Detection from Video
Matuszek, Martin ; Hradiš, Michal (referee) ; Szentandrási, István (advisor)
The aim of the Master's thesis was to study contemporary methods for human pulse detection from standard video and suggest a method, which can be used to detect the pulse. Approaches of detecting miniature changes between frames of a video are presented. Position changes of the feature points or changes in colour of some part of an image are detected. It capitalize on the fact that those changes are caused by the pulse of blood. The method for color changes magnification is selected as a base for pulse detector. Face regions of interest are analyzed to detect frequency of changes of intensity between frames. 1D signal is gained and its analysis leads to heart rate. Approach to create heat map of frequency changes is also presented.
|
|
|
Automatic Photography Categorization
Matuszek, Martin ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis deal with choosing methods, design and implementation of application, which is able of automatic categorization photos based on its content into predetermined groups. Main steps of categorization are described in greater detail. Finding and description of interesting points in image is implemented using SURF, creation of visual dictionary by k-means, mapping on the words through kd-tree structure. Own evaluation is made for categorization. It is described, how the selected steps were implemented with OpenCV and Qt libraries. And the results of runs of application with different settings are shown. And efforts to improve outcome, when the application can categorize right, but success is variable.
|
|
|
Pulse Detection from Video
Matuszek, Martin ; Hradiš, Michal (referee) ; Szentandrási, István (advisor)
The aim of the Master's thesis was to study contemporary methods for human pulse detection from standard video and suggest a method, which can be used to detect the pulse. Approaches of detecting miniature changes between frames of a video are presented. Position changes of the feature points or changes in colour of some part of an image are detected. It capitalize on the fact that those changes are caused by the pulse of blood. The method for color changes magnification is selected as a base for pulse detector. Face regions of interest are analyzed to detect frequency of changes of intensity between frames. 1D signal is gained and its analysis leads to heart rate. Approach to create heat map of frequency changes is also presented.
|
guest ::
