|
|
Determining Head Rotation in Video from Security Camera
Blucha, Ondřej ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
This thesis attempts to create an application to determine head rotation angle in video recorded from a security camera. The application consists of three parts: face detection, facial landmarks detection and determination of person's head rotation. The face detection has been implemented using Viola-Jones and HOG algorithms. Facial landmarks detection has been done using algorithm based on active shape model. Two methods to calculate the head rotation angles have been used: the first method works with anthropometric head features. The second method uses Perspective-n-Point algorithm to find the right rotation angles. Finally, all algorithms implemented have been tested and the proper parameters have been determined.
|
|
|
Person de-identification upon primary biometric traits
Šidó, Balázs ; Burget, Radim (referee) ; Přinosil, Jiří (advisor)
This bachelor’s thesis deals with various methods protecting privacy by de-identification based on the primary biometric traits. The first chapter describes face de-identification with ad-hoc, naive and advanced methods. It also describes the Active Appearance Models and the Active Shape Models. The second chapter consists of a general overview of voice signal processing and of voice de-identification methods by changing the levels of energy in each frequency band and by pitch shift. The following chapters are describing the realized face de-identification program and an algorithm design for reversible face de-identification using the appearance parameters of the Active Appearance Model. This is followed by algorithm designs for voice de-identification. The results of the experiments done with the de-identified pictures are introduced in the last chapter. The realized program were written in Matlab.
|
|
|
Determining Head Rotation in Video from Security Camera
Blucha, Ondřej ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
This thesis attempts to create an application to determine head rotation angle in video recorded from a security camera. The application consists of three parts: face detection, facial landmarks detection and determination of person's head rotation. The face detection has been implemented using Viola-Jones and HOG algorithms. Facial landmarks detection has been done using algorithm based on active shape model. Two methods to calculate the head rotation angles have been used: the first method works with anthropometric head features. The second method uses Perspective-n-Point algorithm to find the right rotation angles. Finally, all algorithms implemented have been tested and the proper parameters have been determined.
|
|
|
Person de-identification upon primary biometric traits
Šidó, Balázs ; Burget, Radim (referee) ; Přinosil, Jiří (advisor)
This bachelor’s thesis deals with various methods protecting privacy by de-identification based on the primary biometric traits. The first chapter describes face de-identification with ad-hoc, naive and advanced methods. It also describes the Active Appearance Models and the Active Shape Models. The second chapter consists of a general overview of voice signal processing and of voice de-identification methods by changing the levels of energy in each frequency band and by pitch shift. The following chapters are describing the realized face de-identification program and an algorithm design for reversible face de-identification using the appearance parameters of the Active Appearance Model. This is followed by algorithm designs for voice de-identification. The results of the experiments done with the de-identified pictures are introduced in the last chapter. The realized program were written in Matlab.
|
guest ::
