|
|
Face recognition in video sequences
Malach, Tobiáš ; Průša,, Zdeněk (referee) ; Slanina, Martin (advisor)
This thesis deals with design, implementation and testing of face recognition system processing video sequences captured by CCTV systems. The use of Local Binary Pattern Histograms (LPBH) and Nearest Neighbor (NN) classifier was suggested according to the survey of face recognition methods. Discrimination power of LBPH features was examined and individual informative features were searched based on Fisher discrimination ratio and mutual correlation. Cluster’s centorid method was utilized for pattern creation because of its best effect on system’s face recognition capability comparing several proposed methods. Software tool for effective face recognition system algorithms performance testing was developed. Video database IFaViD was assembled for training and performance testing of implemented face recognition system.
|
|
|
Video database for face feature recognition
Stříteský, Jan ; Říha, Kamil (referee) ; Vlach, Jan (advisor)
This work compares face databases freely accessible on the Internet which are suitable for the testing of developed algorithms for facial features recognition in a picture. In the course of the work’s project a new face video database was created, encompassing a total of 51 samples. The video database includes a simple application suitable for searching through its contents. In order to limit the size of the video database, compression of individual picture samples was conducted. The created video database can be implemented for testing algorithms for facial features recognition (e.g. face detection in a video, identification of a person, detection of eye blinking, speech recognition).
|
|
|
Design and preparation of database of chemistry experiments for chemistry education
Vrzáčková, Eva ; Šmejkal, Petr (advisor) ; Hájková, Zdeňka (referee)
This bachelor thesis involved the design and creation of a Database of chemical experiments, which serves as a source of demonstration experiments. Videos to individual experiments were delivered using external links. These individual experiments were chosen using criteria from teachers obtained via a general survey. The main criteria were time and material factors, availability of chemicals and also clearness of experiments. A template was made for each experiment, including all the information required. Experiments, for which no suitable video was found, were carried out and recorded. The resulting database includes 58 experiments divided into 25 main categories. Some videos are included in more than one category. The database was then placed on the website www.studiumchemie.cz, the web portal of Charles University Faculty of Natural Science for secondary school Chemistry teaching support.
|
|
|
Design and preparation of database of chemistry experiments for chemistry education
Vrzáčková, Eva ; Šmejkal, Petr (advisor) ; Hájková, Zdeňka (referee)
This bachelor thesis involved the design and creation of a Database of chemical experiments, which serves as a source of demonstration experiments. Videos to individual experiments were delivered using external links. These individual experiments were chosen using criteria from teachers obtained via a general survey. The main criteria were time and material factors, availability of chemicals and also clearness of experiments. A template was made for each experiment, including all the information required. Experiments, for which no suitable video was found, were carried out and recorded. The resulting database includes 58 experiments divided into 25 main categories. Some videos are included in more than one category. The database was then placed on the website www.studiumchemie.cz, the web portal of Charles University Faculty of Natural Science for secondary school Chemistry teaching support.
|
|
|
Face recognition in video sequences
Malach, Tobiáš ; Průša,, Zdeněk (referee) ; Slanina, Martin (advisor)
This thesis deals with design, implementation and testing of face recognition system processing video sequences captured by CCTV systems. The use of Local Binary Pattern Histograms (LPBH) and Nearest Neighbor (NN) classifier was suggested according to the survey of face recognition methods. Discrimination power of LBPH features was examined and individual informative features were searched based on Fisher discrimination ratio and mutual correlation. Cluster’s centorid method was utilized for pattern creation because of its best effect on system’s face recognition capability comparing several proposed methods. Software tool for effective face recognition system algorithms performance testing was developed. Video database IFaViD was assembled for training and performance testing of implemented face recognition system.
|
|
|
Video database for face feature recognition
Stříteský, Jan ; Říha, Kamil (referee) ; Vlach, Jan (advisor)
This work compares face databases freely accessible on the Internet which are suitable for the testing of developed algorithms for facial features recognition in a picture. In the course of the work’s project a new face video database was created, encompassing a total of 51 samples. The video database includes a simple application suitable for searching through its contents. In order to limit the size of the video database, compression of individual picture samples was conducted. The created video database can be implemented for testing algorithms for facial features recognition (e.g. face detection in a video, identification of a person, detection of eye blinking, speech recognition).
|
guest ::
