|
|
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.
|
|
|
Deep Learning for Facial Recognition in Video
Stratil, Jan ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This bachelor's thesis deals with facial recognition in video using deep neural networks. This task is split into 2 parts. The first part deals with training network that produces compact feature vector which represents the face identity from a video frame. The second part deals with training aggregation network that aggregates those feature vectors into one. This aggregation is fast and it has shown that its results are better than naive pooling methods. Results are tested on the LFW dataset, where it achieves 92.8% accuracy and on the YTF dataset, where the accuracy is 84.06%.
|
|
|
Web defects classification
Janošík, Zdeněk ; Petyovský, Petr (referee) ; Honec, Peter (advisor)
In this master thesis is described how to design and implement classifier of defects detected during the final stage of production nonwovens. The beginning of the thesis is devoted to the analysis of options for image processing and classification. Followed by the part, where is described process of image segmentation and extraction of feature vector. Description of classifier implementation and table of achieved results of classification on real images of detected defects.
|
|
|
Deep Learning for Facial Recognition in Video
Stratil, Jan ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This bachelor's thesis deals with facial recognition in video using deep neural networks. This task is split into 2 parts. The first part deals with training network that produces compact feature vector which represents the face identity from a video frame. The second part deals with training aggregation network that aggregates those feature vectors into one. This aggregation is fast and it has shown that its results are better than naive pooling methods. Results are tested on the LFW dataset, where it achieves 92.8% accuracy and on the YTF dataset, where the accuracy is 84.06%.
|
|
|
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.
|
|
|
Web defects classification
Janošík, Zdeněk ; Petyovský, Petr (referee) ; Honec, Peter (advisor)
In this master thesis is described how to design and implement classifier of defects detected during the final stage of production nonwovens. The beginning of the thesis is devoted to the analysis of options for image processing and classification. Followed by the part, where is described process of image segmentation and extraction of feature vector. Description of classifier implementation and table of achieved results of classification on real images of detected defects.
|
guest ::
