|
|
An Application for Analyzing the Resilience of Facial Recognition Algorithms against a Deepfake Image
Kučík, Adam ; Pleško, Filip (referee) ; Goldmann, Tomáš (advisor)
This thesis focuses on creating an application capable of determing whether a given image is deepfake or not. The application is created by using the convolutional neural network vgg-net. Part of the work is to create a Siamese neural network and test if it is suitable for detecting deepfake images. Several configurations of vgg16 and vgg19 networks are created within the thesis. Each configuration contain tables with the success rates of individual models agains our created deepfake dataset. The thesis also includes a section where we discuss deepfake algorithms that are open-source and describe the work with them. The entire application is implemented in Python using the TensorFlow library.
|
|
|
Detection and Analysis of Violators in the Monitored Area
Sadílek, Jakub ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
The aim of this thesis is to create an internet application for detection and analysis of violators in the monitored area. Such an application then can be used for automated processing of records from security cameras or other captured videos from the guarded area. The first part of the work is focused on the theory of neural networks for object detection and classification in the image and recognition of people by their face. The next part describes used technologies for application development. The result is a client-server application with the possibility of configuration of processing, which allows detection of violators, identification of persons, object tracking and counting, path drawing, definition of the monitored area, usage of own detector, etc. Processed videos at the end can be played, downloaded or together with a list of detected violators shared on the internet via link.
|
|
|
Detection and Analysis of Violators in the Monitored Area
Sadílek, Jakub ; Drahanský, Martin (referee) ; Goldmann, Tomáš (advisor)
The aim of this thesis is to create an internet application for detection and analysis of violators in the monitored area. Such an application then can be used for automated processing of records from security cameras or other captured videos from the guarded area. The first part of the work is focused on the theory of neural networks for object detection and classification in the image and recognition of people by their face. The next part describes used technologies for application development. The result is a client-server application with the possibility of configuration of processing, which allows detection of violators, identification of persons, object tracking and counting, path drawing, definition of the monitored area, usage of own detector, etc. Processed videos at the end can be played, downloaded or together with a list of detected violators shared on the internet via link.
|
guest ::
