|
|
Application for Recognition of People by Face
Svoboda, Jakub ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Person identification has in the recent years gained notoriety as one of the most powerful ways of extracting information from image data. This thesis is focused on the task of human identification from facial photographs. To solve this task, we employ algorithms based on neural networks, which produce more robust results than traditional algorithms. In this thesis, we studied the common approaches for solving this problem and based on the gathered knowledge we created an architecture of a neural network trained to tackle the task of human identification and verification based on facial photographs. We have then further improved the model architecture and the training process by performing various experiments and observing the results. The final model has reached an accuracy comparable to other state-of-the-art models. Furthermore, we created a desktop application to demonstrate the results visually and to enable easier manipulation with the identity database. The knowledge gathered in this thesis can be used for improvements of current identification models or models modified for solving similar tasks.
|
|
|
Facial Recognition in Video and its Applications in Law Enforcement
Fabián, Jan ; Šťastná, Dagmar (referee) ; Šedrlová, Magdalena (advisor)
This bachelor thesis aims to describe the facial recognition technology and its use in practice. In recent years, facial recognition technology became a heavily discussed topic, whether in connection with the deployment of this technology in China or due to its general potential for law enforcement. Facial recognition technology is a perfect example of a two-sided coin, as it brings many new possibilities of crime prevention etc. but also has the risk of being used to invade personal privacy. This thesis is based on a literature survey of some of the available resources dealing with this topic. It focuses on the history of this technology, methods used by facial recognition and mentions some examples of the use of video-based facial recognition in practice along with the social risks of the application of this technology.
|
|
|
Model Adaptation in Person Identification
Stratil, Jan ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
This thesis deals with facial recognition using convolutional neural networks and with their current problems, which are pose, lighting and expression variance. It summarizes existing approaches, architectures and most recent loss functions. Further it deals with methods for rotating faces using GAN networks. In this thesis 3 neural networks are designed and trained for facial recognition. The best of them achieves 99.38% accuracy on LFW dataset and 88.08% accuracy on CPLFW dataset. Next face rotation network PCGAN is designed, which can be used for face frontalization or data augmentation purposes. This network is evaluated on Multi-PIE dataset and using the face frontalization it increases identification accuracy.
|
|
|
Deep Learning for Facial Recognition in Video
Jeřábek, Vladimír ; Sochor, Jakub (referee) ; Hradiš, Michal (advisor)
This work deals with face recognition in video using neural networks. In the beginning, there is described the process of selection and verification of convolution neural network to generate feature vectors from images of different identities. In the next part, this work deals with the aggregation of feature vectors from video frames. Aggregation takes place through aggregation neural networks. At the end of this work, the results obtained by the aggregation methods are discussed.
|
|
|
Deep learning based face recognition in real conditions
Horňáková, Veronika ; Kříž, Petr (referee) ; Přinosil, Jiří (advisor)
This bachelor thesis explores the area of face recognition using deep learning technique. Face recognition is used for two main reasons: verification and identification. In this thesis we describe the techniques of deep learning, mostly the convolutional neural networks, which are the most significant method for processing images - detection, classification and segmentation of the image. The process of face recognition is divided into four main steps: face detection, face selection, face extraction and face classification. We chosen three of the existing programs for face recognition (OpenFace, FaceNet and Face_Recognition), which are described in this thesis, in particular the principle of the human face recognition. Thanks to the tests with the data set of Labeled Faces in the Wild (LFW) we could specify the accuracy and the time requirement of each application. Testing of FaceNet and Face_Recognition ran on real data with face detection in video with complicated conditions. The test compares two images and tries to determine if is the same person. The test results are show in graph and table.
|
|
|
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%.
|
|
|
Convolutional Neural Networks for Emotion Recognition
Jileček, Jan ; Najman, Pavel (referee) ; Hradiš, Michal (advisor)
Convolutional neural networks are used for various tasks, but foremost in machine learning, in which they excel. This work is going to introduce some existing frameworks, other algorithms for recognition and then we describe the training dataset creation and the model for emotion recognition training process. Mentioned model has accuracy of 60%. It is used for emotion statistics retrieval from movie trailers. Model for genre recognition is created from those statistics and then finally used in our application for genre recognition of the input trailer, with best accuracy of 47%.
|
guest ::
