|
|
Comparison of deep learning and classical methods for traffic signs detection
Geiger, Petr ; Šikudová, Elena (advisor) ; Mirbauer, Martin (referee)
The goal of this thesis is to explore and evaluate classic and deep neural network computer vision methods in the task of detection position of a level crossing barrier. This thesis is based on an initial detection algorithm using a Stable Wave Detector. The initial algorithm is optimized both in performance and quality of the results. Both is crucial, because the best method should be suitable as a component of the real-time level crossing safety system. Then an another approach is implemented using deep neural networks and optimized in the same manner. Throughout the work several datasets are created for both training and testing of the algorithms. Both approaches are finally evaluated on the same test datasets and the results are compared.
|
|
|
Indonesian-English Neural Machine Translation
Dwiastuti, Meisyarah ; Popel, Martin (advisor) ; Novák, Michal (referee)
Title: Indonesian-English Neural Machine Translation Author: Meisyarah Dwiastuti Department: Institute of Formal and Applied Linguistics Supervisor: Mgr. Martin Popel, Ph.D., Institute of Formal and Applied Linguis- tics Abstract: In this thesis, we conduct a study on neural machine translation (NMT) for an under-studied language, Indonesian, specifically for English-Indonesian (EN-ID) and Indonesian-English (ID-EN) in a low-resource domain, TED talks. Our goal is to implement domain adaptation methods to improve the low-resource EN-ID and ID-EN NMT systems. First, we implement model fine-tuning method for EN-ID and ID-EN NMT systems by leveraging a large parallel corpus contain- ing movie subtitles. Our analysis shows the benefit of this method for the improve- ment of both systems. Second, we improve our ID-EN NMT system by leveraging English monolingual corpora through back-translation. Our back-translation ex- periments focus on how to incorporate the back-translated monolingual corpora to the training set, in which we investigate various existing training regimes and introduce a novel 4-way-concat training regime. We also analyze the effect of fine- tuning our back-translation models with different scenarios. Experimental results show that our method of implementing back-translation followed by model...
|
|
|
Deep Neural Networks Approximation
Stodůlka, Martin ; Mrázek, Vojtěch (referee) ; Vaverka, Filip (advisor)
The goal of this work is to find out the impact of approximated computing on accuracy of deep neural network, specifically neural networks for image classification. A version of framework Caffe called Ristretto-caffe was chosen for neural network implementation, which was extended for the use of approximated operations. Approximated computing was used for multiplication in forward pass for convolution. Approximated components from Evoapproxlib were chosen for this work.
|
|
|
Pedestrian Identification
Jurča, Jan ; Špaňhel, Jakub (referee) ; Hradiš, Michal (advisor)
This thesis deals with pedestrian identification from video sequence based on person, face and gait recognition. For person and face recognition are used pretrained networks. While for gait recognition is implemented and compared many different networks. Final pedestrian recognition is based on multimodal fusion realized by neural network. For the purpose of the work was created dataset, along with a set of tools that allow its almost automatic creation.
|
|
|
Convolutional Networks for Document Layout Analysis
Endrych, David ; Herout, Adam (referee) ; Kodym, Oldřich (advisor)
The goal of this thesis is to create a tool for analyzig the page layouts of text documents. The problem is solved by convolution neural networks. The architecture chosen in this thesis is the U-Net architecture. The cross entropy error function with weight map is used for train the network model. Paragraph regions are obtained throught connected component analysis. Experiments are evaluated using the Symmetric Best Dice object metric. Experiments have shown that it is better to use all paragraph edges than to focus only on vertical paragraph edges. In addition, experiments show that batche sampling strategies and adaptive resolution help to improve analysis results. The experiments also describe the application of separators, which is useful in analyzing multi-column documents.
|
|
|
Deep Neural Networks for Defect Detection
Juřica, Tomáš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The goal of this work is to bring automatic defect detection to the manufacturing process of plastic cards. A card is considered defective when it is contaminated with a dust particle or a hair. The main challenges I am facing to accomplish this task are a very few training data samples (214 images), small area of target defects in context of an entire card (average defect area is 0.0068 \% of the card) and also very complex background the detection task is performed on. In order to accomplish the task, I decided to use Mask R-CNN detection algorithm combined with augmentation techniques such as synthetic dataset generation. I trained the model on the synthetic dataset consisting of 20 000 images. This way I was able to create a model performing 0.83 AP at 0.1 IoU on the original data test set.
|
|
|
Object detection for video surveillance using the SSD approach
Dobranský, Marek ; Lokoč, Jakub (advisor) ; Božovský, Petr (referee)
The surveillance cameras serve various purposes ranging from security to traffic monitoring and marketing. However, with the increasing quantity of utilized cameras, manual video monitoring has become too laborious. In re- cent years, a lot of development in artificial intelligence has been focused on processing the video data automatically and then outputting the desired no- tifications and statistics. This thesis studies the state-of-the-art deep learning models for object detection in a surveillance video and takes an in-depth look at SSD architecture. We aim to enhance the performance of SSD by updating its underlying feature extraction network. We propose to replace the initially used VGG model by a selection of modern ResNet, Xception and NASNet classifica- tion networks. The experiments show that the ResNet50 model offers the best trade-off between speed and precision, while significantly outperforming VGG. With a series of modifications, we improved the Xception model to match the ResNet performance. On top of the architecture-based improvements, we ana- lyze the relationship between SSD and a number of detected classes and their selection. We also designed and implemented a new detector with the use of temporal context provided by the video frames. This detector delivers enhanced precision while...
|
|
|
Detector of the Human Head in Image
Svoboda, Jakub ; Orság, Filip (referee) ; Goldmann, Tomáš (advisor)
Detection of human head is an important part of person detection and identification algorithms. This thesis is focused on the detection of human head with methods based on neural networks. The majority the of conventional detectors can identify objects within a limited range of positions, whereas models based on neural networks offer a more robust approach. In this thesis we trained the current state-of-the-art models and compared their accuracy and speed. The most accurate model proved to be RetinaNet which has reached 85.15% AP. This detector can be used to improve current available algorithms for person detection, identification and tracking.
|
|
|
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 for Image Classification
Ziková, Jana ; Veľas, Martin (referee) ; Hradiš, Michal (advisor)
This bachelor thesis deals with electronic commerce website products classification using product's photographs. For this purpose we use already implemented models of deep convolutional neural networks. Tho goal of this theses is to design experiments that will lead to the best possible results in product images classification.
|
guest ::
