|
|
Improving Consistency in Text Recognition Datasets
Tvarožný, Matúš ; Hradiš, Michal (referee) ; Kišš, Martin (advisor)
This work is concerned with increasing the consistency of datasets for text recognition. This paper describes the problems that cause the inconsistency and then presents solutions to eliminate it. The effect of the properties of the polygons defining the text line boundaries and hence how the modified version of the dataset, which is composed of ideal text line variants, affected the accuracy of the model is investigated. Further, the work focuses on detecting and then removing or modifying text lines whose ground truth transcription does not match the actual text they contain. Experimentation showed that removing the visual inconsistency on the training set did not have a significant effect on the trained model, but modifying the test set improved the OCR accuracy of the model by 1.1\% CER. By modifying the dataset so that it did not contain mutually inconsistent pairs of recognized text and the corresponding ground truth, the model improved by a maximum of only 0.2\% CER after re-training. The main finding of this work is, above all, the proven beneficial effect of removing inconsistencies on test suites, thanks to which it is possible to determine a more realistic error rate of the OCR model.
|
|
|
Algorithms for named entities recognition
Winter, Luca ; Heriban, Pavel (referee) ; Šťastný, Jiří (advisor)
The aim of this work is to find out which algorithm is the best at recognizing named entities in e-mail messages. The theoretical part explains the existing tools in this field. The practical part describes the design of two tools specifically designed to create new models capable of recognizing named entities in e-mail messages. The first tool is based on a neural network and the second tool uses a CRF graph model. The existing and newly created tools and their ability to generalize are compared on a subset of e-mail messages provided by Kiwi.com.
|
|
|
Recurrent Neural Networks in Computer Vision
Křepský, Jan ; Řezníček, Ivo (referee) ; Španěl, Michal (advisor)
The thesis concentrates on using recurrent neural networks in computer vision. The theoretical part describes the basic knowledge about artificial neural networks with focus on a recurrent architecture. There are presented some of possible applications of the recurrent neural networks which could be used for a solution of real problems. The practical part concentrates on face recognition from an image sequence using the Elman simple recurrent network. For training there are used the backpropagation and backpropagation through time algorithms.
|
|
|
Machine Translation Using Artificial Neural Networks
Holcner, Jonáš ; Beneš, Karel (referee) ; Szőke, Igor (advisor)
The goal of this thesis is to describe and build a system for neural machine translation. System is built with recurrent neural networks - encoder-decoder architecture in particular. The result is a nmt library used to conduct experiments with different model parameters. Results of the experiments are compared with system built with the statistical tool Moses.
|
|
|
Convolutional Networks for Historic Text Recognition
Kišš, Martin ; Zemčík, Pavel (referee) ; Hradiš, Michal (advisor)
The aim of this work is to create a tool for automatic transcription of historical documents. The work is mainly focused on the recognition of texts from the period of modern times written using font Fraktur. The problem is solved with a newly designed recurrent convolutional neural networks and a Spatial Transformer Network. Part of the solution is also an implemented generator of artificial historical texts. Using this generator, an artificial data set is created on which the convolutional neural network for line recognition is trained. This network is then tested on real historical lines of text on which the network achieves up to 89.0 % of character accuracy. The contribution of this work is primarily the newly designed neural network for text line recognition and the implemented artificial text generator, with which it is possible to train the neural network to recognize real historical lines of text.
|
|
|
Tempo detector based on a neural network
Suchánek, Tomáš ; Smékal, Zdeněk (referee) ; Ištvánek, Matěj (advisor)
This Master’s thesis deals with beat tracking systems, whose functionality is based on neural networks. It describes the structure of these systems and how the signal is processed in their individual blocks. Emphasis is then placed on recurrent and temporal convolutional networks, which by they nature can effectively detect tempo and beats in audio recordings. The selected methods, network architectures and their modifications are then implemented within a comprehensive detection system, which is further tested and evaluated through a cross-validation process on a genre-diverse data-set. The results show that the system, with proposed temporal convolutional network architecture, produces comparable results with foreign publications. For example, within the SMC dataset, it proved to be the most successful, on the contrary, in the case of other datasets it was slightly below the accuracy of state-of-the-art systems. In addition,the proposed network retains low computational complexity despite increased number of internal parameters.
|
|
|
Active Learning for OCR
Kohút, Jan ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
The aim of this Master's thesis is to design methods of active learning and to experiment with datasets of historical documents. A large and diverse dataset IMPACT of more than one million lines is used for experiments. I am using neural networks to check the readability of lines and correctness of their annotations. Firstly, I compare architectures of convolutional and recurrent neural networks with bidirectional LSTM layer. Next, I study different ways of learning neural networks using methods of active learning. Mainly I use active learning to adapt neural networks to documents that the neural networks do not have in the original training dataset. Active learning is thus used for picking appropriate adaptation data. Convolutional neural networks achieve 98.6\% accuracy, recurrent neural networks achieve 99.5\% accuracy. Active learning decreases error by 26\% compared to random pick of adaptations data.
|
|
|
Deep Neural Networks for Text Recognition
Kavuliak, Daniel ; Hradiš, Michal (referee) ; Kišš, Martin (advisor)
The aim of this work is to build a model for handwritten text recognition, which will use non-autoregressive decoder. This type of decoder calculates character predictions independently of other predicted characters, which can be advantageous in terms of inference speed, but the quality of the prediction is worse. The motivation is to design a non-autoregressive decoder, which will have the task of refining the encoder's predictions. The task was solved with the help of decoders, which mask the encoder's predictions or partially suppress the information due to the use of information about unmasked symbols or using input sequence information. Subsequently, a series of experiments was performed, where the best model reached a character error rate of 8.92 %. But the assignment was not fulfilled, because the encoder itself reached 6.38 %.
|
|
|
Classification with Use of Neural Networks in the Keras Environment
Pyšík, Michal ; Burgetová, Ivana (referee) ; Bartík, Vladimír (advisor)
Tato práce zkoumá problematiku klasifikace pomocí umělých neuronových sítí s využitím knihovny Keras, poskytující vysokoúrovňové rozhraní pro práci s umělými neuronovými sítěmi v programovacím jazyce Python. Cílem práce je prozkoumat rozsáhlé možnosti této knihovny v oblasti klasifikace a porovnat různé typy a topologie umělých neuronových sítí formou experimentů na vybraných datasetech, což je doplněno jednoduchou experimentální aplikací sloužící především jako rozhraní pro tyto experimenty.
|
|
| |
guest ::
