|
|
Automatic Text Recognition for Robots
Hartman, Zdeněk ; Materna, Zdeněk (referee) ; Španěl, Michal (advisor)
This bachelor thesis describe module design for text detection and recognition for use in robotic systems. To detect charters is used Stroke Width transform, which is applied on the input edge image. In the output image after Stroke Width transform are found connected components. For letter grouping into a words is used Hough transform, which is applied on the created binary image. This image contains points, which corresponding positions of found connected components. To recognize signs in detected areas is used Tesseract library. Before recognition detected areas are extracted and rotated into a horizontal position. This proposed detector can detect even rotated text. Accuracy of detection of the text is 75% above the test set "informační tabule".
|
|
| |
|
|
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The aim of this Master's thesis is to design methods of active learning and to experiment with datasets of historical documents.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.
|
|
|
Data extraction from document scans
Macháč, Bohuslav ; Kolomazník, Jan (advisor) ; Krajíček, Václav (referee)
In this work I developed an application capable of extracting data from scanned documents. For optical character recognition, I used external OCR engine Tesseract, but it can be easily changed. I use document templates, which have informations about data areas and its data types. I tried to automatize most of the steps which are required to extract data or create new data template. User can improve or change results of these steps. For export from application I implemented components, which export data to XML, HTML or plain text. Another components can be easily added, to adapt application for various uses.
|
|
|
Text Recognition Enhanced by Writer Identity
Trněný, Matěj ; Kišš, Martin (referee) ; Kohút, Jan (advisor)
The objective of this theses was to implement a neural network for text recognition enhanced by writers identity. Adversarial learning method was selected for this purpose. Usefulness of this method was verified by experiments. This net should yield better results on data which are not similar to data contained in training data set. Accuracy of the resulting net was compared to method single-task learning and method multi-task learning. Net implementing single-task learning method has reached average character recognition error of 7, 995%, net implementing multi-task learning method has reached average error of 7, 565% and net implementing adversarial learning method has reached average error of 7, 573%. In comparison to the net implementing single-task learning multi-task learning has improvement of 5, 38% and adversarial learning has reached improvement of 5, 28%.
|
|
|
Adaptation of Neural Networks to Target Writer
Sekula, Jakub ; Hradiš, Michal (referee) ; Kohút, Jan (advisor)
This bachelor's thesis deals with the adaptation of neural networks to a specific writer with an aim to improve recognition of handwritten text of this specific writer. The method that I use is fast, requires small training dataset and uses regularization, which tries to keep the distribution of regularized weights in adaptation network similar to the one in the original network. I tested this method on dataset of printed text called IMPACT and dataset of handwritten text. When testing on dataset of handwritten text I was able to improve recognition on two diaries with pre adaptation recognition error rate of 10,82 % and 1,82 % to 8,48 % and 0,77 % with a small number of adaptation iterations and using small amount of training lines. When testing on IMPACT dataset I was able to improve recognition error rate from 32,88 % to 5,30 %.
|
|
|
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.
|
|
|
Methods used for OCR
Čermák, Marek ; Marada, Tomáš (referee) ; Zuth, Daniel (advisor)
Although OCR (Optical Character Recognition) is a topic which has been a subject of research since the second half of the 19th century, it has recieved a significant attention in the field of computer vision and object detection recently. This thesis presents history of OCR and briefly describes techniques which have been used over the course of time for character recognition. Main focus lies in the current text recognition methods introduced by soft computing. Since the major portion of the field is covered by neural networks, various architectures will be presented. Eventually a software for alphanumeric characters recognition will be implemented using a convolutional neural network.
|
|
|
Modul do serverové aplikace pro rozpoznávání identifikačních údajů z osobních dokladů
BARTYZAL, Miroslav
This Master's thesis deals with the creation of a server-side system used for the automated reading of personal information from photographed identity documents. It is focused on the processing of photographs made by camera phones with respect to various quality of their images. Text localization in images and its recognition by means of neural network are the subject of this thesis. The final system is tested by the client application which was created for the Android operating system.
|
|
|
Mobile System for Text Recognition on Android
Tomešek, Jan ; Kolář, Martin (referee) ; Zemčík, Pavel (advisor)
This thesis deals with creation of a mobile library for preprocessing of images with text which represents a part of a system for text recognition. The library is realized with emphasis on generality of use, efficiency and portability. The library providing a set of algorithms primarily for image quality assessment and text detection was created in this thesis. These algorithms enable a substantial decrease in volume of transmitted data and speed up and refinement of the recognition process. An example application for the Android platform able to analyze composition of foods stated on their wrappings was created as well. Overall, the library (system) simplifies development of mobile applications with focus on text extraction and analysis. The mobile application then provides a comfortable way of food harmfulness verification. The thesis offers a reader an overview of current solutions and tools available in this field, it provides a breakdown of important image preprocessing algorithms and guides him through the construction of the library and the application for mobile devices.
|
guest ::
