|
|
Multi-Modal Text Recognition
Kabáč, Michal ; Herout, Adam (referee) ; Kišš, Martin (advisor)
The aim of this thesis is to describe and create a method for correcting text recognizer outputs using speech recognition. The thesis presents an overview of current methods for text and speech recognition using neural networks. It also presents a few existing methods of connecting the outputs of two modalities. Within the thesis, several approaches for the correction of recognizers, which are based on algorithms or neural networks, are designed and implemented. An algorithm based on the principle of searching the outputs of recognizers using levenshtain alignment was proven to be the best approach. It scans the outputs, if the uncertainty of the text recognizer character is less than the pre-selected limit. As part of the work, an annotation server was created for the text transcripts, which was used to collect recordings for the evaluation of experiments.
|
|
|
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 %.
|
|
|
Sudoku Solver for Android
Hrbas, Vojtěch ; Herout, Adam (referee) ; Páldy, Alexander (advisor)
This work deals with solving Sudoku game which is taken by a camera of a mobile device running Android. It discusses possibilities of image processing, possibilities of recognizing the text in the image and principle and solving of Sudoku game. It also examines existing applications for Android that solve Sudoku. Then it proposes the application itself for solving Sudoku and summarizes the results of testing the application in terms of performance and users.
|
|
|
Deep Learning for OCR in GUI
Hamerník, Pavel ; Špaňhel, Jakub (referee) ; Lysek, Tomáš (advisor)
Optical character recognition (OCR) has been a topic of interest for many years. It is defined as the process of digitizing a document image into a sequence of characters. Despite decades of intense research, OCR systems with capabilities to that of human still remains an open challenge. In this work there is presented a design and implementation of such system, which is capable of detecting texts in graphical user interfaces.
|
|
|
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.
|
|
|
iPhone Application for Number Plate Recognition
Sládeček, Roman ; Dvořák, Radim (referee) ; Procházka, Boris (advisor)
This thesis talks about theoretical and practical side of development of application for Apple iPhone mobile cell phone and for its operating system called iOS. In theoretical part are contained informations about history of this device, about tools for creating application for this mobile platform and there is shortly sketched procedure and process how the application is deployed into the phone. Next part deals with the licence number plates, their signification and integrity restrictions. Main core of whole thesis is a practical part about creation and implementation mobile application for recognition of that number plates with supporting of built-in camera and its consecutive text representation or manipulation with that data. In the final part there is a review of results which this application brings after testing and experimenting in different conditions.
|
|
|
Support for Codenames Game on Mobile Phone with OS Android
Hurta, Martin ; Fajčík, Martin (referee) ; Smrž, Pavel (advisor)
The aim of this thesis is to create an support application for word association board game Codenames on mobile phones with operating system Android. The solution consists of detection and recognition of the game board using the OpenCV and Tess-two libraries and Google Firebase ML Kit tools and providing support during the game, including an optional level of assistance and the ability to play on multiple devices with Google Play Games services. These features motivate the user to further use the application and provide data in~the form of generated game records, that are useful for further development and validation of association models or strategies for automatic playing.
|
|
|
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.
|
|
|
Deep Learning for OCR in GUI
Hamerník, Pavel ; Špaňhel, Jakub (referee) ; Lysek, Tomáš (advisor)
Optical character recognition (OCR) has been a topic of interest for many years. It is defined as the process of digitizing a document image into a sequence of characters. Despite decades of intense research, OCR systems with capabilities to that of human still remains an open challenge. In this work there is presented a design and implementation of such system, which is capable of detecting texts in graphical user interfaces.
|
|
|
Automatic Delivery Note Transcription
Necpál, Dávid ; Kišš, Martin (referee) ; Hradiš, Michal (advisor)
This bachelor thesis aims to create a system for automatic transcription of delivery notes - documents with a fixed structure. The solution is divided into two parts. The first part is table lines detection and subsequent detection and extraction of cells, that contain required data. The second part is handwritten numeric characters recognition in the images of the cutted cells. The resulting system can detect cells with the required data with 100 % accuracy with well-scanned delivery notes, while the success rate of numerical character recognition is more than 95 % for individual characters and more than 92 % for entire character sequences. The benefit of this work is a system for automatic transcription of delivery notes, which provides faster and easier otherwise lengthy rewriting of the contents of delivery notes to the information system in the retail. By using this system, the employee saves more than 50 % of the time on each delivery note.
|
guest ::
