|
|
Neural Networks for Automatic Table Recognition
Piwowarski, Lukáš ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
Tato práce seznamuje čtenáře se současnými technikami rozpoznávání tabulek, které se používají především k získávání informací z ručně psaných nebo tištěných historických tabulek. Představujeme také metodu založenou na grafové neuronové síti, která je inspirována představenými přístupy. Metoda se skládá ze tří fází: fáze inicializace grafu, fáze klasifikace uzlů/hran a fáze transformace grafu na text. Ve fázi inicializace grafu používáme algoritmus viditelnosti uzlů a OCR k vytvoření počáteční grafové reprezentace vstupní tabulky. Ve fázi klasifikace uzlů a hran jsou uzly a hrany klasifikovány a ve fázi transformace grafu na text zarovnáváme uzly grafu do mřížky, která je pak použita k vytvoření konečné textové reprezentace tabulky. Náš implementovaný model byl schopen dosáhnout přesnosti 68 % u detekce horizontálních sousedů, přesnosti 71 % u detekce vertikálních sousedů a přesnosti 83 % u detekce buněk na datové sadě ABP.
|
|
|
Handwritten text recognition using a sliding window
Ďuriš, Denis ; Povoda, Lukáš (referee) ; Rajnoha, Martin (advisor)
This bachelor thesis deals with optical character recognition. It focuses on recognizing hand-written text. The theoretical introduction describes the methods used for optical character recognition and selected machine learning methods. Subsequently, the work describes two methods for making cutouts of characters, using a sliding window. Cutouts are used in training and testing datasets of machine learning models. The document includes methods to improve the accuracy of character recognition. The accuracy of the models is evaluated in conclusion. Charcters in cutouts are clasified by an automated recognition program.
|
|
|
License Plate Detection and Recognition from Still Image
Janíček, Kryštof ; Sochor, Jakub (referee) ; Špaňhel, Jakub (advisor)
This thesis describes the design and implementation of system for detection and recognition of license plate. This system is divided into three parts which are license plate detection, character segmentation and optical character recognition. License plate detection is done by cascade classifier that achieves hit rate of 95.5% and precision rate of 95.9%. Character segmentation is based on contour finding that achieves hit rate of 93.3% and precision rate of 96.5%. Optical character recognition is done by neural network and achieves hit rate of 98.4% for individual characters. The whole system is able to detect and recognize up to 81.5% of license plates from the test data set.
|
|
|
Picture analysis and comparing
Novotný, Václav ; Nováček, Petr (referee) ; Richter, Miloslav (advisor)
This bachelor thesis concerns about analysis and image correlation. It discusses possibilities of image processing and hardware data collection system. Image database is created and algorithms for processing and comparing acquired images with reference are designed and created in this thesis.
|
|
|
Automatic Invoice Recognition and Processing
Ščešňák, Vladimír ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This work aims to design and implement application for automatic recognition and processing invoices with assistance using computer vision. The work deals with the analysis of existing invoices, design and implementation of an algorithm for correctly recognition, selection of appropriate test patterns and also design and implementation of the user interface.
|
|
|
Active Learning for Work with Archive Materials
Štajerová, Alžbeta ; Hříbek, David (referee) ; Rozman, Jaroslav (advisor)
The aim of this Master's thesis is to design and implement an OCR system for archival historical documents containing handwriting text. The first part of the thesis deals with the study of optical character recognition, the process of OCR pipepline. Then the topic of active learning and its methods is described. The thesis reviews the available solutions for recognition of handwritten historical documents. I further describe the neural network architectures used for text detection. The thesis results in the design and subsequent implementation of system for text recognition of historical documents, enabling user annotation, full-text search in annotation records.
|
|
|
User Interface for Efficient Corrections of OCR Output
Szepsi, Pavol ; Kapinus, Michal (referee) ; Hradiš, Michal (advisor)
The aim of the present bachelor thesis was to design and implement a web user interface for checking and correcting OCR outputs which will be suitable for mobile and touchscreen devices. The user interface uses the OCR output variants that the user can use to modify the recognized text. The interface is implemented in JavaScript using the Vue JS framework. XAMPP package is used for the server part. The tool Axios is used for communication between the user interface and the server. The created interface allows users to quickly and easily correct the OCR outputs, either on a computer or on a mobile device.
|
|
|
Neural Networks for Automatic Table Recognition
Piwowarski, Lukáš ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
Tato práce seznamuje čtenáře se současnými technikami rozpoznávání tabulek, které se používají především k získávání informací z ručně psaných nebo tištěných historických tabulek. Představujeme také metodu založenou na grafové neuronové síti, která je inspirována představenými přístupy. Metoda se skládá ze tří fází: fáze inicializace grafu, fáze klasifikace uzlů/hran a fáze transformace grafu na text. Ve fázi inicializace grafu používáme algoritmus viditelnosti uzlů a OCR k vytvoření počáteční grafové reprezentace vstupní tabulky. Ve fázi klasifikace uzlů a hran jsou uzly a hrany klasifikovány a ve fázi transformace grafu na text zarovnáváme uzly grafu do mřížky, která je pak použita k vytvoření konečné textové reprezentace tabulky. Náš implementovaný model byl schopen dosáhnout přesnosti 68 % u detekce horizontálních sousedů, přesnosti 71 % u detekce vertikálních sousedů a přesnosti 83 % u detekce buněk na datové sadě ABP.
|
|
|
Character recognition of machine-written documents
Kindermann, Hubert ; Blažek, Jan (advisor) ; Kolomazník, Jan (referee)
In the present thesis we solve the problem of symbol extraction and recognition from printed documents digitized by the scanner or camera. We introduce a noise resistant algorithm of document lighting normalization. We continue with the extraction of individual characters from the document and their recognition with a system of feedforward multilayer neural networks. We also focus on processing of the resulting set of recognized characters, which is necessary for further use of the extracted text. The last step is correction of the output based on surrounding letters of each character. We have successfully implemented an automatic system containing all the above components.
|
|
|
Handwriting recognition using neural network
Petr, Martin ; Surynek, Pavel (advisor) ; Pergel, Martin (referee)
Title: Handwriting recognition using neural network Author: Martin Petr Department: Department of Theoretical Computer Science and Mathematical Logic Supervisor: RNDr. Pavel Surynek, PhD. Supervisor's e-mail address: pavel.surynek@mff.cuni.cz Abstract: Pattern recognition finds its use in many fields whose development has been affected by computer science and computer technology. Among these, the conversion of handwritten or printed text into computer-encoded text has a particularly prominent position. In the presented work we propose a method for recognizing handwritten characters in real-time using feedforward neural network as the basic classification mechanism. Dealing with differences among individual instances of each handwritten character we thoroughly explored the possibility of suppressing these while emphasizing characteristics that are essential for successful recognition. For these purposes we employed discrete cosine transform, whose time-proven application in audio and video signal processing or even directly in the field of pattern recognition provided a convincing argument for us to use it in our work as well. As a means of suppressing variations among various writing instruments we proposed preprocessing of input images using binarization and skeletonization. The designed method was...
|
guest ::
