|
|
Optical Character Recognition in Images
Kadlic, Pavel ; Mlích, Jozef (referee) ; Chmelař, Petr (advisor)
The bachelor's thesis focuses on detection, localization, tracking and extraction of text from images and videos. There are described algorithms achieving optical chacarcter recognition. The thesis deals with implementation of algorithms, selecting a suitable sample of test data and its evaluation.
|
|
|
Neural Network Letter Recognition
Kluknavský, František ; Hradiš, Michal (referee) ; Šilhavá, Jana (advisor)
This work uses handwritten character recognition as a model problem for using multilayer perceptron, error backpropagation learning algorithm and finding their optimal parameters, hidden layer size, learning rate and length, ability to handle damaged data. Results were acquired by repeated simulation and testing the neural network using 52,152 English lowercase letters. Best results, smallest network and shortest learning time was at 60 neurons in the hidden layer and learning rate of 0.01. Bigger networks achieved the same ability to recognize unknown patterns and higher robustness at highly damaged data processing.
|
|
|
Autonomous Crossword Puzzles for Android Platform
Buno, Petr ; Polok, Lukáš (referee) ; Beran, Vítězslav (advisor)
This thesis deals with algorithms for search in the recognized text of the captured image and it discusses the development of applications for the Android mobile platform. This paper presents the libraries for text recognition in image and existing algorithms to search for text string. The practical part is devoted to the design and implementation of applications for autonomous search crossword puzzles from photos taken by the user. The teoretical part describes the important tools for developing applications for the Android platform, the principles of text recognition from the image and puzzle WordFind rules. At the end the paper summarizes the results and evaluation to find success solution, intuitive GUI and overall usability. In the conclusion, the evaluation of results and outlines possible application extension.
|
|
|
Mobile Interpreter for Android
Homola, Vladimír ; Maršík, Lukáš (referee) ; Beran, Vítězslav (advisor)
This bachelor thesis describes implementation of the Mobile interpreter application with focus on its user interface. The goal is to create an application with such interface with which the users will be able to work effectively and with pleasure. The first part contains a summary of the knowledge learned during study of this problem. After that is definition of the future user, situations in which he used it and design of system and its interface. Description of implementation and user testing is in the last part.
|
|
|
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".
|
|
|
Android app - Energy Monitor with Prediction
John, Tomáš ; Herout, Adam (referee) ; Szőke, Igor (advisor)
The thesis describes process of creation mobile application used for recording and processing data from consumption energy meters. Application targets on devices with operating system Android. The task was to study similar solutions and then design and implement own one. Enriched by the possibility of predict future energy consumption, using historical outdoor temperatures. Also bring the optional OCR (Optical Character Recognition) reading meter's values. Weather data obtain from internet weather service. And from stored data be able to make user- rendly charts and statistics showing energy consumption.
|
|
| |
|
|
Image processing using Android device - electricity meter value recognition
Sliž, Jiří ; Klečka, Jan (referee) ; Honec, Peter (advisor)
The aim of the work is to design an application for mobile devices with the Android operating system. This application allows image capturing with a camera and image processing with the support of the OpenCV library. The purpose of this application is automatic value recognition of the analog electrometer. The text contains a description of the analog electrometers. The following is characteristic of Android operating system, and this part is directly connected to a draft of the application itself. Next part contains the image processing algorithms, testing and implementation into Android application.
|
|
|
Optical Recognition and Analysis for Home Metering
Machala, Petr ; Fedra, Zbyněk (referee) ; Povalač, Aleš (advisor)
The topic of this master’s thesis is a study and solution of problems regarding an optical recognition and home metering analysis for the following recording and statistical processing. For this required application a STMicroelectronics 32F429IDISCOVERY development board with ARM Cortex-M4 microcontroller and OmniVision OV7670 camera module was used, where a required firmware was implemented. This thesis therefore generally represents a complex solution from acquisition of images by used camera module to final analysis and data processing and building a functional prototype of the proposed sensor system.
|
|
| |
guest ::
