|
|
Optical Character Recognition at Camera Captured Images
Kindermann, Hubert ; Blažek, Jan (advisor) ; Kolomazník, Jan (referee)
We present solution of steps necessary for binarization and text lines detection contained in printed documents digitized by the camera. We introduce a normalization of non-uniform illumination method for text photographs. We propose input bitmap binarization algorithm based on two-dimensional probability pixel model which also considers its surrounding. We continue with description of robust text lines orientation detector based on optimization of risk function using first order derivatives of image function. In the end we present text lines detection and segmentation algorithm. Final shape of segmented lines is optimized with usage of graph algorithm. Powered by TCPDF (www.tcpdf.org)
|
|
|
Detection and Recognition of License Plates
Tykva, Jiří ; Zemčík, Pavel (referee) ; Juránek, Roman (advisor)
Cílem této bakalářské práce je návrh, implementace a testování systému, který v reálném čase pomocí neuronových sítí bude detekovat a rozpoznávat registrační značky vozidel. Nasbíraná data budou ukládána do databáze. Architektura systému je rozdělena do tří hlavních částí. První část řeší detekci registrační značky v obraze pomocí TensorFlow Object Detection API. Detektor dosahuje přesnosti 98.15 % AP při rychlosti kolem 14 fps. Druhá část se zabývá sledováním značek ve videu pomocí algoritmu SORT. Třetí část systému se věnuje holistickému rozpoznávání textu registrační značky a dosahuje až 0.6% chybovosti při rozpoznávání jednotlivých znaků a 2% chybovosti při rozpoznávání celého textu. Výsledný systém lze použít například pro policejní oddělení za účelem sledování kradených vozidel či automatického vybírání dálničních poplatků.
|
|
|
Applications of Approximate Computation in Genetic Programming
Ševčík, David ; Vašíček, Zdeněk (referee) ; Bidlo, Michal (advisor)
This thesis deals with ways of application of approximate circuits into evolutionary design of classifiers using Cartesian genetic programming. The problem of hand-written digit recognition was chosen as a case study. The goal is to validate the capability of classifiers, which use approximate circuits to provide results with certain advantages compared to other conventional classifiers. The thesis demonstrates that by using approximate computing it is possible to acquire classifiers with a simpler implementation, while matching or sometimes even exceeding the precision of the other conventional classifiers.
|
|
|
Braille Reader for Android OS
Bokiš, Daniel ; Dluhoš, Ondřej (referee) ; Procházka, Boris (advisor)
This thesis deals with the analysis and recognition of the Braille characters from a photo taken by a mobile phone. It describes design and implementation of application for recognition on Android OS mobile platform. Described general principles of analysis and processing of image are also applicable in other systems.
|
|
|
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.
|
|
|
Optical Character Recognition at Camera Captured Images
Kindermann, Hubert ; Blažek, Jan (advisor) ; Kolomazník, Jan (referee)
We present solution of steps necessary for binarization and text lines detection contained in printed documents digitized by the camera. We introduce a normalization of non-uniform illumination method for text photographs. We propose input bitmap binarization algorithm based on two-dimensional probability pixel model which also considers its surrounding. We continue with description of robust text lines orientation detector based on optimization of risk function using first order derivatives of image function. In the end we present text lines detection and segmentation algorithm. Final shape of segmented lines is optimized with usage of graph algorithm. Powered by TCPDF (www.tcpdf.org)
|
|
|
Recongition of symbols in digitalized mathematical expressions
Haas, František ; Valla, Tomáš (advisor) ; Mareš, Martin (referee)
This bachelor thesis focuses on finding suitable methods and algorithms for text segmentation and character recognition using artificial neural networks. Firstly, the thesis covers basic principles of artificial neuron and artificial neural networks, structure of convolutional neural networks and mainly backpropagation algorithm and stochastic Levenberg-Marquardt algorithm. Then the thesis describes image processing and image segmentation to single symbols using graph algorithms. This thesis also includes implementation of these methods and algorithms in an application which converts digital mathematical expressions to vector format.
|
|
|
License Plate Detection and Recognition
Řepka, Michal ; Sochor, Jakub (referee) ; Herout, Adam (advisor)
This paper addresses the problem of object detection and recognition from still images using methods of computer vision. The objects of detection are czech license plates and the goal of this paper was to create an automatic license plate anotation tool. Suggested solution uses edge detection and machine learned cascading classifiers. Created application was then tested on dataset taken by the author.
|
|
|
Caligraphy Editor with Japanese Character Recognition
Horáček, Petr ; Žák, Pavel (referee) ; Švub, Miroslav (advisor)
This work focuses on creating an application to support Japanese character learning. It also contains a brief overview of Japanese writing's history and evolution. Based on the study of existing options, this work sets the requirements for the application. It discusses problems and tries to find possible solutions. Character recognition is an important part. The work describes chosen solutions and their implementations. It ends by demonstrating achieved results and discussing options for further development of the system.
|
|
| |
guest ::
