|
|
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.
|
|
|
Defect detection using smart camera
Hons, Viktor ; Boštík, Ondřej (referee) ; Honec, Peter (advisor)
This thesis deals with the application of smart cameras and verification of its functions. In the first part the term smart camera is defined, the parts of it and the most common applications are presented. A review of smart cameras from the different manufactures on the market is made. After selection of the proper camera model three task from real industrial application are specified – inspection of capacitor print, inspection of beer label and dimension measurement. With the picked camera the tasks are performed, including the layout of workplace, scene and lighting. Further the reliability is tested together with the successfulness and the speed of designed solution.
|
|
|
Deep Networks for Handwriting Recognition
Richtarik, Lukáš ; Herout, Adam (referee) ; Hradiš, Michal (advisor)
The work deals with the issue of handrwritten text recognition problem with deep neural networks. It focuses on the use of sequence to sequence method using encoder-decoder model. It also includes design of encoder-decoder model for handwritten text recognition using a transformer instead of recurrent neurons and a set of experiments that were performed on it.
|
|
|
Recognition of Handwriting for Mobile Phones
Talaš, Vladimír ; Chalupníček, Kamil (referee) ; Schwarz, Petr (advisor)
The goal of this project is to create a mobile phone application, which can use phone camera to get a photography. This photography contains text, application has an ability to find a text, recognize all characters and send output as SMS. In this application there are implemented algorithms for text recognize from pictures based on Hidden Markovov Models. The particular stress is put on training of the model, to maximalise a succes of text recognition. There are some experiments model training with model variables, which are leading in better ability of text recognition. It was achieved a value of 97% succesfully recognized characters.
|
|
|
Hand Writing Letters Recognition
Jelínek, Radek ; Žák, Jakub (referee) ; Zbořil, František (advisor)
The thesis deals with handwriting recognition and conversion into digital form. Recognition is focused on recognition of letters and finding success when you did not use the dictionary for word recognition. One part of document is compare with commercial applications.
|
|
|
Social Network Analysis using methods of pattern recognition
Križan, Viliam ; Burget, Radim (referee) ; Atassi, Hicham (advisor)
Diplomová práca sa zaoberá rozpoznávaním emócií z textu v sociálnych sieťach. Práca popisuje súčasné metódy extrakcie príznakov, používané lexikóny, korpusy a klasifikátory. Emócie boli rozpoznávané na základe klasifikátoru, netrénovaného na anotovaných dátach z mikroblogovacej siete Twitter. Výhodou použitia služby Twitter, bolo geografické vymedzenie dát, ktoré umožňuje sledovanie zmien emócií populácie v rôznych mestách. Prvým prístupom klasifikácie bolo vytvorenie Baseline algoritmu, ktorý používal jednoduchý lexikón. Pre zlepšenie klasifikácie sme v druhom bode použili komplexnejší SVM klasifikátor. SVM klasifikátory, extrakcie a selekcie príznakov boli použité z dostupnej Python knižnice Scikit. Dáta pre natrénovanie klasifikátoru boli zhromažďované z oblasti USA, a to s pomocou vytvorenej aplikácie. Klasifikátor bol natrénovaný na dátach, označených pri ich zhromažďovaní - bez manuálnej anotácie. Boli použité dve rôzne implantácie SVM klasifikátorov. Výsledné klasifikované emócie, v rôznych mestách a dňoch, boli zobrazené v podobe farebných značiek na mape.
|
|
|
iOS Application for Pokemon's GO Players Community
Pihrt, Patrik ; Kočí, Radek (referee) ; Hrubý, Martin (advisor)
Pokémon Go is one of the most successful mobile game applications ever created. The game is supported on Android and iOS platforms. This bachelor's thesis describes the way of finding out certain type of information from game's screenshot. Those screenshots are inserted to the application by user, datas are calculated and Pokémon's individual value is known and showed. Results are saved and can be seen anytime. The application provides the newest gaming information.
|
|
|
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%.
|
|
|
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.
|
|
|
OCR Trained with Unanotated Data
Buchal, Petr ; Dobeš, Petr (referee) ; Hradiš, Michal (advisor)
The creation of a high-quality optical character recognition system (OCR) requires a large amount of labeled data. Obtaining, or in other words creating, such a quantity of labeled data is a costly process. This thesis focuses on several methods which efficiently use unlabeled data for the training of an OCR neural network. The proposed methods fall into the category of self-training algorithms. The general approach of all proposed methods can be summarized as follows. Firstly, the seed model is trained on a limited amount of labeled data. Then, the seed model in combination with the language model is used for producing pseudo-labels for unlabeled data. Machine-labeled data are then combined with the training data used for the creation of the seed model and they are used again for the creation of the target model. The successfulness of individual methods is measured on the handwritten ICFHR 2014 Bentham dataset. Experiments were conducted on two datasets which represented different degrees of labeled data availability. The best model trained on the smaller dataset achieved 3.70 CER [%], which is a relative improvement of 42 % in comparison with the seed model, and the best model trained on the bigger dataset achieved 1.90 CER [%], which is a relative improvement of 26 % in comparison with the seed model. This thesis shows that the proposed methods can be efficiently used to improve the OCR error rate by means of unlabeled data.
|
guest ::
