Home > Search Results: keywords:"Convolution networks"
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 2 records found  Search took 0.00 seconds. 
Traffic sign classification by deep learning
 Harmanec, Adam ; Blažek, Jan (advisor) ; Kratochvíl, Miroslav (referee)
Classification of road signs has been studied for many years and very promising results have been achieved. We present the analysis of used data sets as very limited for real case classification. In this thesis we analyse publicly available data sets and by merging and extending them, we create a wider and more comprehensive data set applicable in the Czech Republic. Finally, we propose a new convolutional neural network architecture and test it along with several preprocessing techniques on the new data set reaching accuracy of over 99%.
Detailed record
Character recognition of real scenes using neural networks
 Fiala, Petr ; Neumann, Lukáš (advisor) ; Berka, Petr (referee)
This thesis focuses on a problem of character recognition from real scenes, which has earned significant amount of attention with the development of modern technology. The aim of the paper is to use an algorithm that has state-of-art performance on standard data sets and apply it for the recognition task. The chosen algorithm is a convolution network with deep structure where the application of the specified model has not yet been published. The implemented solution is built on theoretical parts which are provided in comprehensive overview. Two types of neural network are used in the practical part: a multilayer perceptron and the convolution model. But as the complex structure of the convolution networks gives much better performance compare with the classification error of the MLP on the first data set, only the convolution structure is used in the further experiments. The model is validated on two public data sets that correspond with the specification of the task. In order to obtain an optimal solution based on the data structure several tests had been made on the modificated network and with various adjustments on the input data. Presented solution provided comparable prediction rate compare to the best results of the other studies while using artificially generated learning pattern. In conclusion, the thesis describes possible extensions and improvements of the model, which should lead to the decrease of the classification error.
Detailed record

Interested in being notified about new results for this query?
Subscribe to the RSS feed.
Digital Repository :: Search :: Submit :: Personalize :: Help
Powered by Invenio v1.1.2
Maintained by admin.invenio@techlib.cz
This site is also available in the following languages:
Česky  English