Home > Search Results: keywords:"rozpoznávání obrázků"
Search:
Search Tips :: Advanced Search
Search collections:
Sort by: Display results: Output format:
National Repository of Grey Literature 3 records found  Search took 0.00 seconds. 
Deep Learning for Image Recognition
 Munzar, Milan ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
Neural networks are one of the state-of-the-art models for machine learning today. One may found them in autonomous robot systems, object and speech recognition, prediction and many others AI tasks. The thesis describes this model and its extension which is used in an object recognition. Then explains an application of a convolutional neural networks(CNNs) in an image recognition on Caltech101 and Cifar10 datasets. Using this exemplar application, the thesis discusses and measures efficiency of techniques used in CNNs. Results show that the convolutional networks without advanced extensions are able to reach a 80\% recognition accuracy on Cifar-10 and a 37\% accuracy on Caltech101.
Detailed record
Simple Image Composition Game for Annotations
 Juřička, Karel ; Beran, Vítězslav (referee) ; Smrž, Pavel (advisor)
This bachelor thesis is dedicated to process of creating web game application for the image annotations. Before images are composed to gameboard, it's necessary to select and identify object. With the architecture consisting of the game client and the server more players can play together in same game.The basic system is designed to allow implementations of various gaming applications, working with prepared annotation tool. 
Detailed record
Deep Learning for Image Recognition
 Munzar, Milan ; Kolář, Martin (referee) ; Hradiš, Michal (advisor)
Neural networks are one of the state-of-the-art models for machine learning today. One may found them in autonomous robot systems, object and speech recognition, prediction and many others AI tasks. The thesis describes this model and its extension which is used in an object recognition. Then explains an application of a convolutional neural networks(CNNs) in an image recognition on Caltech101 and Cifar10 datasets. Using this exemplar application, the thesis discusses and measures efficiency of techniques used in CNNs. Results show that the convolutional networks without advanced extensions are able to reach a 80\% recognition accuracy on Cifar-10 and a 37\% accuracy on Caltech101.
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