National Repository of Grey Literature 10 records found  Search took 0.00 seconds. 
Detection of characteristic facial features in tele-X-ray image
Hruška, Martin ; Přinosil, Jiří (referee) ; Mišurec, Jiří (advisor)
Description cephalometric images and the characteristic points on the skull for cephalometric analysis. Theoretical analysis of digital image editing and image before the actual detection. The range of possible methods for determining the characteristic points on the face. Experimental verification of edge detectors, Hu moments with neural networks and Haar wavelets with Viola-Jones detector.
OCR module for recognition of letters and numbers
Kapusta, Ján ; Přinosil, Jiří (referee) ; Sigmund, Milan (advisor)
This paper describes basic methods used for optical character recognition. It explains all procedures of recognition from adjustment of picture, processing, feature extracting to matching algorithms. It compares methods and algorithms for character recognition obtained graphically distorted or else modified image so-called „captcha“, used in present. Further it compares method based on invariant moments and neural network as final classifier and method based on correlation between normals and recognized characters.
Short-Term Forecast Based on Image of Sky
Volf, Martin ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
The bachelor's thesis submitted is dedicated to weather forecast based only on a video stream. At first, basic weather information which the sky can provide are presented. Cloud types including their properties and methods which the sky can most efficiently describe are dealt with. At second, basic circumstances between weather information are discussed. The objective of this work is to prove accuracy of the methods used for gaining data from the video stream and to find out whether it could be possible to use them for forecasting the rain, air humidity and sunshine for the period of time one hour later.
Game with Hand Gesture Control
Baštek, Jozef ; Žák, Pavel (referee) ; Hradiš, Michal (advisor)
This paper is intended for computer vision usage as a way of human-computer interacion. It covers design and implementation of interface for game controlling by hand gestures and movements, that are captured by camera. It describes and evaluates image segmentation algorithms (background subtraction, thresholding, Bayes' theorem, gaussian model) as well as hand gesture classification algorithms (knowledge-based classification, Hu invariant moments and K-nearest neighours). Implementation includes machanical contruction of camera holder and 3D FPS game as a interface usage demonstration.
Image descriptors
Dula, Marek ; Druckmüller, Miloslav (referee) ; Procházková, Jana (advisor)
Image processing is a growing industry that makes extensive use of image descriptors to analyze objects in a photo. Nowadays, practically all photos go through Image processing, for example for our convenience when browsing digital photos or for our safety, but also for marketing purposes.
Short-Term Forecast Based on Image of Sky
Volf, Martin ; Španěl, Michal (referee) ; Hradiš, Michal (advisor)
The bachelor's thesis submitted is dedicated to weather forecast based only on a video stream. At first, basic weather information which the sky can provide are presented. Cloud types including their properties and methods which the sky can most efficiently describe are dealt with. At second, basic circumstances between weather information are discussed. The objective of this work is to prove accuracy of the methods used for gaining data from the video stream and to find out whether it could be possible to use them for forecasting the rain, air humidity and sunshine for the period of time one hour later.
Game with Hand Gesture Control
Baštek, Jozef ; Žák, Pavel (referee) ; Hradiš, Michal (advisor)
This paper is intended for computer vision usage as a way of human-computer interacion. It covers design and implementation of interface for game controlling by hand gestures and movements, that are captured by camera. It describes and evaluates image segmentation algorithms (background subtraction, thresholding, Bayes' theorem, gaussian model) as well as hand gesture classification algorithms (knowledge-based classification, Hu invariant moments and K-nearest neighours). Implementation includes machanical contruction of camera holder and 3D FPS game as a interface usage demonstration.
Detection of characteristic facial features in tele-X-ray image
Hruška, Martin ; Přinosil, Jiří (referee) ; Mišurec, Jiří (advisor)
Description cephalometric images and the characteristic points on the skull for cephalometric analysis. Theoretical analysis of digital image editing and image before the actual detection. The range of possible methods for determining the characteristic points on the face. Experimental verification of edge detectors, Hu moments with neural networks and Haar wavelets with Viola-Jones detector.
OCR module for recognition of letters and numbers
Kapusta, Ján ; Přinosil, Jiří (referee) ; Sigmund, Milan (advisor)
This paper describes basic methods used for optical character recognition. It explains all procedures of recognition from adjustment of picture, processing, feature extracting to matching algorithms. It compares methods and algorithms for character recognition obtained graphically distorted or else modified image so-called „captcha“, used in present. Further it compares method based on invariant moments and neural network as final classifier and method based on correlation between normals and recognized characters.
Image Recognition, Static Hand Gesture Recognition Software
KAPOUN, Jan
This thesis deals with recognition of static hand gestures in a real-time video feed. It is an accompanying paper to the application that I created. Within the framework of this thesis, you will find necessary algorithms for background segmentation and image recognition that were implemented in the application. This thesis also describes problems that I came across when writing the software and also some dead-ends I found when trying to choose the best algorithms. The application source code along with images and a video presentation can be downloaded here: http://jankapoun.own.cz/soft_AI.php

Interested in being notified about new results for this query?
Subscribe to the RSS feed.