|
|
Automatic Selection of Representative Pictures
Bartoš, Peter ; Svoboda, Pavel (referee) ; Polok, Lukáš (advisor)
There are billions of photos on the internet and as the size of these digital repositories grows, finding target picture becomes more and more difficult. To increase the informational quality of photo albums we propose a new method that selects representative pictures from a group of photographs using computer vision algorithms. The aim of this study is to analyze the issues about image features, image similarity, object clustering and examine the specific characteristics of photographs. Tests show that there is no universal image descriptor that can easily simulate the process of clustering performed by human vision. The thesis proposes a hybrid algorithm that combines the advantages of selected features together using a specialized multiple-step clustering algorithm. The key idea of the process is that the frequently photographed objects are more likely to be representative. Thus, with a random selection from the largest photo clusters certain representative photos are obtained. This selection is further enhanced on the basis of optimization, where photos with better photographic properties are being preferred.
|
|
|
Android Application with Content Based Image Retrieval
Ligač, Filip ; Angelov, Michael (referee) ; Bartoš, Peter (advisor)
This thesis deals with the development on the mobile platform Android and algorithms for comparing images. The work identifies different ways of getting information and representation of these images and comparing them together. The theoretical part describes all necessary tools which are needed for development and a little description of their functionality. The practical part is devoted to describing the implementation of the application which detects hockey cards according to the photo taken by user. This part also contains testing results with evaluating success of each method for detection and their usefulness on mobile platform. In the conclusion there is a review of overall results and possible upgrades of the application.
|
|
|
Similarity search in image collections
Navrátil, Lukáš ; Bartoš, Tomáš (advisor) ; Skopal, Tomáš (referee)
Detection of keypoints from image and their characterization by using descriptors is common technique in some branches of computer vision. The goal of this thesis is to explore and confirm usability of this technique for similarity retrieval in image collections. For this purpose it will be created a web application used for collecting ratings of similarity from users which will be subsequently compared with results computed by the implementation of SURF algorithm, one of algorithms used for detection and description of image keypoints. It will also be discussed the impact of metrics and parameters influencing results of computation of similarity between images and it will be made an effort to find settings for which computed results will be closest to user's similarity perception.
|
|
|
Similarity search in image collections
Navrátil, Lukáš ; Bartoš, Tomáš (advisor) ; Skopal, Tomáš (referee)
Detection of keypoints from image and their characterization by using descriptors is common technique in some branches of computer vision. The goal of this thesis is to explore and confirm usability of this technique for similarity retrieval in image collections. For this purpose it will be created a web application used for collecting ratings of similarity from users which will be subsequently compared with results computed by the implementation of SURF algorithm, one of algorithms used for detection and description of image keypoints. It will also be discussed the impact of metrics and parameters influencing results of computation of similarity between images and it will be made an effort to find settings for which computed results will be closest to user's similarity perception.
|
|
|
Android Application with Content Based Image Retrieval
Ligač, Filip ; Angelov, Michael (referee) ; Bartoš, Peter (advisor)
This thesis deals with the development on the mobile platform Android and algorithms for comparing images. The work identifies different ways of getting information and representation of these images and comparing them together. The theoretical part describes all necessary tools which are needed for development and a little description of their functionality. The practical part is devoted to describing the implementation of the application which detects hockey cards according to the photo taken by user. This part also contains testing results with evaluating success of each method for detection and their usefulness on mobile platform. In the conclusion there is a review of overall results and possible upgrades of the application.
|
|
|
Automatic Selection of Representative Pictures
Bartoš, Peter ; Svoboda, Pavel (referee) ; Polok, Lukáš (advisor)
There are billions of photos on the internet and as the size of these digital repositories grows, finding target picture becomes more and more difficult. To increase the informational quality of photo albums we propose a new method that selects representative pictures from a group of photographs using computer vision algorithms. The aim of this study is to analyze the issues about image features, image similarity, object clustering and examine the specific characteristics of photographs. Tests show that there is no universal image descriptor that can easily simulate the process of clustering performed by human vision. The thesis proposes a hybrid algorithm that combines the advantages of selected features together using a specialized multiple-step clustering algorithm. The key idea of the process is that the frequently photographed objects are more likely to be representative. Thus, with a random selection from the largest photo clusters certain representative photos are obtained. This selection is further enhanced on the basis of optimization, where photos with better photographic properties are being preferred.
|
guest ::
