|
|
Content Based Photo Search
Dvořák, Pavel ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis covers design and practical realization of a tool for quick search in large image databases, containing from tens to hundreds of thousands photos, based on image similarity. The proposed technique uses various methods of descriptor extraction, creation of Bag of Words dictionaries and methods of storing image data in PostgreSQL database. Further, experiments with the implemented software were carried out to evaluate the search time effectivity and scaling possibilities of the design solution.
|
|
|
Image Database Query by Example
Dobrotka, Matúš ; Hradiš, Michal (referee) ; Veľas, Martin (advisor)
This thesis deals with content-based image retrieval. The objective of the thesis is to develop an application, which will compare different approaches of image retrieval. First basic approach consists of keypoints detection, local features extraction and creating a visual vocabulary by clustering algorithm - k-means. Using this visual vocabulary is computed histogram of occurrence count of visual words - Bag of Words (BoW), which globally represents an image. After applying an appropriate metrics, it follows finding similar images. Second approach uses deep convolutional neural networks (DCNN) to extract feature vectors. These vectors are used to create a visual vocabulary, which is used to calculate BoW. Next procedure is then similar to the first approach. Third approach uses extracted vectors from DCNN as BoW vectors. It is followed by applying an appropriate metrics and finding similar images. The conclusion describes mentioned approaches, experiments and the final evaluation.
|
|
|
Photo Instead of QR Code
Štol, Jakub ; Španěl, Michal (referee) ; Beran, Vítězslav (advisor)
This thesis focuses on create system, which according to user's photo search the most similar photo in dataset a display additional information about this photo such as photo content, place and author. The system is primarily focused on fields, where the user wants to use this system and get information, which he want such as museums or galleries. Theoretical part focuses on concept system according to methods of image processing and searching image in the dataset. Practical part focuses on concept creating web application, which display more information about the photo via web interface.
|
|
|
Photo Instead of QR Code
Štol, Jakub ; Španěl, Michal (referee) ; Beran, Vítězslav (advisor)
This thesis focuses on create system, which according to user's photo search the most similar photo in dataset a display additional information about this photo such as photo content, place and author. The system is primarily focused on fields, where the user wants to use this system and get information, which he want such as museums or galleries. Theoretical part focuses on concept system according to methods of image processing and searching image in the dataset. Practical part focuses on concept creating web application, which display more information about the photo via web interface.
|
|
|
Photo Catalog
Tomeš, Jiří ; Kopecký, Michal (advisor) ; Martínek, Vladislav (referee)
The thesis describes design and implementation of photo organiser. The emphasis is put on simplicity, platform independence and on ability to burn the program together with photos and collected metadata on CD or DVD. The user can assign photos to own tag hierarchies. Search is then possible not only by defined tags, but also by basic and EXIF information stored within photographs. The application provides a flexible environment that can be customised to your needs.
|
|
|
Content Based Photo Search
Dvořák, Pavel ; Beran, Vítězslav (referee) ; Španěl, Michal (advisor)
This thesis covers design and practical realization of a tool for quick search in large image databases, containing from tens to hundreds of thousands photos, based on image similarity. The proposed technique uses various methods of descriptor extraction, creation of Bag of Words dictionaries and methods of storing image data in PostgreSQL database. Further, experiments with the implemented software were carried out to evaluate the search time effectivity and scaling possibilities of the design solution.
|
|
|
Image Database Query by Example
Dobrotka, Matúš ; Hradiš, Michal (referee) ; Veľas, Martin (advisor)
This thesis deals with content-based image retrieval. The objective of the thesis is to develop an application, which will compare different approaches of image retrieval. First basic approach consists of keypoints detection, local features extraction and creating a visual vocabulary by clustering algorithm - k-means. Using this visual vocabulary is computed histogram of occurrence count of visual words - Bag of Words (BoW), which globally represents an image. After applying an appropriate metrics, it follows finding similar images. Second approach uses deep convolutional neural networks (DCNN) to extract feature vectors. These vectors are used to create a visual vocabulary, which is used to calculate BoW. Next procedure is then similar to the first approach. Third approach uses extracted vectors from DCNN as BoW vectors. It is followed by applying an appropriate metrics and finding similar images. The conclusion describes mentioned approaches, experiments and the final evaluation.
|
guest ::
