Thesis Details

Vyhledávání fotografií v databázi podle příkladu

Bachelor's Thesis Student: Dobrotka Matúš Academic Year: 2014/2015 Supervisor: Veľas Martin, Ing., Ph.D.
English title
Image Database Query by Example
Language
Czech
Abstract

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.

Keywords
image retrieval, keypoint, SIFT, local features, visual vocabulary, bag of words, clustering, k-means, neural networks, deep convolutional neural networks, convolution
Department
Degree Programme
Information Technology
Files
Status
defended, grade D
Date
15 June 2015
Reviewer
Committee
Smrž Pavel, doc. RNDr., Ph.D. (DCGM FIT BUT), předseda
Beran Vítězslav, doc. Ing., Ph.D. (DCGM FIT BUT), člen
Drábek Vladimír, doc. Ing., CSc. (DCSY FIT BUT), člen
Orság Filip, Ing., Ph.D. (DITS FIT BUT), člen
Ryšavý Ondřej, doc. Ing., Ph.D. (DIFS FIT BUT), člen
Citation
DOBROTKA, Matúš. Vyhledávání fotografií v databázi podle příkladu. Brno, 2015. Bachelor's Thesis. Brno University of Technology, Faculty of Information Technology. 2015-06-15. Supervised by Veľas Martin. Available from: https://www.fit.vut.cz/study/thesis/16392/
BibTeX
@bachelorsthesis{FITBT16392,
    author = "Mat\'{u}\v{s} Dobrotka",
    type = "Bachelor's thesis",
    title = "Vyhled\'{a}v\'{a}n\'{i} fotografi\'{i} v datab\'{a}zi podle p\v{r}\'{i}kladu",
    school = "Brno University of Technology, Faculty of Information Technology",
    year = 2015,
    location = "Brno, CZ",
    language = "czech",
    url = "https://www.fit.vut.cz/study/thesis/16392/"
}
Back to top