Thesis Details
Vyhledávání fotografií v databázi podle příkladu
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.
image retrieval, keypoint, SIFT, local features, visual vocabulary, bag of words, clustering, k-means, neural networks, deep convolutional neural networks, convolution
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
@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/" }