Thesis (Selection of subject)Thesis (Selection of subject)(version: 368)
Thesis details
   Login via CAS
The Impact of Image Resolution on the Precision of Content-based Retrieval
Thesis title in Czech: Vliv rozlišení obrázku na přesnost vyhledávání podle obsahu
Thesis title in English: The Impact of Image Resolution on the Precision of Content-based Retrieval
Key words: Podobnostní vyhledávání, vyhledávání v obrázcích, rozlišení obrázku, signatury, SIFT, SURF, VLAD, BoW
English key words: Similarity search, image retrieval, image resolution, feature signatures, SIFT, SURF, VLAD, BoW
Academic year of topic announcement: 2014/2015
Thesis type: diploma thesis
Thesis language: angličtina
Department: Department of Software Engineering (32-KSI)
Supervisor: doc. RNDr. Jakub Lokoč, Ph.D.
Author: hidden - assigned and confirmed by the Study Dept.
Date of registration: 19.02.2015
Date of assignment: 19.02.2015
Confirmed by Study dept. on: 10.03.2015
Date and time of defence: 09.09.2015 09:30
Date of electronic submission:30.07.2015
Date of submission of printed version:31.07.2015
Date of proceeded defence: 09.09.2015
Opponents: prof. RNDr. Tomáš Skopal, Ph.D.
The goal of this thesis is to compare two content-based image retrieval approaches - bag of features based models and feature signature based models. Author should evaluate retrieval precision of given similarity models depending on resolution of input images and try to find optimal configuration of the models for different image resolutions and data sets. Experiments should be performed on several different benchmark datasets commonly used in image retrieval. The main comparison should be made between signature based model based on PCT descriptors and SQFD distance and BoW based models with SIFT/SURF descriptors.
Introduction to Information Retrieval
C. D. Manning, P. Raghavan, and H. Schutze. Cambridge University Press, 2008

Distinctive image features from scale-invariant keypoints
David G. Lowe. International Journal of Computer Vision, 2004

Aggregating local images descriptors into compact codes
H. Jégou, F. Perronnin, M. Douze, J. Sanchez, P. Pérez and C. Schmid. IEEE Transactions on
Pattern Analysis and Machine Intelligence, 2012

Object retrieval with large vocabularies and fast spatial matching
J. Philbin, O. Chum, M. Isard, J. Sivic, A. Zisserman. CVPR, 2007

Visual Image Search: Feature Signatures or/and Global Descriptors
J. Lokoč, D. Novák, M. Batko, T. Skopal. SISAP, 2012
Charles University | Information system of Charles University |