Thesis (Selection of subject)Thesis (Selection of subject)(version: 368)
Thesis details
   Login via CAS
Comparison of signature-based and semantic similarity models
Thesis title in Czech: Porovnání signaturových a sémantických podobnostních modelů
Thesis title in English: Comparison of signature-based and semantic similarity models
Key words: CNN deskriptory, barevné signatury, vyhledávání v obrázcích, podobnostní vyhledávání
English key words: CNN descriptors, color signatures, image retrieval, similarity search
Academic year of topic announcement: 2015/2016
Thesis type: Bachelor's 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: 05.11.2015
Date of assignment: 05.11.2015
Confirmed by Study dept. on: 24.11.2015
Date and time of defence: 06.09.2017 00:00
Date of electronic submission:24.07.2017
Date of submission of printed version:21.07.2017
Date of proceeded defence: 06.09.2017
Opponents: RNDr. František Mráz, CSc.
 
 
 
Guidelines
Autor práce porovná na několika doménách známé podobnostní modely založené na barevných signaturách a modely založené na sémantických deskriptorech z konvolučních neuronových sítí. Kromě porovnání těchto modelů autor integruje barevné signaturové modely do knihovny open CV a dále navrhne a implementuje .NET knihovnu pro práci s populární konvoluční neuronovou sítí AlexNet.
References
M. Kruliš, J. Lokoč, and T. Skopal. Efficient extraction of clustering-based feature signatures using gpu architectures. Multimedia Tools and Applications, pages 1-33, 2015.

C. Beecks, M. S. Uysal, and T. Seidl. Signature quadratic form distance. In Proceedings of the ACM International Conference on Image and Video Retrieval, CIVR '10, pages 438-445, 2010.

A. Krizhevsky, I. Sutskever, and G. E. Hinton. Imagenet classification with deep convolutional neural networks. Advances in Neural Information Processing Systems 25: Proceedings of 26th Annual Conference on Neural Information
Processing Systems, pages 1097-1105, 2012.

D. Novak, M. Batko, and P. Zezula. Large-scale similarity data management with distributed metric index. Inf. Process. Manage., 48(5):855-872, 2012.

P. Zezula, G. Amato, V. Dohnal, and M. Batko. Similarity Search: The Metric Space Approach, volume 32 of Advances in Database Systems. Springer US, 2006.
 
Charles University | Information system of Charles University | http://www.cuni.cz/UKEN-329.html