Ogrodje za ocenjevanje barve svetila z linearnimi digitalnimi filtri, prilagojenimi na posamezno sliko

Šavc, Martin

| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

First page > Show document

Show document

Title:	Ogrodje za ocenjevanje barve svetila z linearnimi digitalnimi filtri, prilagojenimi na posamezno sliko
Authors:	ID Šavc, Martin (Author) ID Potočnik, Božidar (Mentor) More about this mentor...
Files:	DOK_Savc_Martin_2019.pdf (15,35 MB) MD5: 62F01E38F19E8FBA855EB95B401B1D99 PID: 20.500.12556/dkum/9d187f68-4bc9-436e-a439-669cf04cc34f
Language:	Slovenian
Work type:	Doctoral dissertation
Typology:	2.08 - Doctoral Dissertation
Organization:	FERI - Faculty of Electrical Engineering and Computer Science
Abstract:	V doktorski nalogi raziskujemo problem barvne vztrajnosti oziroma problem ocenjevanja barve uniformne osvetlitve scene na podlagi zajete digitalne slike. Predstavimo posplošitev uveljavljenega ogrodja sivih robov z vpeljavo diskretizacije in operacije konvolucije. Za ocenjevanje osvetlitve z našim ogrodjem predlagamo uporabo filtrov, prilagojenih vsebini slike. Filtre konstruiramo bodisi z metodo linearne analize osnovnih komponent (PCA) ali z metodo neodvisnih komponent (ICA). Metodo pospešimo tako, da namesto računanja celotne konvolucije uporabimo zgolj vzorce iz slike oziroma uporabimo tehniko podvzorčenja. Skonstruirane prilagojene filtre v nadaljevanju uporabimo tudi kot samostojne metode barvne vztrajnosti v postopku kombiniranja metod. V eksperimentalnem delu opravimo tri večje eksperimente z uveljavljenima javnima evalvacijskima podatkovnima zbirkama Gehler-Shi in NUS. V prvem eksperimentu primerjamo rezultate predlaganih metod z metodami ogrodja sivih robov in drugimi modernimi metodami ocenjevanja osvetlitve. Predlagani metodi barvne vztrajnosti iz našega ogrodja dosegata nižje napake in nižji povprečni rang od drugih metod ogrodja sivih robov. Predlagana metoda kombiniranja rezultatov pa dosega nižje napake od izvorne metode. V drugem eksperimentu primerjamo odpornost naših metod barvne vztrajnosti in metod ogrodja sivih robov na manjše spremembe v sceni. Spremembe simuliramo z rotacijo in translacijo slik. Pokažemo, da je predlagana metoda barvne vztrajnosti odporna na rotacijo scene, kadar v našem ogrodju uporabimo filtre, ki so prilagojeni vsebini slike z analizo osnovnih komponent. Po drugi strani pa so vse primerjane metode občutljive na premike v sceni. V tretjem eksperimentu primerjamo natančnost ocenjevanja osvetlitve, in sicer če v našem predlaganem ogrodju uporabimo bodisi tehniko podvzorčenja oziroma če osvetlitev ocenjujemo s pomočjo konvolucije. Pokažemo statistično značilno razliko v rezultatih med obema pristopoma. Ocena osvetlitve, pridobljena s podvzorčenjem, je bolj natančna od ocene osvetlitve, izračunane s pomočjo konvolucije. S predlaganimi pristopi v tej doktorski disertaciji dobimo primerljive ali boljše rezultate od sodobnih metod barvne vztrajnosti ob nižji računski kompleksnosti.
Keywords:	barvna vztrajnost, ocenjevanje osvetlitve, ogrodje sivih robov, konvolucija, prilagajanje filtrov, analiza osnovnih komponent, PCA, analiza neodvisnih komponent, ICA
Place of publishing:	Maribor
Place of performance:	Maribor
Publisher:	M. Šavc
Year of publishing:	2020
Number of pages:	IX, 115 str.
PID:	20.500.12556/DKUM-75545
UDC:	005.922.52:004.932(043.3)
COBISS.SI-ID:	24866819
NUK URN:	URN:SI:UM:DK:4NS21NZT
Publication date in DKUM:	11.08.2020
Views:	1539
Downloads:	172
Metadata:
Categories:	KTFMB - FERI
:	Copy citation

Average score:	(0 votes)
Your score:	Voting is allowed only for logged in users.
Share:

Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Licences

License:	CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International

Link:	http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:	The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.
Licensing start date:	03.12.2019

Secondary language

Language:	English
Title:	Illuminant estimation framework using linear digital filters adapted to each individual image
Abstract:	A problem of colour constancy or a problem of estimating the colour of scene’s uniform illuminant based on captured digital images, respectively, is researched in this doctoral thesis. A generalisation of the established greyedge framework is presented by introducing a discretization and convolution operation. Filters adapted to image content are proposed for estimating the illuminant with our framework. Filters are constructed using either Principal Component Analysis (PCA) or Independent Component Analysis (ICA). The method is sped up so that instead of calculating the whole convolution only samples from the image are used or subsampling technique is applied, respectively. The constructed adapted filters are also used as individual colour constancy algorithms in a combinational method. Three major experiments on established public evaluation data sets Gegler-Shi and NUS are conducted in the experimental part of this dissertation. Results of the proposed methods are in the first experiment compared to results of the grey-edge framework methods and of other modern illuminant estimation methods. The proposed colour constancy methods from our framework achieve lower errors and lower mean rank than other grey-edge framework methods. The proposed combinational method achieves lower errors than the original method. The robustness of our colour constancy methods and grey-edge framework methods are in the second experiment compared with respect to minor scene changes. The changes are simulated by image rotation and translation. It is demonstrated that the proposed colour constancy method is robust to scene rotation when filters adapted to image content by Principal Component Analysis are used in our framework. On the other hand all compared methods are sensitive to scene translations. Accuracy of the illumination estimation is compared in the third experiment with respect to our proposed framework if either subsampling technique is used or the illuminant is estimated by convolution. A statistically significant difference in results is shown between both approaches. The illuminant estimation obtained by subsampling is more accurate than the illuminant estimation calculated by convolution comparable or better results at lower computational complexity than other modern colour constancy methods.
Keywords:	colour constancy, illuminant estimation, grey edge framework, convolution, filter adaptation, principal component analysis, PCA, independent component analysis, ICA

Comments

Leave comment

You must log in to leave a comment.

Comments (0)

0 - 0 / 0

There are no comments!

Back