diplomsko delo
Gorazd Gorup (Author), Matija Marolt (Mentor), Žiga Lesar (Co-mentor)

Abstract

V diplomski nalogi se lotevamo problema samodejnega generiranja prenosnih funkcij za poljubne volumetrične podatke. Proučimo dva pristopa z uporabo strojnega učenja. Prvi pristop vključuje pridobivanje učnih podatkov na podlagi človeške klasifikacije dobrih prenosnih funkcij. Na vhod nevronske mreže podamo volumetrične podatke, izhode pa primerjamo z ugodnimi prenosnimi funkcijami iz učnih podatkov. Drugi pristop obsega računalniško generiranje volumnov in klasificiranje značilnosti v njih. Med učenjem nevronske mreže vizualiziramo volumne z generiranimi prenosnimi funkcijami in učenje usmerjamo s štetjem ustrezno vidnih značilnosti na vizualizacijah. Pristopa primerjamo po uspešnosti in kakovosti generiranih prenosnih funkcij. Prvi pristop trpi zaradi pomanjkanja učnih podatkov in posledičnega pretiranega prileganja, z drugim pristopom pa ni mogoče izvesti učenja, saj cenilna funkcija ni odvedljiva.

Keywords

grafika;volumetrični podatki;prenosne funkcije;VPT;strojno učenje;nevronske mreže;računalništvo in informatika;univerzitetni študij;diplomske naloge;

Data

Language: Slovenian
Year of publishing:
Typology: 2.11 - Undergraduate Thesis
Organization: UL FRI - Faculty of Computer and Information Science
Publisher: [G. Gorup]
UDC: 004.8(043.2)
COBISS: 150448131 Link will open in a new window
Views: 13
Downloads: 6
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Interactive discovery of volumetric data through the use of transfer function galleries
Secondary abstract: In this thesis, we tackle the problem of automatic transfer function generation for volumetric data rendering. We study two methods using machine learning techniques. The first method involves gathering training data through suitable transfer function selection and classification by human users. We use these training transfer functions to optimize a generative neural network. With the second method we take an automated approach of generating volumetric data and labelling generated features, then training neural network by rendering volumes with generated transfer functions, and comparing the feature visibility on visualizations with expected render output. We compare both methods based on learning success and quality of generated transfer functions. The first method suffers from over-fitting due to small amount of training data, while with the second method we show that the training of the network cannot be performed using gradient descent method.
Secondary keywords: graphics;volumetric data;transfer functions;VPT;machine learning;neural networks;computer science;computer and information science;diploma;
Type (COBISS): Bachelor thesis/paper
Study programme: 1000468
Thesis comment: Univ. v Ljubljani, Fak. za računalništvo in informatiko
Pages: 81 str.
ID: 18712105