diplomsko delo
Abstract
V diplomskem delu smo podrobno raziskali algoritem k-means, ki v kontekstu strojnega učenja spada v skupino algoritmov nenadzorovanega učenja. Proučili smo probleme in možnost iskanja dominantnih barv na digitalni fotografiji z uporabo omenjenega algoritma. Raziskali smo različne barvne modele in iskanje barvnih harmonij. Izdelali smo aplikacijo, ki omogoča fotografiranje (npr. oblačil), iskanje dominantnih barv in določanje različnih barvnih harmonij.
Keywords
strojno učenje;k-means;barvni modeli;dominantne barve;barvne harmonije;diplomske naloge;
Data
Language: |
Slovenian |
Year of publishing: |
2016 |
Typology: |
2.11 - Undergraduate Thesis |
Organization: |
UM FERI - Faculty of Electrical Engineering and Computer Science |
Publisher: |
D. Šnajder |
UDC: |
004.85.021(043.2) |
COBISS: |
19844374
|
Views: |
1076 |
Downloads: |
74 |
Average score: |
0 (0 votes) |
Metadata: |
|
Other data
Secondary language: |
English |
Secondary title: |
USING MACHINE LEARNING METHODS FOR DETERMINING DOMINANT COLOR ON DIGITAL PHOTOGRAPHY |
Secondary abstract: |
In this thesis we carried out a detailed research of k-means algorithm, which in the context of machine learning is classified into the group of unsupervised learning algorithms. We examined the possibilities for determining dominant color in the digital photography using the k-means algorithm. We also researched various color models and how to find color harmonies. In the end, an application was implemented with which the user can take a picture (e.g. of clothing), find dominant colors and determine the color harmonies. |
Secondary keywords: |
machine learning;ak-means;color models;dominant colors;harmonies; |
URN: |
URN:SI:UM: |
Type (COBISS): |
Undergraduate thesis |
Thesis comment: |
Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko, Računalništvo in informatika |
Pages: |
X, 63 f. |
ID: |
9161405 |