Image representation and reconstruction by compositing Gaussian ellipses
Abstract In this paper, a method of stroke‐based rendering is proposed for image representation and reconstruction. The proposed method involves compositing a set of ellipses that greatly vary in location, size, rotation angle, color, and opacity. This study proves that alpha compositing is differen...
Main Author: | |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2024-02-01
|
Series: | IET Image Processing |
Subjects: | |
Online Access: | https://doi.org/10.1049/ipr2.12964 |
_version_ | 1797333772941656064 |
---|---|
author | Chang‐Chieh Cheng |
author_facet | Chang‐Chieh Cheng |
author_sort | Chang‐Chieh Cheng |
collection | DOAJ |
description | Abstract In this paper, a method of stroke‐based rendering is proposed for image representation and reconstruction. The proposed method involves compositing a set of ellipses that greatly vary in location, size, rotation angle, color, and opacity. This study proves that alpha compositing is differentiable if a two‐dimensional Gaussian function is used to draw a solid ellipse. The gradient method can then be employed for automatically identifying the parameters of each ellipse such that the difference between the input image and the composited image is minimized. Experimental results indicate that the proposed method can represent various types of images including portraits, landscapes, buildings, street scenes, artificial objects, medical images etc. The proposed method can particularly render the most details and significant features of an input image with fewer strokes compared to other stroke‐based rendering algorithms. This study also demonstrates that the proposed method can be applied in painting style simulation and sparse‐view computed tomography imaging. |
first_indexed | 2024-03-08T08:09:56Z |
format | Article |
id | doaj.art-cde0d85cd96e404c8918df06ffe642ba |
institution | Directory Open Access Journal |
issn | 1751-9659 1751-9667 |
language | English |
last_indexed | 2024-03-08T08:09:56Z |
publishDate | 2024-02-01 |
publisher | Wiley |
record_format | Article |
series | IET Image Processing |
spelling | doaj.art-cde0d85cd96e404c8918df06ffe642ba2024-02-02T09:31:01ZengWileyIET Image Processing1751-96591751-96672024-02-0118249350610.1049/ipr2.12964Image representation and reconstruction by compositing Gaussian ellipsesChang‐Chieh Cheng0Information Technology Service Center National Yang Ming Chiao Tung University Hsinchu TaiwanAbstract In this paper, a method of stroke‐based rendering is proposed for image representation and reconstruction. The proposed method involves compositing a set of ellipses that greatly vary in location, size, rotation angle, color, and opacity. This study proves that alpha compositing is differentiable if a two‐dimensional Gaussian function is used to draw a solid ellipse. The gradient method can then be employed for automatically identifying the parameters of each ellipse such that the difference between the input image and the composited image is minimized. Experimental results indicate that the proposed method can represent various types of images including portraits, landscapes, buildings, street scenes, artificial objects, medical images etc. The proposed method can particularly render the most details and significant features of an input image with fewer strokes compared to other stroke‐based rendering algorithms. This study also demonstrates that the proposed method can be applied in painting style simulation and sparse‐view computed tomography imaging.https://doi.org/10.1049/ipr2.12964computerised tomographygradient methodsimage reconstructionimage representationrendering (computer graphics) |
spellingShingle | Chang‐Chieh Cheng Image representation and reconstruction by compositing Gaussian ellipses IET Image Processing computerised tomography gradient methods image reconstruction image representation rendering (computer graphics) |
title | Image representation and reconstruction by compositing Gaussian ellipses |
title_full | Image representation and reconstruction by compositing Gaussian ellipses |
title_fullStr | Image representation and reconstruction by compositing Gaussian ellipses |
title_full_unstemmed | Image representation and reconstruction by compositing Gaussian ellipses |
title_short | Image representation and reconstruction by compositing Gaussian ellipses |
title_sort | image representation and reconstruction by compositing gaussian ellipses |
topic | computerised tomography gradient methods image reconstruction image representation rendering (computer graphics) |
url | https://doi.org/10.1049/ipr2.12964 |
work_keys_str_mv | AT changchiehcheng imagerepresentationandreconstructionbycompositinggaussianellipses |