Optimized Anaglyph Colorization
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 100 === The anaglyph image, primarily used for red-cyan eyeglasses, has the following flaws: it only reproduces partial colors, often brings retinal rivalry and ghosting to viewers. In this work, we propose a method for anaglyph image re-coloring to enhance the color p...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2012
|
Online Access: | http://ndltd.ncl.edu.tw/handle/76359378881590498341 |
id |
ndltd-TW-100NTU05392128 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-100NTU053921282015-10-13T21:50:44Z http://ndltd.ncl.edu.tw/handle/76359378881590498341 Optimized Anaglyph Colorization 利用最佳化方法於紅藍立體影像全彩化 Chih-Lin Zeng 曾志霖 碩士 國立臺灣大學 資訊工程學研究所 100 The anaglyph image, primarily used for red-cyan eyeglasses, has the following flaws: it only reproduces partial colors, often brings retinal rivalry and ghosting to viewers. In this work, we propose a method for anaglyph image re-coloring to enhance the color perception and reduce the visual fatigue. When an anaglyph image is given, a corresponding stereo pair can be derived. The goal of this work is to restore lost colors of the stereo pair and thus convert the anaglyph into full-color 3D contents. Our main idea is to transfer existing information of the images to each other and we formulate this problem as a labeling problem. We integrate terms of pixel matching, color correlation, and spatial smoothness into the proposed cost function. Graph cuts algorithm is also utilized to solve for the local minimum. We also proposed a progressive restoration scheme due to the restoration difficulty of right and left eye image. Finally, we compare our results with the input anaglyph and the results of a disparity-based (na‥ıve color transfer method) color restoration. Our user study shows that the results from our method improve the viewing experience for anaglyph contents. 歐陽明 2012 學位論文 ; thesis 40 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 100 === The anaglyph image, primarily used for red-cyan eyeglasses, has the following flaws: it only reproduces partial colors, often brings retinal rivalry and ghosting to viewers. In this work, we propose a method for anaglyph image re-coloring to enhance the color perception and reduce the visual fatigue. When an anaglyph image is given, a corresponding stereo pair can be derived. The goal of this work is to restore lost colors of the stereo pair and thus
convert the anaglyph into full-color 3D contents. Our main idea is to transfer existing information of the images to each other and we formulate this problem as a labeling problem. We integrate terms of pixel matching, color correlation, and spatial smoothness into the proposed cost function. Graph cuts algorithm is also utilized to solve for the local minimum. We also proposed a progressive restoration scheme due to the restoration difficulty of right and left eye image. Finally, we compare our results with the input anaglyph and the results of a disparity-based (na‥ıve color transfer method) color restoration.
Our user study shows that the results from our method improve the viewing experience for anaglyph contents.
|
author2 |
歐陽明 |
author_facet |
歐陽明 Chih-Lin Zeng 曾志霖 |
author |
Chih-Lin Zeng 曾志霖 |
spellingShingle |
Chih-Lin Zeng 曾志霖 Optimized Anaglyph Colorization |
author_sort |
Chih-Lin Zeng |
title |
Optimized Anaglyph Colorization |
title_short |
Optimized Anaglyph Colorization |
title_full |
Optimized Anaglyph Colorization |
title_fullStr |
Optimized Anaglyph Colorization |
title_full_unstemmed |
Optimized Anaglyph Colorization |
title_sort |
optimized anaglyph colorization |
publishDate |
2012 |
url |
http://ndltd.ncl.edu.tw/handle/76359378881590498341 |
work_keys_str_mv |
AT chihlinzeng optimizedanaglyphcolorization AT céngzhìlín optimizedanaglyphcolorization AT chihlinzeng lìyòngzuìjiāhuàfāngfǎyúhónglánlìtǐyǐngxiàngquáncǎihuà AT céngzhìlín lìyòngzuìjiāhuàfāngfǎyúhónglánlìtǐyǐngxiàngquáncǎihuà |
_version_ |
1718069398616408064 |