A Super-Resolution Algorithm using Patch Structure Matching
碩士 === 國立成功大學 === 電腦與通信工程研究所 === 101 === The main purpose of super resolution technology is to generate high-resolution (HR) images from low-resolution (LR) images. In this thesis, a vector quantization (VQ) based super resolution algorithm is proposed to produce HR images. Firstly, the initial blur...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2013
|
Online Access: | http://ndltd.ncl.edu.tw/handle/76449690143335516424 |
id |
ndltd-TW-101NCKU5652020 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-101NCKU56520202016-03-18T04:41:51Z http://ndltd.ncl.edu.tw/handle/76449690143335516424 A Super-Resolution Algorithm using Patch Structure Matching 利用區塊結構比對之超解析演算法 Peng-YuChen 陳鵬宇 碩士 國立成功大學 電腦與通信工程研究所 101 The main purpose of super resolution technology is to generate high-resolution (HR) images from low-resolution (LR) images. In this thesis, a vector quantization (VQ) based super resolution algorithm is proposed to produce HR images. Firstly, the initial blurred HR images are generated by a simple interpolation method. Furthermore, the high-frequency information images are obtained by searching the pre-trained codebook to find the best matching codevector. The final enlarged images are generated by combining the initial blurred images and the high-frequency information images. In order to predict the high-frequency information accurately, a patch structure matching method is proposed in the codebook searching phase. Besides, LBG training algorithm is also modified to adapt to the patch structure matching. Experimental results show that the proposed algorithm produces HR images with better visual quality. Shen-Chuan Tai 戴顯權 2013 學位論文 ; thesis 53 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立成功大學 === 電腦與通信工程研究所 === 101 === The main purpose of super resolution technology is to generate high-resolution (HR) images from low-resolution (LR) images. In this thesis, a vector quantization (VQ) based super resolution algorithm is proposed to produce HR images. Firstly, the initial blurred HR images are generated by a simple interpolation method. Furthermore, the high-frequency information images are obtained by searching the pre-trained codebook to find the best matching codevector. The final enlarged images are generated by combining the initial blurred images and the high-frequency information images. In order to predict the high-frequency information accurately, a patch structure matching method is proposed in the codebook searching phase. Besides, LBG training algorithm is also modified to adapt to the patch structure matching. Experimental results show that the proposed algorithm produces HR images with better visual quality.
|
author2 |
Shen-Chuan Tai |
author_facet |
Shen-Chuan Tai Peng-YuChen 陳鵬宇 |
author |
Peng-YuChen 陳鵬宇 |
spellingShingle |
Peng-YuChen 陳鵬宇 A Super-Resolution Algorithm using Patch Structure Matching |
author_sort |
Peng-YuChen |
title |
A Super-Resolution Algorithm using Patch Structure Matching |
title_short |
A Super-Resolution Algorithm using Patch Structure Matching |
title_full |
A Super-Resolution Algorithm using Patch Structure Matching |
title_fullStr |
A Super-Resolution Algorithm using Patch Structure Matching |
title_full_unstemmed |
A Super-Resolution Algorithm using Patch Structure Matching |
title_sort |
super-resolution algorithm using patch structure matching |
publishDate |
2013 |
url |
http://ndltd.ncl.edu.tw/handle/76449690143335516424 |
work_keys_str_mv |
AT pengyuchen asuperresolutionalgorithmusingpatchstructurematching AT chénpéngyǔ asuperresolutionalgorithmusingpatchstructurematching AT pengyuchen lìyòngqūkuàijiégòubǐduìzhīchāojiěxīyǎnsuànfǎ AT chénpéngyǔ lìyòngqūkuàijiégòubǐduìzhīchāojiěxīyǎnsuànfǎ AT pengyuchen superresolutionalgorithmusingpatchstructurematching AT chénpéngyǔ superresolutionalgorithmusingpatchstructurematching |
_version_ |
1718207382577741824 |