Improvement of Low Quality Image
碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 100 === Currently, many devices are available to capture images. The image color is usually distorted if a low cost device is adapted. This thesis explores an approach of improving the low-quality digital images such as cell phone cameras through correction of distorte...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2012
|
Online Access: | http://ndltd.ncl.edu.tw/handle/77738125267770762316 |
id |
ndltd-TW-100NTOU5394037 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-100NTOU53940372015-10-13T23:28:41Z http://ndltd.ncl.edu.tw/handle/77738125267770762316 Improvement of Low Quality Image 低品質影像之畫質改良 Jia-Hui Chu 朱家慧 碩士 國立臺灣海洋大學 資訊工程學系 100 Currently, many devices are available to capture images. The image color is usually distorted if a low cost device is adapted. This thesis explores an approach of improving the low-quality digital images such as cell phone cameras through correction of distorted color images. This thesis proposes a color correction algorithm for the low-quality digital images. The proposed method uses the expectation maximization algorithm (EM algorithm) to obtain the parameters, which assign input images into many defects classes. There are three processing steps for the proposed method. First, global color attributes of the low quality input image are used in a Gaussian mixture model (GMM) framework to classify the input images into M predefined global classes. In the second step, the input image is processed with a non-linear color correction algorithm for each of the M global classes. This color correction algorithm, referred to as RSCC (resolution synthesis color correction), applies a spatially varying color correction, which is determined by the local color attributes of the input image. Last, the outputs of the RSCC predictors are combined using the global classification weights to generate the corrected color image. Zone-Chang Lai 賴榮滄 2012 學位論文 ; thesis 52 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立臺灣海洋大學 === 資訊工程學系 === 100 === Currently, many devices are available to capture images. The image color is usually distorted if a low cost device is adapted. This thesis explores an approach of improving the low-quality digital images such as cell phone cameras through correction of distorted color images.
This thesis proposes a color correction algorithm for the low-quality digital images. The proposed method uses the expectation maximization algorithm (EM algorithm) to obtain the parameters, which assign input images into many defects classes. There are three processing steps for the proposed method. First, global color attributes of the low quality input image are used in a Gaussian mixture model (GMM) framework to classify the input images into M predefined global classes. In the second step, the input image is processed with a non-linear color correction algorithm for each of the M global classes. This color correction algorithm, referred to as RSCC (resolution synthesis color correction), applies a spatially varying color correction, which is determined by the local color attributes of the input image. Last, the outputs of the RSCC predictors are combined using the global classification weights to generate the corrected color image.
|
author2 |
Zone-Chang Lai |
author_facet |
Zone-Chang Lai Jia-Hui Chu 朱家慧 |
author |
Jia-Hui Chu 朱家慧 |
spellingShingle |
Jia-Hui Chu 朱家慧 Improvement of Low Quality Image |
author_sort |
Jia-Hui Chu |
title |
Improvement of Low Quality Image |
title_short |
Improvement of Low Quality Image |
title_full |
Improvement of Low Quality Image |
title_fullStr |
Improvement of Low Quality Image |
title_full_unstemmed |
Improvement of Low Quality Image |
title_sort |
improvement of low quality image |
publishDate |
2012 |
url |
http://ndltd.ncl.edu.tw/handle/77738125267770762316 |
work_keys_str_mv |
AT jiahuichu improvementoflowqualityimage AT zhūjiāhuì improvementoflowqualityimage AT jiahuichu dīpǐnzhìyǐngxiàngzhīhuàzhìgǎiliáng AT zhūjiāhuì dīpǐnzhìyǐngxiàngzhīhuàzhìgǎiliáng |
_version_ |
1718085528896667648 |