COLOR IMAGE QUALITY ASSESSMENT BASED ON BINARY FEATURES OBTAINED FROM K-MEANS CLUSTERING CLASSIFICATION
碩士 === 大同大學 === 通訊工程研究所 === 102 === Most of image quality assessment (IQA) methods only concern about gray image, and don’t make use of image color information sufficiently at present. A method for reduced-reference color image quality assessment is proposed, which based on structural features and e...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2014
|
Online Access: | http://ndltd.ncl.edu.tw/handle/42jvpj |
id |
ndltd-TW-102TTU05650021 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-102TTU056500212019-05-15T21:32:55Z http://ndltd.ncl.edu.tw/handle/42jvpj COLOR IMAGE QUALITY ASSESSMENT BASED ON BINARY FEATURES OBTAINED FROM K-MEANS CLUSTERING CLASSIFICATION 基於K-means分群方法擷取二元特徵之彩色影像品質評估 Pin-yuan Hsieh 謝秉原 碩士 大同大學 通訊工程研究所 102 Most of image quality assessment (IQA) methods only concern about gray image, and don’t make use of image color information sufficiently at present. A method for reduced-reference color image quality assessment is proposed, which based on structural features and efficiently uses the color information. The structure information inherent in three-dimensional (3D) color signals can be obtained from K-means clustering classification. The final image quality assessment is defined by the weighted combination of three components. To verify the validity of the proposed metric is evaluated against a large amount of test images in LIVE database and compared with that of the famous Structural Similarity Measure for Color Image (CMSSIM). The experiments show that the proposed objective method has a good coincidence with the subjective perception, and can reflect the image quality effectively. Chun-Hsien Chou 周俊賢 2014 學位論文 ; thesis 56 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 大同大學 === 通訊工程研究所 === 102 === Most of image quality assessment (IQA) methods only concern about gray image, and don’t make use of image color information sufficiently at present. A method for reduced-reference color image quality assessment is proposed, which based on structural features and efficiently uses the color information. The structure information inherent in three-dimensional (3D) color signals can be obtained from K-means clustering classification. The final image quality assessment is defined by the weighted combination of three components. To verify the validity of the proposed metric is evaluated against a large amount of test images in LIVE database and compared with that of the famous Structural Similarity Measure for Color Image (CMSSIM). The experiments show that the proposed objective method has a good coincidence with the subjective perception, and can reflect the image quality effectively.
|
author2 |
Chun-Hsien Chou |
author_facet |
Chun-Hsien Chou Pin-yuan Hsieh 謝秉原 |
author |
Pin-yuan Hsieh 謝秉原 |
spellingShingle |
Pin-yuan Hsieh 謝秉原 COLOR IMAGE QUALITY ASSESSMENT BASED ON BINARY FEATURES OBTAINED FROM K-MEANS CLUSTERING CLASSIFICATION |
author_sort |
Pin-yuan Hsieh |
title |
COLOR IMAGE QUALITY ASSESSMENT BASED ON BINARY FEATURES OBTAINED FROM K-MEANS CLUSTERING CLASSIFICATION |
title_short |
COLOR IMAGE QUALITY ASSESSMENT BASED ON BINARY FEATURES OBTAINED FROM K-MEANS CLUSTERING CLASSIFICATION |
title_full |
COLOR IMAGE QUALITY ASSESSMENT BASED ON BINARY FEATURES OBTAINED FROM K-MEANS CLUSTERING CLASSIFICATION |
title_fullStr |
COLOR IMAGE QUALITY ASSESSMENT BASED ON BINARY FEATURES OBTAINED FROM K-MEANS CLUSTERING CLASSIFICATION |
title_full_unstemmed |
COLOR IMAGE QUALITY ASSESSMENT BASED ON BINARY FEATURES OBTAINED FROM K-MEANS CLUSTERING CLASSIFICATION |
title_sort |
color image quality assessment based on binary features obtained from k-means clustering classification |
publishDate |
2014 |
url |
http://ndltd.ncl.edu.tw/handle/42jvpj |
work_keys_str_mv |
AT pinyuanhsieh colorimagequalityassessmentbasedonbinaryfeaturesobtainedfromkmeansclusteringclassification AT xièbǐngyuán colorimagequalityassessmentbasedonbinaryfeaturesobtainedfromkmeansclusteringclassification AT pinyuanhsieh jīyúkmeansfēnqúnfāngfǎxiéqǔèryuántèzhēngzhīcǎisèyǐngxiàngpǐnzhìpínggū AT xièbǐngyuán jīyúkmeansfēnqúnfāngfǎxiéqǔèryuántèzhēngzhīcǎisèyǐngxiàngpǐnzhìpínggū |
_version_ |
1719117373396484096 |