Development of Fuzzy Automatic Contrast Enhancement Based onFuzzy C-Means Clustering in CIELAB Color Space
碩士 === 中原大學 === 機械工程研究所 === 103 === Some traditional methods for image contrast enhancement are based on histogram equalization, which however has the drawbacks of productions of visual artifacts or excessive image strengthening due to human adjustment parameters. This thesis proposed a novel method...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2015
|
Online Access: | http://ndltd.ncl.edu.tw/handle/pd4p7n |
id |
ndltd-TW-103CYCU5489026 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-103CYCU54890262019-05-15T22:07:30Z http://ndltd.ncl.edu.tw/handle/pd4p7n Development of Fuzzy Automatic Contrast Enhancement Based onFuzzy C-Means Clustering in CIELAB Color Space 基於在CIELAB 色彩空間中進行行模糊C 均值聚類類的模糊自動化對比度度增強法的研發 Boting-Rex Lin 林柏廷 碩士 中原大學 機械工程研究所 103 Some traditional methods for image contrast enhancement are based on histogram equalization, which however has the drawbacks of productions of visual artifacts or excessive image strengthening due to human adjustment parameters. This thesis proposed a novel method called Fuzzy Automatic Contrast Enhancement (FACE). FACE first performs a fuzzy clustering method to segment an image while the pixels with similar colors in the CIELAB color space are classified into smaller image clusters with similar characteristics. The pixels in each group are then to be spread out away from the center of the belonging cluster in the RBD color space in order to enhance the image contrast but keeping the similarity of pixel colors in the same cluster. A universal contrast enhancement variable ( UCEV) was defined and optimized to maximize the image randomness (i.e. entropy of the image) in order to automatically enhance the image contrast. A more uncongested pixel distribution of the image ensures a greater image contrast. The proposed entropy-maximization method is capable of improving the image quality without man-made control parameters. The fully automated image enhancement process intelligently clusters the pixels with similar color characteristics and is general for the contrast enhancement of images in various color distributions. In this thesis, many images with different color distributions were tested experimentally and the results showed that FACE is capable of avoiding visual artifacts and excessive strengthening. Compared with the traditional histogram equalization method, the proposed method shows higher effectiveness in contrast enhancement and performs better in retaining the colors of the original images. Po-Ting Lin 林柏廷 2015 學位論文 ; thesis 114 zh-TW |
collection |
NDLTD |
language |
zh-TW |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 中原大學 === 機械工程研究所 === 103 === Some traditional methods for image contrast enhancement are based on
histogram equalization, which however has the drawbacks of productions of
visual artifacts or excessive image strengthening due to human adjustment
parameters. This thesis proposed a novel method called Fuzzy Automatic
Contrast Enhancement (FACE). FACE first performs a fuzzy clustering
method to segment an image while the pixels with similar colors in the CIELAB
color space are classified into smaller image clusters with similar characteristics.
The pixels in each group are then to be spread out away from the center of the
belonging cluster in the RBD color space in order to enhance the image contrast
but keeping the similarity of pixel colors in the same cluster. A universal
contrast enhancement variable ( UCEV) was defined and optimized to
maximize the image randomness (i.e. entropy of the image) in order to
automatically enhance the image contrast. A more uncongested pixel
distribution of the image ensures a greater image contrast. The proposed
entropy-maximization method is capable of improving the image quality without
man-made control parameters. The fully automated image enhancement process
intelligently clusters the pixels with similar color characteristics and is general
for the contrast enhancement of images in various color distributions. In this
thesis, many images with different color distributions were tested
experimentally and the results showed that FACE is capable of avoiding visual
artifacts and excessive strengthening. Compared with the traditional histogram equalization method, the proposed method shows higher effectiveness in
contrast enhancement and performs better in retaining the colors of the original
images.
|
author2 |
Po-Ting Lin |
author_facet |
Po-Ting Lin Boting-Rex Lin 林柏廷 |
author |
Boting-Rex Lin 林柏廷 |
spellingShingle |
Boting-Rex Lin 林柏廷 Development of Fuzzy Automatic Contrast Enhancement Based onFuzzy C-Means Clustering in CIELAB Color Space |
author_sort |
Boting-Rex Lin |
title |
Development of Fuzzy Automatic Contrast Enhancement Based onFuzzy C-Means Clustering in CIELAB Color Space |
title_short |
Development of Fuzzy Automatic Contrast Enhancement Based onFuzzy C-Means Clustering in CIELAB Color Space |
title_full |
Development of Fuzzy Automatic Contrast Enhancement Based onFuzzy C-Means Clustering in CIELAB Color Space |
title_fullStr |
Development of Fuzzy Automatic Contrast Enhancement Based onFuzzy C-Means Clustering in CIELAB Color Space |
title_full_unstemmed |
Development of Fuzzy Automatic Contrast Enhancement Based onFuzzy C-Means Clustering in CIELAB Color Space |
title_sort |
development of fuzzy automatic contrast enhancement based onfuzzy c-means clustering in cielab color space |
publishDate |
2015 |
url |
http://ndltd.ncl.edu.tw/handle/pd4p7n |
work_keys_str_mv |
AT botingrexlin developmentoffuzzyautomaticcontrastenhancementbasedonfuzzycmeansclusteringincielabcolorspace AT línbǎitíng developmentoffuzzyautomaticcontrastenhancementbasedonfuzzycmeansclusteringincielabcolorspace AT botingrexlin jīyúzàicielabsècǎikōngjiānzhōngjìnxíngxíngmóhúcjūnzhíjùlèilèidemóhúzìdònghuàduìbǐdùdùzēngqiángfǎdeyánfā AT línbǎitíng jīyúzàicielabsècǎikōngjiānzhōngjìnxíngxíngmóhúcjūnzhíjùlèilèidemóhúzìdònghuàduìbǐdùdùzēngqiángfǎdeyánfā |
_version_ |
1719124833626750976 |