Object Removal Algorithm/Hardware in Image Processing
碩士 === 國立成功大學 === 電機工程學系碩博士班 === 92 === We propose a novel algorithm for object removal in image processing. The proposed algorithm can filter and compensate the unwanted object in digital photograph. For different background texture, we present an object removal algorithm integrates weighted inte...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2004
|
Online Access: | http://ndltd.ncl.edu.tw/handle/07673837842783838507 |
id |
ndltd-TW-092NCKU5442198 |
---|---|
record_format |
oai_dc |
spelling |
ndltd-TW-092NCKU54421982016-06-17T04:16:58Z http://ndltd.ncl.edu.tw/handle/07673837842783838507 Object Removal Algorithm/Hardware in Image Processing 影像處理之物體移除演算法及硬體架構 Hong-Ming Wang 王泓銘 碩士 國立成功大學 電機工程學系碩博士班 92 We propose a novel algorithm for object removal in image processing. The proposed algorithm can filter and compensate the unwanted object in digital photograph. For different background texture, we present an object removal algorithm integrates weighted interpolation and sub-patch texture synthesis to fill the lost region. The sub-patch texture synthesis algorithm can past a line each time and weighted interpolation technique with block-smoothing method. The proposed regular algorithms are suitable to be integrated in smart digital camera due to the regularity. The comparison of previous algorithms is also provided in this thesis. We present a first algorithm used in constrained texture synthesis by regular synthesizing order. The proposed algorithm can achieve better performance, faster computation and regular architecture for VLSI design. Jhing-Fa Wang 王駿發 2004 學位論文 ; thesis 68 en_US |
collection |
NDLTD |
language |
en_US |
format |
Others
|
sources |
NDLTD |
description |
碩士 === 國立成功大學 === 電機工程學系碩博士班 === 92 === We propose a novel algorithm for object removal in image processing. The proposed algorithm can filter and compensate the unwanted object in digital photograph. For different background texture, we present an object removal algorithm integrates weighted interpolation and sub-patch texture synthesis to fill the lost region. The sub-patch texture synthesis algorithm can past a line each time and weighted interpolation technique with block-smoothing method. The proposed regular algorithms are suitable to be integrated in smart digital camera due to the regularity. The comparison of previous algorithms is also provided in this thesis. We present a first algorithm used in constrained texture synthesis by regular synthesizing order. The proposed algorithm can achieve better performance, faster computation and regular architecture for VLSI design.
|
author2 |
Jhing-Fa Wang |
author_facet |
Jhing-Fa Wang Hong-Ming Wang 王泓銘 |
author |
Hong-Ming Wang 王泓銘 |
spellingShingle |
Hong-Ming Wang 王泓銘 Object Removal Algorithm/Hardware in Image Processing |
author_sort |
Hong-Ming Wang |
title |
Object Removal Algorithm/Hardware in Image Processing |
title_short |
Object Removal Algorithm/Hardware in Image Processing |
title_full |
Object Removal Algorithm/Hardware in Image Processing |
title_fullStr |
Object Removal Algorithm/Hardware in Image Processing |
title_full_unstemmed |
Object Removal Algorithm/Hardware in Image Processing |
title_sort |
object removal algorithm/hardware in image processing |
publishDate |
2004 |
url |
http://ndltd.ncl.edu.tw/handle/07673837842783838507 |
work_keys_str_mv |
AT hongmingwang objectremovalalgorithmhardwareinimageprocessing AT wánghóngmíng objectremovalalgorithmhardwareinimageprocessing AT hongmingwang yǐngxiàngchùlǐzhīwùtǐyíchúyǎnsuànfǎjíyìngtǐjiàgòu AT wánghóngmíng yǐngxiàngchùlǐzhīwùtǐyíchúyǎnsuànfǎjíyìngtǐjiàgòu |
_version_ |
1718308617448325120 |