Object Removal Algorithm/Hardware in Image Processing

• Main Authors: Hong-Ming Wang, 王泓銘
• Other Authors: Jhing-Fa Wang
• Format: Others
• Language: en_US
• Published: 2004
• Online Access: http://ndltd.ncl.edu.tw/handle/07673837842783838507

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.