A Multimedia Watermarking Technique Based on SVMs

博士 === 淡江大學 === 資訊工程學系博士班 === 97 === Digital watermarking is an important technique for protection and identification of the content of digital multimedia. From our previous work on digital watermarking technique based on support vector machines (SVMs) and tolerable position map (TPM), a thorough st...

Full description

Bibliographic Details
Main Authors: Chia-Jen Wang, 王佳仁
Other Authors: Shwu-Huey Yen
Format: Others
Language:en_US
Published: 2009
Online Access:http://ndltd.ncl.edu.tw/handle/06968073959962443585
id ndltd-TW-097TKU05392003
record_format oai_dc
spelling ndltd-TW-097TKU053920032015-10-13T14:49:22Z http://ndltd.ncl.edu.tw/handle/06968073959962443585 A Multimedia Watermarking Technique Based on SVMs 一個基於SVMs之多媒體浮水印技術 Chia-Jen Wang 王佳仁 博士 淡江大學 資訊工程學系博士班 97 Digital watermarking is an important technique for protection and identification of the content of digital multimedia. From our previous work on digital watermarking technique based on support vector machines (SVMs) and tolerable position map (TPM), a thorough study on feature selection and TPM generation is conducted. The improved system is endorsed by a complete set of experiments. It not only inherits the good characteristics from the original algorithm, but also shows significant improvements on time consumption as well as the robustness of low-pass filtering attacks. The proposed algorithm is also extended to a scene-based video watermarking technique. The excellent performance on NC values is achieved by averaging extracted watermarks from many frames of one scene into the final extracted watermark. The issue on collusion attacks is also detailed discussed. Our video watermarking technique is shown to be robust to video compression and collusion attacks. The proposed video watermarking technique has its novelty and practicability on SVM-applications. Shwu-Huey Yen 顏淑惠 2009 學位論文 ; thesis 62 en_US
collection NDLTD
language en_US
format Others
sources NDLTD
description 博士 === 淡江大學 === 資訊工程學系博士班 === 97 === Digital watermarking is an important technique for protection and identification of the content of digital multimedia. From our previous work on digital watermarking technique based on support vector machines (SVMs) and tolerable position map (TPM), a thorough study on feature selection and TPM generation is conducted. The improved system is endorsed by a complete set of experiments. It not only inherits the good characteristics from the original algorithm, but also shows significant improvements on time consumption as well as the robustness of low-pass filtering attacks. The proposed algorithm is also extended to a scene-based video watermarking technique. The excellent performance on NC values is achieved by averaging extracted watermarks from many frames of one scene into the final extracted watermark. The issue on collusion attacks is also detailed discussed. Our video watermarking technique is shown to be robust to video compression and collusion attacks. The proposed video watermarking technique has its novelty and practicability on SVM-applications.
author2 Shwu-Huey Yen
author_facet Shwu-Huey Yen
Chia-Jen Wang
王佳仁
author Chia-Jen Wang
王佳仁
spellingShingle Chia-Jen Wang
王佳仁
A Multimedia Watermarking Technique Based on SVMs
author_sort Chia-Jen Wang
title A Multimedia Watermarking Technique Based on SVMs
title_short A Multimedia Watermarking Technique Based on SVMs
title_full A Multimedia Watermarking Technique Based on SVMs
title_fullStr A Multimedia Watermarking Technique Based on SVMs
title_full_unstemmed A Multimedia Watermarking Technique Based on SVMs
title_sort multimedia watermarking technique based on svms
publishDate 2009
url http://ndltd.ncl.edu.tw/handle/06968073959962443585
work_keys_str_mv AT chiajenwang amultimediawatermarkingtechniquebasedonsvms
AT wángjiārén amultimediawatermarkingtechniquebasedonsvms
AT chiajenwang yīgèjīyúsvmszhīduōméitǐfúshuǐyìnjìshù
AT wángjiārén yīgèjīyúsvmszhīduōméitǐfúshuǐyìnjìshù
AT chiajenwang multimediawatermarkingtechniquebasedonsvms
AT wángjiārén multimediawatermarkingtechniquebasedonsvms
_version_ 1717758649131073536