WPD-based blind image steganalysis
Based on wavelet package decomposition（WPD）,a new blind image steganalysis method was presented,which can detect the stego images with comparatively high accuracy.Firstly,by three scales of WPD,image was decomposed into some coefficient subbands,and the multi-order absolute characteristic function m...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Editorial Department of Journal on Communications
2008-01-01
|
| Series: | Tongxin xuebao |
| Subjects: | |
| Online Access: | http://www.joconline.com.cn/zh/article/74653699/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841537515709792256 |
|---|---|
| author | LUO Xiang-yang1 LIU Fen-lin1 WANG Dao-shun2 |
| author_facet | LUO Xiang-yang1 LIU Fen-lin1 WANG Dao-shun2 |
| author_sort | LUO Xiang-yang1 |
| collection | DOAJ |
| description | Based on wavelet package decomposition（WPD）,a new blind image steganalysis method was presented,which can detect the stego images with comparatively high accuracy.Firstly,by three scales of WPD,image was decomposed into some coefficient subbands,and the multi-order absolute characteristic function moments of histogram were extracted as features from these subbands and image itself.And then,these features were processed and a back-propagation（BP） neural network was designed to classify original and stego images.A series of experiments were made to validate the performance of proposed method for five kinds of typical steganography methods,including LSB,SS,Jsteg,F5 and MB.Results show the method can detect stego and original images reliably,and the average detection accuracy of this method exceeds those of its closest competitors by at least 7.5% and up to 17.2%.Moreover,the influence of integral and non-integral WPD for the detection accuracy was discussed. |
| format | Article |
| id | doaj-art-17636927a4b94e83b2098f8c79fc1a3a |
| institution | Kabale University |
| issn | 1000-436X |
| language | zho |
| publishDate | 2008-01-01 |
| publisher | Editorial Department of Journal on Communications |
| record_format | Article |
| series | Tongxin xuebao |
| spelling | doaj-art-17636927a4b94e83b2098f8c79fc1a3a2025-01-14T08:32:08ZzhoEditorial Department of Journal on CommunicationsTongxin xuebao1000-436X2008-01-0117318274653699WPD-based blind image steganalysisLUO Xiang-yang1LIU Fen-lin1WANG Dao-shun2Based on wavelet package decomposition（WPD）,a new blind image steganalysis method was presented,which can detect the stego images with comparatively high accuracy.Firstly,by three scales of WPD,image was decomposed into some coefficient subbands,and the multi-order absolute characteristic function moments of histogram were extracted as features from these subbands and image itself.And then,these features were processed and a back-propagation（BP） neural network was designed to classify original and stego images.A series of experiments were made to validate the performance of proposed method for five kinds of typical steganography methods,including LSB,SS,Jsteg,F5 and MB.Results show the method can detect stego and original images reliably,and the average detection accuracy of this method exceeds those of its closest competitors by at least 7.5% and up to 17.2%.Moreover,the influence of integral and non-integral WPD for the detection accuracy was discussed.http://www.joconline.com.cn/zh/article/74653699/steganographyblind detectionwavelet packet decompositionBP neural network |
| spellingShingle | LUO Xiang-yang1 LIU Fen-lin1 WANG Dao-shun2 WPD-based blind image steganalysis Tongxin xuebao steganography blind detection wavelet packet decomposition BP neural network |
| title | WPD-based blind image steganalysis |
| title_full | WPD-based blind image steganalysis |
| title_fullStr | WPD-based blind image steganalysis |
| title_full_unstemmed | WPD-based blind image steganalysis |
| title_short | WPD-based blind image steganalysis |
| title_sort | wpd based blind image steganalysis |
| topic | steganography blind detection wavelet packet decomposition BP neural network |
| url | http://www.joconline.com.cn/zh/article/74653699/ |
| work_keys_str_mv | AT luoxiangyang1 wpdbasedblindimagesteganalysis AT liufenlin1 wpdbasedblindimagesteganalysis AT wangdaoshun2 wpdbasedblindimagesteganalysis |