CN107240059A - The modeling method of image digital watermark embedment strength regressive prediction model - Google Patents
The modeling method of image digital watermark embedment strength regressive prediction model Download PDFInfo
- Publication number
- CN107240059A CN107240059A CN201710228008.7A CN201710228008A CN107240059A CN 107240059 A CN107240059 A CN 107240059A CN 201710228008 A CN201710228008 A CN 201710228008A CN 107240059 A CN107240059 A CN 107240059A
- Authority
- CN
- China
- Prior art keywords
- watermark
- embedded
- image
- embedment strength
- prediction model
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T1/00—General purpose image data processing
- G06T1/0021—Image watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2201/00—General purpose image data processing
- G06T2201/005—Image watermarking
Abstract
The invention discloses the modeling method of image digital watermark embedment strength regressive prediction model, watermark evaluating is set first, including for weighing the similarity NC of watermark robustness and for weighing the concealed Y-PSNR PSNR of watermark, and the weight beta between two parameters is determined according to demand, SVM methods are recycled to carry out machine learning on training set, set up the regressive prediction model on watermark embedment strength, the prediction to the optimal watermark embedment strength of original image to be embedded is realized, finally application DWT conversion is embedded in digital watermarking to original image.
Description
Technical field
The present invention relates to field of information security technology, and in particular to a kind of image digital watermark embedment strength regression forecasting mould
The modeling method of type.
Background technology
With the rapid development of information technology, information security issue becomes increasingly conspicuous.Digital watermark technology is by the way that watermark is believed
Breath is embedded into digital product (including multimedia, document, software etc.), and then distinguishes the versions such as source, the creator of digital product
Weigh information, it has also become the study hotspot in copyright protection of digital product field.The function of copyright protection is realized, digital watermarking should
Possess two characteristics：One is robustness, refer to after signal transacting (including interchannel noise, shearing, rotation etc.), digital watermarking
Energy holding part integrality simultaneously can be extracted and differentiate；Two be disguised, and it is not perceived to refer to digital watermarking, and is not influenceed
The normal of digital product is used, and will not reduce the quality of former digital product.
Practice have shown that, during digital watermarking is embedded in image, robustness of the watermark embedment strength to digital watermarking
Have a great impact with disguise.But all it is in the prior art, that digital watermarking is directly embedded in image using watermarking algorithm, and
In the process, due to the reference model without embedding strength of digital watermark, embedding algorithm intensity can not accurate handle
Control, therefore the robustness and disguise of digital watermarking are generally poor.
In addition, in the prior art, the digital watermarking of image, but this mode are generally carried out using Block DCT
The problem of existing is that, when carrying out the digital watermarking of image, can have intrinsic block effect, so as to influence the Shandong of digital watermarking
Rod and disguise.
The content of the invention
The invention is intended to provide a kind of modeling method of image digital watermark embedment strength regressive prediction model, with image
During middle embedded digital watermarking, its robustness and disguise is set to reach optimal.
The modeling method of image digital watermark embedment strength regressive prediction model in this programme, image digital watermark insertion
The modeling method of intensity regressive prediction model, comprises the following steps：
1) obtain historical data and set up data set, including training set and test set；
2) original image chosen on data set carries out embedding algorithm, and obtains being embedded in the figure after watermark
Picture；
3) according to below equation, the similarity NC of robustness for weighing watermark is calculated and for weighing the hidden of watermark
The Y-PSNR PSNR of property,
Wherein W represents embedded watermark information, and W' represents the watermark information extracted, and MSE represents mean square error, and formula is represented
For：I is original image, and I' is the image after embedded watermark；
4) above-mentioned two evaluating NC and PSNR weight beta are set so that β NC+ (1- β) PSNR obtains maximum
Watermark embedment strength α during value, as optimal digital watermark embedment strength；
5) to the repeat step 1 one by one of all images on data set) arrive step 4)；
6) machine learning is carried out on training set using SVM, obtains the regressive prediction model on watermark embedment strength.
Further, step 2) in, embedding algorithm is carried out to the original image on data set, and obtain being embedded in watermark
The mode of image afterwards is：
1) an original image I on input data set；
2) one-level DWT conversion is carried out to original image I, obtains tetra- coefficient of frequencies of LL, LH, HL, HH, watermark is believed in selection
Breath is embedded on LH and HL；
3) coefficient of frequency LH and HL are respectively divided into n × n coefficient block, calculate the side of coefficient block on all correspondence positions
Difference, selects l wherein minimum coefficient block, is designated as { u respectivelyi, i=1 ..., l, { vi, i=1 ..., l }, it is used as watermark
The embedded location of information；
4) according to following embedding formula, watermark information is respectively embedded in above-mentioned coefficient block：
Wherein siWatermark information is represented, α represents watermark embedment strength undetermined；
5) IDWT conversion is carried out to the coefficient block after embedded watermark, obtains being embedded in the image I' after watermark.
Further, after step 102.1, in addition to step 102.2：Tested on test set and performance evaluation.
The beneficial effects of the invention are as follows：
(1) regressive prediction model on watermark embedment strength is set up with SVM, realizes the numeral to original image to be embedded
The prediction of the optimal watermark embedment strength of watermark, it is ensured that the robustness of watermark and it is disguised reach optimum efficiency, and can be with
It is self-defined weigh watermark robustness similarity NC and for the weight for the concealed Y-PSNR PSNR for weighing watermark
β, meets user to robustness or concealed stresses；
(2) converted using DWT, the subgraph of Multiresolution Decomposition, generation different spaces and separate bands carried out to image,
Then realize that local watermark is embedded according to the local characteristicses of wavelet coefficient, compared to other watermarking algorithms, be effectively improved
The robustness and disguise of digital watermarking, are eliminated using the intrinsic block effect of Block DCT.
Brief description of the drawings
Fig. 1 is the block diagram of image digital watermark embedded system embodiment of the present invention；
Fig. 2 is the schematic flow sheet for the regressive prediction model that embedding strength of digital watermark is set up by machine learning module；
Fig. 3 is the workflow schematic diagram of digital watermark embedding module.
Embodiment
Below by embodiment, the present invention is further detailed explanation：
Embodiment is substantially as shown in drawings：Image digital watermark embedded system disclosed in the present embodiment, as shown in Fig. 1, bag
Include machine learning module 10, input module 20, watermark embedding module 30, output module 40.
Machine learning module 10, for setting up the regressive prediction model on watermark embedment strength using SVM, realization is treated
The prediction of the optimal watermark embedment strength of embedded original image, including pretreatment unit 101, machine learning unit 102.Pretreatment
Unit, for setting up data set, data set includes training set and test set, and all images concentrated to data are carried out one by one
Digital watermark embedding, a corresponding optimal watermark embedment strength is determined for each image；Machine learning unit, utilizes SVM
Machine learning is carried out on training set, the regressive prediction model on embedding strength of digital watermark is obtained, machine learning unit is also
For being tested on test set regressive prediction model and performance evaluation.
The calculation of optimal digital watermark embedment strength is：Two evaluatings are set, namely for weighing numeral
The similarity NC of watermark robustness and for weighing the concealed Y-PSNR PSNR of watermark, sets NC and PSNR weight
β so that when β NC+ (1- β) PSNR obtains maximum, and obtained embedding strength of digital watermark is optimal digital watermark
Embedment strength.
Input module 20, the digital watermark embedding request currently triggered for responding, obtains original image I to be embedded0；
Watermark embedding module 30, the optimal watermark for being predicted according to the regressive prediction model of watermark embedment strength is embedded in strong
Degree, digital watermarking is embedded in using DWT conversion to original image；
Output module 40, the image of digital watermarking is had been inserted into for exporting.
The present embodiment additionally provides the modeling method of embedding strength of digital watermark regressive prediction model, passes through above-mentioned engineering
Practise module 10 to realize, as shown in Fig. 2 the step of regressive prediction model including setting up optimal digital watermark embedment strength；
Step 101.1：Obtain historical data and set up data set, including training set and test set；
Step 101.2：An original image I on input data set；
Step 101.3：One-level DWT conversion is carried out to original image I, tetra- coefficient of frequencies of LL, LH, HL, HH are obtained, selected
Watermark information is embedded on LH and HL；
Step 101.4：Coefficient of frequency LH and HL are respectively divided on n × n coefficient block, all correspondence positions of calculating and are
The variance yields of several piece, selects l wherein minimum coefficient block, is designated as { u respectivelyi, i=1 ..., l, { vi, i=1 ..., l },
It is used as the embedded location of watermark information；
Step 101.5：According to following embedding formula, watermark information is respectively embedded in above-mentioned coefficient block：
Wherein siWatermark information is represented, α represents watermark embedment strength undetermined；
Step 101.6：IDWT conversion is carried out to the coefficient block after embedded watermark, obtains being embedded in the image I' after watermark；
Step 101.7：According to below equation, the similarity NC of robustness for weighing watermark is calculated and for weighing water
The concealed Y-PSNR PSNR of print,
Wherein W represents embedded watermark information, and W' represents the watermark information extracted, and MSE represents mean square error, and formula is represented
For：I is original image, and I' is the image after embedded watermark；
Step 101.8：Above-mentioned two evaluating NC and PSNR weight beta are set so that β NC+ (1- β) PSNR takes
Watermark embedment strength α when obtaining maximum is optimal digital watermark embedment strength；
Step 101.9：To the repeat step 101.2- steps 101.8 one by one of all images on data set；
Step 102.1：Machine learning is carried out on training set using SVM, obtains pre- on the recurrence of watermark embedment strength
Survey model；
Pretreatment, to the image zooming-out characteristic attribute on data set, is set to X=(x1,x2,...,xm)
If the training set that above step is obtained is { (Xi,αi) | i=1 ..., n }, wherein XiFor the spy of i-th of original image
Levy attribute, αiFor the optimal embedment strength of i-th of original image, and Xi∈Rm, αi∈R；
Step 1：Choose kernel function K (xi, x), using cross validation, choose corresponding kernel functional parameter；
Choose RBF K (xi, x)=exp (- γ | | x-xi||2)；γ ＞ 0.
Step 2：By the x of sample space, xiWith Φ (x), Φ (xi) replace, and application K (xi,xj)=Φ (xi)·Φ
(xj)；
Step 3：It is required that the functional form of fitting is
F (x)=w Φ (x)+b
According to structuring risk minimum principle, corresponding optimization problem is
So that
w·Φ(x)+b-αi≤ε+ξi, i=1,2 ..., n
Whereinε ＞ 0 are parameter given in advance, by controlled in double optimization method C and
ε two parameters control SVM generalization ability
It is final to determine that nonlinear solshing is：
Wherein b can try to achieve by constraints
Above procedure directly sets up the regressive prediction model of optimal watermark embedment strength using Libsvm-2.85.
Step 102.2：Tested on test set and performance evaluation.
As shown in figure 3, modeling method of the present embodiment based on above-mentioned embedding strength of digital watermark regressive prediction model, is also carried
Image digital watermark embedding grammar has been supplied, has been comprised the following steps：
A. the step of setting up the regressive prediction model of optimal digital watermark embedment strength；
Step 101.1：Obtain historical data and set up data set, including training set and test set；
Step 101.2：An original image I on input data set；
Step 101.3：One-level DWT conversion is carried out to original image I, tetra- coefficient of frequencies of LL, LH, HL, HH are obtained, it is as follows
Shown in table, watermark information is embedded on LH and HL by selection；
| LL | LH |
| HL | HH |
Optionally, two grades of DWT can be carried out to original image to convert.
Step 101.4：Coefficient of frequency LH and HL are respectively divided on n × n coefficient block, all correspondence positions of calculating and are
The variance yields of several piece, selects l wherein minimum coefficient block, is designated as { u respectivelyi, i=1 ..., l, { vi, i=1 ..., l },
It is used as the embedded location of watermark information；
Step 101.5：According to following embedding formula, watermark information is respectively embedded in above-mentioned coefficient block：
Wherein siWatermark information is represented, α represents watermark embedment strength undetermined；
Step 101.6：IDWT conversion is carried out to the coefficient block after embedded watermark, obtains being embedded in the image I' after watermark；
Step 101.7：According to below equation, the similarity NC of robustness for weighing watermark is calculated and for weighing water
The concealed Y-PSNR PSNR of print,
Wherein W represents embedded watermark information, and W' represents the watermark information extracted, and MSE represents mean square error, and formula is represented
For：I is original image, and I' is the image after embedded watermark；
Step 101.8：Above-mentioned two evaluating NC and PSNR weight beta are set so that β NC+ (1- β) PSNR takes
Watermark embedment strength α when obtaining maximum is optimal digital watermark embedment strength；
Step 101.9：To the repeat step 101.2- steps 101.8 one by one of all images on data set；
Step 102.1：Machine learning is carried out on training set using SVM, obtains pre- on the recurrence of watermark embedment strength
Survey model；
B. image digital watermark Embedded step：
The digital watermark embedding currently triggered is responded by input module to ask, and obtains the original graph of digital watermarking to be embedded
Picture；
The optimal watermark embedment strength predicted by watermark embedding module according to regressive prediction model, using DWT conversion pair
Original image is embedded in digital watermarking.
Specifically：
Step 30.1：To original image I0One-level DWT conversion is carried out, tetra- coefficient of frequencies of LL, LH, HL, HH are obtained；
Step 30.2：Coefficient of frequency LH and HL are respectively divided on n × n coefficient block, all correspondence positions of calculating and are
The variance yields of several piece, selects l wherein minimum coefficient block, is designated as { u respectivelyi, i=1 ..., l, { ui, i=1 ..., l },
It is used as the embedded location of watermark information；
Step 30.3：Using the regressive prediction model obtained by machine learning module on optimal watermark embedment strength, I is obtained
Optimal watermark embedment strength；
Step 30.4：According to following embedding formula, watermark information is respectively embedded in above-mentioned coefficient block：
Wherein siRepresent watermark information；
Step 30.5：IDWT conversion is carried out to the coefficient block after embedded watermark, obtains being embedded in the image I after watermark0’。
C. step is exported：
The image for having been inserted into digital watermarking is exported by output module.
Above-described is only that the known general knowledge such as concrete structure and characteristic is not made herein in embodiments of the invention, scheme
Excessive description, technical field that the present invention belongs to is all before one skilled in the art know the applying date or priority date
Ordinary technical knowledge, can know prior arts all in the field, and with using normal experiment hand before the date
The ability of section, one skilled in the art can improve and implement under the enlightenment that the application is provided with reference to self-ability
This programme, some typical known features or known method should not implement the application as one skilled in the art
Obstacle.It should be pointed out that for those skilled in the art, without departing from the structure of the invention, can also make
Go out several modifications and improvements, these should also be considered as protection scope of the present invention, these effects implemented all without the influence present invention
Fruit and practical applicability.The scope of protection required by this application should be based on the content of the claims, the tool in specification
Body embodiment etc. records the content that can be used for explaining claim.
Claims (3)
1. the modeling method of image digital watermark embedment strength regressive prediction model, it is characterised in that comprise the following steps：
1) obtain historical data and set up data set, including training set and test set；
2) original image chosen on data set carries out embedding algorithm, and obtains being embedded in the image after watermark；
3) according to below equation, the similarity NC of robustness for weighing watermark is calculated and for weighing the concealed of watermark
Y-PSNR PSNR,
Wherein W represents embedded watermark information, and W' represents the watermark information extracted, and MSE represents mean square error, and formula is expressed as：I is original image, and I' is the image after embedded watermark；
4) above-mentioned two evaluating NC and PSNR weight beta are set so that during β NC+ (1- β) PSNR acquirement maximums
Watermark embedment strength α, as optimal digital watermark embedment strength；
5) to the repeat step 1 one by one of all images on data set) arrive step 4)；
6) machine learning is carried out on training set using SVM, obtains the regressive prediction model on watermark embedment strength.
2. the modeling method of image digital watermark embedment strength regressive prediction model according to claim 1, its feature exists
In：Step 2) in, embedding algorithm is carried out to the original image on data set, and obtain being embedded in the side of the image after watermark
Formula is：
1) an original image I on input data set；
2) one-level DWT conversion is carried out to original image I, obtains tetra- coefficient of frequencies of LL, LH, HL, HH, selected watermark information is embedding
Enter onto LH and HL；
3) coefficient of frequency LH and HL are respectively divided into n × n coefficient block, calculate the variance of coefficient block on all correspondence positions
Value, selects l wherein minimum coefficient block, is designated as { u respectivelyi, i=1 ..., l, { vi, i=1 ..., l }, believe as watermark
The embedded location of breath；
4) according to following embedding formula, watermark information is respectively embedded in above-mentioned coefficient block：
Wherein siWatermark information is represented, α represents watermark embedment strength undetermined；
5) IDWT conversion is carried out to the coefficient block after embedded watermark, obtains being embedded in the image I' after watermark.
3. the modeling method of image digital watermark embedment strength regressive prediction model according to claim 1, its feature exists
In：After step 102.1, in addition to step 102.2：Tested on test set and performance evaluation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710228008.7A CN107240059A (en) | 2017-04-07 | 2017-04-07 | The modeling method of image digital watermark embedment strength regressive prediction model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710228008.7A CN107240059A (en) | 2017-04-07 | 2017-04-07 | The modeling method of image digital watermark embedment strength regressive prediction model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107240059A true CN107240059A (en) | 2017-10-10 |
Family
ID=59983790
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710228008.7A Pending CN107240059A (en) | 2017-04-07 | 2017-04-07 | The modeling method of image digital watermark embedment strength regressive prediction model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107240059A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112561768A (en) * | 2020-12-02 | 2021-03-26 | 中国电子科技集团公司第十五研究所 | Computer screen optimal watermark type determination method and system based on deep learning |
| CN112613045A (en) * | 2020-11-30 | 2021-04-06 | 全球能源互联网研究院有限公司 | Data watermark embedding method and system for target data |
| CN113691885A (en) * | 2021-09-09 | 2021-11-23 | 深圳万兴软件有限公司 | Video watermark removing method and device, computer equipment and storage medium |
| CN117473469A (en) * | 2023-12-28 | 2024-01-30 | 广东佛山联创工程研究生院 | Model watermark embedding method and device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1514409A (en) * | 2003-07-28 | 2004-07-21 | 西安电子科技大学 | Small wave region digital water marking mathod based on image target region |
| CN1975780A (en) * | 2006-12-28 | 2007-06-06 | 付永钢 | Robust digital watermark inserting and detecting method based on supporting vector |
| US20090136082A1 (en) * | 2007-11-27 | 2009-05-28 | Ali Zandifar | Embedding Data in Images |
| CN102254295A (en) * | 2011-07-13 | 2011-11-23 | 西安电子科技大学 | Color halftoning image watermarking algorithm based on support vector machine |
| CN104217388A (en) * | 2014-01-22 | 2014-12-17 | 河南师范大学 | Method and device of embedding and extracting image watermark based on FSSVM (Fuzzy Smooth Support Vector Machine) |
| CN104680473A (en) * | 2014-12-20 | 2015-06-03 | 辽宁师范大学 | Machine learning-based color image watermark embedding and detecting method |
| CN104732474A (en) * | 2015-03-30 | 2015-06-24 | 陕西师范大学 | Digital watermark embedding and extracting method based on multi-level wavelet coefficient weighting and quantification |
-
2017
- 2017-04-07 CN CN201710228008.7A patent/CN107240059A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1514409A (en) * | 2003-07-28 | 2004-07-21 | 西安电子科技大学 | Small wave region digital water marking mathod based on image target region |
| CN1975780A (en) * | 2006-12-28 | 2007-06-06 | 付永钢 | Robust digital watermark inserting and detecting method based on supporting vector |
| US20090136082A1 (en) * | 2007-11-27 | 2009-05-28 | Ali Zandifar | Embedding Data in Images |
| CN102254295A (en) * | 2011-07-13 | 2011-11-23 | 西安电子科技大学 | Color halftoning image watermarking algorithm based on support vector machine |
| CN104217388A (en) * | 2014-01-22 | 2014-12-17 | 河南师范大学 | Method and device of embedding and extracting image watermark based on FSSVM (Fuzzy Smooth Support Vector Machine) |
| CN104680473A (en) * | 2014-12-20 | 2015-06-03 | 辽宁师范大学 | Machine learning-based color image watermark embedding and detecting method |
| CN104732474A (en) * | 2015-03-30 | 2015-06-24 | 陕西师范大学 | Digital watermark embedding and extracting method based on multi-level wavelet coefficient weighting and quantification |
Non-Patent Citations (4)
| Title |
|---|
| B.JAGADEESH等: ""Digital Image Watermark Extraction in Discrete Wavelet Transform Domain using Support"", 《INT. J. OF RECENT TRENDS IN ENGINEERING & TECHNOLOGY》 * |
| 刘一楠: ""基于机器学习的图像数字水印算法研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
| 刘红岩等: ""基于小波变换的CDMA图像盲水印算法"", 《计算机应用与软件》 * |
| 王树梅等: ""数字水印嵌入强度最优化分析"", 《计算机安全》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112613045A (en) * | 2020-11-30 | 2021-04-06 | 全球能源互联网研究院有限公司 | Data watermark embedding method and system for target data |
| CN112561768A (en) * | 2020-12-02 | 2021-03-26 | 中国电子科技集团公司第十五研究所 | Computer screen optimal watermark type determination method and system based on deep learning |
| CN112561768B (en) * | 2020-12-02 | 2024-03-29 | 中国电子科技集团公司第十五研究所 | Method and system for determining optimal watermark type of computer screen based on deep learning |
| CN113691885A (en) * | 2021-09-09 | 2021-11-23 | 深圳万兴软件有限公司 | Video watermark removing method and device, computer equipment and storage medium |
| CN113691885B (en) * | 2021-09-09 | 2024-01-30 | 深圳万兴软件有限公司 | Video watermark removal method and device, computer equipment and storage medium |
| CN117473469A (en) * | 2023-12-28 | 2024-01-30 | 广东佛山联创工程研究生院 | Model watermark embedding method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107194863A (en) | Image digital watermark embedded system and method | |
| CN107240059A (en) | The modeling method of image digital watermark embedment strength regressive prediction model | |
| CN101968883B (en) | Method for fusing multi-focus images based on wavelet transform and neighborhood characteristics | |
| CN101980284B (en) | Two-scale sparse representation-based color image noise reduction method | |
| CN103077506B (en) | In conjunction with local and non-local adaptive denoising method | |
| CN103200421B (en) | No-reference image quality evaluation method based on Curvelet transformation and phase coincidence | |
| Mehta et al. | An adaptive framework to image watermarking based on the twin support vector regression and genetic algorithm in lifting wavelet transform domain | |
| Hasegawa et al. | Image inpainting on the basis of spectral structure from 2-D nonharmonic analysis | |
| Noor et al. | Highly robust hybrid image watermarking approach using Tchebichef transform with secured PCA and CAT encryption | |
| Dappuri et al. | Non-blind RGB watermarking approach using SVD in translation invariant wavelet space with enhanced Grey-wolf optimizer | |
| CN114897694A (en) | Image super-resolution reconstruction method based on mixed attention and double-layer supervision | |
| Cai et al. | Joint depth and density guided single image de-raining | |
| Sun et al. | A blind dual color images watermarking based on quaternion singular value decomposition | |
| CN106097257B (en) | A kind of image de-noising method and device | |
| CN103839244B (en) | Real-time image fusion method and device | |
| CN102314675B (en) | Wavelet high-frequency-based Bayesian denoising method | |
| Agarwal et al. | A novel image watermarking technique using fuzzy-BP network | |
| CN102339460B (en) | Adaptive satellite image restoration method | |
| Wang et al. | Image inpainting based on multi-frequency probabilistic inference model | |
| CN103632375A (en) | Image scrambling evaluation method and image scrambling evaluation device | |
| Chen et al. | Overview of digital image restoration | |
| Liu et al. | Graph representation learning for spatial image steganalysis | |
| CN103793880A (en) | Structure self-adaptive and structure keeping image local distortion method | |
| CN113989140A (en) | Image restoration method based on cycle feature reasoning of self-attention mechanism | |
| CN106203480A (en) | Nonlinear feature extraction based on data incomplete and sorting technique |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20171010 |