CN114511435A - Zero watermark generation method and device, electronic equipment and storage medium - Google Patents
Zero watermark generation method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114511435A CN114511435A CN202210086245.5A CN202210086245A CN114511435A CN 114511435 A CN114511435 A CN 114511435A CN 202210086245 A CN202210086245 A CN 202210086245A CN 114511435 A CN114511435 A CN 114511435A
- Authority
- CN
- China
- Prior art keywords
- image
- watermark
- original carrier
- carrier image
- mapping
- 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
- 238000000034 method Methods 0.000 title claims abstract description 70
- 239000011159 matrix material Substances 0.000 claims description 70
- 238000013507 mapping Methods 0.000 claims description 60
- 230000009466 transformation Effects 0.000 claims description 22
- 238000004364 calculation method Methods 0.000 claims description 18
- 238000000354 decomposition reaction Methods 0.000 claims description 17
- 238000013528 artificial neural network Methods 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 16
- 238000000513 principal component analysis Methods 0.000 claims description 15
- 230000008569 process Effects 0.000 claims description 12
- 230000009467 reduction Effects 0.000 claims description 12
- 238000007781 pre-processing Methods 0.000 claims description 10
- 238000012549 training Methods 0.000 claims description 10
- 230000000739 chaotic effect Effects 0.000 claims description 6
- 238000006467 substitution reaction Methods 0.000 claims description 5
- 230000000007 visual effect Effects 0.000 claims description 5
- 230000001131 transforming effect Effects 0.000 claims description 4
- 239000013598 vector Substances 0.000 claims description 4
- 230000004393 visual impairment Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 35
- 238000010586 diagram Methods 0.000 description 17
- 238000005516 engineering process Methods 0.000 description 6
- 238000004590 computer program Methods 0.000 description 4
- 238000000844 transformation Methods 0.000 description 4
- 241000219739 Lens Species 0.000 description 3
- 241001504519 Papio ursinus Species 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000010008 shearing Methods 0.000 description 3
- 230000001174 ascending effect Effects 0.000 description 2
- 230000006835 compression Effects 0.000 description 2
- 238000007906 compression Methods 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000007306 turnover Effects 0.000 description 2
- 241000282575 Gorilla Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 241000282577 Pan troglodytes Species 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000004806 packaging method and process Methods 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000007639 printing Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Images
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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/10—Protecting distributed programs or content, e.g. vending or licensing of copyrighted material ; Digital rights management [DRM]
- G06F21/16—Program or content traceability, e.g. by watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
- G06F21/60—Protecting data
- G06F21/602—Providing cryptographic facilities or services
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Computer Hardware Design (AREA)
- Computer Security & Cryptography (AREA)
- General Engineering & Computer Science (AREA)
- Technology Law (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Bioethics (AREA)
- General Health & Medical Sciences (AREA)
- Editing Of Facsimile Originals (AREA)
- Image Processing (AREA)
Abstract
The invention provides a zero watermark generation method, a device, electronic equipment and a storage medium, wherein the zero watermark generation method comprises the following steps: the zero watermark obtained by the technical scheme of the invention has higher robustness against geometric attacks and improves the safety performance of the zero watermark.
Description
Technical Field
The present invention relates to the field of image processing and anti-counterfeiting technologies, and in particular, to a zero watermark generation method and apparatus, an electronic device, and a storage medium.
Background
Nowadays, due to popularization of networks and use of high-precision printers and scanners, security problems such as digital copyright information tampering and embezzlement are gradually increased. The digital watermarking technology is widely applied to the fields of copyright protection, printing and packaging anti-counterfeiting and the like as one of the methods with low cost and good anti-counterfeiting performance. Digital watermarking technology is a technology for embedding a specific digital signal (image or text) into a digital product (image, text, audio) to protect the copyright, integrity, copy protection or despatch tracking of the digital product. The zero watermark digital watermarking technology is to encrypt the carrier image on the premise of not destroying the visual information of the original image by encoding the carrier image.
Disclosure of Invention
The embodiment of the invention mainly aims to provide a zero watermark generation method, a zero watermark generation device, electronic equipment and a storage medium, and aims to improve the anti-counterfeiting performance of the zero watermark.
One aspect of the present invention provides a zero watermark generating method, including: responding to a generation request, acquiring a first original carrier image and a first watermark image, and performing preprocessing on the first original carrier image and the first watermark image to obtain a second original carrier image and a second watermark image; reconstructing the second original carrier image to obtain a reconstructed image, and acquiring a characteristic value and a characteristic value matrix before and after reconstruction of the second original carrier image; reducing the dimension of the reconstructed image to obtain a mapping, and acquiring an example hit number and a weight position of the mapping; performing scrambling processing on the second watermark image according to the characteristic value and the characteristic value matrix to obtain a scrambled image; encrypting the scrambled image to obtain a third watermark image; performing decomposition on the second original carrier image to obtain singular values and singular value mean values, and constructing a characteristic singular value matrix according to the singular values and the singular value mean values; and determining a target zero watermark according to the second original carrier image and the characteristic singular value matrix.
According to the zero watermark generating method, reconstructing the second original carrier image to obtain a reconstructed image includes: performing dimensionality reduction processing on the original carrier image by a PCA (principal component analysis) method to obtain a reconstructed image; the PCA analysis method comprises the steps of obtaining the size of the second original carrier image, calculating the pixel mean value of the second original carrier image according to columns, and calculating the pixel mean value of the second original carrier image according to a formula
Cov(X,Y)＝E((X-E(Y)(Y-E(Y))，
And calculating covariance of each column, and determining dimension of a reconstructed image according to visual loss caused by minimum dimension reduction, wherein E () represents expectation, X is expectation of pixels of a row of the first original carrier image, and Y is expectation of pixels of a row of the first original carrier image, E (Y) is expectation of pixels of a column of the second original carrier image.
According to the zero watermark generating method, obtaining the eigenvalue and the eigenvalue matrix before and after the reconstruction of the second original carrier image comprises: and performing descending order arrangement on the covariance of each column, selecting k maximum values in the covariance of each column, determining eigenvectors of the covariance of the k maximum values, and forming an eigenvector matrix by taking the eigenvectors as column vectors respectively.
According to the zero watermark generation method, the dimensionality reduction is performed on the reconstructed image to obtain a mapping, and an example hit number and a weight position of the mapping are obtained, and the method comprises the following steps: establishing a self-organizing mapping neural network, executing reconstructed image input through the self-organizing mapping neural network according to a Kohonen learning rule, outputting a matrix with a dimensionality of 4 orders, and executing training to obtain the mapping; and recording the example hit number and the weight position obtained in the training process.
According to the zero watermark generating method, wherein scrambling the second watermark image according to the eigenvalue and the eigenvalue matrix to obtain a scrambled image, the method includes: reading the second watermark image, obtaining the size of the second watermark image, setting the size as the maximum cycle number of the calculation process, and executing Arnold scrambling processing, wherein the Arnold scrambling parameter is set as the Arnold scrambling parameter
Where x, y denote the position of the image pixel before transformation, xn+1、yn+1The pixel position after transformation is shown, N represents the current transformation frequency, N represents the image size, mod is a modulus operation, a, b and N are parameters, and a, b and N are obtained by the following steps: wherein a is the number of the feature values before reconstruction of the second original carrier image, b is the number of the feature values after reconstruction of the second original carrier image, and n is the arithmetic square root of the pixel mean of the reconstructed image.
According to the zero watermark generating method, encrypting the scrambled image to obtain a third watermark image includes: generating a Logistic chaotic sequence through Logistic mapping, wherein the Logistic mapping comprises the following steps: setting a system parameter u and a system initial value x of Logitics mapping, wherein u is any positive integer, and the value range of x is [0,1 ]; the calculation mode through Logitics mapping is
xn+1＝xnu(1-xn)；xn∈[-1,1]
Where u is the maximum of the example number of hits and x is the average of the weight positions; and transforming the Logistic chaotic sequence into a substitution value encryption sequence y through an auxiliary key, sequentially replacing pixels of the scrambled image by using the encryption sequence y, and outputting the image with the pixels replaced.
The zero watermark generating method, wherein sequentially replacing the pixels of the scrambled image by using an encryption sequence y, comprises: performing bitwise logical operation on the scrambled image, judging whether each pixel value is a prime number according to the sequence from top to bottom and from left to right, and if the pixel value is a prime number, performing the following calculation on the pixels of the scrambled image by using a y sequence:
k(n)＝[(y×1015)％256]wherein]For rounding operations,% is a remainder operation, otherwise, the pixel value is kept unchanged.
According to the zero watermark generation method, the step of performing decomposition on the second original carrier image to obtain singular values and singular value mean values, and the step of constructing a characteristic singular value matrix according to the singular values and the singular value mean values comprises the following steps: acquiring the singular value of the second original carrier image, and calculating the singular value mean value;
by the formula
Constructing the characteristic singular value matrix; and carrying out XOR operation on the second original carrier image and the characteristic singular value matrix to obtain the target zero watermark model.
The zero watermark generating method, wherein the method further comprises: performing peak signal-to-noise ratio comparison on the second original carrier image and a third watermark image to obtain a comparison result, and determining the visual effect of the first original carrier image maintained by the target zero watermark; or performing geometric attack on the third watermark image, extracting the target zero watermark, calculating a normalized correlation coefficient of the extracted watermark, and determining the geometric attack robustness of the target zero watermark according to the normalized correlation coefficient.
Another embodiment of the present invention further includes a zero watermark generation apparatus, including: the initialization module is used for responding to a generation request, acquiring a first original carrier image and a first watermark image, and performing preprocessing on the first original carrier image and the first watermark image to obtain a second original carrier image and a second watermark image; the reconstruction module is used for reconstructing the second original carrier image to obtain a reconstructed image and acquiring a characteristic value and a characteristic value matrix before and after reconstruction of the second original carrier image; the dimension reduction module is used for reducing the dimension of the reconstructed image to obtain mapping and acquiring the example hit number and the weight position of the mapping; the scrambling module is used for performing scrambling processing on the second watermark image according to the characteristic value and the characteristic value matrix to obtain a scrambled image; the encryption module is used for encrypting the scrambled image to obtain a third watermark image; the decomposition module is used for performing decomposition on the second original carrier image to obtain singular values and singular value mean values, and constructing a characteristic singular value matrix according to the singular values and the singular value mean values; and the zero watermark generating module is used for determining a target zero watermark according to the second original carrier image and the characteristic singular value matrix.
Another aspect of the embodiments of the present invention provides an electronic device, including a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the method as described above.
Embodiments of the present invention also disclose a computer program product or computer program comprising computer instructions stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and executed by the processor, to cause the computer device to perform the methods described above.
The invention has the beneficial effects that: the zero watermark obtained by the technical scheme of the invention has higher robustness against geometric attacks and improves the safety performance of the zero watermark.
Additional aspects and advantages of the invention will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the invention.
Drawings
The above and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
fig. 1 is a flowchart illustrating a zero watermark generating method according to an embodiment of the present invention.
Fig. 2 is a flowchart illustrating another zero watermark generating method according to an embodiment of the present invention.
Fig. 3a, 3b, and 3c are a lena diagram, a babon diagram, and a plane diagram of an original carrier image according to an embodiment of the present invention.
Fig. 4 is a watermark image of an embodiment of the present invention.
Fig. 5a, 5b, 5c are a lena diagram, a babon diagram and a plane diagram of the PCA image reconstruction according to the embodiment of the present invention.
Fig. 6 is an encrypted watermark image subjected to Arnold transformation and Logitics mapping according to an embodiment of the present invention.
Fig. 7a, 7b and 7c are a lena diagram, a babon diagram and a plane diagram of a carrier image carrying a zero watermark according to an embodiment of the present invention.
FIG. 8 is a watermark diagram extracted after a compression attack, according to an embodiment of the invention.
Fig. 9 is a watermark image extracted after a carrier image lena image carrying a zero watermark is subjected to 45 ° rotation attack according to an embodiment of the present invention.
Fig. 10 is a watermark image extracted after the carrier image lena image carrying the zero watermark is subjected to a shearing attack at the upper left corner 1/4 according to the embodiment of the present invention.
Fig. 11 is a schematic diagram of a zero watermark generating apparatus according to an embodiment of the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. In the following description, suffixes such as "module", "part", or "unit" used to denote elements are used only for facilitating the explanation of the present invention, and have no peculiar meaning in itself. Thus, "module", "component" or "unit" may be used mixedly. "first", "second", etc. are used for the purpose of distinguishing technical features only and are not to be understood as indicating or implying relative importance or implicitly indicating the number of indicated technical features or implicitly indicating the precedence of the indicated technical features. In the following description, the method steps are labeled continuously for convenience of examination and understanding, and the implementation sequence of the steps is adjusted without affecting the technical effect achieved by the technical scheme of the invention in combination with the overall technical scheme of the invention and the logical relationship among the steps. The embodiments described below with reference to the accompanying drawings are illustrative only for the purpose of explaining the present invention, and are not to be construed as limiting the present invention.
As shown in fig. 1, an embodiment of the present invention provides a flow of a zero watermark generating method, where the flow method includes:
s100, responding to the generation request, acquiring a first original carrier image and a first watermark image, and performing preprocessing on the first original carrier image and the first watermark image to obtain a second original carrier image and a second watermark image;
in some embodiments, the pre-treatment employs a graying treatment;
s200, reconstructing the second original carrier image to obtain a reconstructed image, and acquiring a characteristic value and a characteristic value matrix before and after reconstruction of the second original carrier image;
in some embodiments, the first original carrier image is reduced in dimension by a PCA analysis method to obtain a reconstructed image, and the initial and reconstructed eigenvalues and eigenvalue matrix are recorded.
S300, reducing the dimension of the reconstructed image to obtain mapping, and acquiring the example hit number and the weight position of the mapping;
in some embodiments, the reconstructed image is reduced in dimension by constructing a self-organizing mapping neural network, a low-dimensional discrete mapping is generated, and the example hit numbers and weight positions obtained by mapping are recorded.
S400, scrambling the second watermark image according to the characteristic value and the characteristic value matrix to obtain a scrambled image;
in some embodiments, the Arnold scrambling process may be performed on the second watermark image, and the arithmetic square root of the average of the pixels of the reconstructed image obtained in step S100 is calculated and rounded.
S500, encrypting the scrambled image to obtain a third watermark image;
in some embodiments, the obtained scrambled image is secondarily encrypted through Logitics mapping to obtain an encrypted watermark;
s600, decomposing the second original carrier image to obtain singular values and singular value mean values, and constructing a characteristic singular value matrix according to the singular values and the singular value mean values;
and S700, determining the target zero watermark according to the second original carrier image and the characteristic singular value matrix.
Referring to fig. 2, an embodiment of the present invention discloses a technical scheme for encrypting an image based on PCA image reconstruction, SOM neural network, logistic mapping, and Arnold scrambling to construct a zero watermark model, which is specifically implemented according to the following steps:
referring to fig. 3a, 3b, and 3c, a lens image, a babon image, and a plane image of an original carrier image according to an embodiment of the present invention are shown, respectively, and fig. 4 is a watermark image, where lens is an animal image, babon is a gorilla image, and a plane airplane image.
Step 1, reducing the dimension of an original carrier image by a PCA analysis method to obtain a reconstructed image, and recording initial and reconstructed eigenvalues and an eigenvalue matrix;
the lena, baboon and plane images reconstructed from the PCA images are shown in fig. 5a, 5b, 5c, respectively.
In some embodiments, wherein the resolution of the original carrier image is 72 to 1200 dpi; the size is 128px 1024 px; reading an original carrier image; acquiring the size of an original carrier image; the covariance of each column is calculated using the following formula:
Cov(X,Y)＝E((X-E(Y)(Y-E(Y))
wherein E () represents expectation, X is first original carrier image row pixel expectation, Y is first original carrier image row pixel expectation E (Y) is second original carrier image column pixel expectation, then the column covariances are arranged in descending order, the largest k of them are selected. Then, the corresponding k eigenvectors are respectively used as column vectors to form an eigenvector matrix, and the implementation is realized by the following mode:
calling a sort () function in MATLAB software to carry out ascending sequence arrangement, then using a fliplr () function to turn over the obtained matrix left and right, and then selecting the largest k covariances according to a preset dimensionality reduction percentage;
step 2, constructing a self-organizing mapping neural network to reduce the dimension of the reconstructed image, generating low-dimensional discrete mapping, and recording the number of example hits and the weight position obtained by mapping;
the self-organizing mapping neural network is constructed by the following steps:
inputting an nctool command in MATLAB software, calling a self-organizing mapping neural network, defaulting the function as a Kohonen learning rule, setting the input and output dimensionalities of the reconstructed image obtained in the step 1 to be a matrix of 4 orders, and starting training. Recording and outputting sample hits and weight position obtained in the training process after the training is finished;
step 3, performing Arnold scrambling processing on the watermark image, calculating the arithmetic square root of the pixel average value of the reconstructed image obtained in the step 1 and rounding;
the Arnold scrambling processing of the watermark image is realized by the following modes:
reading and calling an immead () function to read a watermark image in MATLAB software, calling a size () function to obtain the size of the watermark image, and setting the size as the maximum loop times of the calculation process. The Arnold scrambling parameter is set as follows:
where x, y denote the position of the image pixel before transformation, xn+1、yn+1Representing the pixel position after the transformation; a. b is a parameter; n represents the number of current transformations, N represents the image size, mod is the modulo operation.
The setting of a, b and n is determined by the following modes:
a, rounding the arithmetic square root of the number of the original eigenvalues obtained by PCA analysis in the step 1;
b, rounding the arithmetic square root of the number of the new characteristic values obtained by PCA analysis in the step 1;
and n is the arithmetic square root of the pixel mean value of the reconstructed image obtained by PCA analysis in the step 1.
Step 4, carrying out secondary encryption on the scrambled image obtained in the step 3 through Logitics mapping to obtain an encrypted watermark;
and constructing a Logitics system, and setting a system parameter u and a system initial value x, wherein u is any positive integer, and the numeric area of x is [0,1 ]. The logistic system is calculated by the following formula:
xn+1＝xnu(1-xn)；xn∈[-1,1]system parameter u ═ maximum value of the number of example hits recorded in step 2
System initial value x is the average of the weight positions recorded in step 2
And transforming the logistic chaotic sequence into a substitution value encryption sequence y by using an auxiliary key, sequentially substituting pixels of the original image by using the y sequence, and outputting the image with the pixels substituted.
Pixels of the original image are sequentially replaced by utilizing the y sequence, and the image with the replaced pixels is output by the following modes:
firstly, carrying out bitwise logical operation on an image, judging whether each pixel value is a prime number or not according to the sequence from top to bottom and from left to right, and if the pixel value is the prime number, carrying out the following calculation on the pixel by using a y sequence:
k(n)＝[(y×1015)％256]wherein]For rounding operations,% is for remainder operations.
Otherwise the pixel values are kept unchanged.
The encrypted watermark image after Arnold transformation and Logitics mapping is shown in FIG. 6.
the SVD decomposition of the reconstructed image is realized by the following modes:
svd () function is called in MATLAB software to calculate the singular values of the reconstructed image, and then mean () function is called to calculate the singular value mean.
Constructing a characteristic singular value matrix according to the relation between each singular value and singular value mean quality inspection, and realizing the following steps:
respectively comparing the singular value mean value obtained by calculation with each element in the singular value matrix, and constructing a characteristic singular matrix according to the following relational expression:
wherein s isiRepresenting singular value matrix elements;
representing a mean of singular values; s'iRepresenting the eigensingular value matrix elements.
Step 6, calculating the original carrier image and the characteristic singular value matrix obtained in the step 5 by utilizing an exclusive OR operation to complete the construction of a zero watermark model;
the lena diagram, the baboon diagram and the plane diagram of the carrier image carrying the zero watermark are respectively shown in fig. 7a, 7b and 7 c.
In some embodiments, the embedding of the zero watermark is achieved by:
and (5) carrying out exclusive OR operation on the characteristic singular value matrix obtained in the step (5) and the original carrier image, and calling a function xor () in MATLAB software to obtain a sequence LS.
In some embodiments, the extraction of the zero watermark is achieved by:
and 6.2, extracting the watermark of the encrypted carrier image, and extracting the watermark by a method of constructing a characteristic singular value matrix by carrying out SOM neural network operation, inverse Logitics mapping, Arnold inverse transformation and SVD decomposition on the image.
The inverse Logistics mapping is implemented as follows:
and taking the number of example hits, the weight position and the image size obtained by the operation of the self-organizing mapping neural network of the encrypted carrier image as parameters of inverse Logitics mapping.
The Arnold inverse transform is implemented as follows:
reading and calling an immead () function in MATLAB software to read the encrypted carrier image, calling a size () function to obtain the size of the encrypted carrier image, and setting the size as the maximum loop number of the calculation process.
Where x, y denote the position of the image pixel before transformation, xn+1、yn+1Representing the pixel position after the transformation; a. b is a parameter; n represents the number of current transformations, N represents the image size, mod is the modulo operation.
The invention is
Step 7, comparing the peak signal-to-noise ratio of the original carrier image in the step 1 with the encrypted image embedded with the watermark, and judging whether the zero watermark model provided by the invention can keep the original visual effect of the image;
the image peak signal-to-noise ratio is determined by:
i, K respectively representing an original image and a processed image; MSE is the mean square error of two pixel values; i. j represents the horizontal and vertical coordinate position of the pixel point;
representing the maximum pixel value of the image. And calling the psnr () function in MATLAB software to realize the calculation of the peak signal-to-noise ratio of the two graphs.
And 8, referring to a watermark image extracted after the compression attack in the figure 8, carrying out geometric attack on the encrypted image embedded with the watermark, then extracting the watermark, calculating a normalized correlation coefficient of the extracted watermark, and judging whether the zero watermark model provided by the invention has geometric attack robustness.
Carrying out geometric attack on the encrypted image embedded with the watermark, and realizing the following steps:
the method adopts 3 common geometric attack algorithms of zooming, rotating and shearing to verify, and invokes an immediate () function in MATLAB software to complete the zooming attack; referring to fig. 9, a watermark image extracted after a carrier image lena image carrying a zero watermark is subjected to 45 ° rotation attack completes the rotation attack by calling an error () function; assuming a clipping range, referring to fig. 10, a watermark diagram extracted after a carrier image lena diagram is subjected to a clipping attack at the upper left corner 1/4 is illustrated, and a pixel value in the clipping range is adjusted to 255 to represent white color to simulate a clipping effect.
The calculation of the normalized correlation coefficient of the extracted watermark is realized by the following modes:
writing a program code in MATLAB software according to the following formula to calculate and extract a normalized correlation coefficient (NC) between the watermark image and the original watermark image:
wherein W (i, j) represents the original watermark image; w' (i, j) represents extracting a watermark image; n denotes a watermark image size.
In one embodiment of the process of the present invention,
taking a lens (figure) image, a baboon (chimpanzee) image and a plane (airplane) image as original watermark carrier images, taking a letter 'Y' as watermark information, specifically:
(1) reducing the dimension of the original carrier image by a PCA analysis method to obtain a reconstructed image, and recording initial and reconstructed eigenvalues and an eigenvalue matrix; the image size was set at 512px with a resolution of 300dpi
Reading an original carrier image in MATLAB software; acquiring the size of an original carrier image; the covariance of each column is calculated using the following formula:
Cov(X,Y)＝E((X-E(Y)(Y-E(Y))
then, the covariance of each column is sorted in descending order, and the largest k covariance is selected. Then, the corresponding k eigenvectors are respectively used as column vectors to form an eigenvector matrix, and the implementation is realized by the following mode:
calling a sort () function in MATLAB software to carry out ascending sequence arrangement, then using a fliplr () function to turn over the obtained matrix left and right, and then selecting the largest k covariances according to a preset dimensionality reduction percentage;
(2) constructing a self-organizing mapping neural network to reduce the dimension of the reconstructed image, generating low-dimensional discrete mapping, and recording the example hit number and the weight position obtained by mapping;
the self-organizing mapping neural network is constructed by the following steps:
inputting an nctool command in MATLAB software, calling a self-organizing mapping neural network, defaulting the function as a Kohonen learning rule, setting the reconstructed image obtained in the step (1) as a network input and output dimension as a 4-order matrix, and starting training. Recording and outputting sample hits and weight position obtained in the training process after the training is finished;
(3) performing Arnold scrambling processing on the watermark image, calculating and rounding the arithmetic square root of the pixel average value of the reconstructed image obtained in the step 1, and calculating the arithmetic square root of the pixel average value of the reconstructed image to be 10;
the Arnold scrambling processing of the watermark image is realized by the following modes:
reading and calling an immead () function to read a watermark image in MATLAB software, calling a size () function to obtain the size of the watermark image, and setting the size as the maximum loop times of the calculation process. The Arnold scrambling parameter is set as follows:
where x, y denote the position of the image pixel before transformation, xn+1、yn+1Representing the pixel position after the transformation; a. b is a parameter; n represents the number of current transformations, N represents the image size, mod is the modulo operation.
The setting of a, b and n in the invention is determined by the following modes:
a＝12；
b＝7；
n＝10。
(4) carrying out secondary encryption on the scrambled image obtained in the step 3 through Logitics mapping to obtain an encrypted watermark;
and constructing a Logitics system, and setting a system parameter u to 7 and a system initial value x to 0.6, wherein u is any positive integer, and x has a value range of [0,1 ]. The logistic system is calculated by the following formula:
xn+1＝xnu(1-xn)；xn∈[-1,1]
system parameter u ═ maximum value of example number of hits recorded in step 2
System initial value x is the average of the weight positions recorded in step 2
And transforming the logistic chaotic sequence into a substitution value encryption sequence y by using an auxiliary key, sequentially substituting pixels of the original image by using the y sequence, and outputting the image with the pixels substituted.
Pixels of the original image are replaced by the y sequence in sequence, and the output of the image after replacing the pixels is realized by the following modes:
firstly, carrying out bitwise logical operation on an image, judging whether each pixel value is a prime number or not according to the sequence from top to bottom and from left to right, and if the pixel value is the prime number, carrying out the following calculation on the pixel by using a y sequence:
k(n)＝[(y×1015)％256]wherein]For rounding operations,% is the remainder operation.
Otherwise, keeping the pixel value unchanged
(5) Performing SVD on the reconstructed image obtained in the step 1, calculating singular value mean values, and constructing a characteristic singular value matrix according to the relation between each singular value and the singular value mean value;
the SVD decomposition of the reconstructed image is realized by the following modes:
the svd () function is called in MATLAB software to compute the singular values of the reconstructed image, and then the mean () function is called to compute the mean of the singular values.
Constructing a characteristic singular value matrix according to the relation between each singular value and singular value mean quality inspection, and realizing the following steps:
respectively comparing the singular value mean value obtained by calculation with each element in the singular value matrix, and constructing a characteristic singular matrix according to the following relational expression:
wherein s isiRepresenting singular value matrix elements;
representing a mean of singular values; s'iRepresenting the eigensingular value matrix elements.
(6) Calculating the original carrier image and the characteristic singular value matrix obtained in the step 5 by utilizing an exclusive OR operation to complete the construction of a zero watermark model;
the embedding of the zero watermark is realized by the following modes:
and carrying out XOR operation on the obtained characteristic singular value matrix and the original carrier image, and calling a function xor () in MATLAB software to obtain a sequence LS.
The extraction of the zero watermark is realized by the following modes:
and extracting the watermark by a method of constructing a characteristic singular value matrix by carrying out SOM neural network operation, inverse Logitics mapping, Arnold inverse transformation and SVD decomposition on the image.
The inverse Logistics mapping is implemented as follows:
and taking the number of example hits, the weight position and the image size obtained by the operation of the self-organizing mapping neural network of the encrypted carrier image as parameters of inverse Logitics mapping.
The Arnold inverse transform is implemented as follows:
reading and calling an immead () function in MATLAB software to read the encrypted carrier image, calling a size () function to obtain the size of the encrypted carrier image, and setting the size as the maximum loop number of the calculation process.
Where x, y denote the position of the image pixel before transformation, xn+1、yn+1Representing the pixel position after transformation; a. b is a parameter; n represents the number of current transformations, N represents the image size, mod is the modulo operation.
The invention is
(7) Comparing the peak signal-to-noise ratio of the original carrier image in the step 1 with the encrypted image embedded with the watermark, and judging whether the zero watermark model provided by the invention can keep the original visual effect of the image;
the image peak signal-to-noise ratio is determined by:
i, K respectively represents an original image and a processed image; MSE is the mean square error of two pixel values; i. j represents the horizontal and vertical coordinate position of the pixel point;
representing the maximum pixel value of the image. And calling the psnr () function in MATLAB software to realize the calculation of the peak signal-to-noise ratio of the two graphs.
The images produced by the present invention were verified in MATLAB as shown in table 1.
TABLE 1 Peak Signal-to-noise ratio index PSNR
(8) And carrying out geometric attack on the encrypted image embedded with the watermark, then extracting the watermark, calculating a normalized correlation coefficient of the extracted watermark, and judging whether the zero watermark model provided by the invention has geometric attack robustness.
Carrying out geometric attack on the encrypted image embedded with the watermark, and realizing the following steps:
the method adopts 3 common geometric attack algorithms of zooming, rotating and shearing to verify, and invokes an immediate () function in MATLAB software to complete the zooming attack; invoking an imrotate () function to complete the rotation attack; setting a cutting range, and adjusting the pixel value in the cutting range to be 255 to represent white to simulate a cutting effect.
The calculation of the normalized correlation coefficient of the extracted watermark is realized by the following modes:
writing a program code in MATLAB software according to the following formula to calculate and extract a normalized correlation coefficient (NC) between the watermark image and the original watermark image:
wherein W (i, j) represents the original watermark image; w' (i, j) represents extracting a watermark image; n denotes a watermark image size. The images produced by the present invention were verified in MATLAB as shown in table 2.
TABLE 2 NC values extracted after geometric attack
As shown in fig. 11, an embodiment of the present invention further provides a zero watermark generating and analyzing apparatus, which includes a preprocessing module 1101, a reconstruction module 1102, a dimension reduction module 1103, a scrambling module 1104, an encryption module 1105, a decomposition module 1106, and a zero watermark generating module 1107;
the preprocessing module is used for preprocessing the first original carrier image and the first watermark image to obtain a second original carrier image and a second watermark image; the reconstruction module is used for reconstructing the second original carrier image to obtain a reconstructed image and acquiring a characteristic value and a characteristic value matrix before and after reconstruction of the second original carrier image; the dimension reduction module is used for reducing the dimension of the reconstructed image to obtain mapping and acquiring the example hit number and the weight position of the mapping; the scrambling module is used for performing scrambling processing on the second watermark image according to the characteristic value and the characteristic value matrix to obtain a scrambled image; the encryption module is used for encrypting the scrambled image to obtain a third watermark image; the decomposition module is used for performing decomposition on the second original carrier image to obtain singular values and singular value mean values, and constructing a characteristic singular value matrix according to the singular values and the singular value mean values; and the zero watermark generating module is used for determining the target zero watermark according to the second original carrier image and the characteristic singular value matrix.
Exemplarily, under the cooperation of the preprocessing module, the reconstruction module, the dimension-reducible module, the scrambling module, the encryption module, the decomposition module, and the zero-watermark generating module in the apparatus, the apparatus of the embodiment may implement any one of the foregoing zero-watermark generating methods, that is, in response to a generation request, obtaining a first original carrier image and a first watermark image, and performing preprocessing on the first original carrier image and the first watermark image to obtain a second original carrier image and a second watermark image; reconstructing the second original carrier image to obtain a reconstructed image, and acquiring a characteristic value and a characteristic value matrix before and after reconstruction of the second original carrier image; reducing the dimension of the reconstructed image to obtain mapping, and acquiring the example hit number and the weight position of the mapping; performing scrambling processing on the second watermark image according to the characteristic value and the characteristic value matrix to obtain a scrambled image; encrypting the scrambled image to obtain a third watermark image; performing decomposition on the second original carrier image to obtain singular values and singular value mean values, and constructing a characteristic singular value matrix according to the singular values and the singular value mean values; and determining the target zero watermark according to the second original carrier image and the characteristic singular value matrix. The method utilizes analysis and reconstruction of images, dimension reduction, mapping and scrambling to construct an encrypted watermark model, and utilizes singular value mean to construct a characteristic singular value matrix to obtain the target zero watermark.
The embodiment of the invention also provides the electronic equipment, which comprises a processor and a memory;
the memory stores a program;
the processor executes the program to execute the zero watermark generation method; the electronic device has a software function of loading and operating the zero watermark generation provided by the embodiment of the present invention, for example, a Personal Computer (PC), a mobile phone, a smart phone, a Personal Digital Assistant (PDA), a wearable device, a pocket PC, a tablet PC, and the like.
An embodiment of the present invention further provides a computer-readable storage medium, where the storage medium stores a program, and the program is executed by a processor to implement the zero watermark generating method described above.
In alternative embodiments, the functions/acts noted in the block diagrams may occur out of the order noted in the operational illustrations. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality/acts involved. Furthermore, the embodiments presented and described in the flow charts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logic flows presented herein. Alternative embodiments are contemplated in which the order of various operations is changed and in which sub-operations described as part of larger operations are performed independently.
The embodiment of the invention also discloses a computer program product or a computer program, which comprises computer instructions, and the computer instructions are stored in a computer readable storage medium. The computer instructions may be read by a processor of a computer device from a computer-readable storage medium, and the computer instructions executed by the processor cause the computer device to perform the zero-watermark generation method described above.
Furthermore, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and/or features may be integrated in a single physical device and/or software module, or one or more functions and/or features may be implemented in a separate physical device or software module. It will also be appreciated that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, the actual implementation of the various functional modules in the apparatus disclosed herein will be understood within the ordinary skill of an engineer, given the nature, function, and internal relationship of the modules. Accordingly, those skilled in the art can, using ordinary skill, practice the invention as set forth in the claims without undue experimentation. It is also to be understood that the specific concepts disclosed are merely illustrative of and not intended to limit the scope of the invention, which is defined by the appended claims and their full scope of equivalents.
The functions, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.
More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
While embodiments of the invention have been shown and described, it will be understood by those of ordinary skill in the art that: various changes, modifications, substitutions and alterations can be made to the embodiments without departing from the principles and spirit of the invention, the scope of which is defined by the claims and their equivalents.
While the preferred embodiments of the present invention have been illustrated and described, it will be understood by those skilled in the art that various changes in form and details may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (12)
1. A zero watermark generation method, comprising:
responding to a generation request, acquiring a first original carrier image and a first watermark image, and performing preprocessing on the first original carrier image and the first watermark image to obtain a second original carrier image and a second watermark image;
reconstructing the second original carrier image to obtain a reconstructed image, and acquiring a characteristic value and a characteristic value matrix before and after reconstruction of the second original carrier image;
reducing the dimension of the reconstructed image to obtain a mapping, and acquiring an example hit number and a weight position of the mapping;
performing scrambling processing on the second watermark image according to the characteristic value and the characteristic value matrix to obtain a scrambled image;
encrypting the scrambled image to obtain a third watermark image;
performing decomposition on the second original carrier image to obtain singular values and singular value mean values, and constructing a characteristic singular value matrix according to the singular values and the singular value mean values;
and determining a target zero watermark according to the second original carrier image and the characteristic singular value matrix.
2. The zero-watermark generating method according to claim 1, wherein the performing reconstruction on the second original carrier image to obtain a reconstructed image comprises:
performing dimensionality reduction processing on the original carrier image by a PCA (principal component analysis) method to obtain a reconstructed image;
the PCA analysis method comprises the steps of obtaining the size of the second original carrier image, calculating the pixel mean value of the second original carrier image according to columns, and calculating the pixel mean value of the second original carrier image according to a formula
Cov(X,Y)＝E((X-E(Y)(Y-E(Y))，
And calculating covariance of each column, and determining dimension of a reconstructed image according to visual loss caused by minimum dimension reduction, wherein E () represents expectation, X is expectation of pixels of a row of the first original carrier image, and Y is expectation of pixels of a row of the first original carrier image, E (Y) is expectation of pixels of a column of the second original carrier image.
3. The method according to claim 2, wherein the obtaining the eigenvalue and the eigenvalue matrix before and after the reconstruction of the second original carrier image comprises:
and performing descending order arrangement on the covariance of each column, selecting k maximum values in the covariance of each column, determining eigenvectors of the covariance of the k maximum values, and forming an eigenvector matrix by taking the eigenvectors as column vectors respectively.
4. The method of claim 1, wherein the reducing dimensions of the reconstructed image to obtain a mapping and obtaining the number of example hits and the position of the weight of the mapping comprises:
establishing a self-organizing mapping neural network, executing reconstructed image input through the self-organizing mapping neural network according to a Kohonen learning rule, outputting a matrix with a dimensionality of 4 orders, and executing training to obtain the mapping;
and recording the example hit number and the weight position obtained in the training process.
5. The method according to claim 1, wherein the performing scrambling processing on the second watermark image according to the eigenvalue and the eigenvalue matrix to obtain a scrambled image comprises:
reading the second watermark image, obtaining the size of the second watermark image, setting the size as the maximum cycle number of the calculation process, and executing Arnold scrambling processing, wherein the Arnold scrambling parameter is set as the Arnold scrambling parameter
Where x, y denote the position of the image pixel before transformation, xn+1、yn+1The pixel position after transformation is shown, N represents the current transformation frequency, N represents the image size, mod is a modulus operation, a, b and N are parameters, and a, b and N are obtained by the following steps:
wherein a is the number of the feature values before reconstruction of the second original carrier image, b is the number of the feature values after reconstruction of the second original carrier image, and n is the arithmetic square root of the pixel mean value of the reconstructed image.
6. A zero watermark generation method according to claim 1, wherein the encrypting the scrambled image to obtain a third watermark image comprises:
generating a Logistic chaotic sequence through Logistic mapping, wherein the Logistic mapping comprises the following steps:
setting a system parameter u and a system initial value x of Logitics mapping, wherein u is any positive integer, and the value range of x is [0,1 ];
the calculation mode through Logitics mapping is
xn+1＝xnu(1-xn)；xn∈[-1,1]
Where u is the maximum of the example number of hits and x is the average of the weight positions;
and transforming the Logistic chaotic sequence into a substitution value encryption sequence y through an auxiliary key, sequentially replacing pixels of the scrambled image by using the encryption sequence y, and outputting the image with the pixels replaced.
7. A zero-watermark generation method according to claim 6, wherein the sequentially replacing pixels of the scrambled image with an encryption sequence y comprises:
performing bitwise logical operation on the scrambled image, judging whether each pixel value is a prime number according to the sequence from top to bottom and from left to right, and if the pixel value is a prime number, performing the following calculation on the pixels of the scrambled image by using a y sequence:
k(n)＝[(y×1015)％256]wherein]For rounding operations,% is a remainder operation, otherwise, the pixel value is kept unchanged.
8. The method of claim 6, wherein the performing decomposition on the second original carrier image to obtain singular values and singular value means, and constructing a characteristic singular value matrix according to the singular values and the singular value means includes:
acquiring the singular value of the second original carrier image, and calculating the singular value mean value;
by the formula
Constructing the characteristic singular value matrix;
and carrying out XOR operation on the second original carrier image and the characteristic singular value matrix to obtain the target zero watermark model.
9. A zero watermark generation method according to claim 1, wherein the method further comprises:
performing peak signal-to-noise ratio comparison on the second original carrier image and a third watermark image to obtain a comparison result, and determining the visual effect of the first original carrier image maintained by the target zero watermark;
or performing geometric attack on the third watermark image, extracting the target zero watermark, calculating a normalized correlation coefficient of the extracted watermark, and determining the geometric attack robustness of the target zero watermark according to the normalized correlation coefficient.
10. A zero watermark generation apparatus, comprising:
the initialization module is used for responding to a generation request, acquiring a first original carrier image and a first watermark image, and performing preprocessing on the first original carrier image and the first watermark image to obtain a second original carrier image and a second watermark image;
the reconstruction module is used for reconstructing the second original carrier image to obtain a reconstructed image and acquiring a characteristic value and a characteristic value matrix before and after reconstruction of the second original carrier image;
the dimension reduction module is used for reducing the dimension of the reconstructed image to obtain mapping and acquiring the example hit number and the weight position of the mapping;
the scrambling module is used for performing scrambling processing on the second watermark image according to the characteristic value and the characteristic value matrix to obtain a scrambled image;
the encryption module is used for encrypting the scrambled image to obtain a third watermark image;
the decomposition module is used for performing decomposition on the second original carrier image to obtain singular values and singular value mean values, and constructing a characteristic singular value matrix according to the singular values and the singular value mean values;
and the zero watermark generating module is used for determining a target zero watermark according to the second original carrier image and the characteristic singular value matrix.
11. An electronic device comprising a processor and a memory;
the memory is used for storing programs;
the processor executes the program to implement the zero watermark generation method of any one of claims 1-9.
12. A computer-readable storage medium, characterized in that the storage medium stores a program, which is executed by a processor to implement the zero watermark generation method according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210086245.5A CN114511435A (en) | 2022-01-25 | 2022-01-25 | Zero watermark generation method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210086245.5A CN114511435A (en) | 2022-01-25 | 2022-01-25 | Zero watermark generation method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114511435A true CN114511435A (en) | 2022-05-17 |
Family
ID=81549284
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210086245.5A Pending CN114511435A (en) | 2022-01-25 | 2022-01-25 | Zero watermark generation method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114511435A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036145A (en) * | 2023-10-07 | 2023-11-10 | 江西财经大学 | Meta-universe light field image robust zero watermarking method, system, equipment and storage medium |
-
2022
- 2022-01-25 CN CN202210086245.5A patent/CN114511435A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117036145A (en) * | 2023-10-07 | 2023-11-10 | 江西财经大学 | Meta-universe light field image robust zero watermarking method, system, equipment and storage medium |
| CN117036145B (en) * | 2023-10-07 | 2024-01-09 | 江西财经大学 | Meta-universe light field image robust zero watermarking method, system, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wan et al. | A comprehensive survey on robust image watermarking | |
| Fang et al. | Screen-shooting resilient watermarking | |
| Islam et al. | Geometric distortion correction based robust watermarking scheme in LWT-SVD domain with digital watermark extraction using SVM | |
| Li et al. | A QDCT-and SVD-based color image watermarking scheme using an optimized encrypted binary computer-generated hologram | |
| Murali et al. | An efficient ROI based copyright protection scheme for digital images with SVD and orthogonal polynomials transformation | |
| Gul et al. | A novel pixel-wise authentication-based self-embedding fragile watermarking method | |
| Neekhara et al. | FaceSigns: semi-fragile neural watermarks for media authentication and countering deepfakes | |
| Aparna et al. | A blind medical image watermarking for secure e-healthcare application using crypto-watermarking system | |
| Pal et al. | A secure reversible color image watermarking scheme based on LBP, lagrange interpolation polynomial and weighted matrix | |
| Tang et al. | An end-to-end screen shooting resilient blind watermarking scheme for medical images | |
| Wu et al. | An image authentication and recovery system based on discrete wavelet transform and convolutional neural networks | |
| Aberna et al. | Vision transformer-based watermark generation for authentication and tamper detection using schur decomposition and hybrid transforms | |
| CN114511435A (en) | Zero watermark generation method and device, electronic equipment and storage medium | |
| Li et al. | A reversible watermarking for image content authentication based on wavelet transform | |
| Xia et al. | Improved PHARM for JPEG steganalysis: Making PHARM more efficient and effective | |
| Melman et al. | Methods for countering attacks on image watermarking schemes: Overview | |
| Li et al. | Block mapping and dual-matrix-based watermarking for image authentication with self-recovery capability | |
| Shankar et al. | Moderate embed cross validated and feature reduced Steganalysis using principal component analysis in spatial and transform domain with Support Vector Machine and Support Vector Machine-Particle Swarm Optimization | |
| Gao et al. | Steganographic secret sharing via AI-generated photorealistic images | |
| Cu et al. | A robust data hiding scheme using generated content for securing genuine documents | |
| CN114330621A (en) | Two-dimensional code anti-counterfeiting method and device based on identification information and storage medium | |
| Aslam et al. | Image Forgery Detection Using Convolutional Neural Network | |
| Gorle et al. | A novel dynamic image watermarking technique with features inspired by quantum computing principles | |
| Song et al. | A survey on Deep-Learning-based image steganography | |
| Moataz | Watermarking medical scans: Saliency filter pixels |
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 |