CN111598763B - Method and system for extracting hidden watermark based on mobile phone and image enhancement - Google Patents
Method and system for extracting hidden watermark based on mobile phone and image enhancement Download PDFInfo
- Publication number
- CN111598763B CN111598763B CN202010352108.2A CN202010352108A CN111598763B CN 111598763 B CN111598763 B CN 111598763B CN 202010352108 A CN202010352108 A CN 202010352108A CN 111598763 B CN111598763 B CN 111598763B
- Authority
- CN
- China
- Prior art keywords
- watermark
- image
- mobile phone
- gray
- printing
- 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.)
- Active
Links
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
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2201/00—General purpose image data processing
- G06T2201/005—Image watermarking
- G06T2201/0065—Extraction of an embedded watermark; Reliable detection
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Editing Of Facsimile Originals (AREA)
- Image Processing (AREA)
Abstract
The invention relates to a method and a system for extracting a hidden watermark based on mobile phone and image enhancement, which utilizes the phenomenon that human eyes are insensitive to yellow, a hidden watermark with gray scale within a preset range is manually generated on a color channel, the printed matter printed with the hidden watermark is not perceived by human eyes to have watermark patterns, when the printed matter is shot by a mobile phone, the contents such as an image or coding information of the hidden watermark can be displayed on a mobile phone screen in real time through a watermark extraction algorithm and an image enhancement algorithm, and when the printed matter is duplicated, the mobile phone shoots the duplicated image again, the hidden watermark image disappears or weakens due to duplication, the hidden watermark coding information is obviously changed, and the mobile phone can accurately, conveniently and rapidly deduce whether the printed matter is a genuine or a duplicate through an identification algorithm, so that the practicability is high.
Description
Technical Field
The invention relates to a method for extracting a hidden watermark, in particular to a method and a system for extracting a hidden watermark based on mobile phones and image enhancement.
Background
At present, the more convenient the original document is copied, the higher the fineness is, and the more difficult is to distinguish the original document from the copied document. At present, a common method is to use special paper or print with special ink to help people to rapidly distinguish original documents from duplicate documents, but the method increases the use cost, even needs special printing equipment to cooperate, and limits the application range.
Disclosure of Invention
The invention aims to: a method for extracting hidden watermark based on mobile phone and image enhancement is provided to solve the above-mentioned shortcomings existing in the prior art. It is a further object to provide a system implementing the above method.
The technical scheme is as follows: a method for extracting a hidden watermark based on mobile phone and image enhancement comprises the following steps:
step 1, printing and manufacturing: calculating the watermark gray scale range of a printer or a yellow channel of the printer by utilizing the chromatogram, manufacturing a hidden watermark according to the obtained gray scale range, and printing;
step 2, watermark detection: shooting the printed matter containing the hidden watermark, and enhancing the image according to the set parameters so that the hidden watermark is displayed on the mobile phone screen.
In a further embodiment, the step 1 further includes:
step 1-1, generating a standard chromatogram electronic graph, and generating 256 gray scale blocks with gray scale values ranging from 1 to 256 gray scales, wherein 1 is the shallowest, and 256 is the deepest;
step 1-2, printing a standard chromatogram, and printing a chromatogram gray scale block of a Y channel by using a printer to obtain a chromatogram of the Y color channel;
step 1-3, detecting gray blocks of a printing chromatogram by a mobile phone provided with an image enhancement program, searching color blocks with lowest gray values, which can be detected on a mobile phone screen, wherein the gray values of the color blocks in the original standard chromatogram are marked as the lower limit of the gray value range of a preset dark mark pattern;
step 1-4, observing gray blocks of the printing chromatograms by naked eyes, searching color blocks with lowest macroscopic gray values, and marking the gray values of the color blocks in the original standard chromatograms as the upper limit of the gray value range of the preset dark mark pattern.
In a further embodiment, the step 2 further includes: shooting a document by using a preset program at a mobile phone end, after a shot image is obtained, extracting a hidden watermark by the program through a watermark extraction algorithm and an image enhancement algorithm, and enhancing the image of the hidden watermark, so that the hidden watermark is displayed on a mobile phone screen, and roughly judging whether the document is a genuine print or not according to the hidden watermark displayed on the mobile phone screen;
if the printed matter is a copy, the hidden watermark image is weakened or vanished at the moment, the hidden watermark coding information is changed at the moment, and whether the printed matter is the copy is identified through an identification algorithm.
In a further embodiment, after obtaining the hidden watermark image at the specific position by using the mobile phone or the detector, the background simultaneously performs integrity analysis on the extracted hidden watermark, when the integrity is lower than a certain set threshold, the watermark identification result is given as a replica, otherwise, the identification result is given as a genuine print, so as to provide an objective judgment result of the genuine print or the duplicate print.
In a further embodiment, the step of the image enhancement algorithm in step 2 comprises:
step 2-1, setting three groups of parameters (Lsize 1, lsize 2), (Msize 1, msize 2), (Fsize 1, fsize 2), and meeting the conditions that Lsize1 is larger than or equal to Msize1 is larger than or equal to Fsize1, lsize2 is larger than or equal to Msize2 is larger than or equal to Fsize2, meanwhile, the shot pictures are partitioned according to (Fsize 1, fsize 2), the size of each block is Fsize1, fsize2, and when the blocks are partitioned, the part of the pictures which is remained and is smaller than Fsize1 or Fsize2 is discarded, or the part is supplemented to be Fsize1, fsize 2;
step 2-2, calculating an optimal binarization threshold value of a region of Lsize1 x Lsize2 around each block by using a maximum inter-class threshold value method, performing image binarization on the range of the region of Msize1 x Msize2 around the block by using the calculated threshold value, and overlapping and accumulating all blocks of Msize1 x Msize2 according to corresponding spatial positions;
step 2-3, dividing the accumulated image by the evolution value of [ (Msize 1/Fsize 1) × (Msize 2/Fsize 2) ] to obtain the image-enhanced watermark image.
In a further embodiment, the step of the watermark extraction algorithm comprises:
step 3-1, performing edge extraction on the hidden watermark after image enhancement by using an edge detection algorithm;
step 3-2, scaling the extracted hidden watermark according to the preset size according to the edge of the extracted hidden watermark;
and 3-3, calculating the correlation between the extracted hidden watermark and the original watermark in the database by using an image matching algorithm, and when the correlation exceeds a preset threshold value, considering that the hidden watermark is from the original document, otherwise, considering that the hidden watermark is from the copy document.
In a further embodiment, for the paper with different base colors, according to the method of step 1, the gray value range of the watermark Y channel of the paper is calculated and stored in the watermark generating software, and when the watermark pattern is generated on the base color paper, the electronic diagram of the watermark pattern is adjusted according to the gray parameters.
A watermark extraction system based on mobile phone and image enhancement comprises a first module for making watermark according to the obtained gray scale range; and a second module for enhancing the image according to the set parameters; the first module further calculates a watermark gray scale range of a printer or a yellow channel of the printer by utilizing the chromatogram, and makes a hidden watermark according to the obtained gray scale range and prints the hidden watermark; and the second module further shoots the printed matter containing the hidden watermark, and enhances the image according to the set parameters so that the hidden watermark is displayed on the mobile phone screen.
In a further embodiment, the first module further obtains the printing characteristics of the printer or the printing machine by printing or printing a standard yellow channel chromatogram at the printing or printing manufacturing stage, scans or copies the printed standard yellow channel chromatogram by a standard scanner, compares the difference of the front and rear images, and calculates a yellow channel gray value range of a preset dark mark pattern; carrying out gray value adjustment on a given pattern according to the obtained gray range so that the gray value of the pattern is within the gray value range of the yellow channel, and then printing or printing out a printed matter according to a normal flow;
wherein the step of calculating the gray scale range is as follows: firstly, generating a standard chromatogram electronic graph, and generating 256 gray blocks with gray values ranging from 1 to 256 gray, wherein 1 is shallowest, and 256 is deepest; then printing a standard chromatogram, and printing a chromatogram gray scale block of a Y channel by using a printer to obtain a chromatogram of the Y color channel; then detecting gray blocks of the printing chromatograms through a mobile phone provided with an image enhancement program, searching color blocks which can be detected on a mobile phone screen and have the lowest gray values, wherein the gray values of the color blocks in the original standard chromatograms are marked as the lower limit of the gray value range of the preset dark mark patterns; finally, the gray blocks of the printing chromatograms are observed by naked eyes, and the color blocks with the lowest gray values visible by naked eyes are searched, and the gray values of the color blocks in the original standard chromatograms are marked as the upper limit of the gray value range of the preset dark mark pattern;
the second module further shoots the document by using a preset program at the mobile phone end, after a shot image is obtained, the program extracts the hidden watermark through a watermark extraction algorithm and an image enhancement algorithm and enhances the image of the hidden watermark, so that the hidden watermark is displayed on the mobile phone screen, and whether the document is a genuine print is roughly judged according to the hidden watermark displayed on the mobile phone screen; if the printed matter is a copy, the hidden watermark image is weakened or vanished at the moment, the hidden watermark coding information is changed at the moment, and whether the printed matter is a copy is identified by an identification algorithm;
wherein the image enhancement algorithm comprises the following steps: setting three groups of parameters (Lsize 1, lsize 2), (Msize 1, msize 2), (Fsize 1, fsize 2) and meeting the conditions that Lsize1 is larger than or equal to Msize1 is larger than or equal to Fsize1, lsize2 is larger than or equal to Msize2, meanwhile, the size of each block is Fsize1 and Fsize2 when the photographed picture is segmented, and when the pictures are segmented, the part of the picture which is remained and is smaller than Fsize1 or Fsize2 is discarded or is complemented with the size of Fsize1 and Fsize 2; calculating an optimal binarization threshold value of each block peripheral Lsize 1-Lsize 2 region by using a maximum inter-class threshold value method, performing image binarization on the range of the block peripheral Msize 1-Msize 2 region by using the calculated threshold value, and overlapping and accumulating all the blocks of the Msize 1-Msize 2 according to the corresponding spatial positions; dividing the accumulated image by the square value of [ (Msize 1/Fsize 1) × (Msize 2/Fsize 2) ] to obtain an image-enhanced watermark image;
wherein the watermark extraction algorithm comprises the steps of: performing edge extraction on the hidden watermark after image enhancement by using an edge detection algorithm; scaling the extracted hidden watermark according to a preset size according to the extracted hidden watermark edge; calculating the correlation between the extracted hidden watermark and the original watermark in the database by using an image matching algorithm, and when the correlation exceeds a preset threshold value, considering that the hidden watermark is from an original edition document, otherwise, considering that the hidden watermark is from a copy document;
after obtaining the hidden watermark image at the specific position by using the mobile phone or the detector, the background simultaneously carries out integrity analysis on the extracted hidden watermark, when the integrity is lower than a certain set threshold, the watermark identification result is a replica, otherwise, the identification result is a genuine print, so as to provide an objective judgment result of the genuine print or the duplicate print.
The beneficial effects are that: the invention provides a method for extracting hidden watermark based on mobile phone and image enhancement, which utilizes the sensitivity difference of human eyes to different colors to obtain an optimal color channel, generates hidden watermark with gray scale within a preset range on the color channel, prints printed matter with hidden watermark, the human eyes can not perceive watermark patterns, when the printed matter is shot by the mobile phone, the image or code information of the hidden watermark can be displayed on the mobile phone screen in real time through the watermark extraction algorithm and the image enhancement algorithm, when the printed matter is duplicated, the mobile phone shoots duplication again, the hidden watermark image disappears or weakens because of duplication, the hidden watermark code information can be obviously changed, and the mobile phone can accurately, conveniently and rapidly infer whether the printed matter is a genuine version or a duplicate version through the identification algorithm, thereby having high practicability.
Drawings
FIG. 1 is a schematic flow chart of the invention.
Fig. 2 is a schematic diagram of the present invention for blocking an image.
FIG. 3 is a block size diagram of the present invention.
Detailed Description
The applicant believes that the original copy document is more convenient, the fineness is higher and the original copy document is more difficult to distinguish from the copy document, therefore, the invention provides a hidden watermark scheme which is convenient, quick and accurate to distinguish the copy.
Therefore, the method for extracting the hidden watermark based on the mobile phone and the image enhancement, which is provided by the applicant, can provide a method for rapidly and accurately identifying the authenticity of the document on the basis of not increasing the printing cost and changing the printing process.
The technical scheme of the invention is further described below through embodiments and with reference to the corresponding drawings.
The sensitivity of the human eye is different for different colors, for example, red and black are the highest, blue is sequentially carried out, and yellow is the lowest. The mobile phone has different shooting reduction degrees for different colors, for example, red and black have the highest reduction degree, and then yellow and blue have the lowest reduction degree.
By utilizing the characteristic, the hidden watermark with gray scale within a certain range can be manually generated on the yellow channel, the printed matter printed with the hidden watermark is not perceived by human eyes, when the printed matter is shot by a mobile phone, the contents such as the image or the coding information of the hidden watermark can be displayed on the screen of the mobile phone in real time through a watermark extraction algorithm and an image enhancement algorithm, when the printed matter is copied, the mobile phone shoots the copy again, the hidden watermark image disappears or weakens because of the copying, the hidden watermark coding information can be obviously changed, and the mobile phone can accurately infer whether the printed matter is a genuine or a copy through a recognition algorithm.
The scheme includes two stages of printing or printing making and watermark detection. In the printing or printing manufacturing stage, the printing characteristics of a printer or a printing machine are obtained by printing or printing a standard yellow channel chromatogram, then the standard yellow channel chromatogram printed by scanning or copying by a standard scanner is compared with the difference of the front and rear images, and the yellow channel gray value range of the preset dark mark pattern is calculated. The production of the hidden watermark is to adjust the gray value of a given pattern according to the obtained gray range so that the gray value of the pattern is within the gray value range of the yellow channel, and then print or print the printed matter according to the normal flow.
Specifically, the method for calculating the gray scale range is as follows:
(1) And generating a standard chromatogram electronic map. With software, 256 gradation blocks (1 shallowest and 256 deepest) having gradation values from 1 to 256 gradations are generated.
(2) And printing a standard chromatogram. And printing the chromatogram gray scale blocks of the Y channel by using a printer to obtain the chromatograms of the Y color channels.
(3) Detecting gray blocks of a printing chromatogram by a mobile phone provided with an image enhancement program, searching color blocks with the lowest gray values, which can be detected on a mobile phone screen, wherein the gray values of the color blocks in the original standard chromatogram are the lower limit of the gray value range of a preset dark mark pattern.
(4) And (3) searching color blocks with lowest macroscopic gray values by visually observing gray blocks of the printing chromatograms, wherein the gray values of the color blocks in the original standard chromatograms are the upper limit of the gray value range of the preset dark mark pattern.
In the detection stage, a WeChat applet at the mobile phone end is used for shooting a document, after the applet obtains a shot image, the image is enhanced according to set parameters, so that a hidden watermark is displayed on a mobile phone screen, and people can roughly judge whether the document is a genuine print according to the hidden watermark displayed on the mobile phone screen.
Specifically, the image enhancement method is as follows: (the following steps are image enhancement algorithm)
(1) Setting three groups of parameters (Lsize 1, lsize 2), (Msize 1, msize 2), (Fsize 1, fsize 2) and meeting the conditions that Lsize1 is larger than or equal to Msize1 is larger than or equal to Fsize1, lsize2 is larger than or equal to Msize2, meanwhile, the size of each block is Fsize1 and Fsize2 when the photographed picture is segmented, and when the pictures are segmented, the part of the picture which is remained and is smaller than Fsize1 or Fsize2 is discarded or is complemented with the size of Fsize1 and Fsize 2;
(2) Calculating an optimal binarization threshold value of each block peripheral Lsize 1-Lsize 2 region by using a maximum inter-class threshold value method, performing image binarization on the range of the block peripheral Msize 1-Msize 2 region by using the calculated threshold value, and overlapping and accumulating all the blocks of the Msize 1-Msize 2 according to the corresponding spatial positions;
(3) The accumulated image is divided by the square value of [ (Msize 1/Fsize 1) × (Msize 2/Fsize 2) ] to obtain an image-enhanced watermark image.
To specifically describe the process of image enhancement, pseudo code involved in image enhancement is given below:
1. obtaining an image pic, setting the sizes of Lsize, msize and Fsize, setting picM to be the same as pic in size, and setting each pixel value to be 0;
2. blocking the original image pic according to Fsize;
3. selecting a certain partition F in sequence;
4. selecting an image block L containing the block F and having a size of Lsize;
5. calculating an optimal binarization threshold value LevelScale of the image block L by using an Ojin method;
6. selecting an image block M which comprises a partition F and is positioned inside the image block L and has the size of Msize;
7. binarizing the image block M according to the LevelScale;
8. m is accumulated in picM according to its spatial position in pic: picm=picm+m;
9. repeating 3-8 until all the blocks are calculated;
normalization:
obtaining the hidden watermark.
Further, after the mobile phone extracts the hidden watermark, the background simultaneously analyzes the integrity of the extracted hidden watermark, when the integrity is lower than a certain set threshold, the watermark identification result is a replica, otherwise, the identification result is a genuine print, so that an objective judgment result of the genuine print or the duplicate print is provided.
Carrying out integrity analysis of the hidden watermark by calculating the correlation D between the extracted watermark pattern W and the original watermark W0 in the database, and considering that the extracted watermark W is complete when the value of D is smaller than or equal to a preset threshold value; when the value of D is greater than the preset threshold, the extracted watermark W is considered to be incomplete, and the specific calculation method of the correlation D is as follows:
wherein, (i, j) represents a coordinate point on the watermark map, W represents the watermark map extracted by calculation, and W0 represents the original watermark in the database;
the quality of an image can also be determined by the gray value correlation, which is defined as:
wherein A is i，j Gray value representing point (i, j) on watermark pattern A, B i，j Representing the (i, j) point on the watermark map BIs a gray value of (a).
According to experimental statistics of a certain brand printer on white paper, the gray scale range of a yellow channel (Y channel): 1-10 (the upper and lower limits of gray scale are 1-256).
| Printer brand | Y-channel gray value range |
| Kemei C458 | 1-10 |
| Hewlett-packard M750 | 1-8 |
| Canon WG7850 | 3-10 |
| Epson WF-C869 | 2-8 |
| Schle 7800 | 3-12 |
| Light management DD5450C | 1-10 |
Table 1 gray value ranges for Y-channel hidden watermarks for different printers
The dark mark pattern can be words, patterns, figures and images with gray scale meeting the characteristic requirements of a printer or a printer within a certain range. The coded information of the secret mark can be fixed or variable. The default paper is white in color, if the paper is other colors, the test process of 3 is required to be repeated on the paper, the gray value range of the watermark yellow channel of the dark mark generated on the paper by a printer or a printer is obtained and stored in the dark mark generating software, and when the dark mark pattern is generated on the paper with the color, the electronic diagram of the dark mark pattern is adjusted according to the gray parameter. The standard chromatogram is a color patch with gray values ranging from 1 to 256 in sequence on the Y channel.
As described above, although the present invention has been shown and described with reference to certain preferred embodiments, it is not to be construed as limiting the invention itself. 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 (9)
1. A method for extracting a hidden watermark based on mobile phone and image enhancement is characterized by comprising the following steps:
step 1, printing and manufacturing: calculating the watermark gray scale range of a printer or a yellow channel of the printer by utilizing the chromatogram, manufacturing a hidden watermark according to the obtained gray scale range, and printing;
in the printing or printing manufacturing stage, firstly, printing or printing a standard yellow channel chromatogram to obtain the printing characteristic of a printer or a printing machine, then scanning or copying the printed standard yellow channel chromatogram by a standard scanner, comparing the difference of the front and rear images, and calculating the gray value range of the yellow channel of a preset dark mark pattern; carrying out gray value adjustment on a given pattern according to the obtained gray range so that the gray value of the pattern is within the gray value range of the yellow channel, and then printing or printing out a printed matter according to a normal flow;
step 2, watermark detection: shooting the printed matter containing the hidden watermark, and enhancing the image according to the set parameters so that the hidden watermark is displayed on the mobile phone screen.
2. The method for extracting a watermark from a mobile phone and image enhancement according to claim 1, wherein the step of calculating the gray scale range in step 1 further comprises:
step 1-1, generating a standard chromatogram electronic graph, and generating 256 gray scale blocks with gray scale values ranging from 1 to 256 gray scales, wherein 1 is the shallowest, and 256 is the deepest;
step 1-2, printing a standard chromatogram, and printing a chromatogram gray scale block of a yellow channel by using a printer to obtain a chromatogram of the yellow channel;
step 1-3, detecting gray blocks of a printing chromatogram by a mobile phone provided with an image enhancement program, searching color blocks with lowest gray values, which can be detected on a mobile phone screen, wherein the gray values of the color blocks in the original standard chromatogram are marked as the lower limit of the gray value range of a preset dark mark pattern;
step 1-4, observing gray blocks of the printing chromatograms by naked eyes, searching color blocks with lowest macroscopic gray values, and marking the gray values of the color blocks in the original standard chromatograms as the upper limit of the gray value range of the preset dark mark pattern.
3. The method for extracting a watermark from a mobile phone and image enhancement according to claim 1, wherein said step 2 further comprises:
shooting a document by using a preset program at a mobile phone end, after a shot image is obtained, extracting a hidden watermark by the program through a watermark extraction algorithm and an image enhancement algorithm, and enhancing the image of the hidden watermark, so that the hidden watermark is displayed on a mobile phone screen, and roughly judging whether the document is a genuine print or not according to the hidden watermark displayed on the mobile phone screen;
if the printed matter is a copy, the hidden watermark image is weakened or vanished at the moment, the hidden watermark coding information is changed at the moment, and whether the printed matter is the copy is identified through an identification algorithm.
4. A method for extracting a hidden watermark based on mobile phone and image enhancement according to claim 3, wherein: after obtaining the hidden watermark image at the specific position by using the mobile phone or the detector, the background simultaneously carries out integrity analysis on the extracted hidden watermark, when the integrity is lower than a certain set threshold, the watermark identification result is a replica, otherwise, the identification result is a genuine print, so as to provide an objective judgment result of the genuine print or the duplicate print.
5. The method for extracting the hidden watermark based on the mobile phone and the image enhancement according to claim 1, wherein the step of the image enhancement algorithm in the step 2 comprises the following steps:
step 2-1, setting three groups of parameters (Lsize 1, lsize 2), (Msize 1, msize 2), (Fsize 1, fsize 2), and meeting the conditions that Lsize1 is larger than or equal to Msize1 is larger than or equal to Fsize1, lsize2 is larger than or equal to Msize2 is larger than or equal to Fsize2, meanwhile, the shot pictures are partitioned according to (Fsize 1, fsize 2), the size of each block is Fsize1, fsize2, and when the blocks are partitioned, the part of the pictures which is remained and is smaller than Fsize1 or Fsize2 is discarded, or the part is supplemented to be Fsize1, fsize 2;
step 2-2, calculating an optimal binarization threshold value of a region of Lsize1 x Lsize2 around each block by using a maximum inter-class threshold value method, performing image binarization on the range of the region of Msize1 x Msize2 around the block by using the calculated threshold value, and overlapping and accumulating all blocks of Msize1 x Msize2 according to corresponding spatial positions;
step 2-3, dividing the accumulated image by the evolution value of [ (Msize 1/Fsize 1) × (Msize 2/Fsize 2) ] to obtain the image-enhanced watermark image.
6. A method of extracting a watermark from a mobile phone and image enhancement based on claim 3, wherein the step of the watermark extraction algorithm comprises:
step 3-1, performing edge extraction on the hidden watermark after image enhancement by using an edge detection algorithm;
step 3-2, scaling the extracted hidden watermark according to the preset size according to the edge of the extracted hidden watermark;
and 3-3, calculating the correlation between the extracted hidden watermark and the original watermark in the database by using an image matching algorithm, and when the correlation exceeds a preset threshold value, considering that the hidden watermark is from the original document, otherwise, considering that the hidden watermark is from the copy document.
7. The method for extracting the watermark from the watermark based on the mobile phone and the image enhancement according to claim 1, wherein for the paper with different base colors, according to the method of step 1, the gray value range of the yellow channel of the watermark with different base colors is calculated and stored in the watermark generating software, and then when the watermark pattern is generated on the paper with the corresponding base color, the electronic diagram of the watermark pattern is adjusted according to the gray parameters.
8. The hidden watermark extraction system based on mobile phone and image enhancement is characterized by comprising the following modules:
a first module for producing a buried watermark according to the obtained gray scale range;
a second module for enhancing the image according to the set parameters;
the first module is further used for obtaining the printing characteristics of a printer or the printing machine by printing or printing a standard yellow channel chromatogram at the printing or printing manufacturing stage, then scanning or copying the printed standard yellow channel chromatogram by a standard scanner, comparing the difference of the front image and the rear image, and calculating the gray value range of the yellow channel of the preset dark mark pattern; carrying out gray value adjustment on a given pattern according to the obtained gray range so that the gray value of the pattern is within the gray value range of the yellow channel, and then printing or printing out a printed matter according to a normal flow;
and the second module further shoots the printed matter containing the hidden watermark, and enhances the image according to the set parameters so that the hidden watermark is displayed on the mobile phone screen.
9. The system for extracting a watermark from a mobile phone and image enhancement as claimed in claim 8,
the step of calculating the gray scale range by the first module is as follows: firstly, generating a standard chromatogram electronic graph, and generating 256 gray blocks with gray values ranging from 1 to 256 gray, wherein 1 is shallowest, and 256 is deepest; then printing a standard chromatogram, and printing a chromatogram gray scale block of a yellow channel by using a printer to obtain a chromatogram of the yellow channel; then detecting gray blocks of the printing chromatograms through a mobile phone provided with an image enhancement program, searching color blocks which can be detected on a mobile phone screen and have the lowest gray values, wherein the gray values of the color blocks in the original standard chromatograms are marked as the lower limit of the gray value range of the preset dark mark patterns; finally, the gray blocks of the printing chromatograms are observed by naked eyes, and the color blocks with the lowest gray values visible by naked eyes are searched, and the gray values of the color blocks in the original standard chromatograms are marked as the upper limit of the gray value range of the preset dark mark pattern;
the second module further shoots the document by using a preset program at the mobile phone end, after a shot image is obtained, the program extracts the hidden watermark through a watermark extraction algorithm and an image enhancement algorithm and enhances the image of the hidden watermark, so that the hidden watermark is displayed on the mobile phone screen, and whether the document is a genuine print is roughly judged according to the hidden watermark displayed on the mobile phone screen; if the printed matter is a copy, the hidden watermark image is weakened or vanished at the moment, the hidden watermark coding information is changed at the moment, and whether the printed matter is a copy is identified by an identification algorithm;
wherein the image enhancement algorithm comprises the following steps: setting three groups of parameters (Lsize 1, lsize 2), (Msize 1, msize 2), (Fsize 1, fsize 2) and meeting the conditions that Lsize1 is larger than or equal to Msize1 is larger than or equal to Fsize1, lsize2 is larger than or equal to Msize2, meanwhile, the size of each block is Fsize1 and Fsize2 when the photographed picture is segmented, and when the pictures are segmented, the part of the picture which is remained and is smaller than Fsize1 or Fsize2 is discarded or is complemented with the size of Fsize1 and Fsize 2; calculating an optimal binarization threshold value of each block peripheral Lsize 1-Lsize 2 region by using a maximum inter-class threshold value method, performing image binarization on the range of the block peripheral Msize 1-Msize 2 region by using the calculated threshold value, and overlapping and accumulating all the blocks of the Msize 1-Msize 2 according to the corresponding spatial positions; dividing the accumulated image by the square value of [ (Msize 1/Fsize 1) × (Msize 2/Fsize 2) ] to obtain an image-enhanced watermark image;
wherein the watermark extraction algorithm comprises the steps of: performing edge extraction on the hidden watermark after image enhancement by using an edge detection algorithm; scaling the extracted hidden watermark according to a preset size according to the extracted hidden watermark edge; calculating the correlation between the extracted hidden watermark and the original watermark in the database by using an image matching algorithm, and when the correlation exceeds a preset threshold value, considering that the hidden watermark is from an original edition document, otherwise, considering that the hidden watermark is from a copy document;
after obtaining the hidden watermark image at the specific position by using the mobile phone or the detector, the background simultaneously carries out integrity analysis on the extracted hidden watermark, when the integrity is lower than a certain set threshold, the watermark identification result is a replica, otherwise, the identification result is a genuine print, so as to provide an objective judgment result of the genuine print or the duplicate print.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010352108.2A CN111598763B (en) | 2020-04-28 | 2020-04-28 | Method and system for extracting hidden watermark based on mobile phone and image enhancement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010352108.2A CN111598763B (en) | 2020-04-28 | 2020-04-28 | Method and system for extracting hidden watermark based on mobile phone and image enhancement |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111598763A CN111598763A (en) | 2020-08-28 |
| CN111598763B true CN111598763B (en) | 2023-06-02 |
Family
ID=72190765
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010352108.2A Active CN111598763B (en) | 2020-04-28 | 2020-04-28 | Method and system for extracting hidden watermark based on mobile phone and image enhancement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111598763B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114332092B (en) * | 2022-03-16 | 2022-07-26 | 北京中科慧眼科技有限公司 | Defect image detection method, system, intelligent terminal and medium |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1369376A (en) * | 2001-11-15 | 2002-09-18 | 北京中科模识科技有限公司 | Antifraud method for printed matter |
| CN100391745C (en) * | 2005-06-13 | 2008-06-04 | 北京北大方正电子有限公司 | Printing method of security file inlaid with anti-copying back-lines |
| US7925045B2 (en) * | 2007-09-10 | 2011-04-12 | Konica Minolta Systems Laboratory, Inc. | Determining document authenticity in a closed-loop process |
| CN104217392A (en) * | 2014-09-18 | 2014-12-17 | 上海理工大学 | Holographic watermark algorithm resistant to geometric attack |
| CN104376354A (en) * | 2014-11-14 | 2015-02-25 | 深圳三元色数码科技有限公司 | Dot-matrix graphic, constructing method for dot-matrix graphic and method for identifying true dot-matrix graphic |
| CN110991318A (en) * | 2019-11-29 | 2020-04-10 | 电子科技大学 | Method and system for identifying color laser printing file secret mark |
-
2020
- 2020-04-28 CN CN202010352108.2A patent/CN111598763B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111598763A (en) | 2020-08-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| EP2897082B1 (en) | Methods and systems for improved license plate signature matching | |
| US8094869B2 (en) | Fragile and emerging digital watermarks | |
| CN110717450B (en) | Training method and detection method for automatically identifying copied image of original document | |
| US8699089B2 (en) | Variable data image watermarking using infrared sequence structures in black separation | |
| US20080080009A1 (en) | Electronic watermark embedding apparatus and electronic watermark detection apparatus | |
| JP5178925B2 (en) | Void pantograph and method for generating void pantograph | |
| US9159112B2 (en) | Digital watermarking using saturation patterns | |
| US11315378B2 (en) | Method of verifying an authenticity of a printed item and data processing terminal | |
| JPWO2006106677A1 (en) | Printed matter, detection method and detection device for the printed matter, and authentication method and authentication device | |
| US20070041628A1 (en) | Detection of document security marks using run profiles | |
| CN114418899B (en) | Self-adaptive repairing method and system for self-color printing and readable storage medium | |
| CN111598763B (en) | Method and system for extracting hidden watermark based on mobile phone and image enhancement | |
| Wu et al. | A printer forensics method using halftone dot arrangement model | |
| CN111597516B (en) | Document anti-copying method and system based on hidden watermark | |
| US7266216B2 (en) | Inserting and detecting watermarks in images derived from a source image | |
| Van Beusekom et al. | Automatic counterfeit protection system code classification | |
| Pfeifer et al. | Detection of commercial offset printing in counterfeited banknotes | |
| CN104077738A (en) | Color image watermarking method based on local histogram characteristics | |
| KR102137944B1 (en) | Printing matter with for preventing counterfeit and manufacturing method thereof | |
| US7729505B2 (en) | Method and device for watermarking an image | |
| JP4883457B2 (en) | Printed material production method, printed material and authenticity determination method | |
| CN109271761A (en) | A kind of generation and recognition methods that the document based on green feature of making an uproar is anti-fake | |
| Takimoto et al. | Invisible calibration pattern based on human visual perception characteristics | |
| Ryua et al. | Dot based Printout Watermarking Suitable for Practical Environment | |
| CN115908099A (en) | Digital watermark embedding method for binary image |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |