CN117768748A - Watermark processing method based on database - Google Patents
Watermark processing method based on database Download PDFInfo
- Publication number
- CN117768748A CN117768748A CN202410010246.0A CN202410010246A CN117768748A CN 117768748 A CN117768748 A CN 117768748A CN 202410010246 A CN202410010246 A CN 202410010246A CN 117768748 A CN117768748 A CN 117768748A
- Authority
- CN
- China
- Prior art keywords
- watermark
- image
- image frames
- video
- frame
- 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.)
- Granted
Links
- 238000003672 processing method Methods 0.000 title abstract description 5
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000013519 translation Methods 0.000 claims description 21
- 238000000034 method Methods 0.000 claims description 20
- 238000006243 chemical reaction Methods 0.000 claims description 3
- 238000004891 communication Methods 0.000 abstract description 3
- 230000007547 defect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Landscapes
- Editing Of Facsimile Originals (AREA)
- Image Processing (AREA)
Abstract
The invention relates to the technical field of image communication, and particularly discloses a watermark processing method based on a database, which comprises the following steps: obtaining a video stream to be played and a watermark image, carrying out gray processing on the watermark image, and dividing the obtained gray image into a plurality of pixels; selecting any position from a video stream to be played as a watermark area; taking the central point of the watermark area of the first group of image frames as an origin, and optionally taking a direction as an adjustment direction; translating along the adjustment direction to obtain a watermark region of the second group of image frames; repeating the steps to obtain all the processed image frames and generate processed playing video; when the watermark area of the playing video is covered, position change data of the covered area are obtained, and gray level images of the watermark images are generated. According to the invention, after the watermark of the pirate is successfully masked, the gray level image of the watermark image can be reversely deduced from the change rule of the masked area, so that the source of the video is identified.
Description
Technical Field
The invention relates to the technical field of image communication, in particular to a watermark processing method based on a database.
Background
A watermark is a digital or textual marking used to protect intellectual property, identify the source, and confirm the authenticity of a document. It is typically present in the form of translucent or opaque patterns or text in a media file such as a picture, document, audio or video. The watermark can effectively prevent unauthorized copying, spreading and tampering, and has important significance for protecting rights and interests of an creator.
Today, where the internet is very developed, multimedia image communication technology is becoming mature. Many users like to watch videos through electronic products such as mobile phones or computers; in addition, for sharing or saving, many users may record the video in playing; in order to ensure that the copyright of the video is not affected, the producer often sets a corresponding watermark in the video. The common watermark setting mode is to embed a watermark image into a video and display the watermark image at one corner of the video, but a pirate masks corresponding watermark content by blurring, mosaicing and the like the video area corresponding to the watermark image, so that the stolen video cannot identify a source.
A watermark adding method, device, mobile terminal and readable storage medium are disclosed in chinese patent No. 201910335152X, and the scheme thereof is as follows: "control the watermark pictures to be displayed at random positions of the video to be added every random time period" to cope with the above-mentioned watermarking manner. Although the method can solve the problem of blurring or mosaic watermark removal in a video fixed area, a pirate can still call a specific frame with the watermark and carry out targeted processing to remove the watermark, so that the source of the video cannot be identified.
Disclosure of Invention
The invention aims to provide a watermark processing method based on a database, which solves the technical problems.
The aim of the invention can be achieved by the following technical scheme:
a database-based watermarking method comprising the steps of:
obtaining a video stream to be played and a watermark image, carrying out gray processing on the watermark image, dividing the obtained gray image into a plurality of pixels, and obtaining pixel values P i and P i of the pixels to represent the pixel value of the ith pixel, wherein P i is an integer and P i epsilon [0 and 255];
selecting any position from a video stream to be played as a watermark area, and embedding the watermark image into the watermark area of a first group of image frames of the video, wherein the watermark area is overlapped with the watermark image;
taking the central point of the watermark area of the first group of image frames as an origin, and optionally taking a direction as an adjustment direction; translating along the adjustment direction to obtain a watermark region of the second group of image frames, and embedding the watermark image into the watermark region of the second group of image frames, wherein the translation distance of the watermark region corresponds to the pixel value P1;
repeating the steps, sequentially setting watermark areas of different groups of image frames, and embedding the watermark images into the corresponding watermark areas; each group of image frames comprises one image frame or a plurality of continuous image frames, and the image frames in adjacent groups are continuous on a time axis;
acquiring all the processed image frames and generating processed play video; when the watermark area of the playing video is covered, position change data of the covered area are obtained, and gray level images of watermark images are generated according to the position change data.
As a further scheme of the invention: the specific steps for obtaining the translation distance are as follows:
acquiring a pixel value P i of a gray image, and converting the pixel value P i into an n-bit binary number through a preset binary rule;
taking n frames as a group, continuously selecting n x S image frames from a first frame of a video stream to be played, and dividing the n image frames into S groups, wherein S represents the number of pixels;
setting a unit distance D and calculating a translation distance D of the j-th image frame in the i-th group ij ＝d*R ij ，
Wherein the unit distance d represents the minimum identifiable movement distance, R ij The value of the j-th bit in the binary number corresponding to the pixel value P i is represented.
As a further scheme of the invention: the preset binary rules comprise binary, quaternary, penta and decimal, and when the preset binary rules are binary: the pixel values Pi are converted into 8-bit binary numbers and 8 frames are used as a group.
As a further scheme of the invention: after the embedding of the watermark images of the S groups of image frames is completed, continuing to select the subsequent image frames, wherein the watermark areas in the subsequent image frames correspond to the S groups of image frames, and the corresponding rules are as follows:
acquiring image frames after S groups of image frames, wherein the number of the image frames is n, S+delta S;
calculating the number of cycles k=Δs/(n×s), K rounding down;
calculating a deviation value S '=Δs-K (n×s), and calling an S' th image frame of the S group of image frames as a corresponding frame of the (n×s+Δs) th image frame.
As a further scheme of the invention: the specific steps for obtaining the position change data of the covering area to generate the watermark image are as follows:
acquiring a first image frame of a video with a hidden watermark area as a positioning frame;
determining the position of the positioning frame in the playing video according to the image content in the positioning frame;
acquiring translation distances of covered areas in the positioning frames and the subsequent image frames relative to an origin, and calculating the number of the image frames of different groups;
calculating a corresponding pixel value Pi through the binary number, and generating a gray image of the watermark image according to the pixel value P i;
and identifying the video source according to the gray level image.
As a further scheme of the invention: the specific steps for selecting the said rule are as follows:
setting standard recording time length of video and video frame rate;
according to the standard recording duration and the video frame rate, calculating the total number N of image frames of the video in the standard recording duration;
acquiring the pixel number S of the gray level image, and calculating a single group of standard frame numbers (N/S);
calculating the number n of digits of the binary number generated after the conversion of the maximum gray value 255 under each binary rule;
and selecting a binary rule with the bit number N smaller than or equal to a single standard frame number (N/S) to convert the pixel value.
As a further scheme of the invention: the specific steps for acquiring the binary numbers of the different groups of image frames through the positioning frames are as follows:
continuously acquiring n x S image frames by taking the positioning frame as a starting point;
the method comprises the steps of obtaining the position of a positioning frame in a playing video, and dividing n.S image frames into S groups of image frames;
the numbers of the different groups of image frames are acquired respectively.
As a further scheme of the invention: when said translation distance D ij When the translation distance D is larger than the preset maximum value, the translation distance D is obtained ij Minimum value min (D) in (a) and correct the unit distance d=d/R min(D) Wherein R is min(D) The numerical value on the digit corresponding to min (D) is represented.
The invention has the beneficial effects that: it can be understood that, aiming at the video with the watermark, the rights and interests of creators of the video can be effectively protected, but a pirate can still mask watermark images embedded in the video in a mode of blurring the watermark part or adding a mosaic for shielding, so that other people cannot identify the source of the video, and the pirate is prevented from being overtaken in the process of embezzling;
in the prior art, the difficulty of covering the watermark is increased by adopting a random time and random position mode, namely, the watermark is marked on the random position of the image frame at the random time of video playing, so that the specific position of the watermark cannot be accurately positioned by the existing watermark covering algorithm; however, this method still has a defect that the watermark is masked by calling out the randomly generated specific frame with the watermark for separate processing by calling out the specific frame after recording;
in the application, unlike the thinking of the traditional mode, the traditional mode is to improve the difficulty of covering the watermark so as to prevent the problem that the watermark is covered; however, in the application, the main scheme is not only to increase the difficulty of the hidden watermark, but also to set the change rule of the watermark embedding position according to the pixel value characteristics of the watermark image, so that even after the hidden watermark is successfully hidden by a pirate, the pixel value of the watermark image can be deduced reversely from the change rule of the hidden area (the fuzzy area/the mosaic area), thereby restoring the gray level image of the watermark image and further identifying the source of the video.
Drawings
The invention is further described below with reference to the accompanying drawings.
Fig. 1 is a schematic flow chart of a database-based watermarking method of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the present invention is a database-based watermarking method, comprising the steps of:
obtaining a video stream and a watermark image to be played, carrying out gray processing on the watermark image, dividing the obtained gray image into a plurality of pixels, and obtaining pixel values P i of the pixels, wherein Pi represents the pixel value of the ith pixel, P i is an integer, and Pi is E [0, 255];
selecting any position from a video stream to be played as a watermark area, and embedding the watermark image into the watermark area of a first group of image frames of the video, wherein the watermark area is overlapped with the watermark image;
taking the central point of the watermark area of the first group of image frames as an origin, and optionally taking a direction as an adjustment direction; translating along the adjustment direction to obtain a watermark region of the second group of image frames, and embedding the watermark image into the watermark region of the second group of image frames, wherein the translation distance of the watermark region corresponds to the pixel value P1;
repeating the steps, sequentially setting watermark areas of different groups of image frames, and embedding the watermark images into the corresponding watermark areas; each group of image frames comprises one image frame or a plurality of continuous image frames, and the image frames in adjacent groups are continuous on a time axis;
acquiring all the processed image frames and generating processed play video; when the watermark area of the playing video is covered, position change data of the covered area are obtained, and gray level images of watermark images are generated according to the position change data.
It can be understood that, aiming at the video with the watermark, the rights and interests of creators of the video can be effectively protected, but a pirate can still mask watermark images embedded in the video in a mode of blurring the watermark part or adding a mosaic for shielding, so that other people cannot identify the source of the video, and the pirate is prevented from being overtaken in the process of embezzling;
in the prior art, the difficulty of covering the watermark is increased by adopting a random time and random position mode, namely, the watermark is marked on the random position of the image frame at the random time of video playing, so that the specific position of the watermark cannot be accurately positioned by the existing watermark covering algorithm; however, this method still has a defect that the watermark is masked by calling out the randomly generated specific frame with the watermark for separate processing by calling out the specific frame after recording;
in the application, unlike the thinking of the traditional mode, the traditional mode is to improve the difficulty of covering the watermark so as to prevent the problem that the watermark is covered; however, in the application, the main scheme is not only to increase the difficulty of the hidden watermark, but also to set the change rule of the watermark embedding position according to the pixel value characteristics of the watermark image, so that even after the hidden watermark is successfully hidden by a pirate, the pixel value of the watermark image can be deduced reversely from the change rule of the hidden area (the fuzzy area/the mosaic area), thereby restoring the gray level image of the watermark image and further identifying the source of the video.
And it is noted that in conventional watermark masking algorithms, the masked area is coincident with the watermark image and the position of the masked area changes as the position of the watermark image changes; the reason why the covering area is overlapped with the watermark image is to ensure the integrity of the video and keep the clear video picture as much as possible, and the implementation of the scheme is based on the phenomenon that the covering area changes along with the change of the watermark embedding area.
In a preferred embodiment of the present invention, the specific steps for obtaining the translation distance are as follows:
acquiring a pixel value Pi of a gray image, and converting the pixel value Pi into an n-bit binary number through a preset binary rule;
taking n frames as a group, continuously selecting n x S image frames from a first frame of a video stream to be played, and dividing the n image frames into S groups, wherein S represents the number of pixels;
setting a unit distance D and calculating a translation distance D of the j-th image frame in the i-th group ij ＝d*R ij ，
Wherein the unit distance d represents the minimum identifiable movement distance, R ij The value of the j-th bit in the binary number corresponding to the pixel value P i is represented.
In a preferred embodiment of the present invention, the preset binary rule includes binary, quaternary, penta, and decimal, and when the preset binary rule is binary: the pixel values Pi are converted into 8-bit binary numbers and 8 frames are used as a group.
In a preferred embodiment of the present invention, after embedding the watermark image of the S-group image frame is completed, a subsequent image frame is selected continuously, and the watermark area in the subsequent image frame corresponds to the S-group image frame, where the correspondence rule is as follows:
acquiring image frames after S groups of image frames, wherein the number of the image frames is n, S+delta S;
calculating the number of cycles k=Δs/(n×s), K rounding down;
calculating a deviation value S '=Δs-K (n×s), and calling an S' th image frame of the S group of image frames as a corresponding frame of the (n×s+Δs) th image frame.
In a preferred embodiment of the present invention, the specific steps for obtaining position change data of the masked areas to generate the watermark image are as follows:
acquiring a first image frame of a video with a hidden watermark area as a positioning frame;
determining the position of the positioning frame in the playing video according to the image content in the positioning frame;
acquiring translation distances of covered areas in the positioning frames and the subsequent image frames relative to an origin, and calculating the number of the image frames of different groups;
calculating a corresponding pixel value Pi through the binary number, and generating a gray image of the watermark image according to the pixel value P i;
and identifying the video source according to the gray level image.
In a preferred embodiment of the present invention, the specific steps for selecting the said binary rule are as follows:
setting standard recording time length of video and video frame rate;
according to the standard recording duration and the video frame rate, calculating the total number N of image frames of the video in the standard recording duration;
acquiring the pixel number S of the gray level image, and calculating a single group of standard frame numbers (N/S);
calculating the number n of digits of the binary number generated after the conversion of the maximum gray value 255 under each binary rule;
and selecting a binary rule with the bit number N smaller than or equal to a single standard frame number (N/S) to convert the pixel value.
In a preferred embodiment of the present invention, the specific steps for acquiring the number of the system of different sets of image frames by locating the frames are as follows:
continuously acquiring n x S image frames by taking the positioning frame as a starting point;
the method comprises the steps of obtaining the position of a positioning frame in a playing video, and dividing n.S image frames into S groups of image frames;
the numbers of the different groups of image frames are acquired respectively.
In a preferred embodiment of the invention, when said translation distance D ij When the translation distance D is larger than the preset maximum value, the translation distance D is obtained ij Minimum value min (D) in (a) and correct the unit distance d=d/R min(D) Wherein R is min(D) The numerical value on the digit corresponding to min (D) is represented.
The foregoing describes one embodiment of the present invention in detail, but the description is only a preferred embodiment of the present invention and should not be construed as limiting the scope of the invention. All equivalent changes and modifications within the scope of the present invention are intended to be covered by the present invention.
Claims (8)
1. A database-based watermarking method, comprising the steps of:
obtaining a video stream to be played and a watermark image, carrying out gray processing on the watermark image, dividing the obtained gray image into a plurality of pixels, and obtaining a pixel value Pi of the pixel, wherein Pi represents the pixel value of an ith pixel, pi is an integer and Pi is E [0, 255];
selecting any position from a video stream to be played as a watermark area, and embedding the watermark image into the watermark area of a first group of image frames of the video, wherein the watermark area is overlapped with the watermark image;
taking the central point of the watermark area of the first group of image frames as an origin, and optionally taking a direction as an adjustment direction; translating along the adjustment direction to obtain a watermark region of the second group of image frames, and embedding the watermark image into the watermark region of the second group of image frames, wherein the translation distance of the watermark region corresponds to the pixel value P1;
repeating the steps, sequentially setting watermark areas of different groups of image frames, and embedding the watermark images into the corresponding watermark areas; each group of image frames comprises one image frame or a plurality of continuous image frames, and the image frames in adjacent groups are continuous on a time axis;
acquiring all the processed image frames and generating processed play video; when the watermark area of the playing video is covered, position change data of the covered area are obtained, and gray level images of watermark images are generated according to the position change data.
2. A method of database-based watermarking as defined in claim 1, wherein the specific step of obtaining said translation distance is as follows:
acquiring a pixel value Pi of a gray image, and converting the pixel value Pi into an n-bit binary number through a preset binary rule;
taking n frames as a group, continuously selecting n x S image frames from a first frame of a video stream to be played, and dividing the n image frames into S groups, wherein S represents the number of pixels;
setting a unit distance D and calculating a translation distance D of the j-th image frame in the i-th group ij ＝d*R ij ，
Wherein the unit distance d represents the minimum identifiable movement distance, R ij The value of the j-th bit in the binary number corresponding to the pixel value Pi is represented.
3. A method of database based watermarking as claimed in claim 2, wherein the predetermined binary rules include binary, quaternary, penta and decimal, and when the predetermined binary rules are binary: the pixel values Pi are converted into 8-bit binary numbers and 8 frames are used as a group.
4. The method of claim 2, wherein after embedding the watermark image of the S-group image frames, selecting a subsequent image frame is continued, and the watermark area in the subsequent image frame corresponds to the S-group image frames, and the correspondence rule is as follows:
acquiring image frames after S groups of image frames, wherein the number of the image frames is n, S+delta S;
calculating the number of cycles k=Δs/(n×s), K rounding down;
calculating a deviation value S '=Δs-K (n×s), and calling an S' th image frame of the S group of image frames as a corresponding frame of the (n×s+Δs) th image frame.
5. A method of database-based watermarking as claimed in claim 2, wherein the specific step of obtaining position change data of the masked area to generate the watermark image is as follows:
acquiring a first image frame of a video with a hidden watermark area as a positioning frame;
determining the position of the positioning frame in the playing video according to the image content in the positioning frame;
acquiring translation distances of covered areas in the positioning frames and the subsequent image frames relative to an origin, and calculating the number of the image frames of different groups;
calculating a corresponding pixel value Pi through the binary number, and generating a gray image of the watermark image according to the pixel value Pi;
and identifying the video source according to the gray level image.
6. A method of database-based watermarking as claimed in claim 3, wherein the specific step of selecting said binary rule is as follows:
setting standard recording time length of video and video frame rate;
according to the standard recording duration and the video frame rate, calculating the total number N of image frames of the video in the standard recording duration;
acquiring the pixel number S of the gray level image, and calculating a single group of standard frame numbers (N/S);
calculating the number n of digits of the binary number generated after the conversion of the maximum gray value 255 under each binary rule;
and selecting a binary rule with the bit number N smaller than or equal to a single standard frame number (N/S) to convert the pixel value.
7. A method of database-based watermarking as defined in claim 5, wherein the specific step of obtaining the number of the bins of the different sets of image frames by locating the frames is as follows:
continuously acquiring n x S image frames by taking the positioning frame as a starting point;
the method comprises the steps of obtaining the position of a positioning frame in a playing video, and dividing n.S image frames into S groups of image frames;
the numbers of the different groups of image frames are acquired respectively.
8. A method of database-based watermarking as defined in claim 2, wherein, when said translation distance D is ij When the translation distance D is larger than the preset maximum value, the translation distance D is obtained ij Minimum value min (D) in (a) and correct the unit distance d=d/R min(D) Wherein R is min(D) The numerical value on the digit corresponding to min (D) is represented.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410010246.0A CN117768748B (en) | 2024-01-03 | 2024-01-03 | Watermark processing method based on database |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410010246.0A CN117768748B (en) | 2024-01-03 | 2024-01-03 | Watermark processing method based on database |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117768748A true CN117768748A (en) | 2024-03-26 |
| CN117768748B CN117768748B (en) | 2024-06-11 |
Family
ID=90325847
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410010246.0A Active CN117768748B (en) | 2024-01-03 | 2024-01-03 | Watermark processing method based on database |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117768748B (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120163653A1 (en) * | 2010-12-28 | 2012-06-28 | Fujitsu Limited | Digital watermark embedding apparatus, digital watermark embedding method, and digital watermark detection apparatus |
| CN108540867A (en) * | 2018-04-25 | 2018-09-14 | 中影数字巨幕（北京）有限公司 | Film bearing calibration and device |
| CN108596820A (en) * | 2018-04-11 | 2018-09-28 | 重庆第二师范学院 | a kind of image processing system based on information security |
| CN111510767A (en) * | 2020-04-21 | 2020-08-07 | 新华智云科技有限公司 | Video watermark identification method and identification device thereof |
| CN114037593A (en) * | 2021-10-29 | 2022-02-11 | 淮阴工学院 | Reversible image watermarking algorithm based on reverse histogram translation |
-
2024
- 2024-01-03 CN CN202410010246.0A patent/CN117768748B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120163653A1 (en) * | 2010-12-28 | 2012-06-28 | Fujitsu Limited | Digital watermark embedding apparatus, digital watermark embedding method, and digital watermark detection apparatus |
| CN108596820A (en) * | 2018-04-11 | 2018-09-28 | 重庆第二师范学院 | a kind of image processing system based on information security |
| CN108540867A (en) * | 2018-04-25 | 2018-09-14 | 中影数字巨幕（北京）有限公司 | Film bearing calibration and device |
| CN111510767A (en) * | 2020-04-21 | 2020-08-07 | 新华智云科技有限公司 | Video watermark identification method and identification device thereof |
| CN114037593A (en) * | 2021-10-29 | 2022-02-11 | 淮阴工学院 | Reversible image watermarking algorithm based on reverse histogram translation |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117768748B (en) | 2024-06-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7430302B2 (en) | Covert and robust mark for media identification | |
| Biswas et al. | An adaptive compressed MPEG-2 video watermarking scheme | |
| JP3709205B2 (en) | Marking method for binary data sets | |
| JPH10224793A (en) | Image data encoding system | |
| US20010001613A1 (en) | Video-data encoder and recording media wherein a video-data encode program is recorded | |
| US20070098214A1 (en) | Image processing apparatus, image processing method, and storage medium | |
| US20090288170A1 (en) | System and method for object oriented fingerprinting of digital videos | |
| MXPA06006082A (en) | System and method for adaptive marking and coding of film prints. | |
| US20020097891A1 (en) | Electronic watermarking data insertion/detection device | |
| CN110766594A (en) | Information hiding method and device, detection method and device and anti-counterfeiting tracing method | |
| EP1381217A1 (en) | Image data illegal use prevention system | |
| CN117768748B (en) | Watermark processing method based on database | |
| US7831060B2 (en) | Method for protecting content of vector graphics formats | |
| US20050069129A1 (en) | Method of protecting copyright of digital video work | |
| Jambhale et al. | A deep learning approach to invisible watermarking for copyright protection | |
| KR100655059B1 (en) | Data generating method | |
| CN112488899A (en) | Visual encryption color blind watermarking method based on repeated codes and Schur decomposition | |
| Gu et al. | Robust Watermarking of Screen-Photography Based on JND. | |
| CN114693497A (en) | Method and system for processing label based on dark watermark | |
| CN117940949A (en) | Encryption image watermarking method and device and display equipment | |
| CN117118697A (en) | Copyright protection method, system, equipment and medium based on multiple watermarks and blockchain | |
| CN114971993A (en) | Spread spectrum technology digital watermarking method and system based on cloud processing | |
| CN114547561A (en) | Data processing method, device and equipment | |
| CN117952814A (en) | Training method of watermark extraction model, watermark extraction method and related equipment | |
| JP2000151976A (en) | Method for embedding watermark information to image, method for decoding watermark information and recording medium |
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 |