CN109214974A - A kind of portrait photo's processing method based on digital watermarking - Google Patents
A kind of portrait photo's processing method based on digital watermarking Download PDFInfo
- Publication number
- CN109214974A CN109214974A CN201811009930.8A CN201811009930A CN109214974A CN 109214974 A CN109214974 A CN 109214974A CN 201811009930 A CN201811009930 A CN 201811009930A CN 109214974 A CN109214974 A CN 109214974A
- Authority
- CN
- China
- Prior art keywords
- watermark
- coefficient
- information
- point
- value
- 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
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
- G06T1/005—Robust watermarking, e.g. average attack or collusion attack resistant
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Human Computer Interaction (AREA)
- Multimedia (AREA)
- Editing Of Facsimile Originals (AREA)
- Image Processing (AREA)
Abstract
A kind of portrait photo's processing method based on digital watermarking, the addition of production, watermark including watermark information and the detection of watermark；The addition of watermark uses following steps, step 1: carrying out wavelet decomposition to watermark to be added picture；Step 2: calculating watermark embedding depth D, according to hvs characteristic, by analyzing the corresponding position of the LL subband of three rank subbands and its low frequency coefficient mean value of neighborhood, judge the background luminance of the LH and HL of corresponding position, specially, average value is calculated using four field points of each point, for any point (x on HL3, y), the coefficient of the upper corresponding point of LL3 is LL3 (x, y), the coefficient of 4 neighborhood points is LL3 (x-1, y), LL3 (x+1, y), LL3 (x, y-1), LL3 (x, y+1), the average value of the coefficient of this 5 points is calculated as HL3 (x, y) background luminance V, according to the average background brightness mV of entire LL3, V value is divided into two classes, point greater than mV takes insert depth 50, point less than mV Take insert depth 15.Invisible watermark is added to image, does not influence the identification to picture material.
Description
Technical field
The present invention relates to field of face identification, and in particular to a kind of portrait photo's processing method based on digital watermarking.
Background technique
Recognition of face is a kind of biological identification technology for carrying out identification based on facial feature information of people.Face is people
Important information, be to discriminate between the important evidence of different people, have many advantages, such as easy-to-use, contactless, therefore recognition of face skill
Art is more direct and most widely used biometrics identification technology more natural compared with technologies such as fingerprint, irises at present.With each row
The extensive use of each industry, safety in utilization become as question of common concern.In face identification system, illegal person is easy to
In In vivo detection by distorting face picture during transmitting face picture and carrying out face alignment to server later come real
Apply attack and fraud.Therefore, face digital watermarking tamper-resistance techniques, the gradually attention by academia and industry,
Purpose is exactly to prevent illegal person from distorting to the face picture in face identification system.
Current image digital watermark tamper-resistance techniques mainly include the following types:
(1) air space algorithm: most unessential pixel position (LSB:least in randomly selected picture point is embedded of information into
Significant bits) on, this can guarantee that the watermark of insertion is sightless.But due to having used the unessential picture of image
Plain position, the poor robustness of algorithm, watermark information is easily filtering, the operation of image quantization, geometry deformation destroys.
(2) based on the digital watermarking algorithm of discrete cosine transform: dividing the image into 8 × 8 pieces, and be DCT to each piece
Transformation, then random selection constructs all pieces of a subset, to each block of subset, select a set of frequencies and be embedded in two into
Watermark information processed.Since the selection of group of frequencies is not based on most significant component, and the variance of coefficient of frequency is smaller, therefore the party
Method attacks noise, geometry deformation and more documents more sensitive.
Summary of the invention
Portrait photo's processing method based on digital watermarking that in view of the deficiencies of the prior art, the present invention proposes a kind of, specifically
Technical solution is as follows:
A kind of portrait photo's processing method based on digital watermarking, it is characterised in that: production, watermark including watermark information
Addition and watermark detection；
The addition of the watermark uses following steps,
Step 1: wavelet decomposition is carried out to watermark to be added picture；
Step 2: watermark embedding depth D is calculated, according to hvs characteristic, the correspondence position of the LL subband by analyzing three rank subbands
It sets and its low frequency coefficient mean value of neighborhood, the background luminance of the LH and HL of corresponding position is judged, specifically, utilizing the four of each point
A field point calculates average value, and for any point (x, y) on HL3, the coefficient of the upper corresponding point of LL3 is LL3 (x, y), 4 neighbours
The coefficient of domain point is LL3 (x-1, y), LL3 (x+1, y), LL3 (x, y-1), LL3 (x, y+1), calculates the flat of the coefficient of this 5 points
V value is divided into two classes according to the average background brightness mV of entire LL3 by background luminance V of the mean value as HL3 (x, y), is greater than mV
Point take insert depth 50, the point less than mV takes insert depth 15；
Step 3: watermark is embedded according to watermark information sequence, watermark information is added to through the value according to insertion watermark,
It is realized to adjust the value of the coefficient of LH and HL subband, according to the insert depth D determined in step 2, the watermark that need to currently be embedded in
Information is w, first assumes that the coefficient of current embedded location on LH is C, by calculating the ratio x=round (C/D) of C and D, according to
C is obtained such as under type:
S1: if w=0, x are even number or w=1, x is odd number:
C=x*D is then enabled, enters step 4, otherwise, enters step S2；
S2: if w=1, x are even number or w=0, x odd number:
CT=x*D+D is then enabled, into S3；
S3: if x*D < C:
Then C=x*D-D enters step 4, otherwise, into S4；
S4: if x*D > C:
Then C=CT；
Step 4: carrying out wavelet inverse transformation, obtain adding watermarked image.
Further: step 1 specifically: wavelet decomposition is carried out to watermark to be added picture, selects the level of three rank subbands
Detail subbands and vertical detail subband are used to carry out the addition of watermark information.
Further: the production of the watermark information includes, step 1: for watermark picture, being changed into single pass ash
Degree figure, or its some channel in any colour gamut is taken, and binaryzation is carried out to single pass pictorial information, obtain binary system
Watermark encoder information；
Step 2: binary system is converted to by character string using the string encodings such as unicode rule for watermark character string
Watermark encoder information.
Step 3: encryption scramble is carried out to watermark binary coding.
Further: the detection of the watermark includes the following steps:
Step 1: the sequence information of watermark to be added is calculated according to the method in addition watermark；
Step 2: carrying out three-level wavelet decomposition to picture to be detected, calculate the mean coefficient of each point in LL sub-band,
And watermark embedding depth D is determined according to the identical rule in addition watermark；
Step 3: according to the insert depth calculated in step 2, the watermark information w of insertion is restored, rule is as follows:
S1: if round (C/D) is even number, w=0；
S2: if round (C/D) is odd number, w=1；
Step 4: the w extracted is formed into the watermark sequence in watermark sequence, with step 1 and is compared, phase relation is calculated
Number, if W0 is watermark to be detected, W1 is the watermark extracted, then related coefficient P is
P=inner (W0, W1)/(| W0 | * | W1 |)
Wherein inner () is the inner product for calculating two vectors, | | it is to calculate vector field homoemorphism value；
Step 5: according to the value of P, taking is to detect watermark when P > 0.7.
The invention has the benefit that first, invisible watermark is added to image, does not influence the identification to picture material.
Second, source picture, the design of more convenient picture storage system are not depended on to the detection of watermark information.
Third, watermark information have stronger robustness, picture is compressed, damage transmission etc. operation, do not influence water
The detection of official seal breath.
4th, to distorting, image content operation is sensitive, can effectively prevent forging picture.
Detailed description of the invention
Fig. 1 is image wavelet decomposition chart of the invention；
Fig. 2 is work flow diagram of the invention.
Specific embodiment
The preferred embodiments of the present invention will be described in detail with reference to the accompanying drawing, so that advantages and features of the invention energy
It is easier to be readily appreciated by one skilled in the art, so as to make a clearer definition of the protection scope of the present invention.
It is as depicted in figs. 1 and 2:
A kind of portrait photo's processing method based on digital watermarking, the addition of production, watermark including watermark information and
The detection of watermark；
The production of watermark information includes,
Step 1: for watermark picture, being changed into single pass grayscale image, or take its some in any colour gamut
Channel, and binaryzation is carried out to single pass pictorial information, obtain binary watermark encoder information；
Step 2: binary system is converted to by character string using the string encodings such as unicode rule for watermark character string
Watermark encoder information.
Step 3: encryption scramble being carried out to watermark binary coding, guarantees the safety of watermark information.
The invisibility principle of watermark are as follows: mainly according to the characteristic of human visual system HVS, watermark information is added to
Human eye is difficult to the region perceived, and HVS mainly has several features, first is that human eye to noise susceptibility attached by luminance area compared with
Small, in the brighter place addition information of picture, human eye is more difficult to discover, second is that human eye to the noise resolution power of high-frequency region compared with
It is low, it is more sensitive to low frequency region, third is that human eye has different sensibility to different gray scales, it is most sensitive to intermediate gray-scale,
Sensibility decline in gray scale and high gray scale over the ground.Based on the above characteristic, therefore, the position of watermark addition is determined in the following way
With carry out watermark addition:
The addition of watermark uses following steps,
Step 1: to watermark to be added picture carry out wavelet decomposition, discrete wavelet transformer change commanders picture breakdown at it is a series of not
With the subgraph of resolution ratio, original image generates a low frequency sub-band LLn and corresponding to every rank after N rank wavelet transformation
Level, vertically, the details of diagonal direction carry HLi, LHi, HHi
(i=1,2,3 ... N).
LL subband is the subband true to nature of image, and the low-frequency information containing image, being embedded in watermark will affect the vision effect of human eye
Fruit；And HL, LH, HH belong to the high-frequency sub-band of image, the watermark information of insertion influences very little to the visual experience of human eye, but excessively
The subband of high frequency is also easy to receive the influence of noises such as picture compression, and therefore, the invisibility and robustness for comprehensively considering watermark are wanted
It asks, this method selects the addition of the level detail subband and vertical detail subband progress watermark information of three rank subbands；
Step 2: watermark embedding depth D is calculated, according to hvs characteristic, the correspondence position of the LL subband by analyzing three rank subbands
It sets and its low frequency coefficient mean value of neighborhood, the background luminance of the LH and HL of corresponding position is judged, specifically, utilizing the four of each point
A field point calculates average value, and for any point (x, y) on HL3, the coefficient of the upper corresponding point of LL3 is LL3 (x, y), 4 neighbours
The coefficient of domain point is LL3 (x-1, y), LL3 (x+1, y), LL3 (x, y-1), LL3 (x, y+1), calculates the flat of the coefficient of this 5 points
V value is divided into two classes according to the average background brightness mV of entire LL3 by background luminance V of the mean value as HL3 (x, y), is greater than mV
Point take insert depth 50, the point less than mV takes insert depth 15；
Step 3: watermark is embedded according to watermark information sequence, watermark information is added to through the value according to insertion watermark,
It is realized to adjust the value of the coefficient of LH and HL subband, according to the insert depth D determined in step 2, the watermark that need to currently be embedded in
Information is w, first assumes that the coefficient of current embedded location on LH is C, by calculating the ratio x=round (C/D) of C and D, according to
C is obtained such as under type:
S1: if w=0, x are even number or w=1, x is odd number:
C=x*D is then enabled, enters step 4, otherwise, enters step S2；
S2: if w=1, x are even number or w=0, x odd number:
CT=x*D+D is then enabled, into S3；
S3: if x*D < C:
Then C=x*D-D enters step 4, otherwise, into S4；
S4: if x*D > C:
Then C=CT；
Step 4: carrying out wavelet inverse transformation, obtain adding watermarked image；
2, a kind of portrait photo's processing method based on digital watermarking according to claim 1, it is characterised in that: step 1 tool
Body are as follows: wavelet decomposition is carried out to watermark to be added picture, the level detail subband of three rank subbands and vertical detail subband is selected to use
In the addition for carrying out watermark information.
The detection of watermark includes the following steps:
Step 1: the sequence information of watermark to be added is calculated according to the method in addition watermark；
Step 2: carrying out three-level wavelet decomposition to picture to be detected, calculate the mean coefficient of each point in LL sub-band,
And watermark embedding depth D is determined according to the identical rule in addition watermark；
Step 3: according to the insert depth calculated in step 2, the watermark information w of insertion is restored, rule is as follows:
S1: if round (C/D) is even number, w=0；
S2: if round (C/D) is odd number, w=1；
Step 4: the w extracted is formed into the watermark sequence in watermark sequence, with step 1 and is compared, phase relation is calculated
Number, if W0 is watermark to be detected, W1 is the watermark extracted, then related coefficient P be P=inner (W0, W1)/(| W0 | * |
W1|)
Wherein inner () is the inner product for calculating two vectors, | | it is to calculate vector field homoemorphism value；Step 5: according to the value of P, P is taken
It is to detect watermark when > 0.7.
Claims (4)
1. a kind of portrait photo's processing method based on digital watermarking, it is characterised in that: production, watermark including watermark information
The detection of addition and watermark；
The addition of the watermark uses following steps,
Step 1: wavelet decomposition is carried out to watermark to be added picture；
Step 2: calculate watermark embedding depth D, according to hvs characteristic, by analyze the LL subband of three rank subbands corresponding position and
The low frequency coefficient mean value of its neighborhood judges the background luminance of the LH and HL of corresponding position, specifically, utilizing four necks of each point
Domain point calculates average value, and for any point (x, y) on HL3, the coefficient of the upper corresponding point of LL3 is LL3 (x, y), 4 neighborhood points
Coefficient be LL3 (x-1, y), LL3 (x+1, y), LL3 (x, y-1), LL3 (x, y+1) calculates the average value of the coefficient of this 5 points
V value is divided by two classes according to the average background brightness mV of entire LL3 as the background luminance V of HL3 (x, y), the point greater than mV
Insert depth 50 is taken, the point less than mV takes insert depth 15；
Step 3: watermark being embedded according to watermark information sequence, watermark information is added to by the value according to insertion watermark, to adjust
The value for saving the coefficient of LH and HL subband is realized, according to the insert depth D determined in step 2, the watermark information that need to currently be embedded in
It is w, first assumes that the coefficient of current embedded location on LH is C, by calculating the ratio x=round (C/D) of C and D, according to as follows
Mode obtains C:
S1: if w=0, x are even number or w=1, x is odd number:
C=x*D is then enabled, enters step 4, otherwise, enters step S2；
S2: if w=1, x are even number or w=0, x odd number:
CT=x*D+D is then enabled, into S3；
S3: if x*D < C:
Then C=x*D-D enters step 4, otherwise, into S4；
S4: if x*D > C:
Then C=CT；
Step 4: carrying out wavelet inverse transformation, obtain adding watermarked image.
2. a kind of portrait photo's processing method based on digital watermarking according to claim 1, it is characterised in that: step 1 tool
Body are as follows: wavelet decomposition is carried out to watermark to be added picture, the level detail subband of three rank subbands and vertical detail subband is selected to use
In the addition for carrying out watermark information.
3. a kind of portrait photo's processing method based on digital watermarking according to claim 1, it is characterised in that: the watermark
The production of information includes, step 1: for watermark picture, being changed into single pass grayscale image, or take it in any colour gamut
Some channel, and to single pass pictorial information carry out binaryzation, obtain binary watermark encoder information；
Step 2: binary water is converted to by character string using the string encodings such as unicode rule for watermark character string
Print encoded information.
Step 3: encryption scramble is carried out to watermark binary coding.
4. a kind of portrait photo's processing method based on digital watermarking according to claim 1, it is characterised in that: the watermark
Detection include the following steps:
Step 1: the sequence information of watermark to be added is calculated according to the method in addition watermark；
Step 2: carrying out three-level wavelet decomposition to picture to be detected, calculates the mean coefficient of each point in LL sub-band, and root
Watermark embedding depth D is determined according to the identical rule in addition watermark；
Step 3: according to the insert depth calculated in step 2, the watermark information w of insertion is restored, rule is as follows:
S1: if round (C/D) is even number, w=0；
S2: if round (C/D) is odd number, w=1；
Step 4: forming the watermark sequence in watermark sequence, with step 1 for the w extracted and compare, calculate related coefficient, if
W0 is watermark to be detected, and W1 is the watermark extracted, then related coefficient P is
P=inner (W0, W1)/(| W0 | * | W1 |)
Wherein inner () is the inner product for calculating two vectors, | | it is to calculate vector field homoemorphism value；
Step 5: according to the value of P, taking is to detect watermark when P > 0.7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811009930.8A CN109214974B (en) | 2018-08-31 | 2018-08-31 | Portrait photo processing method based on digital watermark |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811009930.8A CN109214974B (en) | 2018-08-31 | 2018-08-31 | Portrait photo processing method based on digital watermark |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109214974A true CN109214974A (en) | 2019-01-15 |
| CN109214974B CN109214974B (en) | 2021-05-25 |
Family
ID=64985791
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811009930.8A Active CN109214974B (en) | 2018-08-31 | 2018-08-31 | Portrait photo processing method based on digital watermark |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109214974B (en) |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6332030B1 (en) * | 1998-01-15 | 2001-12-18 | The Regents Of The University Of California | Method for embedding and extracting digital data in images and video |
| CN101042769A (en) * | 2007-01-12 | 2007-09-26 | 中国人民解放军国防科学技术大学 | Active mode digital image content identification method based on wavelet and DCT dual domain |
| CN101482965A (en) * | 2009-01-05 | 2009-07-15 | 深圳大学 | Digital watermark imbedding and detecting method and device |
| CN102930498A (en) * | 2012-11-13 | 2013-02-13 | 上海电力学院 | Digital watermarking embedding and extracting method based on lifting wavelet |
| CN103886537A (en) * | 2012-12-20 | 2014-06-25 | 天津职业技术师范大学 | Printing and scanning resistant digital watermarking method |
| CN107067363A (en) * | 2017-04-18 | 2017-08-18 | 海南大学 | A kind of non-blind robust Spatial Domain Image Watermark method constant based on pixel order relation |
| CN107292806A (en) * | 2017-06-28 | 2017-10-24 | 南京师范大学 | A kind of remote sensing image digital watermark embedding and extracting method based on quaternion wavelet |
| CN107578365A (en) * | 2017-09-11 | 2018-01-12 | 哈尔滨工程大学 | Small echo digital watermark embedding and extracting method based on quantum weeds optimizing mechanism |
-
2018
- 2018-08-31 CN CN201811009930.8A patent/CN109214974B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6332030B1 (en) * | 1998-01-15 | 2001-12-18 | The Regents Of The University Of California | Method for embedding and extracting digital data in images and video |
| CN101042769A (en) * | 2007-01-12 | 2007-09-26 | 中国人民解放军国防科学技术大学 | Active mode digital image content identification method based on wavelet and DCT dual domain |
| CN101482965A (en) * | 2009-01-05 | 2009-07-15 | 深圳大学 | Digital watermark imbedding and detecting method and device |
| CN102930498A (en) * | 2012-11-13 | 2013-02-13 | 上海电力学院 | Digital watermarking embedding and extracting method based on lifting wavelet |
| CN103886537A (en) * | 2012-12-20 | 2014-06-25 | 天津职业技术师范大学 | Printing and scanning resistant digital watermarking method |
| CN107067363A (en) * | 2017-04-18 | 2017-08-18 | 海南大学 | A kind of non-blind robust Spatial Domain Image Watermark method constant based on pixel order relation |
| CN107292806A (en) * | 2017-06-28 | 2017-10-24 | 南京师范大学 | A kind of remote sensing image digital watermark embedding and extracting method based on quaternion wavelet |
| CN107578365A (en) * | 2017-09-11 | 2018-01-12 | 哈尔滨工程大学 | Small echo digital watermark embedding and extracting method based on quantum weeds optimizing mechanism |
Non-Patent Citations (4)
| Title |
|---|
| XIAOHUI LI.ETC: "RESEARCH ON IMAGE DIGITAL WATERMARKING BASED ON WAVELET TRANSFORM AND GREY RELATIONAL ANALYSIS", 《INTERNATIONAL CONFERENCE ON WAVELET ACTIVE MEDIA TECHNOLOGY AND INFORMATION PROCESSING 》 * |
| 李娜 郑晓势 李士锋: "一种基于小波变换的自适应图像水印算法", 《计算机工程》 * |
| 王炳锡等: "《数字水印技术》", 30 November 2003 * |
| 蒯力刚 梁家栋 赵盼: "《基于置乱系统的脆弱数字水印算法》", 《学术讨论--基金项目》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109214974B (en) | 2021-05-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Chen et al. | Full 4-D quaternion discrete Fourier transform based watermarking for color images | |
| Song et al. | A robust region-adaptive dual image watermarking technique | |
| Banoci et al. | A novel method of image steganography in DWT domain | |
| Azeroual et al. | Real-time image tamper localization based on fragile watermarking and Faber-Schauder wavelet | |
| CN102024249A (en) | Digital image watermarking method based on visual perception characteristics | |
| Song et al. | Recent advances and classification of watermarking techniques in digital images | |
| Zhang et al. | Robust image watermarking algorithm based on QWT and QSVD using 2D Chebyshev-Logistic map | |
| Sikder et al. | A semi-fragile watermarking method using slant transform and LU decomposition for image authentication | |
| Dai et al. | A novel steganography algorithm based on quantization table modification and image scrambling in DCT domain | |
| Adi et al. | Imperceptible image watermarking based on chinese remainder theorem over the edges | |
| Ahmaderaghi et al. | Perceptual watermarking for Discrete Shearlet transform | |
| Ali et al. | Copyright protection for digital image by watermarking technique | |
| CN109214974A (en) | A kind of portrait photo's processing method based on digital watermarking | |
| Fallahpour et al. | Flexible image watermarking in JPEG domain | |
| Islam et al. | SVM regression based robust image watermarking technique in joint DWT-DCT domain | |
| Qi et al. | Improved affine resistant watermarking by using robust templates | |
| Wang et al. | New gray-scale watermarking algorithm of color images based on quaternion Fourier transform | |
| Elahian et al. | Improved robust DWT-watermarking in YCbCr color space | |
| Adi et al. | Feature image watermarking based on Bicubic interpolation of wavelet coefficients using CRT | |
| Mathivadhani et al. | Digital watermarking and information hiding using wavelets, SLSB and Visual cryptography method | |
| Li et al. | High capacity watermark embedding based on invariant regions of visual saliency | |
| Su et al. | A watermarking algorithm for color image based on YIQ color space and integer wavelet transform | |
| Singhal et al. | Local binary pattern operator based steganography in wavelet domain | |
| Leng et al. | High payload data hiding based on just noticeable distortion profile and LSB substitution | |
| Xie | A blind watermarking algorithm based on color space conversion in dct domain |
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 | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20200106 Address after: 215021 building D2, artificial intelligence Industrial Park, No. 88, Jinjihu Avenue, Suzhou Industrial Park, Suzhou City, Jiangsu Province Applicant after: Jiangsu yuncongxihe artificial intelligence Co., Ltd Address before: 511457 Room 1011, 26 Jinlong Road, Nansha District, Guangzhou City, Guangdong Province Applicant before: Guangzhou Honghuang Intelligent Technology Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |