CN106709853A - Image retrieval method and system - Google Patents
Image retrieval method and system Download PDFInfo
- Publication number
- CN106709853A CN106709853A CN201611089797.2A CN201611089797A CN106709853A CN 106709853 A CN106709853 A CN 106709853A CN 201611089797 A CN201611089797 A CN 201611089797A CN 106709853 A CN106709853 A CN 106709853A
- Authority
- CN
- China
- Prior art keywords
- image
- original image
- mark
- original
- lsb bit
- 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
- 238000000034 method Methods 0.000 title claims abstract description 27
- 230000002441 reversible effect Effects 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 19
- 239000000284 extract Substances 0.000 claims description 16
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 14
- 238000003780 insertion Methods 0.000 claims description 6
- 230000037431 insertion Effects 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 3
- 238000007689 inspection Methods 0.000 claims description 2
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 238000001514 detection method Methods 0.000 description 4
- 238000010801 machine learning Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000002427 irreversible effect Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000004224 protection Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
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
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Editing Of Facsimile Originals (AREA)
- Storage Device Security (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an image retrieval method and system. The method comprises the steps that an original image is embedded after annotation information is encrypted into ciphertext data, and substituted original pixels are used as a watermark generation annotation image through a reversible watermarking algorithm; and the ciphertext data in the annotation image is extracted and decrypted, the decryption result is matched with retrieval conditions to acquire a target annotation image, a pixel value of the original image corresponding to the target annotation image is calculated, and a watermark is output after being extracted. The algorithm has a small influence on the original image, and the original image can be restored in one hundred percent at a receiving end; meanwhile, the algorithm is high in speed and adaptive to a large quantity of sample annotation scenes, so that space complexity is lowered; the encrypted annotation information is prevented from being tampered, and therefore the validity, relevancy and manageability of the annotation information are improved.
Description
Technical field
The invention belongs to technical field of image processing, in particular to a kind of image search method and system.
Background technology
With the fast development of Information ＆ Communication Technology, various view data increase in explosion index formula.How to magnanimity
View data carry out effective management and become a problem demanding prompt solution.With pattern-recognition and machine Learning Theory with
The development of algorithm, is realizing the automatic management of image to a certain degree very much.It is current mainly to include two kinds of image management modes：Image
Machine learning is marked with traditional images.Wherein, image machine learning techniques mainly train steady using a large amount of markd samples
Fixed disaggregated model, to realize to unknown a series of images detection, classification and identification；And traditional image labeling method then leads to
Newly-built one secondary file corresponding with image is crossed, the object information of artificial/machine mark is recorded.Both notation methods are being passed
Defeated and storage aspect, on the one hand increased bandwidth cost or spatial content expense, on the other hand and is easily lost or damages.Separately
Outward, the poor information encryption protections of most marks, the information of mark is dangerous and easy leakage.
The content of the invention
To solve above-mentioned technical disadvantages, the present invention utilizes encryption technology and reversible water mark the technology markup information in original image
Prevent markup information from revealing, while reducing bandwidth cost, the spatial content expense of image after mark, improve the pipe to view data
Reason.
The invention provides a kind of image search method, comprise the following steps：
Original image, the original image that will be replaced using reversible water mark algorithm are embedded in after markup information is encrypted as into ciphertext data
Element is used as watermark generation mark image；
Extract and ciphertext data and decrypt in mark image, decrypted result and search condition match obtain target and mark
Image, calculates the pixel value of original image corresponding with target mark image and is exported after extracting watermark.
Further, in image search method of the present invention, it is described markup information is encrypted as it is embedding after ciphertext data
Enter original image, included using mark image is generated after the addition watermark of reversible water mark algorithm
Original image LSB bit is obtained, original image LSB bit content is extracted and preserve, by the insertion original image LSB bit life of ciphertext data
Into the first mark image；
Original image LSB bit content watermark to the first mark image generation second is marked into image.
Further, in image search method of the present invention, the acquisition original image LSB bit is extracted and preserved
Original image LSB bit content, ciphertext data insertion original image LSB bit generation first is marked into image includes
Markup information is obtained, markup information N coding is encoded to according to after coding schedule, and it is tested；
N coding after verification is encrypted generation ciphertext character string；
Embedded ciphertext text string generation first marks image in the original image after extracting LSB bit content.
Further, in image search method of the present invention, described extraction ciphertext data and decrypt in mark image,
Decrypted result and search condition are carried out to match acquisition target mark image, original image corresponding with target mark image is calculated
Pixel value simultaneously to be extracted export after watermark and included
Obtain search condition；
Mark image LSB bit is obtained, ciphertext data is extracted and is decrypted acquisition markup information；
Markup information and search condition are carried out to match acquisition target mark image；
After calculating the pixel value and the LSB bit content of the original image for extracting watermark of original image corresponding with target mark image
Output original image.
Present invention also offers a kind of image indexing system, including
Image processing apparatus, for markup information to be encrypted as after ciphertext data into embedded original image, are calculated using reversible water mark
Mark image is generated after method addition watermark；
Retrieval device, ciphertext data and decrypt in mark image for being extracted, and decrypted result and search condition are carried out
With target mark image is obtained, calculate the pixel value of original image corresponding with target mark image and exported after extracting watermark.
Further, in image indexing system of the present invention, image processing apparatus include
First processing module, for obtaining original image LSB bit, extracts and preserves original image LSB bit content, by ciphertext data
Embedded original image LSB bit generation first marks image；
Second processing module, for original image LSB bit content watermark to the first mark image generation second to be marked into image.
Further, in image indexing system of the present invention, first processing module includes
Coding module, for obtaining markup information, N coding is encoded to according to after coding schedule by markup information, and to it
Test；
Encrypting module, for N coding after verification to be encrypted into generation ciphertext character string；
Generation module, figure is marked for the embedded ciphertext text string generation first in the original image after extracting LSB bit content
Picture.
Further, in image indexing system of the present invention, the retrieval device includes
Interface module, for obtaining search condition；
Deciphering module, for obtaining mark image LSB bit, extracts ciphertext data and decrypts acquisition markup information；
Enquiry module, for carrying out markup information and search condition to match acquisition target mark image；
Processing module, mark the pixel value of the corresponding original image of image with target and extract the original image of watermark for calculating
LSB bit content after export original image.
To sum up, influence very little, algorithm speed of the algorithm proposed by the present invention to original image soon, are adapted to the mark of great amount of samples
In note scene, space complexity is reduced, the markup information of encryption prevents from being tampered, improve the validity of markup information, close
Connection property with it is managerial.
Brief description of the drawings
Fig. 1 is the schematic flow sheet of image search method one embodiment of the present invention；
Fig. 2 is the schematic flow sheet of S101 in image search method one embodiment of the present invention；
Fig. 3 to markup information in image search method one embodiment of the present invention to encode and verifies latter in fact
Apply the structure composition schematic diagram of example；
Fig. 4 is the implementation after markup information being encoded and verified in image search method one embodiment of the present invention
The structural representation of example；
Fig. 5 is the structural representation of the piecemeal of original image in image search method one embodiment of the present invention；
Fig. 6 is the schematic flow sheet of S102 in image search method one embodiment of the present invention；
Fig. 7 is the structural representation of image indexing system one embodiment of the present invention.
Specific embodiment
As shown in figure 1, the invention provides a kind of image search method, comprising the following steps：
S101, markup information is encrypted as after ciphertext data embedded original image, will be replaced using reversible water mark algorithm
Original pixels are used as watermark generation mark image；
Digital watermark technology is that some identification informations (i.e. watermark) are embedded in digital carrier, and does not influence initial carrier
The method of use value.The robustness attacked according to digital watermarking resistance can be classified as robust digital watermark and rapid wear numeral
The class of watermark two.Invertibity according to digital watermarking watermark can be classified as reversible digital watermarking and irreversible digital watermarking two
Class.Wherein, reversible digital watermarking requirement can not only intactly extract watermark extracting end, and can free of losses recover original
Beginning carrier.This special watermark is mainly used in medical treatment, military and judicial domain application scenes at present.Reversible digital water
Print field can be divided into two class algorithms：Spatial-domain algorithm and transform-domain algorithm.Current existing reversible water mark algorithm is main
Concentrate on spatial domain, use the reversible water mark algorithm of spatial domain in the present embodiment, propose based on bit reversal can inverse number
Word digital watermark:In transmitting terminal, when embedded watermark bit is 1, the LSB bit in the block of original image is overturn, do not overturn otherwise.
Receiving terminal, according to image itself flatness feature, to receiving, image can carry out watermark bit extraction simultaneously and original image is extensive
It is multiple.
S102, extract and ciphertext data and decrypt in mark image, decrypted result and search condition match obtain mesh
Mark mark image, calculates the pixel value of original image corresponding with target mark image and is exported after extracting watermark.
The present invention is encrypted to markup information first, prevents markup information from revealing or being tampered, while using reversible
Watermarking algorithm can recover original image in receiving terminal to adding watermark on image with 100% ground.During specific implementation, markup information
It is optional including founder, the beacon information of the owner, sign of buyer (i.e. sequence number) etc..Marked with traditional artificial image
Method is compared, and the present invention need not set up secondary file, it is not necessary to image is associated with the secondary file of mark, is reduced
Space complexity, reduces idle capacity expense.
Further, S101 includes as shown in Figure 2
S1011, acquisition original image LSB bit, extract and preserve original image LSB bit content, and ciphertext data are embedded in into original image
LSB bit generation first marks image；
Further, the S1011 includes
Markup information is obtained, markup information is encoded to N coding according to after coding schedule, N=12 is taken in the present embodiment, most
2 can be represented greatly12=4096 classifications, and it is verified；
N coding after verification is encrypted generation ciphertext character string；
Embedded ciphertext text string generation first marks image in the original image after extracting LSB bit content.
During specific implementation, the information of being labeled with is encoded and verified optionally to be carried out in accordance with the following steps：
(1) artificial/machine is passed through to search 12 coding schedules to the markup information of image, the markup informations such as classification is carried out
Coding；
(2) information for marking verify and optionally utilize odd even Error Correction of Coding, have four error correcting codes.
What is utilized in the present embodiment is 12 coding schedules, is 20 after encoding and check for 12 after markup information being encoded
Position, it is specific optional as shown in Figure 3-4, wherein, first four is prefix, and 0000,1111 represent artificial mark, machine mark respectively
Note.
Verifying rule is：1-4 markup information obtains first error correcting code；5-8 markup information obtains second
Error correcting code；9-12 markup information obtains the 3rd error correcting code；Front three error correcting code obtains the 4th error correcting code.Add simultaneously
Four identification informations of prefix 0000/1111, represent artificial or machine mark respectively, will markup information be encoded to 20.Need
Illustrate, the present embodiment, for coding schedule is encoded to markup information, will also optionally be marked according to 12 during specific implementation
Note information is encoded to other coding, and the present invention is not limited herein.
During specific implementation, the algorithm of encryption is optional to be carried out according to equation below：
Wherein, d is initial data, and ks is pseudo random number, and c is ciphertext string data,Represent XOR.The AES
Using simple xor operation, encryption process is same algorithm, it is easy to the realization of hardware, is conducive to improve encryption and decryption speed
Degree.
It should be noted that the present embodiment is only one embodiment of the present of invention, it is also optionally utilized during specific implementation
He is encrypted AES.
S1012, by original image LSB bit content watermark to first mark image generation second mark image.
During specific implementation, optionally carry out in accordance with the following steps：
A original image LSB that () will remove central area is grouped, and the optional form according to n × n carries out piecemeal, n=3,
5,7 ... 15, n=3 is taken in the present embodiment, i.e., carry out piecemeal according to 3 × 3.
B () to 9 positions in piecemeal as shown in figure 5, be numbered, the wherein LSB at block center is indicating bit, in insertion
Process keeps constant, and 8 LSB of surrounding change with embedded reversible water mark.
If c () embedded watermark is that 0,8 LSB do not overturn.If embedded watermark is that 1,8 LSB are overturn.
Rule is as follows：
Wherein, i represents the numbering of piecemeal, and m represents embedded water
Print, LSBiExpression does not overturn,Represent upset.
It is optional using multistage embedding strategy during specific implementation for the accuracy for improving watermark detection and recover, that is, exist
Multiple blocks (group) carry out same embedding operation according to step (a)-(c), until 20 bits of LSB of all of original image
It is embedded.
The quality of image can be estimated using PSNR (Y-PSNR).Assessment is calculated according to equation below：
According to international standard image library, carrying out gray level image to mark image carries out algorithm simulating, obtains table group image
PSNR is essentially 51dB, and picture quality is very good, it was demonstrated that to after the embedded original image of mark encryption and watermark to original image
Influence is little；The algorithm speed that coding encrypting is carried out to markup information of the invention is fast simultaneously, can adapt to the mark in great amount of samples
In note scene, space complexity is reduced, it is therefore prevented that mark is tampered, and improves validity, relevance and the pipe of markup information
Rationality.
Further, as shown in fig. 6, S102 includes
S1021, acquisition search condition；
S1022, acquisition mark image LSB bit, extract ciphertext data and simultaneously decrypt acquisition markup information；During specific implementation, can
That selects is carried out in accordance with the following steps：
(1) LSB of the central area of embedded watermarking images is navigated to, the data of 20 bit encryptions are extracted.
(2) data are decrypted as follows：
(3) the labeled data bag that will be obtained carries out following detection：
If a () identification division is 1111 or 0000 detection for carrying out below, otherwise abandon, operation below is not performed.
B () is detected to the check bit of packet, if mistake, directly abandon, and operation below is not performed.
(4) the mark part of the packet that will be obtained is decoded by coding schedule, obtains image labeling information.
S1023, markup information and search condition match acquisition target mark image；
It is defeated after S1024, calculating pixel value corresponding with target mark image and the LSB bit content of the original image for extracting watermark
Go out original image.
It is optional during specific implementation that target mark image is carried out in accordance with the following steps：
(1) to equally carrying out piecemeal, such as 3*3 containing watermarking images.
(2) LSB to the 1-8 positions of each block overturns.
(3) smoothness value before the upset of each block and after upset is calculated respectively, it is as follows：
Wherein, P0Refer to the pixel value in the middle of block, Pi,Refer to the pixel value before the upset around block and after upset respectively, and
H0,H1Refer to respectively block upset before and upset after gentle angle value.Smoothness is smaller closer to true picture.
(4) recover the original pixel value of each block, and extract watermark, it is as follows：
Wherein, re_PiRefer to the pixel value recovered in block, m refers to the watermark information for extracting.
Specifically, the pixel value P of some block of image is such as received0=7, P1=P2=6, P3=P4=...=P8=7.
After the bit reversal of the LSB bit of 8 positions therein, pixel valueIt is calculated H0
=2 ＜ H1=6, thus may determine that the block before upset is the block of original image, and the watermark bit for extracting is 0.
It is managed present invention aim to former data (data such as image, audio, video), the convenient inspection according to user
The view data of user's query demand is facilitated after rope condition is retrieved, therefore the present invention is labeled to original image.This hair
Acquisition markup information is decrypted to all of mark image after bright acquisition search condition, is matched and retrieval bar according to markup information
The corresponding target mark image of part is simultaneously exported.
As shown in fig. 7, present invention also offers a kind of image indexing system, including
Image processing apparatus 10, for markup information to be encrypted as after ciphertext data into embedded original image, using reversible water mark
The original pixels that algorithm will be replaced mark image as watermark generation；
Retrieval device 20, ciphertext data and decrypt in mark image for being extracted, and decrypted result is carried out with search condition
Matching obtains target mark image, calculates the pixel value of original image corresponding with target mark image and is exported after extracting watermark.
Further, image processing apparatus include
First processing module, for obtaining original image LSB bit, extracts and preserves original image LSB bit content, by ciphertext data
Embedded original image LSB bit generation first marks image；
Second processing module, for original image LSB bit content watermark to the first mark image generation second to be marked into image.
Further, first processing module includes
Coding module, for obtaining markup information, N coding is encoded to according to after coding schedule by markup information, and to it
Test；
Encrypting module, for N coding after verification to be encrypted into generation ciphertext character string；
Generation module, figure is marked for the embedded ciphertext text string generation first in the original image after extracting LSB bit content
Picture.
Further, the retrieval device includes
Interface module, for obtaining search condition；
Deciphering module, for obtaining mark image LSB bit, extracts ciphertext data and decrypts acquisition markup information；
Enquiry module, for carrying out markup information and search condition to match acquisition target mark image；
Processing module, mark the pixel value of the corresponding original image of image with target and extract the original image of watermark for calculating
LSB bit content after export original image.
The preferred embodiments of the present invention are the foregoing is only, is not intended to limit the invention, for the skill of this area
For art personnel, the present invention can have various modifications and variations.It is all within the spirit and principles in the present invention, made any repair
Change, equivalent, improvement etc., should be included within the scope of the present invention.
Claims (8)
1. a kind of image search method, it is characterised in that comprise the following steps：
Original image is embedded in after markup information is encrypted as into ciphertext data, the original pixels that will be replaced using reversible water mark algorithm are made
It is watermark generation mark image；
Extract and ciphertext data and decrypt in mark image, decrypted result and search condition match obtain target mark figure
Picture, calculates the pixel value of original image corresponding with target mark image and is exported after extracting watermark.
2. image search method according to claim 1, it is characterised in that described that markup information is encrypted as ciphertext data
Original image is embedded in afterwards, is included as watermark generation mark image by the use of the original pixels that reversible water mark algorithm will be replaced
Original image LSB bit is obtained, original image LSB bit content is extracted and preserve, by ciphertext data insertion original image LSB bit generation the
One mark image；
Original image LSB bit content watermark to the first mark image generation second is marked into image.
3. image search method according to claim 2, it is characterised in that the acquisition original image LSB bit, extracts and protects
Original image LSB bit content is deposited, ciphertext data insertion original image LSB bit generation first is marked into image includes
Markup information is obtained, markup information N coding is encoded to according to after coding schedule, and it is tested；
N coding after verification is encrypted generation ciphertext character string；
Embedded ciphertext text string generation first marks image in the original image after extracting LSB bit content.
4. image search method according to claim 1, it is characterised in that ciphertext data are simultaneously in the extraction mark image
Decryption, decrypted result and search condition are carried out to match acquisition target mark image, calculate original corresponding with target mark image
The pixel value of image simultaneously to be extracted export after watermark and included
Obtain search condition；
Mark image LSB bit is obtained, ciphertext data is extracted and is decrypted acquisition markup information；
Markup information and search condition are carried out to match acquisition target mark image；
Exported after the pixel value and the LSB bit content of the original image for extracting watermark that calculate original image corresponding with target mark image
Original image.
5. a kind of image indexing system, it is characterised in that including
Image processing apparatus, for markup information to be encrypted as after ciphertext data into embedded original image, will using reversible water mark algorithm
The original pixels being replaced are used as watermark generation mark image；
Retrieval device, ciphertext data and decrypt in mark image for being extracted, and decrypted result and search condition match obtaining
Target mark image is taken, the pixel value of original image corresponding with target mark image is calculated and is exported after extracting watermark.
6. image indexing system according to claim 1, it is characterised in that image processing apparatus include
First processing module, for obtaining original image LSB bit, extracts and preserves original image LSB bit content, by the insertion of ciphertext data
Original image LSB bit generation first marks image；
Second processing module, for original image LSB bit content watermark to the first mark image generation second to be marked into image.
7. image indexing system according to claim 6, it is characterised in that first processing module includes
Coding module, for obtaining markup information, is encoded to N coding, and it is carried out according to after coding schedule by markup information
Inspection；
Encrypting module, for N coding after verification to be encrypted into generation ciphertext character string；
Generation module, image is marked for the embedded ciphertext text string generation first in the original image after extracting LSB bit content.
8. image indexing system according to claim 5, it is characterised in that the retrieval device includes
Interface module, for obtaining search condition；
Deciphering module, for obtaining mark image LSB bit, extracts ciphertext data and decrypts acquisition markup information；
Enquiry module, for carrying out markup information and search condition to match acquisition target mark image；
Processing module, for calculating the original image for marking the pixel value of the corresponding original image of image and extracting watermark with target
Original image is exported after LSB bit content.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611089797.2A CN106709853B (en) | 2016-11-30 | 2016-11-30 | Image retrieval method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611089797.2A CN106709853B (en) | 2016-11-30 | 2016-11-30 | Image retrieval method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106709853A true CN106709853A (en) | 2017-05-24 |
| CN106709853B CN106709853B (en) | 2020-12-29 |
Family
ID=58934447
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611089797.2A Active CN106709853B (en) | 2016-11-30 | 2016-11-30 | Image retrieval method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106709853B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107967688A (en) * | 2017-12-21 | 2018-04-27 | 联想(北京)有限公司 | The method and system split to the object in image |
| CN108848270A (en) * | 2018-06-29 | 2018-11-20 | 维沃移动通信（深圳）有限公司 | A kind of processing method and mobile terminal of screenshotss image |
| CN110503591A (en) * | 2018-05-16 | 2019-11-26 | 武汉智云星达信息技术有限公司 | The method that effective intelligent image zooming-out and certification based on feature contour two dimension code watermark compare |
| CN111212196A (en) * | 2020-01-13 | 2020-05-29 | 深圳市商汤科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN113326394A (en) * | 2021-06-30 | 2021-08-31 | 合肥高维数据技术有限公司 | Vector diagram watermark embedding and tracing method and system |
| CN113919384A (en) * | 2021-09-09 | 2022-01-11 | 同济大学 | Encryption gray level image coding and decoding method for commodity outer package |
| CN114117494A (en) * | 2021-11-30 | 2022-03-01 | 国网重庆市电力公司电力科学研究院 | Encryption type data annotation system and use method thereof |
| CN116431855A (en) * | 2023-06-13 | 2023-07-14 | 荣耀终端有限公司 | Image retrieval method and related equipment |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060120558A1 (en) * | 2004-10-20 | 2006-06-08 | Yun-Qing Shi | System and method for lossless data hiding using the integer wavelet transform |
| CN1790420A (en) * | 2005-12-01 | 2006-06-21 | 北京北大方正电子有限公司 | Method and apparatus for embedding and detecting digital watermark in text file |
| CN101059863A (en) * | 2006-04-20 | 2007-10-24 | 刘瑞祯 | Embed and detection method for identifying water mark, its system and uses |
| CN102903076A (en) * | 2012-10-24 | 2013-01-30 | 兰州理工大学 | Method for embedding and extracting reversible watermark of digital image |
| CN104268824A (en) * | 2014-09-19 | 2015-01-07 | 柳州师范高等专科学校 | Self-adaptation reversible watermarking method used for medical image authentication and doctor-patient information hiding |
| CN104715442A (en) * | 2015-04-10 | 2015-06-17 | 福建师范大学 | Hamming-code-based quantum image watermarking method |
| CN104794673A (en) * | 2015-03-30 | 2015-07-22 | 北京交通大学 | Reversible digital watermark implementation method of encrypted domain utilizing most significant bits |
-
2016
- 2016-11-30 CN CN201611089797.2A patent/CN106709853B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060120558A1 (en) * | 2004-10-20 | 2006-06-08 | Yun-Qing Shi | System and method for lossless data hiding using the integer wavelet transform |
| CN1790420A (en) * | 2005-12-01 | 2006-06-21 | 北京北大方正电子有限公司 | Method and apparatus for embedding and detecting digital watermark in text file |
| CN101059863A (en) * | 2006-04-20 | 2007-10-24 | 刘瑞祯 | Embed and detection method for identifying water mark, its system and uses |
| CN102903076A (en) * | 2012-10-24 | 2013-01-30 | 兰州理工大学 | Method for embedding and extracting reversible watermark of digital image |
| CN104268824A (en) * | 2014-09-19 | 2015-01-07 | 柳州师范高等专科学校 | Self-adaptation reversible watermarking method used for medical image authentication and doctor-patient information hiding |
| CN104794673A (en) * | 2015-03-30 | 2015-07-22 | 北京交通大学 | Reversible digital watermark implementation method of encrypted domain utilizing most significant bits |
| CN104715442A (en) * | 2015-04-10 | 2015-06-17 | 福建师范大学 | Hamming-code-based quantum image watermarking method |
Non-Patent Citations (3)
| Title |
|---|
| JAGREETI KAUR 等: "Comparison of LSB and Predictive Coding using PSNR and MSE", 《INTERNATIONAL JOURNAL OF COMPUTER APPLICATIONS》 * |
| 曲欣欣: "基于医学图像的可逆信息隐藏算法研究", 《万方数据库》 * |
| 饶俊慧 等: "基于Gabor纹理特征和可逆水印的图像检索算法", 《玉林师范学院学报（自然科学）》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107967688A (en) * | 2017-12-21 | 2018-04-27 | 联想(北京)有限公司 | The method and system split to the object in image |
| CN110503591A (en) * | 2018-05-16 | 2019-11-26 | 武汉智云星达信息技术有限公司 | The method that effective intelligent image zooming-out and certification based on feature contour two dimension code watermark compare |
| CN108848270A (en) * | 2018-06-29 | 2018-11-20 | 维沃移动通信（深圳）有限公司 | A kind of processing method and mobile terminal of screenshotss image |
| CN111212196A (en) * | 2020-01-13 | 2020-05-29 | 深圳市商汤科技有限公司 | Information processing method and device, electronic equipment and storage medium |
| CN113326394A (en) * | 2021-06-30 | 2021-08-31 | 合肥高维数据技术有限公司 | Vector diagram watermark embedding and tracing method and system |
| CN113919384A (en) * | 2021-09-09 | 2022-01-11 | 同济大学 | Encryption gray level image coding and decoding method for commodity outer package |
| CN113919384B (en) * | 2021-09-09 | 2023-08-04 | 同济大学 | Encrypted grayscale image encoding and decoding method for commodity packaging |
| CN114117494A (en) * | 2021-11-30 | 2022-03-01 | 国网重庆市电力公司电力科学研究院 | Encryption type data annotation system and use method thereof |
| CN116431855A (en) * | 2023-06-13 | 2023-07-14 | 荣耀终端有限公司 | Image retrieval method and related equipment |
| CN116431855B (en) * | 2023-06-13 | 2023-10-20 | 荣耀终端有限公司 | Image retrieval method and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106709853B (en) | 2020-12-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106709853A (en) | Image retrieval method and system | |
| US20230360165A1 (en) | Method and apparatus for protecting digital photos from alteration | |
| Ansari et al. | SVD based fragile watermarking scheme for tamper localization and self-recovery | |
| Yin et al. | Separable and Error‐Free Reversible Data Hiding in Encrypted Image with High Payload | |
| CN101458810B (en) | A Vector Map Watermarking Method Based on Object Attributes | |
| CN107742272B (en) | A semi-fragile watermarking method based on image tampering location and recovery | |
| CN105184537B (en) | A kind of the cloud commodity distribution control method and system of real time monitoring cargo state | |
| CN105141409B (en) | A kind of implementation method, terminal and the server of screen Digital watermark | |
| CN113129198B (en) | Zero watermark generation method and system and copyright infringement comparison method and system | |
| CN104823203A (en) | Biometric template security and key generation | |
| CN105761197B (en) | A kind of remote sensing image water mark method based on property invariant | |
| CN101472161A (en) | Method, device and system for embedding and removing watermark | |
| CN109348230A (en) | A Reversible Data Hiding Method for High-capacity Images in Ciphertext Domain | |
| CN104063731A (en) | Two-dimension code anti-counterfeiting printing and verification method adopting digital watermark technology | |
| CN112487365A (en) | Information steganography method and information detection method and device | |
| CN114567711A (en) | Large-capacity encrypted image information hiding method based on block capacity label | |
| CN105225089A (en) | A kind of logistics monitoring method and system obtaining goods real time kinematics track | |
| CN116805069A (en) | Trajectory data zero watermark generation method, detection method, device and storage medium | |
| CN106127668A (en) | GPS and the guard method in IOS end digitized video of the BEI-DOU position system space time information | |
| CN102523535A (en) | Video stream and global positioning system (GPS) real-time registration and synchronous transmission method based on digital watermarking technology | |
| CN103853946B (en) | A kind of GIS vector data copyright authentication method based on FCM cluster feature | |
| Sonnleitner | A robust watermarking approach for large databases | |
| CN105741222A (en) | Steganographic information positioning method based on pixel subset embedding rate estimation | |
| Kumar et al. | Data hiding with dual based reversible image using sudoku technique | |
| CN114553549B (en) | Data encryption method and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |