CN102959588A - Method for detecting tampering with color digital image based on chroma of image - Google Patents
Method for detecting tampering with color digital image based on chroma of image Download PDFInfo
- Publication number
- CN102959588A CN102959588A CN2011800044127A CN201180004412A CN102959588A CN 102959588 A CN102959588 A CN 102959588A CN 2011800044127 A CN2011800044127 A CN 2011800044127A CN 201180004412 A CN201180004412 A CN 201180004412A CN 102959588 A CN102959588 A CN 102959588A
- Authority
- CN
- China
- Prior art keywords
- image
- edge image
- chroma
- new edge
- chromatic component
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 34
- 238000012549 training Methods 0.000 claims abstract description 22
- 238000001514 detection method Methods 0.000 description 9
- 238000006243 chemical reaction Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 238000000605 extraction Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 5
- 238000012360 testing method Methods 0.000 description 3
- 230000007704 transition Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012795 verification Methods 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241000283070 Equus zebra Species 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005242 forging Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000013519 translation Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/00002—Diagnosis, testing or measuring; Detecting, analysing or monitoring not otherwise provided for
- H04N1/00005—Diagnosis, testing or measuring; Detecting, analysing or monitoring not otherwise provided for relating to image data
-
- 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
- G06T1/0028—Adaptive watermarking, e.g. Human Visual System [HVS]-based watermarking
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N1/00—Scanning, transmission or reproduction of documents or the like, e.g. facsimile transmission; Details thereof
- H04N1/00002—Diagnosis, testing or measuring; Detecting, analysing or monitoring not otherwise provided for
- H04N1/00026—Methods therefor
- H04N1/00037—Detecting, i.e. determining the occurrence of a predetermined state
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2201/00—General purpose image data processing
- G06T2201/005—Image watermarking
- G06T2201/0201—Image watermarking whereby only tamper or origin are detected and no embedding takes place
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Health & Medical Sciences (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
A method for detecting the tampering with a color digital image based on the chroma of the image is provided. The method comprises a training process and a classifying process. The training process includes: converting the color image in the training database which has been signed with the classification information from the RGB color space to the YCbCr color space and extracting its chroma weight; calculating the edge image of the chroma weight and truncating the grey values which are larger than the threshold to obtain a new edge image; calculating the steady state distribution of Markov chain for the new edge image; inputting the features which have been signed with the classification information into the SVM classifier to be trained and obtain a classifier model. The classifying process includes: converting a color image which is randomly input from the RGB color space to the YCbCr color space and extracting its chroma weight; calculating the edge image of the chroma weight and truncating the grey values which are larger than the threshold to obtain a new edge image; calculating the steady state distribution of Markov chain for the new edge image as the features; inputting the features into classifier model of the train process to be classified and getting the result of the judgement.
Description
Color digital image altering detecting method technical field based on image chroma
The present invention relates to the altering detecting method of area of pattern recognition, more particularly to color digital image.Background technology
With developing rapidly for computer in recent years and multimedia technology, particularly great amount of images processing software（Such as Photoshop) appearance so that distorting, forging oneself for digital picture is no longer a difficult matter.The image largely distorted is appeared in news report, even photo contest, legal argument.This make it that society is very urgent to the demand of distorted image detection technique.Digital image tampering is detected（Digital Image Tampering Detection) purpose be by analyzing view data and then finding the presence of tampering, or even tampered region can be navigated to.Detected by distorted image and can be found that unreal PHOTO NEWS, the image evidence forged etc., for the network information security, public safety, judicial evidence collection etc. is significant.
The booming of image processing software makes distorted image operation more and more easier, the various technologies of Digital Image Processing are used alternatingly so that the means mixed the spurious with the genuine of distorted image are more and more brilliant, but also make tampered image be increasingly difficult to be detected by people's subjectivity simultaneously, this is accomplished by carrying out tampered image discriminating by computerized algorithm auxiliary.Current digital image tampering detection algorithm is divided into two major classes：Active mode and passive mode.Active mode is needed in true picture generating process（When taking pictures）Or before issue, watermark information is embedded in wherein.In authentication image authenticity, watermark information only need to be extracted from image, if watermark information is destroyed, illustrates that image is possible to be tampered.But this mode is not very convenient in actual applications, we can not allow all cameras to add watermark embedding module.This causes passive evidence obtaining mode to obtain very big concern.Passive mode is directly to be collected evidence in itself from image, think to distort uniformity [the A.C. Popescu and H. Farid that operation destroys image, " Exposing digital forgeries in color filter array interpolated images, " IEEE Transactions on Signal Processing, vol. 53, no. 10, pp. 3948-3959, 2005.], or the camera intrinsic noise in image is changed or disappear [J. Lukas, J, Fridrich, M. Goljan, " Detecting digital image forgeries using sensor pattern noise, " Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series., vol. 6072, pp. 362-372, 2006], or the high-order statistic of image is changed [Y.Q. Shi, W. Chen, and C. Chen,
I
" A natural image model approach to splicing detection, " Proceedings of the 9ih workshop on Multimedia ＆ security, pp.51-62,2007] the o content of the invention
It is an object of the invention to provide a kind of color digital image altering detecting method based on image chroma, the color image tamper automatic detection of precise and high efficiency can be realized.
To achieve the above object, a kind of color digital image altering detecting method based on image chroma, including training process and assorting process, the training process includes：
From RGB color spaces YCbCr color spaces are transformed into the coloured image of marked classification information in training storehouse, and extract its chromatic component；
The edge image of chromatic component is calculated, and the gray value more than threshold value is blocked, new edge image is obtained；
The steady-state distribution of Markov chain is calculated new edge image；
The feature for having marked classification information is input in SVM classifier and is trained, sorter model is obtained；
The assorting process includes：
YCbCr color spaces are transformed into from rgb color space to the coloured image that arbitrarily inputs, and extract its chromatic component；
The edge image of chromatic component is calculated, and the gray value more than threshold value is blocked, new edge image is obtained；
Feature is used as to the steady-state distribution that new edge image calculates Markov chain；
The sorter model that the feature is loaded into training process is classified, and obtains court verdict.
The method of the present invention can be used for the tampering detection of the multi-medium datas such as image.It can operate with the corresponding products such as content evidence obtaining, the discriminating of internet multimedia, news report picture, judicial picture evidence etc..Because the present invention does not need the embedded watermark information into image in advance, image need to only be analyzed in itself and its inspection feature extraction is simple, quick, efficient, therefore can effectively be applied under the contents such as large-scale data communication, multimedia transmission evidence obtaining environment.Brief description of the drawings
The image to be detected used in flow chart Fig. 2 embodiment of the present invention of color image tamper detection method of Fig. 1 present invention based on image chroma；The image is tampered image.Zebra comes from other pictures in figure.In figure（A) it is testing image, the image is tampered image.（B), (c), (d) are respectively that the coloured image is transformed into after YCbCr color spaces, the edge image of Y, Cb, Cr component.Embodiment
As shown in figure 1, the technical solution adopted in the present invention comprises the following steps：
Training step S1:First, to marked classification information in training storehouse（Tampering class or true class) coloured image carry out color space conversion, take its chromatic component, then calculate the markov steady-state distribution of its edge image, be used as characteristic vector.Secondly, classifier training is carried out to the characteristic set of extraction, obtains the model parameter of grader.
Classifying step S2:Color space conversion is carried out to the coloured image arbitrarily inputted, take its chromatic component, the markov steady-state distribution of its edge image is calculated as feature, in the sorter model that the characteristic vector of extraction is input to the parameter setting that step S1 training is obtained, the classification information of input picture is exported（Tampering class or true class）.
The training step S1 processes are as follows：
Step S11:Color space conversion is carried out to coloured image in training set, it is transformed into by YCbCr color spaces from rgb color space by transformation matrix, wherein Y refers to luminance component, and Cb refers to chroma blue component, and Cr refers to red chrominance component.Extract its chromatic component (Cb or Cr).
Step S12:To the chromatic component obtained in step S11, its edge image is calculated, and its gray value for being more than specific threshold T (such as T=8) is blocked（Number more than 8 is all replaced with 8）, obtain new edge image.
Step S13:The steady-state distribution of its Markov chain is calculated the edge image obtained in S12, and steady-state distribution refers to distribution when Markov chain reaches plateau, can describe Markov chain with it.It regard probability distribution during this plateau as characteristics of image { pb P2, P3, P4, P5, P6, P7, p8, p9, totally 9 tie up.
Step S14:The feature for having marked classification information is input in SVM classifier and is trained, sorter model is obtained.
The classifying step S2 is as follows：
Step S21:Color space conversion is carried out to the coloured image currently inputted, it is transformed into YCbCr color spaces from RGB color spaces, its chromatic component is extracted（Cb or Cr).
Step S22:To the chromatic component obtained in step S21, its edge image is calculated, and its gray value for being more than Τ is blocked, new edge image is obtained.
Step S23:The steady-state distribution of its Markov chain is calculated the edge image obtained in S22 and as feature.
Step S24:Sorter model obtained by being loaded into step S14, the feature obtained in step S23 input SVM classifier is classified, obtain present image whether be tampered image result of determination, complete tampered image and detect.
Described color space conversion refers to coloured image being transformed into YCbCr color spaces from RGB color spaces, such as formula（1) .
(1)
Edge image refers to carry out convolution operation with template M to the chromatic component of coloured image, the image obtained by its absolute value is then taken, such as formula（2) .
E=M I (2) wherein, M be a 3X3 matrix, can use:
Calculating is obtained after edge image, utilizes formula（3) truncation is carried out to it（E (i, j) of usual T=8)<T
(3)
Steady-state distribution described in T e (i, j) >=T（τ) it is expressed as：
π = πΡ
Wherein it is by formula（2) transition probability matrix of the edge image obtained, its calculation formula is:
^ H are the length and width of edge image in formula, are impulse function, and equal sign takes 1 when setting up, and are 0 when invalid.
The SVM classifier of the present invention, as kernel function, finds optimal sorter model parameter using RBF by way of traversal search.
Embodiments in accordance with the present invention, in color image tamper detection, carry out feature extraction to the image in training storehouse first, then carry out classifier training and obtain sorter model；The sorter model trained is used for Image Blind tampering detection, the testing result of binaryzation is provided：True picture or tampered image.
As shown in figure 1, first to pending image file, being defined as after color image format entering this flow.Secondly color space conversion is carried out to coloured image（RGB is transformed into YCbCr) and take its Cr component（Or Cb components）And calculate its edge image and blocked, then, based on the present invention, calculate the transition probability matrix of edge image and its steady-state distribution will be regard as feature, finally, input the feature into the good grader of training in advance and go to be detected, provide image whether be tampered image result.
Embodiment
Illustrated by taking the image in Fig. 2 as an example.
First, color space conversion is carried out to the image（Rgb space is transformed into YCbCr space）.Then, Cr edge image is calculated（Fig. 2 d) and block it with T=8.Based on the present invention, the transition probability matrix corpse of the edge image is sought.
Secondly, steady-state distribution Γ is calculated, characteristic vector τ={ ρ of one 9 dimension is obtainedΐ 5 p2, p.,, ρ4, Ρ5,
Ρ 6, Ρ 7, Ρ 8, Ρ9}。
Finally, obtained characteristic vector is input in the sorter model for having trained parameter, obtains grader and export the classification information of the picture for tampered image.
Sorter model file is by known label（True picture or tampered image）Image pattern, carry out feature extraction, then carry out classifier training and obtain.SVM is a kind of grader, and it farthest separates the sample of different labels mainly by finding a classification interface in feature space.The occurrence of parameter regulation mainly prevented study（I.e. verification and measurement ratio is very high on training sample, and verification and measurement ratio is extremely low on test sample storehouse）.
It is described above, it is only the embodiment in the present invention, but protection scope of the present invention is not limited thereto.Any those skilled in the art for being familiar with the technology disclosed herein technology
In the range of, line translation or replacement can be entered.The conversion and replacement carried out should all be covered within the scope of the present invention.Therefore, protection scope of the present invention should be defined by the protection domain of claims.
Claims (1)
- Claim1. a kind of color digital image altering detecting method based on image chroma, including training process and assorting process, the training process include：δ is transformed into the coloured image of marked classification information in training storehouse from RGB color spacesYCbCr color spaces, and extract its chromatic component；The edge image of chromatic component is calculated, and the gray value more than threshold value is blocked, new edge image is obtained；The steady-state distribution of Markov chain is calculated new edge image；The feature for having marked classification information is input in SVM classifier and is trained by 0, obtains sorter model；The assorting process includes-from rgb color space YCbCr color spaces are transformed into the coloured image that arbitrarily inputs, and extract its chromatic component；5 calculate the edge image of chromatic component, and the gray value more than threshold value is blocked, and obtain new edge image；Feature is used as to the steady-state distribution that new edge image calculates Markov chain；The sorter model that the feature is loaded into training process is classified, and obtains court verdict.0 2. according to the method described in claim 1, it is characterised in that the marked classification information includes distorting information or real information.3. the method according to claim 1, it is characterised in that coloured image is transformed into YCbCr color spaces from rgb color space as the following formula：5 4. according to the method described in claim 1, it is characterised in that the chromatic component includes chroma blue component and red chrominance component.5. according to the method described in claim 1, it is characterised in that the gray value of threshold value is carried out as the following formula truncation-6. according to the method described in claim 1, it is characterised in that the threshold value is 8.7. method according to claim 6, it is characterised in that the number more than 8 is all replaced with 8.8. according to the method described in claim 1, it is characterised in that the sorter model is used to basic function as kernel function, to find optimal sorter model parameter.
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| PCT/CN2011/073444 WO2012145909A1 (en) | 2011-04-28 | 2011-04-28 | Method for detecting tampering with color digital image based on chroma of image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN102959588A true CN102959588A (en) | 2013-03-06 |
Family
ID=47071563
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2011800044127A Pending CN102959588A (en) | 2011-04-28 | 2011-04-28 | Method for detecting tampering with color digital image based on chroma of image |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN102959588A (en) |
| WO (1) | WO2012145909A1 (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654089A (en) * | 2014-08-20 | 2016-06-08 | 江南大学 | Image re-sampling detection based on Markov process and Gabor filtering |
| CN105678308A (en) * | 2016-01-12 | 2016-06-15 | 中国科学院自动化研究所 | Image stitching testing method based on illumination direction inconsistency |
| CN108230227A (en) * | 2018-02-06 | 2018-06-29 | 中国银行股份有限公司 | A kind of recognition methods of distorted image, device and electronic equipment |
| CN109558872A (en) * | 2018-11-22 | 2019-04-02 | 四川大学 | A kind of vehicle color identification method |
| CN110363207A (en) * | 2018-04-09 | 2019-10-22 | 阿里巴巴集团控股有限公司 | Image detection and the generation method of sorter model, device and equipment |
| CN111784708A (en) * | 2020-07-03 | 2020-10-16 | 上海骏聿数码科技有限公司 | Image tamper-proof inspection method and device |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103679626A (en) * | 2013-11-28 | 2014-03-26 | 中国科学院自动化研究所 | Image tampering location method based on DCT coefficient |
| CN106355180B (en) * | 2016-09-07 | 2019-07-02 | 武汉安可威视科技有限公司 | A kind of license plate locating method combined based on color with edge feature |
| CN109416747B (en) * | 2016-09-30 | 2022-01-14 | 富士通株式会社 | Target color recognition method and device and computer system |
| CN108108772B (en) * | 2018-01-06 | 2021-08-10 | 天津大学 | Insulator pollution flashover state detection method based on aerial image of distribution line |
| CN108470141B (en) * | 2018-01-27 | 2021-08-10 | 天津大学 | Statistical feature and machine learning-based insulator identification method in distribution line |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080193031A1 (en) * | 2007-02-09 | 2008-08-14 | New Jersey Institute Of Technology | Method and apparatus for a natural image model based approach to image/splicing/tampering detection |
| CN101493927A (en) * | 2009-02-27 | 2009-07-29 | 西北工业大学 | Image reliability detecting method based on edge direction characteristic |
| CN101777129A (en) * | 2009-11-25 | 2010-07-14 | 中国科学院自动化研究所 | Image matching method based on feature detection |
| CN101859385A (en) * | 2010-06-29 | 2010-10-13 | 上海大学 | Local fuzzy interpolation blind detection method based on images |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3775211B2 (en) * | 2000-11-22 | 2006-05-17 | セイコーエプソン株式会社 | Image information processing method and image information processing apparatus |
| CN101331526B (en) * | 2005-12-16 | 2010-10-13 | Ncr公司 | Banknote validation |
| US7778461B2 (en) * | 2006-05-05 | 2010-08-17 | New Jersey Institute Of Technology | System and/or method for image tamper detection |
| US7991185B2 (en) * | 2006-06-30 | 2011-08-02 | New Jersey Institute Of Technology | Method and apparatus for image splicing/tampering detection using moments of wavelet characteristic functions and statistics of 2-D phase congruency arrays |
| CN101464952A (en) * | 2007-12-19 | 2009-06-24 | 中国科学院自动化研究所 | Abnormal behavior identification method based on contour |
| CN101493939A (en) * | 2009-02-27 | 2009-07-29 | 西北工业大学 | Method for detecting cooked image based on small wave domain homomorphic filtering |
| US8718379B2 (en) * | 2009-09-15 | 2014-05-06 | Texas Instruments Incorporated | Method and apparatus for image capturing tampering detection |
-
2011
- 2011-04-28 CN CN2011800044127A patent/CN102959588A/en active Pending
- 2011-04-28 WO PCT/CN2011/073444 patent/WO2012145909A1/en active Application Filing
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20080193031A1 (en) * | 2007-02-09 | 2008-08-14 | New Jersey Institute Of Technology | Method and apparatus for a natural image model based approach to image/splicing/tampering detection |
| CN101493927A (en) * | 2009-02-27 | 2009-07-29 | 西北工业大学 | Image reliability detecting method based on edge direction characteristic |
| CN101777129A (en) * | 2009-11-25 | 2010-07-14 | 中国科学院自动化研究所 | Image matching method based on feature detection |
| CN101859385A (en) * | 2010-06-29 | 2010-10-13 | 上海大学 | Local fuzzy interpolation blind detection method based on images |
Non-Patent Citations (1)
| Title |
|---|
| WEI WANG 等: "Image tampering detection based on stationary distribution of Markov chain", 《PROCEEDINGS OF 2010 IEEE 17TH INTERNATIONAL CONFERENCE ON IMAGE PROCESSING》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105654089A (en) * | 2014-08-20 | 2016-06-08 | 江南大学 | Image re-sampling detection based on Markov process and Gabor filtering |
| CN105678308A (en) * | 2016-01-12 | 2016-06-15 | 中国科学院自动化研究所 | Image stitching testing method based on illumination direction inconsistency |
| CN108230227A (en) * | 2018-02-06 | 2018-06-29 | 中国银行股份有限公司 | A kind of recognition methods of distorted image, device and electronic equipment |
| CN110363207A (en) * | 2018-04-09 | 2019-10-22 | 阿里巴巴集团控股有限公司 | Image detection and the generation method of sorter model, device and equipment |
| CN109558872A (en) * | 2018-11-22 | 2019-04-02 | 四川大学 | A kind of vehicle color identification method |
| CN109558872B (en) * | 2018-11-22 | 2022-02-11 | 四川大学 | Vehicle color identification method |
| CN111784708A (en) * | 2020-07-03 | 2020-10-16 | 上海骏聿数码科技有限公司 | Image tamper-proof inspection method and device |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2012145909A1 (en) | 2012-11-01 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN102959588A (en) | Method for detecting tampering with color digital image based on chroma of image | |
| Wang et al. | Detection and localization of image forgeries using improved mask regional convolutional neural network | |
| Yang et al. | Source camera identification based on content-adaptive fusion residual networks | |
| Salloum et al. | Image splicing localization using a multi-task fully convolutional network (MFCN) | |
| Zheng et al. | A survey on image tampering and its detection in real-world photos | |
| Mahmoud et al. | Forest fire detection and identification using image processing and SVM | |
| CN112381775B (en) | Image tampering detection method, terminal device and storage medium | |
| CN110349136A (en) | A kind of tampered image detection method based on deep learning | |
| CN111340784B (en) | Mask R-CNN-based image tampering detection method | |
| Duan et al. | Adult image detection method base-on skin color model and support vector machine | |
| CN106203461B (en) | Image processing method and device | |
| Wang et al. | LBP-SVD based copy move forgery detection algorithm | |
| CN106060568B (en) | A kind of video tampering detection and localization method | |
| CN107437293A (en) | A kind of bill anti-counterfeit discrimination method based on bill global characteristics | |
| CN104408728A (en) | Method for detecting forged images based on noise estimation | |
| CN113361474B (en) | Double-current network image counterfeiting detection method and system based on image block feature extraction | |
| Dixit et al. | Copy-move forgery detection exploiting statistical image features | |
| Rhee | Detection of spliced image forensics using texture analysis of median filter residual | |
| CN114581646A (en) | Text recognition method and device, electronic equipment and storage medium | |
| Zhao et al. | A transferable anti-forensic attack on forensic CNNs using a generative adversarial network | |
| CN111476727A (en) | Video motion enhancement method for face changing video detection | |
| Lu et al. | Traffic light recognition | |
| Li et al. | Distinguishing computer graphics from photographic images using a multiresolution approach based on local binary patterns | |
| Zhang et al. | Image splicing detection scheme based on error level analysis and local binary pattern | |
| Mushtaq et al. | Novel method for image splicing detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20130306 |