CN106408036A - Method and system for image camera source identification - Google Patents
Method and system for image camera source identification Download PDFInfo
- Publication number
- CN106408036A CN106408036A CN201510458731.5A CN201510458731A CN106408036A CN 106408036 A CN106408036 A CN 106408036A CN 201510458731 A CN201510458731 A CN 201510458731A CN 106408036 A CN106408036 A CN 106408036A
- Authority
- CN
- China
- Prior art keywords
- image
- camera
- fingerprint
- checked
- convolved
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/74—Image or video pattern matching; Proximity measures in feature spaces
- G06V10/75—Organisation of the matching processes, e.g. simultaneous or sequential comparisons of image or video features; Coarse-fine approaches, e.g. multi-scale approaches; using context analysis; Selection of dictionaries
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Image Processing (AREA)
Abstract
The invention is applicable to the technical field of multimedia information safety, and provides a method and system for image camera source identification. The method includes: obtaining a to-be-detected image, and performing convolution operation on the to-be-detected image to obtain a convolution image of the to-be-detected image; calculating a correlation coefficient between the convolution image of the to-be-detected image and each camera fingerprint in a preset camera fingerprint database; and determining a camera corresponding to the camera fingerprint as the camera source of the to-be-detected image when the correlation coefficient between the convolution image of the to-be-detected image and a certain camera fingerprint is greater than a predetermined threshold. According to the method and system, high detection rate can be maintained, the calculation complexity and the memory occupation are reduced, and real-time detection and camera source identification of massive images are facilitated.
Description
Technical field
The invention belongs to technical field of multimedia information, more particularly, to a kind of side of image camera identifing source
Method and system.
Background technology
With the popularization of digital camera, digital picture is ubiquitous in the modern life, it has also become one kind is very
Important information carrier.These digital pictures are used for the every aspect lived, even news figure, army
Affairs that should be kept secret is close and court evidence etc..However, when the source of a width digital picture is maliciously altered or conceals,
Whether user is difficult to surmise change or conceals the people of image sources and " hatch a sinister plot ", but at least, malice change or
Conceal image sources can cover up facts to a certain extent.If being because not knowing that a width is used as court evidence
Image " is stolen the beams and changed the pillars ", and leads to misjudged case unjust verdict, or because does not know the figure comprising military secrecy information
As stealthily " being exchanged ", and cause national security to be on the hazard, all can cause immeasurable loss.Therefore,
Detection to digital image cameras source it is critical that.
The camera identifing source of digital picture is exactly the technology producing for exposing image stealthily " to be exchanged " behavior.
Sensor all had on each camera, but because the shortcoming of technique is it is impossible to produce the complete phase of two photobehaviors
Same photosensitive unit is so that the photosensitive unit array in different cameral has uniqueness to the incident light of same intensity
Nonuniform response, therefore on image produce mode sensor noise.The mode sensor that different cameral produces
Noise is all different, therefore can be used as the voucher distinguishing different cameral.Camera source technology of identification is to utilize camera
Mode sensor noise pattern as camera fingerprint, identify the camera of digital picture by way of comparing
Source, and then judge a kind of whether consistent with the camera source the being apprised of technology in digital picture source.
Prior art is proposed a kind of conversion based on multi-level Wavelet Transform and extracts mode sensor noise, and then identifies phase
The method in machine source.The method mainly converts and is calculated residual image by carrying out multi-level Wavelet Transform to image,
And then image camera fingerprint is estimated according to residual image, then calculate altimetric image to be checked in the same way
Residual image, the residual image of altimetric image to be checked is compared with camera fingerprint, is finally known according to comparison result
The camera source of other testing image.The method, during actually detected, needs image to carry out multiple wavelet transformation,
Lead to amount of calculation excessive, and wavelet transformation committed memory is high, is not suitable for the higher applied field of requirement of real-time
Close and large nuber of images detects occasion.
Content of the invention
In consideration of it, the embodiment of the present invention provides a kind of method and system of image camera identifing source, to keep
Compared with the case of high detection rate, reducing computation complexity, minimizing EMS memory occupation, beneficial to real-time detection and magnanimity
The camera identifing source of image.
In a first aspect, embodiments providing a kind of method of image camera identifing source, methods described bag
Include：
Obtain altimetric image to be checked, described altimetric image to be checked is carried out with convolution algorithm and obtains described altimetric image to be checked
Convolved image；
Calculate convolved image and each of the default camera fingerprint base camera fingerprint of described altimetric image to be checked
Coefficient correlation；
When the convolved image of described testing image is more than predetermined threshold with the coefficient correlation of a certain camera fingerprint,
Then judge the camera source as described altimetric image to be checked for this corresponding camera of camera fingerprint.
Second aspect, embodiments provides a kind of system of image camera identifing source, described system bag
Include：
Convolved image acquisition module, for obtaining altimetric image to be checked, carries out convolution fortune to described altimetric image to be checked
Calculate the convolved image obtaining described altimetric image to be checked；
Coefficient correlation computing module, the convolved image for calculating described altimetric image to be checked is referred to default camera
The coefficient correlation of each of line storehouse camera fingerprint；
Camera source determining module is related to a certain camera fingerprint for the convolved image when described testing image
When coefficient is more than predetermined threshold, then judge the camera as described altimetric image to be checked for this corresponding camera of camera fingerprint
Source.
The beneficial effect that the embodiment of the present invention compared with prior art exists is：The embodiment of the present invention is extracting phase
It is not necessary to carry out multi-level wavelet transformation during machine fingerprint, and only need to carry out a convolution algorithm, and not
Need again the image after convolution to be calculated, greatly reduce computation complexity, also significantly reduce simultaneously
Demand to amount of memory, is conducive to the camera identifing source of real-time detection and large nuber of images, has stronger easy
With property and practicality.
Brief description
For the technical scheme being illustrated more clearly that in the embodiment of the present invention, below will be to embodiment or existing skill
Art description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description are only
It is only some embodiments of the present invention, for those of ordinary skill in the art, do not paying creative labor
On the premise of dynamic property, other accompanying drawings can also be obtained according to these accompanying drawings.
Fig. 1 be the method for image camera identifing source provided in an embodiment of the present invention realize schematic flow sheet；
Fig. 2 is experiment effect figure provided in an embodiment of the present invention；
Fig. 3 is another experiment effect figure provided in an embodiment of the present invention；
Fig. 4 is the composition structural representation of the system of image camera identifing source provided in an embodiment of the present invention.
Specific embodiment
In below describing, in order to illustrate rather than in order to limit it is proposed that such as particular system structure, technology
Etc detail thoroughly cut to understand the embodiment of the present invention.However, those skilled in the art should
Clear, the other embodiments do not have these details can also be realized the present invention.In other situations,
Omit the detailed description to well-known system, device, circuit and method, in order to avoid unnecessary details
Hinder description of the invention.
In order to technical solutions according to the invention are described, to illustrate below by specific embodiment.
Refer to Fig. 1, be image camera identifing source provided in an embodiment of the present invention method realize flow process,
The method is applicable to all kinds of terminal devices, such as personal computer, panel computer, mobile phone etc..The method master
Comprise the following steps：
Step S101, obtains altimetric image to be checked, described altimetric image to be checked is carried out treating described in convolution algorithm acquisition
The convolved image of detection image.
Particularly, obtain the pixel matrix of altimetric image to be checked, using described pixel matrix and wave filter
Make convolution, obtain the convolved image of described altimetric image to be checked, computing formula is as follows：
Wherein, WxRepresent the convolved image (representing by matrix) of altimetric image to be checked, IxRepresent mapping to be checked
The pixel matrix of picture, H represents wave filter, and H=[1-33-1], H ' represent the transposition of H.
Optionally, described H can also be H=[- 101], the wave filter that H=[1-322-31] etc. is similar to.Separately
Described computing formula can also be outwardOrDeng similar convolution.
In step s 102, calculate in convolved image and the default camera fingerprint base of described altimetric image to be checked
Each camera fingerprint coefficient correlation.
In embodiments of the present invention, in the convolved image calculating described altimetric image to be checked and default camera fingerprint
Before the coefficient correlation of each of storehouse camera fingerprint, also include：
Set up camera fingerprint base.
Described camera fingerprint base of setting up specifically includes：
Obtain the image sets captured by different money cameras, convolution fortune is carried out respectively to every group of image of described acquisition
Calculate and obtain corresponding convolved image, each of which money camera corresponds to one group of image；
According to described corresponding every group of convolved image, estimate that every group of convolved image corresponds to phase using maximum likelihood method
The camera fingerprint of machine；
Described camera fingerprint is stored in camera fingerprint base.
Wherein, described according to described corresponding every group of convolved image, every group of convolution is estimated using maximum likelihood method
The formula of the camera fingerprint of the corresponding camera of image is：
Wherein, KFRepresent the camera fingerprint of different money cameras, described camera fingerprint matrix represents,
N=1,2 ... N, n represent that, with the picture number in the image sets captured by a camera, N represents with a phase
The quantity of the image that machine shoots, F represents the model of camera,OrOrRepresent the corresponding convolved image of the n-th width image captured by F camera,Represent F
The pixel matrix of the n-th width image captured by camera, H represents wave filter, H=[1-33-1], H=[- 101]
Or H=[1-322-31], the transposition of H ' expression H.
Specifically, every in described convolved image and the default camera fingerprint base calculating described altimetric image to be checked
The formula of the coefficient correlation of one camera fingerprint is：
Wherein, R represents coefficient correlation,OrOrWxExpression is treated
The convolved image of detection image, IxRepresent the pixel matrix of altimetric image to be checked, H represents wave filter,
H=[1-33-1], H=[- 101] or H=[1-322-31], H ' represents the transposition of H, p and q represents to be detected
The size (in units of pixel) of image, i and j represents the position coordinates in altimetric image to be checked, Wx(i, j) represents
The convolved image W of described altimetric image to be checkedxIn i-th row jth row element,Represent described altimetric image to be checked
Convolved image WxThe mean value of middle all elements, KF(i, j) represents camera fingerprint KFIn i-th row jth row
Element,Represent camera fingerprint KFThe mean value of middle all elements.
In step s 103, when the convolved image of described testing image and the coefficient correlation of a certain camera fingerprint
During more than predetermined threshold, then judge the camera source as described altimetric image to be checked for this corresponding camera of camera fingerprint.
If it should be noted that there are two or more coefficient correlations to be more than described predetermined threshold, judging
The corresponding camera of maximum correlation coefficient is the camera source of described detection image.
Compared with prior art, the embodiment of the present invention extract camera fingerprint when it is not necessary to carry out multi-level
Wavelet transformation, and only need to carry out a convolution algorithm, and do not need again the image after convolution to be calculated,
Greatly reduce computation complexity, also significantly reduce the demand to amount of memory simultaneously, be conducive in real time
Detection and the camera identifing source of large nuber of images.
In order to further illustrate beneficial effects of the present invention, the present invention has carried out following experiment：
1) extracting camera model respectively is the NIKON D7000 and camera model camera for NIKON D90
Fingerprint, is designated as K respectivelyD7000And KD90.
2) camera source of test chart group 1 known to is NIKON D7000, and the camera source of test chart group 2 is
NIKON D90 (two test chart groups have 25 width jpeg format images respectively).Using the embodiment of the present invention
Methods described extracts the convolved image of two test chart groups respectively, using the trellis diagram of described two test chart groups
As making to mate with two above-mentioned camera fingerprints respectively, can get two groups of each 25 coefficient correlations altogether.
Fig. 2 is the result of calculation of test chart group 1 and camera fingerprint base correlation, and R1 (asterisk) represents survey
Attempt to organize 1 convolved image and camera fingerprint KD7000Coefficient correlation, R2 (circle) represent test chart group
1 convolved image and camera fingerprint KD90Coefficient correlation.Experiment shows, test chart group 1 and camera fingerprint
KD7000There is larger correlation, show that the camera source of image in test chart group is NIKON D7000, with thing
Reality symbol is it was confirmed effectiveness of the invention.
Fig. 3 is the result of calculation of test chart group 2 and camera fingerprint base correlation.R1 (asterisk) represents survey
Attempt to organize 2 convolved image and camera fingerprint KD7000Coefficient correlation, R2 (circle) represent treat mapping group
2 convolved image and camera fingerprint KD90Coefficient correlation.Experiment shows, test chart group 2 and camera fingerprint
KD90There is larger correlation, show that the camera source of image in test chart group is NIKON D90, with true phase
Symbol.
Fig. 4 is the composition structural representation of the system of image camera identifing source provided in an embodiment of the present invention.For
It is easy to illustrate, illustrate only the part related to the embodiment of the present invention.
The system of described image camera identifing source can be to be built in terminal device (such as personal computer, hand
Machine, panel computer etc.) in software unit, hardware cell or software and hardware combining unit.
The system of described image camera identifing source includes：Convolved image acquisition module 41, coefficient correlation calculate mould
Block 42 and camera source determining module 43, the concrete function of wherein each module is as follows：
Convolved image acquisition module 41, for obtaining altimetric image to be checked, carries out convolution to described altimetric image to be checked
Computing obtains the convolved image of described altimetric image to be checked；
Coefficient correlation computing module 42, for calculating the convolved image of described altimetric image to be checked and default camera
The coefficient correlation of each of fingerprint base camera fingerprint；
Camera source determining module 43, for the phase of convolved image and a certain camera fingerprint when described testing image
When closing coefficient more than predetermined threshold, then judge the phase as described altimetric image to be checked for this corresponding camera of camera fingerprint
Machine source.
Further, described camera source determining module, if be additionally operable to there are two or more coefficient correlations big
In described predetermined threshold, then judge the camera source as described detection image for the corresponding camera of maximum correlation coefficient.
Further, described system also includes：
Camera fingerprint base sets up module 44, for calculate described altimetric image to be checked convolved image with default
Before the coefficient correlation of each of camera fingerprint base camera fingerprint, set up camera fingerprint base.
Further, described camera fingerprint base is set up module 44 and is included：
Convolved image acquisition submodule 441, for obtaining the image sets captured by different money cameras, to described
The every group of image obtaining carries out convolution algorithm respectively and obtains corresponding convolved image, and each of which money camera corresponds to
One group of image；
Camera fingerprint calculating sub module 442, for according to described corresponding every group of convolved image, using maximum
Likelihood method estimates the camera fingerprint of the corresponding camera of every group of convolved image；
Sub-module stored 443, for being stored in described camera fingerprint in camera fingerprint base.
Further, according to described corresponding every group of convolved image in described camera fingerprint calculating sub module 442,
Estimate that the formula that every group of convolved image corresponds to the camera fingerprint of camera is using maximum likelihood method：
Wherein, KFRepresent the camera fingerprint of different money cameras, described camera fingerprint matrix represents,
N=1,2 ... N, n represent that, with the picture number in the image sets captured by a camera, N represents with a phase
The quantity of the image that machine shoots, F represents the model of camera,OrOrRepresent the corresponding convolved image of the n-th width image captured by F camera,Represent F
The pixel matrix of the n-th width image captured by camera, H represents wave filter, H=[1-33-1], H=[- 101]
Or H=[1-322-31], the transposition of H ' expression H.
Further, calculate in described coefficient correlation computing module 42 convolved image of described altimetric image to be checked with
The formula of each of the default camera fingerprint base coefficient correlation of camera fingerprint is：
Wherein, R represents coefficient correlation,OrOrWxExpression is treated
The convolved image of detection image, IxRepresent the pixel matrix of altimetric image to be checked, H represents wave filter,
H=[1-33-1], H=[- 101] or H=[1-322-31], H ' represents the transposition of H, p and q represents to be detected
The size of image, i and j represents the position coordinates in altimetric image to be checked, Wx(i, j) represents described altimetric image to be checked
Convolved image WxIn i-th row jth row element,Represent the convolved image W of described altimetric image to be checkedx
The mean value of middle all elements, KF(i, j) represents camera fingerprint KFIn i-th row jth row element,Represent
Camera fingerprint KFThe mean value of middle all elements.
In sum, the embodiment of the present invention becomes it is not necessary to carry out multi-level small echo when extracting camera fingerprint
Change, and only need to carry out a convolution algorithm, and do not need again the image after convolution to be calculated, greatly
Reduce computation complexity, also significantly reduce the demand to amount of memory simultaneously, be conducive to real-time detection and
The camera identifing source of large nuber of images.It is not necessary to increase extra during the embodiment of the present invention is stated in realization
Hardware, can effective reduces cost, there is stronger usability and practicality.
Those skilled in the art can be understood that, for convenience of description and succinctly, only more than
The division stating each functional module is illustrated, in practical application, can be as desired by above-mentioned functions
Distribution is completed by different functional units, module, the internal structure of described system will be divided into different work(
Energy unit or module, to complete all or part of function described above.Each functional module in embodiment
Can be integrated in a processing unit or unit be individually physically present it is also possible to two or
Two or more unit is integrated in a unit, above-mentioned integrated unit both can with the form of hardware realize,
Can also be realized in the form of SFU software functional unit.In addition, the specific name of each functional module is also simply
It is easy to mutually distinguish, be not limited to the protection domain of the application.The concrete work of module in said system
Make process, may be referred to the corresponding process in preceding method embodiment, will not be described here.
Those of ordinary skill in the art are it is to be appreciated that respectively showing with reference to what the embodiments described herein described
The module of example and algorithm steps, can be come with the combination of electronic hardware or computer software and electronic hardware
Realize.These functions to be executed with hardware or software mode actually, depending on the application-specific of technical scheme
And design constraint.Professional and technical personnel can use different methods to each specific application realize
Described function, but this realize it is not considered that beyond the scope of this invention.
It should be understood that disclosed system and method, Ke Yitong in embodiment provided by the present invention
Cross other modes to realize.For example, system embodiment described above is only schematically, for example,
The division of described module, only a kind of division of logic function, actual can have other division side when realizing
Formula, for example multiple units or assembly can in conjunction with or be desirably integrated into another system, or some features can
To ignore, or do not execute.Another, shown or discussed coupling each other or direct-coupling or logical
News connection can be by some interfaces, and the INDIRECT COUPLING of device or unit or communication connect, and can be electrical,
Mechanical or other forms.
The described unit illustrating as separating component can be or may not be physically separate, as
The part that unit shows can be or may not be physical location, you can with positioned at a place, or
Can also be distributed on multiple NEs.Can select therein some or all of according to the actual needs
Unit is realizing the purpose of this embodiment scheme.
In addition, can be integrated in a processing unit in each functional unit in each embodiment of the present invention,
Can also be that unit is individually physically present it is also possible to two or more units are integrated in a unit
In.Above-mentioned integrated unit both can be to be realized in the form of hardware, it would however also be possible to employ SFU software functional unit
Form is realized.
If described integrated unit realized using in the form of SFU software functional unit and as independent production marketing or
During use, can be stored in a computer read/write memory medium.Based on such understanding, the present invention
Part that the technical scheme of embodiment substantially contributes to prior art in other words or this technical scheme
Completely or partially can be embodied in the form of software product, this computer software product is stored in one and deposits
In storage media, including some instructions with so that a computer equipment (can be personal computer, service
Device, or the network equipment etc.) or processor (processor) execution each embodiment institute of the embodiment of the present invention
State all or part of step of method.And aforesaid storage medium includes：USB flash disk, portable hard drive, read-only deposit
Reservoir (ROM, Read-Only Memory), random access memory (RAM, Random Access
Memory), magnetic disc or CD etc. are various can be with the medium of store program codes.
Embodiment described above only in order to technical scheme to be described, is not intended to limit；Although reference
Previous embodiment has been described in detail to the present invention, it will be understood by those within the art that：Its
Still the technical scheme described in foregoing embodiments can be modified, or special to wherein portion of techniques
Levy and carry out equivalent；And these modifications or replacement, do not make the essence of appropriate technical solution depart from this
The spirit and scope of each embodiment technical scheme of bright embodiment.
Claims (10)
1. a kind of method of image camera identifing source is it is characterised in that methods described includes：
Obtain altimetric image to be checked, described altimetric image to be checked is carried out with convolution algorithm and obtains described altimetric image to be checked
Convolved image；
Calculate convolved image and each of the default camera fingerprint base camera fingerprint of described altimetric image to be checked
Coefficient correlation；
When the convolved image of described testing image is more than predetermined threshold with the coefficient correlation of a certain camera fingerprint,
Then judge the camera source as described altimetric image to be checked for this corresponding camera of camera fingerprint.
2. the method for claim 1 is it is characterised in that methods described also includes：
If there are two or more coefficient correlations to be more than described predetermined threshold, judge maximum correlation coefficient pair
The camera answered is the camera source of described detection image.
3. the method for claim 1 it is characterised in that calculate described altimetric image to be checked convolution
Before each of the image and default camera fingerprint base coefficient correlation of camera fingerprint, methods described is also wrapped
Include：
Set up camera fingerprint base；
Described camera fingerprint base of setting up includes：
Obtain the image sets captured by different money cameras, convolution fortune is carried out respectively to every group of image of described acquisition
Calculate and obtain corresponding convolved image, each of which money camera corresponds to one group of image；
According to described corresponding every group of convolved image, estimate that every group of convolved image corresponds to phase using maximum likelihood method
The camera fingerprint of machine；
Described camera fingerprint is stored in camera fingerprint base.
4. method as claimed in claim 3 it is characterised in that described according to described corresponding every group of convolution
Image, estimates that using maximum likelihood method the formula of the camera fingerprint of the corresponding camera of every group of convolved image is：
Wherein, KFRepresent the camera fingerprint of different money cameras, described camera fingerprint matrix represents,
N=1,2 ... N, n represent that, with the picture number in the image sets captured by a camera, N represents with a phase
The quantity of the image that machine shoots, F represents the model of camera,OrOr Represent the corresponding convolved image of the n-th width image captured by F camera,Represent F
The pixel matrix of the n-th width image captured by camera, H represents wave filter, H=[1-3 3-1], H=[- 10 1]
Or H=[1-3 2 2-3 1], the transposition of H ' expression H.
5. method as claimed in claim 4 is it is characterised in that the volume of the described altimetric image to be checked of described calculating
Long-pending image with the formula of the coefficient correlation of each of default camera fingerprint base camera fingerprint is：
Wherein, R represents coefficient correlation,OrOrWxExpression is treated
The convolved image of detection image, IxRepresent the pixel matrix of altimetric image to be checked, H represents wave filter,
H=[1-3 3-1], H=[- 10 1] or H=[1-3 2 2-3 1], H ' represents the transposition of H, p and q represents to be detected
The size of image, i and j represents the position coordinates in altimetric image to be checked, Wx(i, j) represents described altimetric image to be checked
Convolved image WxIn i-th row jth row element,Represent the convolved image W of described altimetric image to be checkedx
The mean value of middle all elements, KF(i, j) represents camera fingerprint KFIn i-th row jth row element,Represent
Camera fingerprint KFThe mean value of middle all elements.
6. a kind of system of image camera identifing source is it is characterised in that described system includes：
Convolved image acquisition module, for obtaining altimetric image to be checked, carries out convolution fortune to described altimetric image to be checked
Calculate the convolved image obtaining described altimetric image to be checked；
Coefficient correlation computing module, the convolved image for calculating described altimetric image to be checked is referred to default camera
The coefficient correlation of each of line storehouse camera fingerprint；
Camera source determining module is related to a certain camera fingerprint for the convolved image when described testing image
When coefficient is more than predetermined threshold, then judge the camera as described altimetric image to be checked for this corresponding camera of camera fingerprint
Source.
7. system as claimed in claim 6, it is characterised in that described camera source determining module, is additionally operable to
If there are two or more coefficient correlations to be more than described predetermined threshold, judge that maximum correlation coefficient is corresponding
Camera is the camera source of described detection image.
8. system as claimed in claim 6 is it is characterised in that described system also includes：
Camera fingerprint base sets up module, in the convolved image calculating described altimetric image to be checked and default phase
Before the coefficient correlation of each of machine fingerprint base camera fingerprint, set up camera fingerprint base；
Described camera fingerprint base is set up module and is included：
Convolved image acquisition submodule, for obtaining the image sets captured by different money cameras, to described acquisition
Every group of image carry out convolution algorithm respectively and obtain corresponding convolved image, corresponding one group of each of which money camera
Image；
Camera fingerprint calculating sub module, for according to described corresponding every group of convolved image, using maximum likelihood
Method estimates the camera fingerprint of the corresponding camera of every group of convolved image；
Sub-module stored, for being stored in described camera fingerprint in camera fingerprint base.
9. system as claimed in claim 8 is it is characterised in that root in described camera fingerprint calculating sub module
According to described corresponding every group of convolved image, estimate the phase of the corresponding camera of every group of convolved image using maximum likelihood method
The formula of machine fingerprint is：
Wherein, KFRepresent the camera fingerprint of different money cameras, described camera fingerprint matrix represents,
N=1,2 ... N, n represent that, with the picture number in the image sets captured by a camera, N represents with a phase
The quantity of the image that machine shoots, F represents the model of camera,OrOr Represent the corresponding convolved image of the n-th width image captured by F camera,Represent F
The pixel matrix of the n-th width image captured by camera, H represents wave filter, H=[1-3 3-1], H=[- 10 1]
Or H=[1-3 2 2-3 1], the transposition of H ' expression H.
10. system as claimed in claim 9 is it is characterised in that described coefficient correlation computing module is fallen into a trap
The convolved image calculating described altimetric image to be checked is related to each of default camera fingerprint base camera fingerprint
The formula of coefficient is：
Wherein, R represents coefficient correlation,OrOrWxExpression is treated
The convolved image of detection image, IxRepresent the pixel matrix of altimetric image to be checked, H represents wave filter,
H=[1-3 3-1], H=[- 10 1] or H=[1-3 2 2-3 1], H ' represents the transposition of H, p and q represents to be detected
The size of image, i and j represents the position coordinates in altimetric image to be checked, Wx(i, j) represents described altimetric image to be checked
Convolved image WxIn i-th row jth row element,Represent the convolved image W of described altimetric image to be checkedx
The mean value of middle all elements, KF(i, j) represents camera fingerprint KFIn i-th row jth row element,Represent
Camera fingerprint KFThe mean value of middle all elements.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510458731.5A CN106408036A (en) | 2015-07-30 | 2015-07-30 | Method and system for image camera source identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510458731.5A CN106408036A (en) | 2015-07-30 | 2015-07-30 | Method and system for image camera source identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106408036A true CN106408036A (en) | 2017-02-15 |
Family
ID=58009473
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510458731.5A Pending CN106408036A (en) | 2015-07-30 | 2015-07-30 | Method and system for image camera source identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106408036A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154080A (en) * | 2017-11-27 | 2018-06-12 | 北京交通大学 | A kind of method that video equipment is quickly traced to the source |
| CN111178166A (en) * | 2019-12-12 | 2020-05-19 | 中国科学院深圳先进技术研究院 | Camera source identification method based on image content self-adaption |
| CN111738274A (en) * | 2020-05-08 | 2020-10-02 | 华南理工大学 | Anti-attack camera source identification method based on local smooth projection |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101616238A (en) * | 2009-07-17 | 2009-12-30 | 中山大学 | A kind of digitized authentication image method of digital camera |
| CN102819831A (en) * | 2012-08-16 | 2012-12-12 | 江南大学 | Camera source evidence obtaining method based on mode noise big component |
| CN103593645A (en) * | 2013-10-11 | 2014-02-19 | 合肥工业大学 | Method for identifying source camera of cutout image |
| CN103714349A (en) * | 2014-01-09 | 2014-04-09 | 成都淞幸科技有限责任公司 | Image recognition method based on color and texture features |
-
2015
- 2015-07-30 CN CN201510458731.5A patent/CN106408036A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101616238A (en) * | 2009-07-17 | 2009-12-30 | 中山大学 | A kind of digitized authentication image method of digital camera |
| CN102819831A (en) * | 2012-08-16 | 2012-12-12 | 江南大学 | Camera source evidence obtaining method based on mode noise big component |
| CN103593645A (en) * | 2013-10-11 | 2014-02-19 | 合肥工业大学 | Method for identifying source camera of cutout image |
| CN103714349A (en) * | 2014-01-09 | 2014-04-09 | 成都淞幸科技有限责任公司 | Image recognition method based on color and texture features |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154080A (en) * | 2017-11-27 | 2018-06-12 | 北京交通大学 | A kind of method that video equipment is quickly traced to the source |
| CN111178166A (en) * | 2019-12-12 | 2020-05-19 | 中国科学院深圳先进技术研究院 | Camera source identification method based on image content self-adaption |
| CN111178166B (en) * | 2019-12-12 | 2023-05-26 | 中国科学院深圳先进技术研究院 | Camera source identification method based on image content self-adaption |
| CN111738274A (en) * | 2020-05-08 | 2020-10-02 | 华南理工大学 | Anti-attack camera source identification method based on local smooth projection |
| CN111738274B (en) * | 2020-05-08 | 2022-04-22 | 华南理工大学 | Anti-attack camera source identification method based on local smooth projection |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Rao et al. | Deep learning local descriptor for image splicing detection and localization | |
| Galdi et al. | Multimodal authentication on smartphones: Combining iris and sensor recognition for a double check of user identity | |
| CN110222573B (en) | Face recognition method, device, computer equipment and storage medium | |
| Chen et al. | Shape matters: deformable patch attack | |
| Tokuda et al. | Computer generated images vs. digital photographs: A synergetic feature and classifier combination approach | |
| Khammari | Robust face anti‐spoofing using CNN with LBP and WLD | |
| WO2021137946A1 (en) | Forgery detection of face image | |
| US20220198711A1 (en) | Learned forensic source system for identification of image capture device models and forensic similarity of digital images | |
| Yang et al. | Convolutional neural network for smooth filtering detection | |
| Zhang et al. | Identifying source camera using guided image estimation and block weighted average | |
| CN106408036A (en) | Method and system for image camera source identification | |
| Tang et al. | Detection of GAN‐Synthesized Image Based on Discrete Wavelet Transform | |
| Mushtaq et al. | Image copy move forgery detection: a review | |
| Hu et al. | Dynamic-aware federated learning for face forgery video detection | |
| Shu et al. | Face spoofing detection based on multi-scale color inversion dual-stream convolutional neural network | |
| WO2022199395A1 (en) | Facial liveness detection method, terminal device and computer-readable storage medium | |
| CN112818868B (en) | Method and device for identifying illegal user based on behavior sequence characteristic data | |
| Wang et al. | Spatial-temporal frequency forgery clue for video forgery detection in VIS and NIR scenario | |
| Assefa et al. | Small‐Scale and Occluded Pedestrian Detection Using Multi Mapping Feature Extraction Function and Modified Soft‐NMS | |
| Bernacki | On robustness of camera identification algorithms | |
| ELSayed et al. | Masked SIFT with align‐based refinement for contactless palmprint recognition | |
| Meena et al. | Image splicing forgery detection techniques: A review | |
| Li et al. | [Retracted] Image Processing and Recognition Algorithm Design in Intelligent Imaging Device System | |
| CN116881967A (en) | Privacy protection method, device and equipment | |
| CN104217390A (en) | Zero watermark method and device and watermark extraction method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170215 |