CN105141842B - A kind of anti-tamper license camera system and method - Google Patents
A kind of anti-tamper license camera system and method Download PDFInfo
- Publication number
- CN105141842B CN105141842B CN201510548572.8A CN201510548572A CN105141842B CN 105141842 B CN105141842 B CN 105141842B CN 201510548572 A CN201510548572 A CN 201510548572A CN 105141842 B CN105141842 B CN 105141842B
- Authority
- CN
- China
- Prior art keywords
- license
- camera
- artwork
- data
- shooting
- 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.)
- Active
Links
Abstract
The invention discloses a kind of anti-tamper license camera system and method, anti-tamper license camera system includes license camera, license camera access service end and license cloud storage end, and license camera includes license artwork taking module, accesses amendment disabled module, watermark encrypting module and transmission communication module;Anti-tamper certificate photograph image pickup method includes: license camera carries out the shooting of license artwork;During the shooting of license artwork generates, forbid user or other softward interview raw image datas, and forbid user or other software modification license artwork datas;License artwork write fragility watermark to shooting is encrypted;Photo after watermark encrypting is compressed and secondary encryption, and is sent in the memory space of license cloud storage end independence preserve.Present invention achieves from being imaged onto generation standard certificate photograph, to ensureing the authenticity of photo, ageing during submitting transmission, prevent photo to be tampered, and very convenient easily obtain certificate photograph.
Description
Technical field
The present invention relates to a kind of license camera system and method, a kind of anti-tamper license camera system and method,
Belong to certificate photograph shooting and processing technology field.
Background technology
Certificate photograph refers to such as identity card, passport, Hong Kong pass, Macao's pass, the Taiwan pass, label of going abroad
The photo that the legal certificate makings such as card, residence permit, social security card use, these photos often have the shooting skill of many to want
Summation shooting quality requirement, from the point of view of present circumstances, people generally can only arrive special photo studio or professional institution (as protected
An company) shoot, and carried out just to obtain one after photo cutting, replacing background etc. process by the personnel of specialty
Meeting the certificate photo of associated specifications, whole process takes a substantial amount of time, and shoots certificate photograph band to people
Carry out inconvenience.
For these reasons, adding the development of mobile Internet, the most basic everybody has mobile phone, panel computer on hand
Deng intelligent terminal, and these intelligent terminals are all equipped with high-definition camera, therefore, to by photo studio professional
Shooting certificate photograph is transformed into that people are self-service completes shooting on intelligent terminal so that certificate photograph shooting networking, just
The demand of profitization is more and more stronger.
Although at present intelligent terminal is equipped with high-definition camera, people still can not oneself at intelligent terminal arsis such as mobile phones
Take the photograph the certificate photograph allowing certificates handling department convince and to accept, allow certificates handling department convince and the photo needs of acceptance: 1) satisfied true
Reality (being the artwork of shooting, without amendment) and ageing (recent photo, in usually 6 months, some requires 3
In individual month) requirement;2) government's public security professional standard of legal certificate accreditation digital photo is reached (such as " GA 461-2004
ID cards digital photo technology require ", " GA482-2012 People's Republic of China (PRC) motor vehicle driving license
Part ", " requirement of GA/T 1180-2014 exit and entry certificates digital photo technology " etc.).
Additionally, reality the most often there is situations below occur:
1) people shoot photo and often like excessively beautifying photo, as brightened, grind skin, anti-acne, plucking eyebrows, add
Double-edged eyelid etc., with certificate photograph, this requires that authenticity creates contradiction;Shooting time does not retrain, and people can be random
Uploading, download and forward photo, this creates contradiction with certificate photograph requirement is ageing.
2) project of certificate photograph government public security Industry code requirements is numerous and in small, broken bits, and people are typically difficult to these standards
Understand completely, perform the most difficult, it is impossible to guarantee that the photo of all shootings all reaches the standard of certificate photograph
Requirement.
Summary of the invention
The invention aims to solve the defect of above-mentioned prior art, it is provided that a kind of anti-tamper license camera system
System, this system achieves from being imaged onto generation standard certificate photograph, ensureing the true of photo during submitting transmission
Property, ageing, prevent photo to be tampered, and very convenient easily obtain certificate photograph.
Another object of the present invention is to provide a kind of anti-tamper certificate photograph image pickup method.
The purpose of the present invention can reach by adopting the following technical scheme that:
A kind of anti-tamper license camera system, described system includes license camera, license camera access service end and card
According to cloud storage end;Described license camera includes:
License artwork taking module, for carrying out the shooting of license artwork;
Access amendment disabled module, during generating in the shooting of license artwork, forbid that user or other software are visited
Ask raw image data, and forbid user or other software modification license artwork datas;
Watermark encrypting module, for being encrypted the write fragility watermark of the license artwork of shooting;
Transmission communication module, for being compressed the photo after watermark encrypting and secondary encryption, and is sent to license cloud
The memory space of storage end independence preserves.
Further, described license artwork taking module includes:
Configuration parameter unit, for detecting whether the acquisition parameters of intelligent terminal camera meets certificate photograph photographing request,
If it is not, then acquisition parameters is configured according to the parameter preset;
Portrait feature extraction unit, for when finding a view the stage, extracts the portrait characteristic of preview frame image;Wherein,
Described portrait characteristic includes that facial contour, trunk profile, portrait profile, eyes, nose, ear and face are special
Levy data;
Sensing data acquiring unit, for when imaging, obtain intelligent terminal Gravity accelerometer data,
Gyroscope sensor data, direction magnetic field sensor data and luminance sensor data;
Brightness, definition and chromaticity distortion data capture unit, for when obtaining sensing data, dividing by image
Analysis obtains the brightness data of preview frame image, definition data and chromaticity distortion data;
Detection reminding unit, for judging intelligent terminal sensing data, the portrait characteristic of preview frame image, bright
Whether degrees of data, definition data and chromaticity distortion data meet legal certificate photograph relevant criterion requirement, if so, when
After shooting push button is pressed, it is thus achieved that raw image data, adjust if it is not, then remind user to carry out shooting;
Intelligence cutting unit, for raw image data is carried out cutting process according to the standard certificate photograph specification set,
Obtain the license artwork of standard size dimensions;
Intelligence is scratched figure and is replaced background cell, for license artwork carries out scratching figure, and according to the certificate photograph mark set
Accurate replace background process, adjust portrait size and location, obtain license preview graph, show intuitively at license to user
Reason result;
Shooting quality scoring unit, for entering item by item license artwork or license preview graph according to government's public security professional standard
Row shooting quality is assessed, and provides suggestion according to comprehensive grading result.
Further, described portrait feature extraction unit extracts the portrait characteristic of preview frame image, specifically includes:
The preview frame image got is converted to gray level image;
Gray level image is carried out characteristic region detection above the waist, when characteristic region above the waist being detected, will
This area pixel information saves as region rectangle data structure above the waist, and gray level image arranges ROI region above the waist,
It is designated as ROIB;
ROIB is carried out the detection of facial contour feature data area, when facial contour feature data area being detected,
This area pixel information is saved as facial contour region rectangle data structure, and gray level image is arranged facial contour
ROI region, is designated as ROIF;
The specific region of ROIF is carried out eyes characteristic region detection, when eyes characteristic region being detected,
This area pixel information is saved as eyes region rectangle data structure, and obtains the coordinate of eyes, with the Y-axis of eyes
Minimum point is new ROI region top, facial contour feature data area is taken eyes area below, is set to nose
Sub-goal ROI region, is designated as ROIN;
ROIF is carried out ears characteristic region detection, when ears characteristic region being detected, by this region picture
Prime information saves as ears region rectangle data structure;
ROIN is carried out nose characteristic region detection, when nose characteristic region being detected, by this region
Pixel Information saves as nasal area rectangle data structure, using the base of nasal area rectangle data structure as new
The top margin of ROI region, takes nose region below to facial contour feature data area, is set to face target ROI district
Territory, is designated as ROIM;
ROIM is carried out face characteristic region detection, when face characteristic region being detected, by this region
Pixel Information saves as face region rectangle data structure;
Region to ROIB, cuts out the region removing ROIF, obtains trunk contour feature data area ROIMB, should
Area pixel information saves as trunk contour area rectangle data structure;
ROIF is carried out rim detection, obtains the line segment at sign mutation edge in contouring head regional extent, the most right
This head edge line segment result carries out head convex closure contour detecting, by the seat of the key point that head convex closure contour detecting obtains
Mark saves as contouring head array;
ROIMB is carried out rim detection, obtains the line segment at sign mutation edge in the range of trunk contour area, then
This trunk edge line segment result is carried out trunk convex closure contour detecting, the key point that trunk convex closure contour detecting is obtained
Coordinate saves as trunk profile array;
Contouring head array and trunk number of contours group are combined, forms portrait profile array.
Further, described detection reminding unit judges the portrait feature of intelligent terminal sensing data, preview frame image
Whether data, brightness data, definition data and chromaticity distortion data meet legal certificate photograph relevant criterion requirement,
Specifically include:
During portrait posture detection and shooting environmental are detected all detection purpose related datas and preset value one by one than
Relatively, satisfactory detection project, then by detection, undesirable detection project, then carry out sound/character/
Graphical cues, real-time reminding user carries out shooting and adjusts;Wherein, described preset value is for meet certificate photograph through checking
The preferred values of shooting standard-required, the detection project of described portrait posture detection includes face whether visible, face size
Whether position meets, portrait distance is the most suitable, whether face rectifies and whether shoulder flushes, described shooting ring
The detection project of border detection include intelligent terminal whether vertically, whether intelligent terminal is shaken, brightness is the most sufficient,
Image is the most clear, whether colourity has deviation;
When there is undesirable detection project, shooting push button is set to can not screening-mode, when all of inspection
When survey project all meets the requirements, being set to by shooting push button can screening-mode.
Further, described shooting quality judge paper unit according to government's public security professional standard to license artwork or license preview
Figure carries out shooting quality assessment item by item, and provides suggestion according to comprehensive grading result, specifically includes:
Obtain the file attribute information of photo;Carry out portrait feature identification by photo gray-scale map and extract portrait characteristic information;
Background information is obtained by edge detecting technology, image Segmentation Technology;Monochrome information is obtained by photo gray-scale map;Logical
Cross photo mean square deviation in Lab color space system and obtain chrominance information;Obtained by the gray-scale map matrix of photo
Sharpness information;
According to the file attribute information obtained, portrait characteristic information, background information, monochrome information, chrominance information, clear
Dimensions is marked by clear degree information item by item, obtains the score value of each dimensions;
According to the score value of each dimensions, and scoring weight, calculate the quality overall score of the photo photographed;
The shooting suggestion of specialty is given according to overall score;
When photo composite score is less than preset value, then it is unsatisfactory for the relevant criterion requirement of legal certificate photograph, it is proposed that use
Family re-shoots, and meets, until shooting, the photo that legal certificate photograph relevant criterion requires.
Further, described license camera also includes:
UI display module, show for view-finder, previewing photos shows, shoot prompting display, shooting quality scoring and
Professional advice shows, license standard drawing shows, and provides user to carry out license type selecting, retake, shoot guide and look into
See, access card is according to the interactive button of cloud storage end;
User management module, for being managed user's registration information and user's certificates handling information.
Further, described license camera access service end includes:
Authorize legitimacy detection module, be used for verifying camera and carry out authorizing legitimacy detection;
AM access module, after when license camera by authorizing legitimacy to detect, license camera access service end just accepts
The certificate photograph that license camera sends processes request, certificate photograph processes required parameter and is sent to certificate photograph intelligent cloud
Processing system;
License standard drawing feedback module, for the license artwork submitted to when license camera, at certificate photograph intelligent cloud
After reason system making processes, feed back whether this license artwork is successfully made the knot of qualified license standard drawing to license camera
Really information.Further, described license camera access service end also includes:
Operation data recordin module, for recording the operation data of the license camera user end of all accesses;
Monitoring module, for monitoring the operation data of license camera user end, when there is abnormal operation behavior, is then carried out
Forbid or send alarm.
Further, described license cloud storage end includes:
Authorize access that module is set, be used for verifying camera and mandate access module is set;
Memory allocation module, for the memory space independent for the distribution of each license camera client;
Cloud storage end amendment attendant exclusion module, is used for the user the forbidding license camera certificate photo to license cloud storage end
Sheet is modified operation, only allows user submitted to by license camera or delete license photograph.
Further, described mandate access arranges module verification camera and arranges mandate access module, specifically includes:
Set up an APP unique sequence numbers database, preserve the APP unique sequence numbers being authorized to;
When the user agent developer of license camera passes through exploitation code to license cloud storage end application to APP unique sequence code
After number, by callback interface, distribute to one access token of license camera, and arrange the time limit of losing efficacy.
Further, described certificate photograph intelligent cloud processing system includes:
Parameter analysis of electrochemical module, the certificate photograph sent for resolving license camera access service end processes required parameter;
License artwork extraction module, for, after resolving certificate photograph process required parameter, extracting to license cloud storage end
License artwork;
License artwork authentication module, for verifying the authenticity of license artwork, particularly as follows:
License artwork is carried out watermark extracting, and deciphers watermark information, use whether the watermark information certificate of inspection leads to according to artwork
Cross, the most then license artwork is not tampered with;If it is not, then license artwork is tampered with;
License artwork processing module, for completing the process of license standard drawing to the license artwork being not tampered with;
Cloud processing system license standard drawing feedback module, for after license artwork has processed and has obtained license standard drawing,
The result completing to make by license standard drawing by license camera access service end feeds back to license camera.
Another object of the present invention can reach by adopting the following technical scheme that:
A kind of anti-tamper certificate photograph image pickup method, described method includes:
License camera carries out the shooting of license artwork;
Described license camera, during the shooting of license artwork generates, forbids user or other softward interview original images
Data, and forbid user or other software modification license artwork datas;
The license artwork write fragility watermark of shooting is encrypted by described license camera;
Photo after watermark encrypting is compressed and secondary encryption by described license camera, and is sent to license cloud storage end
Independent memory space preserves.
Further, the shooting that described license camera carries out license artwork includes:
Whether the acquisition parameters of described license camera calibration intelligent terminal camera meets certificate photograph photographing request, if it is not,
Then according to the parameter preset, acquisition parameters is configured;
When finding a view the stage, described license camera extracts the portrait characteristic of preview frame image;Wherein, described portrait
Characteristic includes facial contour, trunk profile, portrait profile, eyes, nose, ear and face characteristic;
Described license camera, when imaging, obtains the Gravity accelerometer data of intelligent terminal, gyro sensor
Data, direction magnetic field sensor data and luminance sensor data;
Described license camera obtain sensing data time, by graphical analysis obtain preview frame image brightness data,
Definition data and chromaticity distortion data;
Described license camera judge intelligent terminal sensing data, the portrait characteristic of preview frame image, brightness data,
Whether definition data and chromaticity distortion data meet legal certificate photograph relevant criterion requirement, if so, work as shooting push button
After being pressed, it is thus achieved that raw image data, adjust if it is not, then remind user to carry out shooting;
Described license camera carries out cutting process to raw image data according to the standard certificate photograph specification set, it is thus achieved that
The license artwork of standard size dimensions;
Described license camera carries out scratching figure to license artwork, and replaces background process according to the certificate photograph standard set,
Adjust portrait size and location, obtain license preview graph, show license result intuitively to user;
Described license camera carries out shooting quality according to government's public security professional standard item by item to license artwork or license preview graph
Assessment, and provide suggestion according to comprehensive grading result.
Further, described license camera extracts the portrait characteristic of preview frame image, specifically includes:
The preview frame image got is converted to gray level image by described license camera;
Described license camera carries out characteristic region detection above the waist to gray level image, when characteristic above the waist being detected
During according to region, this area pixel information is saved as region rectangle data structure above the waist, and gray level image is arranged
Half body ROI region, is designated as ROIB;
Described license camera carries out the detection of facial contour feature data area to ROIB, when facial contour feature being detected
During data area, this area pixel information is saved as facial contour region rectangle data structure, and gray level image is set
Put facial contour ROI region, be designated as ROIF;
Described license camera carries out eyes characteristic region detection to the specific region of ROIF, when eyes feature being detected
During data area, this area pixel information is saved as eyes region rectangle data structure, and obtains the coordinate of eyes,
It is new ROI region top with the Y-axis minimum point of eyes, facial contour feature data area is taken the district of below eyes
Territory, is set to nose target ROI region, is designated as ROIN;
Described license camera carries out ears characteristic region detection to ROIF, when ears characteristic region being detected
Time, this area pixel information is saved as ears region rectangle data structure;
Described license camera carries out nose characteristic region detection to ROIN, when nose characteristic region being detected
Time, this area pixel information is saved as nasal area rectangle data structure, with the end of nasal area rectangle data structure
While as the top margin of new ROI region, facial contour feature data area is taken nose region below, is set to face
Target ROI region, is designated as ROIM;
Described license camera carries out face characteristic region detection to ROIM, when face characteristic region being detected
Time, this area pixel information is saved as face region rectangle data structure;
The described license camera region to ROIB, cuts out the region removing ROIF, obtains trunk contour feature data area
ROIMB, saves as trunk contour area rectangle data structure by this area pixel information;
Described license camera carries out rim detection to ROIF, obtains sign mutation edge in contouring head regional extent
Line segment, then carries out head convex closure contour detecting to this head edge line segment result, is obtained by head convex closure contour detecting
The coordinate of key point save as contouring head array;
Described license camera carries out rim detection to ROIMB, obtains the sign mutation edge in the range of trunk contour area
Line segment, then this trunk edge line segment result is carried out trunk convex closure contour detecting, trunk convex closure contour detecting is obtained
The coordinate of the key point obtained saves as trunk profile array;
Contouring head array and trunk number of contours group are combined by described license camera, form portrait profile array.
Further, license camera judges intelligent terminal sensing data, the portrait characteristic of preview frame image, bright
Whether degrees of data, definition data and chromaticity distortion data meet legal certificate photograph relevant criterion requirement, specifically include:
Described license camera is by all detection purpose related datas in portrait posture detection and shooting environmental detection and presets
Value compares one by one, satisfactory detection project, then by detection, undesirable detection project, then enter
Lang sound/characters/graphic prompting, real-time reminding user carries out shooting and adjusts;Wherein, described preset value is through authenticator
Close the preferred values of certificate photograph shooting standard-required, the detection project of described portrait posture detection include face whether visible,
Whether face size position meets, portrait distance is the most suitable, whether face rectifies and whether shoulder flushes, institute
The detection project stating shooting environmental detection includes that intelligent terminal is the most vertical, whether intelligent terminal is shaken, brightness is the most equal
Even abundance, image are the most clear, whether colourity has deviation;
When there is undesirable detection project, described license camera shooting push button is set to can not screening-mode,
When all of detection project all meets the requirements, shooting push button is set to by described license camera can screening-mode.
Further, license artwork or license preview graph are entered item by item by described license camera according to government's public security professional standard
Row shooting quality is assessed, and provides suggestion according to comprehensive grading result, specifically includes:
Described license camera obtains the file attribute information of photo;Carry out portrait feature identification by photo gray-scale map to extract
Portrait characteristic information;Background information is obtained by edge detecting technology, image Segmentation Technology;Obtained by photo gray-scale map
To monochrome information;Chrominance information is obtained by photo mean square deviation in Lab color space system;By photo
Gray-scale map matrix obtains sharpness information;
Described license camera according to the file attribute information obtained, portrait characteristic information, background information, monochrome information,
Dimensions is marked by chrominance information, sharpness information item by item, obtains the score value of each dimensions;
Described license camera is according to the score value of each dimensions, and scoring weight, calculates the photo photographed
Quality overall score;The shooting suggestion of specialty is given according to overall score;
When photo composite score is less than preset value, then it is unsatisfactory for the relevant criterion requirement of legal certificate photograph, described card
Camera suggestion user re-shoot, and meets, until shooting, the photo that legal certificate photograph relevant criterion requires.
Further, described method also includes:
License camera access service end verification camera carries out authorizing legitimacy detection;
After license camera is by authorizing legitimacy to detect, described license camera access service end just accepts license camera
Certificate photograph processes request, certificate photograph processes required parameter and is sent to certificate photograph intelligent cloud processing system;
When the license artwork that license camera is submitted to, after certificate photograph intelligent cloud processing system making processes, described card
To license camera, camera access service end feeds back whether this license artwork is successfully made the result of qualified license standard drawing
Information.
Further, described method also includes:
The operation data of the license camera user end of the described license camera access service all accesses of end record;
The operation data of described license camera access service end monitoring license camera user end, when abnormal operation behavior occurs,
Then carry out forbidding or sending alarm.
Further, described method also includes:
Described license cloud storage end verification camera arranges mandate access module;
Described license cloud storage end is the memory space that the distribution of each license camera client is independent;
Described license cloud storage end forbids that the certificate photograph of license cloud storage end is modified behaviour by the user of license camera
Make, only allow user submitted to by license camera or delete license photograph.
Further, described license cloud storage end verification camera arranges mandate access module, specifically includes:
Described license cloud storage end sets up an APP unique sequence numbers database, preserves the APP unique sequence code being authorized to
Number;
When the user agent developer of license camera passes through exploitation code to license cloud storage end application to APP unique sequence code
After number, described license cloud storage end passes through callback interface, distributes to one access token of license camera, and arranges to lose efficacy
Time limit.
Further, described method also includes:
Described certificate photograph intelligent cloud processing system resolves the certificate photograph process request that license camera access service end sends
Parameter;
After resolving certificate photograph process required parameter, described certificate photograph intelligent cloud processing system is to license cloud storage end
Extract license artwork;
The authenticity of described certificate photograph intelligent cloud processing system checking license artwork, particularly as follows:
License artwork is carried out watermark extracting, and deciphers watermark information, use whether the watermark information certificate of inspection leads to according to artwork
Cross, the most then license artwork is not tampered with;If it is not, then license artwork is tampered with;
Described certificate photograph intelligent cloud processing system completes the process of license standard drawing to the license artwork being not tampered with;
After license artwork has processed and obtains license standard drawing, described certificate photograph intelligent cloud processing system passes through license
The result that license standard drawing is completed to make by camera access service end feeds back to license camera.
The present invention has a following beneficial effect relative to prior art:
1, the license camera (intelligent terminal APP) of the present invention is crossed in generation journey in the shooting of license artwork, forbids user
Or other softward interview raw image datas, and forbid user or other software modification license artwork datas, to shooting
The write fragility watermark of license artwork is encrypted, and is compressed the photo after watermark encrypting and secondary encryption,
Make certificate photograph collection and process carry out in enclosed environment, it is ensured that during artwork meet government's public security industry mark
Accurate, artwork is submitted without amendment, artwork transmission, artwork, and photo is captured in real-time, submits in real time, thus real
Show from being imaged onto generation standard certificate photograph, to authenticity and the timeliness guaranteeing certificate photograph during submitting transmission
Property, prevent certificate photograph to be tampered.
2, the license cloud storage end of the present invention is that each license camera client is assigned with independent memory space, all bats
The certificate photograph taken the photograph is stored in license cloud storage end, forbids storing in intelligent terminal local folders, and license
Cloud storage end verification camera is provided with mandate access module, and the license camera only authorized just allows to access, it is ensured that card
The information security of part photo;Additionally, license cloud storage end forbids the user of the license camera certificate to license cloud storage end
Photo is modified operation, only allows user to be submitted or delete to license photograph by license camera, improves photo further
Authenticity.
3, the license camera access service end verification camera of the present invention carries out authorizing legitimacy detection, only by detection
License camera, license camera access service end could accept license camera accreditation request, it is ensured that license camera safety
It is linked in certificate photograph intelligent cloud processing system, and the operation data of all license cameras can be recorded, once go out
Existing abnormal operation behavior, then carry out forbidding or sending alarm.
4, the license camera of the present invention can automatically configure and meet certificate photograph the shooting professional camera parameter of standard, offer
Legal certificate photograph type option, offer standard certificate photograph shooting are reminded support, are provided automatic cutting and background replacement
Support, the mechanism such as shooting effect government public security professional standard project quality detection scoring are provided, give user the bat of specialty
Take the photograph guidance, and only could finally be sended in one's application accreditation by the photo of government's public security professional standard project detection, protect
Demonstrate,prove captured by user photo out and meet certificate photograph government public security Industry code requirements.
5, the present invention only needs user to install a license camera APP at intelligent terminal, self-service shooting can meet government
Public security Industry code requirements, anti-tamper certificate photograph, solve user and use tradition shooting software cannot ensure certificate
The authenticity of photo and ageing, also cannot guarantee captured by photo out meet certificate photograph government public security industry mark
The problem of alignment request.
Accompanying drawing explanation
Fig. 1 is the license camera system topology diagram of the embodiment of the present invention 1.
Fig. 2 is the functional block diagram of the license camera of the embodiment of the present invention 1.
Fig. 3 is the structure chart of the license artwork taking module of the embodiment of the present invention 1.
Fig. 4 is the functional block diagram of the license camera access service end of the embodiment of the present invention 1.
Fig. 5 is license cloud storage end and license camera, the certificate photograph intelligent cloud processing system of the embodiment of the present invention 1
Graph of a relation.
Fig. 6 is the functional block diagram of the license cloud storage end of the embodiment of the present invention 1.
Fig. 7 is that the APP unique sequence numbers of the license cloud storage end of the embodiment of the present invention 1 veritifies flow chart.
Fig. 8 is the functional block diagram of the certificate photograph intelligent cloud processing system of the embodiment of the present invention 1.
Fig. 9 is certificate photograph shooting and the process chart of the embodiment of the present invention 2.
Figure 10 is the license artwork shooting flow chart of the embodiment of the present invention 2.
Detailed description of the invention
Below in conjunction with embodiment and accompanying drawing, the present invention is described in further detail, but embodiments of the present invention do not limit
In this.
Embodiment 1:
As it is shown in figure 1, the license camera system of the present embodiment includes license camera, license camera access service end and card
According to cloud storage end, and accessing an interconnected system: certificate photograph intelligent cloud processing system, wherein license camera accesses clothes
Business end, license cloud storage end and certificate photograph intelligent cloud processing system all exist together a privately owned Intranet, and license camera accesses
Service end and license cloud storage end are connected to internet by fire wall, are to a certain degree ensureing certificate photograph intelligent cloud
The security of processing system, and the APP that license camera is mounted on intelligent terminal (Application, application program),
Intelligent terminal accesses internet equally.
Described license camera has Android version and iOS version, and it is responsible for shooting a width and meets certificate making use
License artwork, license artwork refers to by user by license camera captured in real-time gained, according to license standard cutting figure
As useful region, and the image information such as color, brightness, background, personage's biological characteristic is without the picture number of any process
According to.In shooting process, license camera automatically configures optimal acquisition parameters, automatic detection reminds user to be adjusted to most preferably clap
Take the photograph automatic cutting after state, shooting so that shoot and meet the license artwork that certificate making uses;Subsequently, also verify
Carry out scratching figure according to artwork to replace background, automatically carry out shooting quality government public security professional standard detection etc. and process;It addition,
In license artwork shooting process, user can not carry out any write operation to license artwork, it is ensured that the authenticity of photo;
The write fragility watermark of license artwork is also encrypted by license camera, is compressed photo subsequently and secondary adds
Close, it is transferred to license cloud storage end, encrypts double protection by watermark encrypting and secondary, strengthen the difficulty being cracked,
Reduce the possibility that photo is tampered.
Described license camera access service end is mainly responsible for license camera and is linked into the work of certificate photograph intelligent cloud processing system
Making, its verification camera carries out authorizing legitimacy detection, and only by the license camera of detection, license camera accesses clothes
Business end could accept its accreditation request, the accreditation parameter information used in accreditation is sent to certificate photograph intelligent cloud and processes
System.After certificate photograph intelligent cloud processing system has automatically processed and obtains license standard drawing, license camera accesses clothes
The result that license standard drawing is completed to make by business end feeds back to the license camera of correspondence, and it is accurate that license camera can verify sighting target
Figure carries out preview, but can not carry out any write operation.
Described license cloud storage end is respectively each license camera client and is assigned with independent memory space, all shootings
Certificate photograph be stored in license cloud storage end, forbid storing in intelligent terminal local folders, and license cloud deposit
Chu Duan verification camera is provided with mandate access module, and the license camera only authorized just allows to access, it is ensured that certificate photo
The information security of sheet.License cloud storage end forbids that the certificate photograph of license cloud storage end is entered by the user of license camera equally
Row amendment operation, only allows user submitted to by license camera or delete license photograph.
Whole license camera system collaborative work so that collection and the process of certificate photograph are carried out in enclosed environment, protect
During card, artwork meets government's public security professional standard, artwork is submitted without amendment, artwork transmission, artwork, and photo
It is captured in real-time, submits in real time, it is achieved thereby that from being imaged onto generation standard certificate photograph, to the mistake submitting transmission
Journey guarantees the authenticity of certificate photograph and ageing, prevents certificate photograph to be tampered.
Verify camera, license camera access service end, license cloud storage end and certificate photograph intelligent cloud below to process
System is described in detail:
(1) license camera
As it has been described above, license camera is a professional certificate photograph shooting software, mainly it is responsible for shooting a width and meets
The license artwork that certificate making uses, it is ensured that the authenticity of license artwork, ageing, prevents photo to be tampered, and non-
Often facility easily obtains certificate photograph, as in figure 2 it is shown, license camera includes that main control module, license artwork shoot mould
Block, access amendment disabled module, watermark encrypting module, transmission communication module, UI display module and user management module,
Wherein:
Described main control module is the brain of license camera, and it controls the operation of whole license camera, manages modules
Operation sequential, call and process the data of modules.
Described license artwork taking module, for carrying out the shooting of license artwork, can shoot a width and meet certificate system
Making the license artwork used, this license artwork meets government's public security professional standard, as it is shown on figure 3, this module includes:
Configuration parameter unit, for detecting the acquisition parameters such as the brightness of intelligent terminal camera, exposure, white balance be
No meet certificate photograph photographing request, if it is not, then acquisition parameters is configured, as the most right according to the parameter preset
Jiao, automatic exposure, automatic light-supplementing, white balance etc. configure;Camera configuration parameter is had one to set in advance by license camera
The standard certificate photograph optimal acquisition parameters value put, these parameter values are high-quality by contributing to after experimental verification shooting
The optimum value of the certificate photograph of amount;Therefore, license camera is automatically performed optimal camera parameter and arranges, and embodies license
The professional degree of camera, reduces the requirement to user's specialty shooting ability.
Portrait feature extraction unit, for when finding a view the stage, extracts the portrait characteristic of preview frame image;Wherein,
Described portrait characteristic includes that facial contour, trunk profile, portrait profile, eyes, nose, ear and face are special
Levy data;The extractive technique of portrait feature extraction unit uses OpenCV (Open Source Computer Vision
Library, based on increase income distribution cross-platform computer vision library) cascade classifier target detection technique based on,
Utilize the abundant function library of OpenCV, for shooting feature and the specific requirement of license portrait, in conjunction with independent research
Swift nature recognition methods, it is achieved exclusive portrait Feature Extraction Technology, it is simple to follow-up detection reminding unit, intelligence
Cutting unit, intelligence scratch figure replacement background cell, shooting quality scoring unit calls process to view data.
Sensing data acquiring unit, for when imaging, obtain intelligent terminal Gravity accelerometer data,
Gyroscope sensor data, direction magnetic field sensor data and luminance sensor data, it is simple to follow-up detection is reminded single
Unit calls, and guides the proper use of intelligent terminal of user to complete shooting action in the phase of finding a view, and generates card processing
During according to artwork, it is simple to the correctness of inspection shooting results;
Brightness, definition and chromaticity distortion data capture unit, for when obtaining sensing data, dividing by image
Analysis obtains the brightness data of preview frame image, definition data and chromaticity distortion data, it is simple to follow-up detection is reminded single
Cutting unit first, intelligent, intelligence scratch figure replacement background cell, shooting quality scoring unit calls process.
Detection reminding unit, for judging intelligent terminal sensing data, the portrait characteristic of preview frame image, bright
Whether degrees of data, definition data and chromaticity distortion data meet legal certificate photograph relevant criterion requirement, if so, when
After shooting push button is pressed, it is thus achieved that raw image data, adjust if it is not, then remind user to carry out shooting;Detection is reminded
Preview frame image can be detected in real time by module when shooting, and reminds user to be adjusted, and meets card to shoot
The image of part photo standard, due to user be not specialty certificate photograph shooting personnel, they shooting during very
Difficulty knows the execution standard-required of certificate photograph, it is also difficult to performs standard-required according to this and goes to shoot photo, therefore needs
Them are given the guide of specialty, it is achieved general user also can shoot specially according to guide during shooting photo
The license level of industry shooting personage;The detection of detection reminding unit reminds dimension to include: 1) portrait posture detection: face
Whether seen from, whether face size position meets, portrait distance is the most suitable, whether face is rectified, shoulder is
No flush;2) shooting environmental detection: intelligent terminal is the most vertically, whether intelligent terminal is shaken, brightness is the most uniformly filled
Foot, image are the most clear, whether colourity has deviation.
Intelligence cutting unit, for raw image data is carried out cutting process according to the standard certificate photograph specification set,
Obtain the license artwork of standard size dimensions;On the one hand the automatic complete cutting of license camera makes photo meet standard certificate photograph
Specification requirement, save the artificial cutting time, improve efficiency;On the other hand reduce the redundancy of photo, reduce photograph
Memory space needed for sheet, it is simple to follow-up facile transport;The cutting processing method of intelligence cutting unit can be to obtain eye
The positional information of eyeball, according to image size and the ratio of eye distance size, carries out cutting to photo;
Intelligence is scratched figure and is replaced background cell, for license artwork carries out scratching figure, and according to the certificate photograph mark set
Accurate replace background process, adjust portrait size and location, obtain license preview graph, show intuitively at license to user
Reason result;
Wherein, the method that license artwork carries out scratching figure is: use contour detecting technology fast searching in license artwork
To portrait profile;Region in the portrait profile searched out is set as initial prospect, outside the portrait profile searched out
The region enclosed is set as initial background;Use the Mask bitmap of initial prospect and the Mask bitmap of initial background, pass through
GrabCut function sets up mixed Gauss model, then is obtained the final mask of foreground area and background area by iteration adjustment
Bitmap;Newly-built and artwork transparent empty image bit map of the same size, is reflected the foreground area of final Mask bitmap
The pixel penetrated copies to, in described image bit map, obtain foreground image;Or the background area of final Mask bitmap is reflected
The pixel data in artwork penetrated is erased, and inserts Transparent color, obtains foreground image.
The Mask bitmap of the initial prospect of described use and the Mask bitmap of initial background, set up mixed by GrabCut function
Conjunction Gauss model, the more final Mask bitmap of foreground area and background area is obtained by iteration adjustment, specifically include:
Use the Mask bitmap of initial prospect and the Mask bitmap of initial background, before being set up respectively by GrabCut function
Scape set of pixels and background pixel collection, set up corresponding prospect mixed Gauss model and background mixed Gauss model further;
Each pixel that read pixel is concentrated, is judged each pixel by mask, it is judged that this pixel belongs to background
Pixel or foreground pixel, then judge that it belongs to which in prospect mixed Gauss model or background mixed Gauss model
Gaussian component, is adjusted prospect mixed Gauss model and preliminary background mixed Gauss model according to judged result;
Background mixing height after using gibbs energy theorem again to learn the prospect mixed Gauss model after adjusting or adjust
This model, is iterated adjusting to the background mixed Gauss model after the prospect mixed Gauss model after adjusting or adjustment,
Until iterations completes;
Result of calculation by GrabCut function output foreground and background, it is thus achieved that the foreground area of license artwork and background
The final Mask bitmap in region.
Shooting quality scoring unit, for entering item by item license artwork or license preview graph according to government's public security professional standard
Row shooting quality is assessed, and provides suggestion according to comprehensive grading result;Certificate photograph government public security professional standard has:
" requirement of GA 461-2004 ID cards digital photo technology ", " GA482-2012 China people's republicanism
State's motor vehicle driving certificate ", " requirement of GA/T 1180-2014 exit and entry certificates digital photo technology " etc., these marks
The project of alignment request is numerous and in small, broken bits, and general user cannot remember, also cannot go to judge captured by photo out whether
Meeting the standard of certificate photograph, therefore license camera proposes and uses the mode of shooting quality scoring detection to be clapped user
The photo control test standard taken the photograph detects one by one, and stamps mark to each detection project, finally draws one
Comprehensive quality is marked;Providing comprehensive suggestion again according to comprehensive quality scoring, dimensions is according to government's public security industry
The examination criteria of standard formulation, including 14 sports: 1) the most recent photochrome;2) 24 RGB whether it are not less than
RGB;3) whether it is JPEG compression technology, and whether compression quality meets the requirements;4) whether photo files capacity
Meet the requirements;5) whether image image height width pixel meets the requirements;6) whether background color meets the requirements;7) photo
Surrounding whether Rimless;8) focusing is the most accurate, i.e. image is the most clear;9) face whether clear, levels are rich,
I.e. face are the most visible: 10) whether facial contour is without substantially distortion;11) brightness is the most sufficient, and whether face
Shadow-free, speck;12) the most whether image color equalizes, and whether skin presents true tone, no color differnece;13)
Whether attitude is rectified;14) whether head portrait size and location meet the requirements.
Described access amendment disabled module, during generating in the shooting of license artwork, forbid user or other are soft
Part accesses raw image data, and forbids user or other software modification license artwork datas.It is to say, to shooting
The raw image data (view data of camera output) of gained, in internal processes (until output meets
The license artwork of specification requirement) in, forbid user or other third party softwares, contact these data.
Described watermark encrypting module, for being encrypted the write fragility watermark of the license artwork of shooting;Write
Watermark is encrypted, and can strengthen the protection to photo artwork, prevents user in shooting imaging and to be transmitted across
Photo is distorted by journey (as cutting, beautify, malicious sabotage, maliciously replacement etc.);In certificate photograph intelligent cloud
After processing system or relevant certificates handling department take the photo of watermark encrypting, extract after being deciphered by key (private key)
To watermark information, it is judged that extract the watermark information obtained after deciphering with license artwork correlated characteristic information the most unanimously, if
Inconsistent, license artwork is tampered with, it is impossible to for the making of certificate photograph, if unanimously, then license artwork not by
Distort, may be used for the making of certificate photograph.
Described transmission communication module, for being compressed the photo after watermark encrypting and secondary encryption, and is sent to card
Preserving according in the memory space of cloud storage end independence, wherein compression is so that photo memory space is less, it is simple to number
According to transmission, secondary encryption is the protective capacities in order to improve system on the basis of watermark encrypting further, it is ensured that certificate
Photo is not tampered with during transmission;Additionally, this module is additionally operable to send certificate to license camera access service end
Photo disposal is asked, and receives the license standard drawing result of license camera access service end feedback.
Described UI display module is the window that user is mutual with license camera, show for view-finder, previewing photos shows,
Display, shooting quality scoring are reminded in shooting and professional advice shows, license standard drawing shows, and provide user to demonstrate,prove
According to type (such as identity card, passport, Hong Kong pass, Macao's pass, the Taiwan pass, exit permit, inhabitation
The multiple certificate photo types such as card, social security card) select, retake and (if not reaching requirement, advise retaking, it is impossible to submit to
Accreditation processes), shooting guide check, access card is according to the interactive button of the operation such as cloud storage end, whole UI simple interface
Friendly, the property guided is by force, easily operate.
Described user management module, for being managed user's registration information and user's certificates handling information;After user's registration,
License camera system is that user sets up an independent memory space, the license after user's shooting in license cloud storage end
It is only that artwork and the license standard drawing after certificate photograph intelligent cloud processing system full automatic treatment completes are stored in this
In vertical memory space, defining the write operation authority of user owing to accessing amendment disabled module, user can only browse and look into
See and use photo to carry out the receipt application of certificate, but photo can not be modified, upload and download process;When with
During the application certificate photograph receipt of family, user needs the information such as type, identity card, contact method that fill up a document, and these are done
Card information also leaves in the memory space that this is independent, and only user oneself just has permission and checks;Managed by user
Module, it is ensured that only user itself could access and check certificate photo and relevant certificates handling information thereof, and ensure that individual
The security of people's information.
(2) license camera access service end
License camera access service end is mainly license camera and provides backstage access capability, and it has two main functions:
One be to ensure that license camera secure accessing in certificate photograph intelligent cloud processing system, two is that it records all license cameras
Operation data.
As shown in Figure 4, described license camera access service end includes:
Authorize legitimacy detection module, be used for verifying camera and carry out authorizing legitimacy detection, to guarantee that license camera is pacified
Entirely it is linked in certificate photograph intelligent cloud processing system;
AM access module, after when license camera by authorizing legitimacy to detect, license camera access service end just accepts
Certificate photograph that license camera sends processes request, certificate photograph is processed required parameter (as user type of credential,
User identity card information, the individual essential information etc. of user) it is sent to certificate photograph intelligent cloud processing system;
License standard drawing feedback module, for the license artwork submitted to when license camera, at certificate photograph intelligent cloud
After reason system making processes, feed back whether this license artwork is successfully made the knot of qualified license standard drawing to license camera
Really information.
Operation data recordin module, for recording the operation data of the license camera user end of all accesses, as user makes
With custom, user behavior data etc., it is ensured that user operation trackability;
Monitoring module, for monitoring the operation data of license camera user end, when there is abnormal operation behavior, is then carried out
Forbid or send alarm.
(3) license cloud storage end
License cloud storage end is respectively each license camera client and is assigned with independent memory space, by cloud storage
Separate, allow license camera be not required to directly and dock certificate photograph intelligent cloud processing system, it is ensured that whole license camera system
Security reliability;It addition, the certificate photograph of all shootings is stored in license cloud storage end, forbid at intelligent terminal
Local folders stores, and license cloud storage end verification camera is provided with mandate access module, the card only authorized
Camera could allow to access, it is ensured that the information security of certificate photograph.
License cloud storage end is correspondingly provided with different license cloud subsystems: the storage high in the clouds of license camera, certificate photograph intelligence
The storage high in the clouds that energy cloud processing system is corresponding;In view of the storage safety problem of license cloud storage end, can be at license camera
APP end end arranges mandate access module, only by being just linked into after license camera access service system checking safety
License cloud storage end, and certificate photograph intelligent cloud processing system, owing to being in same Intranet with license cloud storage end, be
Safe and reliable, therefore it is set to trusted system, as shown in Figure 5.
As shown in Figure 6, described license cloud storage end includes:
Authorize access that module is set, be used for verifying camera and mandate access module is set;Wherein, mandate is set and accesses mould
Formula is as it is shown in fig. 7, specifically include:
1) set up an APPID (APP unique sequence numbers) database, preserve the APPID being authorized to;
2) after license camera is succeeded in developing, user agent (User Agent) developer of license camera is by exploitation
Code is to license cloud storage end application APPID, if applying for successfully, then enters step 3);
3) when user agent developer shakes hands with license cloud storage end, it is provided that APPID veritifies to license cloud storage end,
And to license cloud storage end application access token;
4) license cloud storage end is after veritifying APPID and other security information, by callback interface, distributes to license
One access token of camera, and arrange the time limit of losing efficacy.
5) after application, APPID is embedded in the exploitation code of license camera, the follow-up APP whichever is installed,
This APP is to have the APPID authenticated;In the access token valid period, license camera carries access token,
Business interface can be used;Under the mechanism of this token grant, it is ensured that the license camera of access is safe and reliable;
Memory allocation module, for the memory space independent for the distribution of each license camera client;
Cloud storage end amendment attendant exclusion module, is used for the user the forbidding license camera certificate photo to license cloud storage end
Sheet is modified operation, only allows user submitted to by license camera or delete license photograph.
(4) certificate photograph intelligent cloud processing system
The outer welding system of certificate photograph intelligent cloud processing system camera arrangement as evidence, when license camera system proposes accreditation
During request, it is processed into license standard drawing license artwork rapidly, and feedback result is to license camera system, the most whole
The certificate photograph of individual system has processed.
As shown in Figure 8, described certificate photograph intelligent cloud processing system includes:
Parameter analysis of electrochemical module, the certificate photograph sent for resolving license camera access service end processes required parameter;
License artwork extraction module, for, after resolving certificate photograph process required parameter, extracting to license cloud storage end
License artwork, this artwork is saved in the photo of the service end of license cloud after camera has shot as evidence;
License artwork authentication module, for verifying the authenticity of license artwork, particularly as follows:
License artwork is carried out watermark extracting, and deciphers watermark information, use whether the watermark information certificate of inspection leads to according to artwork
Cross, the most then license artwork is not tampered with;If it is not, then license artwork is tampered with;
License artwork processing module, for completing the process of license standard drawing to the license artwork being not tampered with;
Cloud processing system license standard drawing feedback module, for after license artwork has processed and has obtained license standard drawing,
The result completing to make by license standard drawing by license camera access service end feeds back to license camera.
Embodiment 2:
As it is shown in figure 9, the certificate photograph shooting of the present embodiment and handling process license based on embodiment 1 camera system
Realize, comprise the following steps:
After S1, license camera start, start the camera of intelligent terminal, the start-up parameter of retrieval license camera, start
Parameter can be the pixel of preposition/post-positioned pick-up head, exposure, light filling pattern, autofocus mode, white balance mode,
Preview frame frame per second and frame sign, picture format, image size etc., other parameter outside camera pixel is referred to as
Acquisition parameters;
S2, when retrieving start-up parameter, license camera judges whether start-up parameter meets certificate photograph photographing request,
If camera pixel is unsatisfactory for certificate photograph photographing request, then on intelligent terminal, disables this camera, and call intelligence
Can terminal other meet the camera of certificate photograph photographing request, if acquisition parameters is unsatisfactory for certificate photograph photographing request,
Then according to systemic presupposition value, acquisition parameters is carried out parameter adjustment, makes acquisition parameters meet the requirement of certificate photograph shooting,
Then parameter initialization is carried out;
S3, license camera, after initiation parameter, carry out the shooting of license artwork, and the shooting in license artwork generated
Cheng Zhong, forbids user or other softward interview raw image datas, and forbids user or other software modification license artwork
Data, the shooting of license artwork as shown in Figure 10, specifically includes:
S31, get from the camera of intelligent terminal in certain time interval (time interval is that developer sets)
Preview frame image, when finding a view the stage, license camera extracts the portrait characteristic of preview frame image;Wherein, described
Portrait characteristic includes facial contour, trunk profile, portrait profile, eyes, nose, ear and face characteristic
According to;When imaging, obtain the Gravity accelerometer data of intelligent terminal, gyroscope sensor data, direction magnetic
Field sensor data and luminance sensor data;When obtaining sensing data, obtain preview frame figure by graphical analysis
The brightness data of picture, definition data and chromaticity distortion data;
S32, license camera judge intelligent terminal sensing data, the portrait characteristic of preview frame image, brightness data,
Whether definition data and chromaticity distortion data meet legal certificate photograph relevant criterion requirement, if so, work as shooting push button
After being pressed, it is thus achieved that raw image data, adjust if it is not, then remind user to carry out shooting;
S33, license camera carry out cutting process to raw image data according to the standard certificate photograph specification set, it is thus achieved that
The license artwork of standard size dimensions;Wherein, cutting processing method can be the positional information obtaining eyes, according to figure
As size and the ratio of eye distance size, photo is carried out cutting;
S34, license camera carry out scratching figure to license artwork, and are replaced background according to the certificate photograph standard set
Process, adjust portrait size and location, obtain license preview graph, show license result intuitively to user;
S35, license camera carry out shooting quality assessment, and root item by item according to government's public security professional standard to license artwork
Suggestion is given according to comprehensive grading result;
The license artwork write fragility watermark of shooting is encrypted by S4, license camera;
Photo after watermark encrypting is compressed and secondary encryption by S5, license camera, and is sent to license cloud storage end
Preserving in independent memory space, the operation of photographing section completes;
S6, shot after enter certificate photograph processing links, user start the handling process of certificate photograph, license
Camera sends certificate photograph to license camera access service end and processes request, and certificate photograph processes request and also includes user's
Type of credential, user identity are demonstrate,proved the certificate photographs such as the individual essential information of information, user and are processed required parameter, these ginsengs
Number makes for the receipt of standard certificate photograph;
S7, license camera access service end examination & verification license camera mandate legitimacy, when examination & verification by after, license camera
Access service termination is processed by the certificate photograph of license camera and asks, and certificate photograph is processed required parameter and is sent to certificate
Photo intelligent cloud processing system;
S8, certificate photograph intelligent cloud processing system resolve the certificate photograph process request that license camera access service end sends
Parameter, and extract license artwork to license cloud storage end;
The authenticity of S9, certificate photograph intelligent cloud processing system checking license artwork, particularly as follows:
License artwork is carried out watermark extracting, and deciphers watermark information, use whether the watermark information certificate of inspection leads to according to artwork
Cross, the most then license artwork is not tampered with;If it is not, then license artwork is tampered with;
S10, certificate photograph intelligent cloud processing system complete the process of license standard drawing to the license artwork being not tampered with;
License artwork has processed and has obtained license standard drawing, and this license standard drawing is may finally to be used for legal certificate making also
And obtain the photo that accreditation department convinces and receives;
License standard drawing is completed to make by S11, certificate photograph intelligent cloud processing system by license camera access service end
Result feeds back to license camera.
In above-mentioned steps S31, described license camera extracts the portrait characteristic of preview frame image, specifically includes:
1) the preview frame image got is converted to gray level image;
2) gray level image is carried out characteristic region detection above the waist, when characteristic region above the waist being detected,
This area pixel information is saved as region rectangle data structure above the waist, and gray level image is arranged ROI district above the waist
Territory (Region of Interest, i.e. area-of-interest), is designated as ROIB;
3) ROIB is carried out the detection of facial contour feature data area, when facial contour feature data area being detected,
This area pixel information is saved as facial contour region rectangle data structure, and gray level image is arranged facial contour
ROI region, is designated as ROIF;
4) specific region to ROIF carries out eyes characteristic region detection, when eyes characteristic region being detected
Time, this area pixel information is saved as eyes region rectangle data structure, and obtains the coordinate of eyes, with eyes
Y-axis minimum point is new ROI region top, and facial contour feature data area takes eyes area below, arranges
For nose target ROI region, it is designated as ROIN;
5) ROIF is carried out ears characteristic region detection, when ears characteristic region being detected, by this district
Territory Pixel Information saves as ears region rectangle data structure;
6) ROIN is carried out nose characteristic region detection, when nose characteristic region being detected, by this district
Territory Pixel Information saves as nasal area rectangle data structure, using the base of nasal area rectangle data structure as new
The top margin of ROI region, takes nose region below to facial contour feature data area, is set to face target ROI district
Territory, is designated as ROIM;
7) ROIM is carried out face characteristic region detection, when face characteristic region being detected, by this district
Territory Pixel Information saves as face region rectangle data structure;
8) region to ROIB, cuts out the region removing ROIF, obtains trunk contour feature data area ROIMB, will
This area pixel information saves as trunk contour area rectangle data structure;
9) ROIF being carried out rim detection, the line segment obtaining sign mutation edge in contouring head regional extent is (real
It is one group of coordinate points on border), then this head edge line segment result is carried out head convex closure contour detecting, head is convex
The coordinate of the key point that bag contour detecting obtains saves as contouring head array;
10) ROIMB being carried out rim detection, the line segment obtaining sign mutation edge in the range of trunk contour area is (real
It is one group of coordinate points on border), then this trunk edge line segment result is carried out trunk convex closure contour detecting, trunk is convex
The coordinate of the key point that bag contour detecting obtains saves as trunk profile array;
11) contouring head array and trunk number of contours group are combined, form portrait profile array.
In above-mentioned steps S32, described license camera judges the portrait spy of intelligent terminal sensing data, preview frame image
Levy whether data, brightness data, definition data and chromaticity distortion data meet legal certificate photograph relevant criterion requirement,
Specifically include:
1) in portrait posture detection and shooting environmental being detected, all detection purpose related datas and preset value are carried out one by one
Relatively, satisfactory detection project, then by detection, undesirable detection project, then carry out sound/character/
Graphical cues, real-time reminding user carries out shooting and adjusts;Wherein, described preset value is for meet certificate photograph through checking
The preferred values of shooting standard-required, the detection project of described portrait posture detection includes face whether visible, face size
Whether position meets, portrait distance is the most suitable, whether face rectifies and whether shoulder flushes, described shooting ring
The detection project of border detection include intelligent terminal whether vertically, whether intelligent terminal is shaken, brightness is the most sufficient,
Image is the most clear, whether colourity has deviation;
The most visible detection of face, its related data is the eye position of portrait characteristic, nose position, ear
These characteristics are compared by the characteristics such as position, position, the crown, chin portion with default standard feature,
Judge that these face features are the most complete, if complete, prove portrait and clear, then by detection;If it is the most complete
Then carry out sound/character/graphical cues;
The detection whether face size position meets, its related data is the eye position of portrait characteristic, nose position
Put, ear location, position, the crown, the characteristic such as chin portion, calculate head portrait position, eye position, chin position
The requirement whether meeting detection model such as put, if face size meets the requirement of detection model, then by detection;As
Really face size does not meets the requirement of detection model, then carry out sound/character/graphical cues: as face is too small, please be close
Camera;As face is excessive, please away from camera;
Portrait distance the most suitably detects, and calculating portrait size is with the accounting of preview frame picture traverse, according to accounting for
Than calculating the people that the is taken distance to camera, it is judged that this distance whether meet optimal shooting distance scope (as
70cm~90cm), if the nearlyest (less than 70cm), then can produce shooting pattern distortion, if too far (more than 90cm),
The most not fogging clear, the most too far away or too close be all unsatisfactory for certificate photograph standard-required, then shooting push button is set to
Can not screening-mode, transfer simultaneously default information carry out shooting prompting;
The detection whether face is rectified, its related data is the eye position of portrait characteristic, nose position, face
The characteristic such as position, facial contour, carries out three detection: a, generates two lines, calculate two lines and level
The angle of line, it is judged that whether angle is beyond predetermined angle scope;B, acquisition place between the eyebrows (central points of two lines) coordinate,
Obtain center (nose) coordinate of nose, it is thus achieved that the centre coordinate of face, three points are done fitting a straight line and obtains straight line
LC, calculates this straight line and the angle of two field picture vertical direction, it is judged that whether angle is beyond preset range;C, acquisition face
The center line (vertical direction) in region, calculates distance DC of center line FLC and LC of human face region, calculates DC
Ratio with human face region width, it is judged that whether this ratio is beyond preset range;If a, b and c are without departing from scope,
Then proving that face posture meets the requirements, if there being any one to go beyond the scope, then explanation face posture is undesirable, enters
Row voice message/text prompt;
The detection whether shoulder flushes, its related data is the trunk contour feature data of portrait characteristic, carries out two
Detection: a, to the trunk profile coordinate array extracted, fits to a polygon, calculates polygonal center of gravity and obtain
To the coordinate (X1, Y1) of center of gravity, calculate X1 and distance Dweight of preview frame vertical center of gravity line, calculate Dweight
Ratio with preview frame width WF, it is judged that whether ratio is beyond preset range;B, to profile coordinate array, use
Little bounding rectangle algorithms, obtains a minimum rectangle, calculates rectangular vertical center line and the angle of frame vertical center of gravity line,
Judge whether angle exceedes preset range;If a and b is not above preset range, then shoulder flushes, if a and b
In any one do not meet, then carry out sound/character/graphical cues: as asymmetric in left and right shoulder, please adjust;
The detection that intelligent terminal is the most vertical, its related data is direction magnetic field sensor and Gravity accelerometer
Data, with Eulerian angles (yaw angle, the angle of pitch and roll angle) and the Gravity accelerometer of direction magnetic field sensor
XYZ value as initialize perpendicular attitude value, it is thus achieved that the droop of acceleration of gravity XYZ, as correction value,
Judge whether the angu-lar deviation of angle information value after correcting exceedes predetermined deviation value, if exceeding, carry out sound/character/
Graphical cues;Wherein, the droop of acceleration of gravity XYZ is through the data value that obtains of experiment, with different brands,
The intelligent terminal of model is correlated with, the actually detected data of direction magnetic field sensor and Gravity accelerometer are added (or
Deduct) correction value, the angle information value after being corrected further, then calculate the angle information value after correcting and preset
Difference between standard vertical angle value, i.e. obtains angu-lar deviation.
The detection whether intelligent terminal is shaken, its related data is gyroscope sensor data, it is judged that whether terminal device
Be in perpendicular attitude, the most then the value recording gyro sensor is initial value;When there is shake in terminal device,
The value of gyro sensor changes, and calculates the excursion of this value, with default deviation threshold compares, sentences
Whether disconnected its exceeds threshold value, as added 1 beyond threshold value then counter values;When counting (such as 5 seconds) in certain acquisition time
When number device numerical value exceedes threshold value, it is believed that equipment is shaken, then carry out corresponding sound/character/graphical cues;
The detection that brightness is the most sufficient, its related data is the brightness number of luminance sensor data and preview frame image
According to, if the brightness value L of luminance sensor is less than a predetermined low level, then judge that its ambient light is the darkest, if bright
Degree sensor brightness value L more than preset high level, then judge that its ambient light is the brightest, then sound/character/graphical cues its
Change an environment shooting;If between predetermined low level and default high level, then obtain preview frame image, analyze this image
Brightness histogram, calculates its brightness exception COEFFICIENT K and average luminance shift value DA;If brightness exception COEFFICIENT K
Less than 1, then this brightness of image is normal, if brightness exception COEFFICIENT K is more than or equal to 1, and average luminance shift value
DA is more than 0, then ambient light is the brightest;If brightness exception COEFFICIENT K is more than or equal to 1, and average luminance shift value
DA is less than 0, then ambient light is the darkest;
Image detects the most clearly, and its related data is the definition data of preview frame image, i.e. sharpness factor,
Judge that sharpness factor whether more than preset value, the most then passes through detection, if it is not, then sound/character/graphical cues figure
Image sharpness is not enough;
Colourity detection the most devious, its related data is the chromaticity distortion data of preview frame image, i.e. colour cast coefficient,
If colour cast COEFFICIENT K is less than 1 expression ratio compared with normal, if colour cast COEFFICIENT K is more than or equal to 1, then it is assumed that there is color inclined
Difference, carries out sound/character/graphical cues, and wherein colourity mean value Da (red green colour cast estimate) is more than 0, represents
The reddest;Da is the greenest less than 0 expression, and colourity mean value Db (yellow blue colour cast estimate) is more than 0, represents partially yellow;
Db is partially blue less than 0 expression.
2) when there is undesirable detection project, shooting push button is set to can not screening-mode, when all of
When detection project all meets the requirements, being set to by shooting push button can screening-mode.
In above-mentioned steps S34, license artwork is carried out scratching figure by described certificate photo machine, specifically includes:
Use contour detecting technology in license artwork fast searching to portrait profile;In the portrait profile searched out
Region is set as initial prospect, and the region that the portrait profile searched out is peripheral is set as initial background;Before using initially
The Mask bitmap of scape and the Mask bitmap of initial background, set up mixed Gauss model by GrabCut function, then pass through
Iteration adjustment obtains the final Mask bitmap of foreground area and background area;Newly-built and artwork transparent sky of the same size
Image bit map, the pixel that the foreground area of final Mask bitmap is mapped copies to, in described image bit map, obtain
Foreground image;Or the pixel data in the artwork that the background area of final Mask bitmap mapped erases, insert transparent
Look, obtains foreground image.
The Mask bitmap of the initial prospect of described use and the Mask bitmap of initial background, set up mixed by GrabCut function
Conjunction Gauss model, the more final Mask bitmap of foreground area and background area is obtained by iteration adjustment, specifically include:
Use the Mask bitmap of initial prospect and the Mask bitmap of initial background, before being set up respectively by GrabCut function
Scape set of pixels and background pixel collection, set up corresponding prospect mixed Gauss model and background mixed Gauss model further;
Each pixel that read pixel is concentrated, is judged each pixel by mask, it is judged that this pixel belongs to background
Pixel or foreground pixel, then judge that it belongs to which in prospect mixed Gauss model or background mixed Gauss model
Gaussian component, is adjusted prospect mixed Gauss model and preliminary background mixed Gauss model according to judged result;
Background mixing height after using gibbs energy theorem again to learn the prospect mixed Gauss model after adjusting or adjust
This model, is iterated adjusting to the background mixed Gauss model after the prospect mixed Gauss model after adjusting or adjustment,
Until iterations completes;
Result of calculation by GrabCut function output foreground and background, it is thus achieved that the foreground area of license artwork and background
The final Mask bitmap in region.
In above-mentioned steps S35, license artwork is shot item by item by described license camera according to government's public security professional standard
Quality evaluation, and provide suggestion according to comprehensive grading result, specifically include:
1) file attribute information of photo is obtained;Carry out portrait feature identification by photo gray-scale map and extract portrait feature letter
Breath;Background information is obtained by edge detecting technology, image Segmentation Technology;Monochrome information is obtained by photo gray-scale map;
Chrominance information is obtained by photo mean square deviation in Lab color space system;Obtained by the gray-scale map matrix of photo
To sharpness information;
2) according to obtain file attribute information, portrait characteristic information, background information, monochrome information, chrominance information,
Dimensions is marked by sharpness information item by item, obtains the score value of each dimensions;
Dimensions is the examination criteria according to government's public security industry standard formulation, including 14 sports: 1) the most recent
Photochrome;2) 24 RGB RGBs whether it are not less than;3) whether it is JPEG compression technology, and compressed article
Whether matter meets the requirements;4) whether photo files capacity is more than the preset value of corresponding certificate photograph;5) image image height
Whether wide pixel meets the requirement of corresponding certificate photograph;6) whether background color meets the requirement of standard certificate photograph;7)
Photo surrounding whether Rimless;8) focusing is the most accurate, i.e. image is the most clear;9) face whether clear, level
Abundant, i.e. face are the most visible: 10) whether facial contour is without substantially distortion;11) brightness is the most sufficient, face
Portion whether shadow-free, speck;12) whether image color equalizes, and whether skin presents true tone, the most colourless
Difference;13) whether attitude is rectified;14) whether head portrait size and location meet the requirements;
Whether in the recent period the detection of photochrome and scoring, check the photograph taking time in file attribute, it may be judged whether
(in generally 6 months, the having some to require 3 months in) that close-perspective recording is taken the photograph, the most then determine whether photochrome,
If then meeting requirement;When meeting, individual event is 5 points, individual event score=(-40) point when not meeting;
Whether it is not less than detection and the scoring of 24 RGB RGBs, file attribute is searched the figure place of its colour, if
Being not less than 24 (comprising 24) then judges that it meets the requirements;When meeting, individual event is 5 points, and when not meeting, individual event obtains
Point=(-40) point;
Whether it is JPEG compression technology, and compresses the most satisfactory detection of quality and scoring, obtain in file attribute
File suffixes, it is judged that file is either with or without compression, if there being compression, if for JPEG compression, if JPEG compression is then
Meeting the requirements, then judge to compress whether quality meets the requirement of corresponding certificate photograph, if meeting the requirements, then proving that it is full
This standard of foot;When meeting, individual event is 5 points, individual event score=(-40) point when not meeting;
The most satisfactory detection of photo files capacity and scoring, obtain the file size information in file attribute, sentence
Breaking, whether it is more than the preset value of corresponding certificate photograph, if, then it represents that it meets the requirements;Image file size >=card
Part type of lowest value, individual event is 5 points, individual event score=(-40) point during image file size < type of credential minimum;
The image image height the most satisfactory detection of width pixel and scoring, obtain the image pixel information in file attribute,
Judge whether it meets the height and width minimum pixel requirement of corresponding certificate photograph;Image image height >=minimum picture of type of credential
Element, wide >=type of credential minimum pixel, individual event is 10 points, image image height < type of credential minimum pixel, and wide < demonstrate,proves
During part type minimum pixel, individual event score=(-40) point;
The most satisfactory detection of background color and scoring, before background does not the most replace it, can detect background purity,
As long as background is without mixed and disorderly and substantially distinguish with portrait and can meet the requirements;After background replaces to normal background, pass through
Edge detecting technology, image Segmentation Technology obtain background information, it is judged that whether it meets the requirement of standard certificate photo;Symbol
During conjunction, individual event is 5 points, individual event score=(-40) point when not meeting;
The detection of photo surrounding whether Rimless and scoring, use whether edge detecting technology, detection photo surrounding have rule
Bounding box features then, if nothing, then it is assumed that it meets;When meeting, individual event is 5 points, individual event score=(-40) when not meeting
Point;
The detection of focusing the most accurately (image is the most clear) and scoring, if sharpness factor is more than 14, the most clearly,
If sharpness factor is less than 10, then obscure;When meeting, individual event is 5 points, individual event score=(-40) point when not meeting;
Face whether clear, the detection of levels are rich (face are the most visible) and scoring, the portrait feature of extraction photo,
Including eyes, nose, ear, face, facial contour etc., it is judged that these information are the most complete, if complete, can recognize
For meeting this testing requirement;When meeting, individual event is 5 points, individual event score=(-40) point when not meeting;
Whether facial contour is without detection and the scoring of substantially distortion, and whether detection facial contour is poor with default facial contour
Different size (is calculated by the ratio of non-overlapped area and overlapping area), if difference is less than or equal to preset value, then
It is believed that it meets the requirements, if more than preset value, then it is assumed that it is distorted, it is desirable to re-shoot;Individual event when meeting
It is 5 points, individual event score=(-40) point when not meeting;
Whether brightness is uniformly sufficient, face's whether shadow-free, the detection of speck and scoring, obtains the brightness Nogata of photo
Figure, calculates brightness exception COEFFICIENT K, average luminance shift value DA, if brightness exception COEFFICIENT K is less than 1, then and this image
Brightness is normal, if brightness exception COEFFICIENT K is more than or equal to 1, and average luminance shift value DA is more than 0, then brightness
Cross bright;If brightness exception COEFFICIENT K is more than or equal to 1, and average luminance shift value DA is less than 0, then too dark brightness,
Brightness is crossed bright and is not the most secretly complyed with requirement;When meeting, individual event is 5 points, individual event score=(-40) point when not meeting;
Whether image color equalizes, and whether skin presents detection and the scoring of true tone (whether no color differnece), obtains
Photo, is converted to Lab color space image by photo, and each pixel of counting statistics is at a axle of Lab and the look of b axle
Degree mean value Da (red green colour cast estimate) and Db (yellow blue colour cast estimate), calculate colour cast COEFFICIENT K, if look
Parital coefficient K is normal less than 1 expression, if colour cast COEFFICIENT K exists colour cast more than 1 expression, colourity mean value Da is more than
0, represent the reddest;Colourity mean value Da is the greenest less than 0 expression, and colourity mean value Db is more than 0, represents partially yellow;Look
Degree mean value Db is partially blue less than 0 expression;When meeting, individual event is 5 points, individual event score=(-40) point when not meeting;
Detection that whether attitude is rectified and scoring, have 10 detections, wherein portrait whether horizontal center, whether face
The detection that camera, head are the most vertical sees the detection whether above-mentioned face is rectified, the detection ginseng of both shoulders whether level
See the detection whether above-mentioned shoulder flushes;It is unobstructed whether eyes are opened, and obtains eye feature data, calculates in eyes
Between open the width of part, if width is more than preset value, then it represents that it is opened;Lip whether Natural closure, obtains mouth
Whether the characteristic of lip, uses edge detecting technology, it is judged that be a curve in the middle of upper lower lip, if a song
Line, then meet the requirements, if there being the curve of more than two, then proves that it opens;Whether take one's hat off, it is judged that portrait profile and
Default profile is the most variant, if difference is less than preset value, and head color is the most substantially split, then prove that it does not has
It is branded as;Whether without blood-shot eye illness, obtain the characteristic of eye portion, calculate the chromaticity distortion value of eye portion, if look
Degree deviation value in preset range, then proves normal, if (K exists colour cast, Da more than 1 expression in chromaticity distortion value
More than 0, represent the reddest) then there is blood-shot eye illness;Whether without heavy make-up, detect the color error ratio value of face, the look at eyelid position
Color deviation value, the color error ratio value at lip position, if each deviation value is more than the deviation threshold preset, then it is assumed that be dense
Adornment;Hair does not the most cover face, extracts face mask, with default face mask feature compares, it is judged that be
No have bigger difference, if there being larger difference, then it is undesirable;All above meet to obtain 15 points, when not meeting
Individual event score=(-40) point;
The most satisfactory detection of head portrait size and location and scoring, have 5 detections, it is judged that head width pixel,
Gain fame and fortune on photo away from up/down edge range pixel, the crown in head high pixel, interpupillary distance pixel, eyes position
Whether edge pixels meets the pixel request of corresponding certificate photograph;All above meeting to obtain 20 points, when not meeting, individual event obtains
Point=(-40) point;
3) according to the score value of each dimensions, and scoring weight, calculate the quality general comment of the photo photographed
Point;The shooting suggestion of specialty is given according to overall score;
4) when photo composite score is less than preset value, then the relevant criterion requirement of legal certificate photograph it is unsatisfactory for, it is proposed that
User re-shoots, and meets, until shooting, the photo that legal certificate photograph relevant criterion requires.
It will be appreciated by those skilled in the art that all or part of step realizing in above-described embodiment method can pass through program
Instructing relevant hardware to complete, corresponding program can be stored in computer read/write memory medium, described
Storage medium, such as ROM/RAM, disk or CD etc..Additionally, the intelligent terminal in above-described embodiment can be intelligence
Can mobile phone, PDA handheld terminal, panel computer etc..
In sum, the license camera system of the present invention is prevented user from revising by disabling local folders, is used watermark
The reinforcement of encrypted image content is protected, sets up license camera access service end legitimate verification system, is set up license cloud storage
The authority checking system of end so that the collection of certificate photograph and processing is carried out in enclosed environment, it is ensured that during artwork
Meet government's public security professional standard, artwork without amendment, artwork transmission, artwork submit, and photo be captured in real-time,
Submit in real time, it is achieved thereby that from being imaged onto generation standard certificate photograph, guaranteeing certificate during submitting transmission
The authenticity of photo and ageing, prevents certificate photograph to be tampered.License camera in license camera system is by automatically
Configuration meets the professional camera parameter of certificate photograph shooting standard, provides legal certificate photograph type option, offer standard
Certificate photograph shooting is reminded support, is provided automatic cutting and background replacement to support, provide shooting effect government public security industry
The mechanism such as project of standard development quality testing scoring, the shooting giving user's specialty is instructed, and provides a user with a height specialty
License camera.
The above, patent preferred embodiment the most of the present invention, but the protection domain of patent of the present invention is not limited to
This, any those familiar with the art is in the scope disclosed in patent of the present invention, according to patent of the present invention
Technical scheme and inventive concept equivalent or change in addition, broadly fall into the protection domain of patent of the present invention.
Claims (19)
1. an anti-tamper license camera system, it is characterised in that: described system include license camera,
License camera access service end and license cloud storage end;Described license camera includes:
License artwork taking module, for carrying out the shooting of license artwork;
Access amendment disabled module, for license artwork shooting generate during, forbid user or
Other softward interview raw image datas, and forbid user or other software modification license artwork datas;
Watermark encrypting module, for being encrypted the write fragility watermark of the license artwork of shooting;
Transmission communication module, for being compressed the photo after watermark encrypting and secondary encryption, concurrently
Deliver to the memory space of license cloud storage end independence preserves;
Described license camera access service end includes:
Authorize legitimacy detection module, be used for verifying camera and carry out authorizing legitimacy detection;
AM access module, for, only after license camera is by authorizing legitimacy to detect, just accepting license phase
The certificate photograph that machine sends processes request, certificate photograph processes required parameter and is sent to certificate photograph intelligence
Can cloud processing system;
License standard drawing feedback module, for the license artwork submitted to when license camera, through certificate photo
After sheet intelligent cloud processing system making processes, feed back whether this license artwork is successfully made to license camera
The object information of qualified license standard drawing.
A kind of anti-tamper license camera system the most according to claim 1, it is characterised in that:
Described license artwork taking module includes:
Configuration parameter unit, for detecting whether the acquisition parameters of intelligent terminal camera meets certificate photo
Sheet photographing request, if it is not, then configure acquisition parameters according to the parameter preset;
Portrait feature extraction unit, for when finding a view the stage, extracts the portrait feature of preview frame image
Data;Wherein, described portrait characteristic includes facial contour, trunk profile, portrait profile, eye
Eyeball, nose, ear and face characteristic;
Sensing data acquiring unit, for when imaging, the acceleration of gravity obtaining intelligent terminal passes
Sensor data, gyroscope sensor data, direction magnetic field sensor data and luminance sensor data;
Brightness, definition and chromaticity distortion data capture unit, be used for when obtaining sensing data,
The brightness data of preview frame image, definition data and chromaticity distortion data are obtained by graphical analysis;
Detection reminding unit, for judging the portrait spy of intelligent terminal sensing data, preview frame image
Levy whether data, brightness data, definition data and chromaticity distortion data meet legal certificate photograph phase
Close standard-required, if so, after shooting push button is pressed, it is thus achieved that raw image data, if it is not, then
Remind user to carry out shooting to adjust;
Intelligence cutting unit, for entering according to the standard certificate photograph specification set raw image data
Row cutting processes, it is thus achieved that the license artwork of standard size dimensions;
Intelligence is scratched and is schemed to replace background cell, for license artwork carries out scratching figure, and according to setting
Certificate photograph standard is replaced background process, adjusts portrait size and location, obtains license preview graph,
License result intuitively is shown to user;
Shooting quality scoring unit, for pre-to license artwork or license according to government's public security professional standard
Figure of looking at carries out shooting quality assessment item by item, and provides suggestion according to comprehensive grading result.
A kind of anti-tamper license camera system the most according to claim 2, it is characterised in that:
Described portrait feature extraction unit extracts the portrait characteristic of preview frame image, specifically includes:
The preview frame image got is converted to gray level image;
Gray level image is carried out characteristic region detection above the waist, when characteristic above the waist being detected
During region, this area pixel information is saved as region rectangle data structure above the waist, and to gray-scale map
As arranging ROI region above the waist, it is designated as ROIB;
ROIB is carried out the detection of facial contour feature data area, when facial contour feature number being detected
During according to region, this area pixel information is saved as facial contour region rectangle data structure, and to ash
Degree image arranges facial contour ROI region, is designated as ROIF;
The specific region of ROIF is carried out eyes characteristic region detection, when eyes feature being detected
During data area, this area pixel information is saved as eyes region rectangle data structure, and obtains eye
The coordinate of eyeball, is new ROI region top with the Y-axis minimum point of eyes, to facial contour feature number
Take eyes area below according to region, be set to nose target ROI region, be designated as ROIN;
ROIF is carried out ears characteristic region detection, when ears characteristic region being detected,
This area pixel information is saved as ears region rectangle data structure;
ROIN is carried out nose characteristic region detection, when nose characteristic region being detected,
This area pixel information is saved as nasal area rectangle data structure, ties with nasal area rectangle data
The base of structure, as the top margin of new ROI region, takes below nose to facial contour feature data area
Region, is set to face target ROI region, is designated as ROIM;
ROIM is carried out face characteristic region detection, when face characteristic region being detected,
This area pixel information is saved as face region rectangle data structure;
Region to ROIB, cuts out the region removing ROIF, obtains trunk contour feature data area
ROIMB, saves as trunk contour area rectangle data structure by this area pixel information;
ROIF is carried out rim detection, obtains sign mutation edge in contouring head regional extent
Line segment, then carries out head convex closure contour detecting to this head edge line segment result, is taken turns by head convex closure
The coordinate of the key point that wide detection obtains saves as contouring head array;
ROIMB is carried out rim detection, obtains the sign mutation edge in the range of trunk contour area
Line segment, then this trunk edge line segment result is carried out trunk convex closure contour detecting, by trunk convex closure
The coordinate of the key point that contour detecting obtains saves as trunk profile array;
Contouring head array and trunk number of contours group are combined, forms portrait profile array.
A kind of anti-tamper license camera system the most according to claim 2, it is characterised in that:
Described detection reminding unit judge intelligent terminal sensing data, the portrait characteristic of preview frame image,
Whether brightness data, definition data and chromaticity distortion data meet legal certificate photograph relevant criterion is wanted
Ask, specifically include:
All detection purpose related datas and preset value during portrait posture detection and shooting environmental are detected
Compare one by one, satisfactory detection project, then by detection, undesirable detection
Mesh, then carry out sound/character/graphical cues, and real-time reminding user carries out shooting and adjusts;Wherein, institute
Stating preset value is the preferred values meeting certificate photograph shooting standard-required through checking, described portrait posture
The detection project of detection include face whether visible, whether face size position meets, portrait away from
Suitable from whether, whether face rectifies and whether shoulder flushes, the detection of described shooting environmental detection
Mesh includes that intelligent terminal is the most vertical, whether intelligent terminal is shaken, brightness is the most sufficient, image
Whether the most clear, colourity has deviation;
When there is undesirable detection project, shooting push button is set to can not screening-mode,
When all of detection project all meets the requirements, being set to by shooting push button can screening-mode.
A kind of anti-tamper license camera system the most according to claim 2, it is characterised in that:
Described shooting quality judge paper unit according to government's public security professional standard to license artwork or license preview graph by
Item carries out shooting quality assessment, and provides suggestion according to comprehensive grading result, specifically includes:
Obtain the file attribute information of photo;Carry out portrait feature identification by photo gray-scale map and extract people
As characteristic information;Background information is obtained by edge detecting technology, image Segmentation Technology;Pass through photo
Gray-scale map obtains monochrome information;Look is obtained by photo mean square deviation in Lab color space system
Degree information;Sharpness information is obtained by the gray-scale map matrix of photo;
According to the file attribute information obtained, portrait characteristic information, background information, monochrome information, look
Dimensions is marked by degree information, sharpness information item by item, obtains the score of each dimensions
Value;
According to the score value of each dimensions, and scoring weight, calculate the photo that photographs
Quality overall score;The shooting suggestion of specialty is given according to overall score;
When photo composite score is less than preset value, then the relevant criterion being unsatisfactory for legal certificate photograph is wanted
Asking, it is proposed that user re-shoots, meeting, until shooting, the photograph that legal certificate photograph relevant criterion requires
Till sheet.
A kind of anti-tamper license camera system the most according to claim 2, it is characterised in that:
Described license camera also includes:
UI display module, show for view-finder, previewing photos shows, shoot prompting display, shooting
Quality score and professional advice show, license standard drawing shows, and provide user to carry out license type choosing
Select, retake, shoot guide check, access card is according to the interactive button of cloud storage end;
User management module, for being managed user's registration information and user's certificates handling information.
A kind of anti-tamper license camera system the most according to claim 1, it is characterised in that:
Described license camera access service end also includes:
Operation data recordin module, for recording the operation data of the license camera user end of all accesses;
Monitoring module, for monitoring the operation data of license camera user end, when abnormal operation row occur
For, then carry out forbidding or sending alarm.
A kind of anti-tamper license camera system the most according to claim 1, it is characterised in that:
Described license cloud storage end includes:
Authorize access that module is set, be used for verifying camera and mandate access module is set;
Memory allocation module, for the memory space independent for the distribution of each license camera client;
Cloud storage end amendment attendant exclusion module, for forbidding that the user of license camera is to license cloud storage
The certificate photograph of end is modified operation, and only permission user is submitted to by license camera or deletes license phase
Sheet.
A kind of anti-tamper license camera system the most according to claim 8, it is characterised in that:
Described mandate access arranges module verification camera and arranges mandate access module, specifically includes:
Set up an APP unique sequence numbers database, preserve the APP unique sequence numbers being authorized to;
When the user agent developer of license camera is arrived to license cloud storage end application by exploitation code
After APP unique sequence numbers, by callback interface, distribute to one access token of license camera, and about
Surely lost efficacy the time limit.
A kind of anti-tamper license camera system the most according to claim 7, it is characterised in that:
Described certificate photograph intelligent cloud processing system includes:
Parameter analysis of electrochemical module, the certificate photograph sent for resolving license camera access service end processes please
Seek parameter;
License artwork extraction module, for after resolving certificate photograph process required parameter, to license cloud
Storage end extracts license artwork;
License artwork authentication module, for verifying the authenticity of license artwork, particularly as follows:
License artwork is carried out watermark extracting, and deciphers watermark information, use the watermark information certificate of inspection to shine
Whether artwork is passed through, the most then license artwork is not tampered with;If it is not, then license artwork is tampered
Cross;
License artwork processing module, for completing license standard drawing to the license artwork being not tampered with
Process;
Cloud processing system license standard drawing feedback module, for obtaining license when license artwork has processed
After standard drawing, the result completing to make by license standard drawing by license camera access service end feeds back to
License camera.
11. 1 kinds of anti-tamper certificate photograph image pickup methods, it is characterised in that: described method includes:
License camera carries out the shooting of license artwork;
Described license camera, during the shooting of license artwork generates, forbids that user or other software are visited
Ask raw image data, and forbid user or other software modification license artwork datas;
The license artwork write fragility watermark of shooting is encrypted by described license camera;
Photo after watermark encrypting is compressed and secondary encryption by described license camera, and is sent to card
Preserve according in the memory space of cloud storage end independence;
Wherein, described method also includes:
License camera access service end verification camera carries out authorizing legitimacy detection;
Only after license camera is by authorizing legitimacy to detect, described license camera access service end just connects
Processed by the certificate photograph of license camera and ask, certificate photograph is processed required parameter and is sent to certificate photo
Sheet intelligent cloud processing system;
When the license artwork that license camera is submitted to, process through certificate photograph intelligent cloud processing system making
After, to license camera, described license camera access service end feeds back whether this license artwork is successfully made conjunction
The object information of the license standard drawing of lattice.
12. a kind of anti-tamper certificate photograph image pickup methods according to claim 11, its feature
It is: the shooting that described license camera carries out license artwork includes:
Whether the acquisition parameters of described license camera calibration intelligent terminal camera meets certificate photograph shooting
Requirement, if it is not, then configure acquisition parameters according to the parameter preset;
When finding a view the stage, described license camera extracts the portrait characteristic of preview frame image;Wherein,
Described portrait characteristic includes facial contour, trunk profile, portrait profile, eyes, nose, ear
Piece and face characteristic;
Described license camera, when imaging, obtains the Gravity accelerometer data of intelligent terminal, top
Spiral shell instrument sensing data, direction magnetic field sensor data and luminance sensor data;
Described license camera, when obtaining sensing data, obtains preview frame image by graphical analysis
Brightness data, definition data and chromaticity distortion data;
Described license camera judge intelligent terminal sensing data, the portrait characteristic of preview frame image,
Whether brightness data, definition data and chromaticity distortion data meet legal certificate photograph relevant criterion is wanted
Ask, if so, after shooting push button is pressed, it is thus achieved that raw image data, if it is not, then remind user
Carry out shooting to adjust;
Described license camera carries out cutting to raw image data according to the standard certificate photograph specification set
Process, it is thus achieved that the license artwork of standard size dimensions;
Described license camera carries out scratching figure to license artwork, and enters according to the certificate photograph standard set
Row replaces background process, adjusts portrait size and location, obtains license preview graph, show directly to user
The license result seen;
License artwork or license preview graph are entered item by item by described license camera according to government's public security professional standard
Row shooting quality is assessed, and provides suggestion according to comprehensive grading result.
13. a kind of anti-tamper certificate photograph image pickup methods according to claim 12, its feature
It is: described license camera extracts the portrait characteristic of preview frame image, specifically includes:
The preview frame image got is converted to gray level image by described license camera;
Described license camera carries out characteristic region detection above the waist to gray level image, on detecting
During half body characteristic region, this area pixel information is saved as region rectangle data structure above the waist,
And gray level image is arranged ROI region above the waist, it is designated as ROIB;
Described license camera carries out the detection of facial contour feature data area to ROIB, when people being detected
During face contour feature data area, this area pixel information is saved as facial contour region rectangle data
Structure, and gray level image is arranged facial contour ROI region, it is designated as ROIF;
Described license camera carries out eyes characteristic region detection to the specific region of ROIF, works as inspection
When measuring eyes characteristic region, this area pixel information is saved as eyes region rectangle data knot
Structure, and obtain the coordinate of eyes, it is new ROI region top with the Y-axis minimum point of eyes, to people
Face contour feature data area takes eyes area below, is set to nose target ROI region, is designated as
ROIN;
Described license camera carries out ears characteristic region detection to ROIF, when detecting that ears are special
When levying data area, this area pixel information is saved as ears region rectangle data structure;
Described license camera carries out nose characteristic region detection to ROIN, when detecting that nose is special
When levying data area, this area pixel information is saved as nasal area rectangle data structure, with nose
The base of region rectangle data structure is as the top margin of new ROI region, to facial contour feature data
Region takes nose region below, is set to face target ROI region, is designated as ROIM;
Described license camera carries out face characteristic region detection to ROIM, when detecting that face is special
When levying data area, this area pixel information is saved as face region rectangle data structure;
The described license camera region to ROIB, cuts out the region removing ROIF, obtains trunk profile special
Levy data area ROIMB, this area pixel information is saved as trunk contour area rectangle data knot
Structure;
Described license camera carries out rim detection to ROIF, obtains the letter in contouring head regional extent
The line segment of number break edge, then carries out head convex closure contour detecting to this head edge line segment result,
The coordinate of the key point obtained by head convex closure contour detecting saves as contouring head array;
Described license camera carries out rim detection to ROIMB, in the range of obtaining trunk contour area
The line segment at sign mutation edge, then carries out trunk convex closure contour detecting to this trunk edge line segment result,
The coordinate of the key point obtained by trunk convex closure contour detecting saves as trunk profile array;
Contouring head array and trunk number of contours group are combined by described license camera, form portrait
Profile array.
14. a kind of anti-tamper certificate photograph image pickup methods according to claim 12, its feature
Be: license camera judge intelligent terminal sensing data, the portrait characteristic of preview frame image,
Whether brightness data, definition data and chromaticity distortion data meet legal certificate photograph relevant criterion is wanted
Ask, specifically include:
During portrait posture detection is detected by described license camera with shooting environmental, all detection purposes are relevant
Data and preset value compare one by one, satisfactory detection project, then by detection, do not meet
The detection project required, then carry out sound/character/graphical cues, and real-time reminding user carries out shooting and adjusts
Whole;Wherein, described preset value is the preferred values meeting certificate photograph shooting standard-required through checking,
The detection project of described portrait posture detection include face whether visible, whether face size position meets,
Portrait distance is the most suitable, whether face rectifies and whether shoulder flushes, and described shooting environmental is examined
The detection project surveyed includes that intelligent terminal is the most vertical, whether intelligent terminal is shaken, brightness is the most uniform
Abundance, image are the most clear, whether colourity has deviation;
When there is undesirable detection project, shooting push button is set to not by described license camera
Can screening-mode, when all of detection project all meets the requirements, described license camera is by shooting push button
Being set to can screening-mode.
15. a kind of anti-tamper certificate photograph image pickup methods according to claim 12, its feature
It is: described license camera is according to government's public security professional standard to license artwork or license preview graph item by item
Carry out shooting quality assessment, and provide suggestion according to comprehensive grading result, specifically include:
Described license camera obtains the file attribute information of photo;Portrait is carried out special by photo gray-scale map
Levy identification and extract portrait characteristic information;Obtain background by edge detecting technology, image Segmentation Technology to believe
Breath;Monochrome information is obtained by photo gray-scale map;By equal in Lab color space system of photo
Variance yields obtains chrominance information;Sharpness information is obtained by the gray-scale map matrix of photo;
Described license camera according to the file attribute information obtained, portrait characteristic information, background information,
Dimensions is marked by monochrome information, chrominance information, sharpness information item by item, obtains each and comments
The score value of fractional dimension;
Described license camera is according to the score value of each dimensions, and scoring weight, calculates bat
The quality overall score of the photo taken the photograph;The shooting suggestion of specialty is given according to overall score;
When photo composite score is less than preset value, then the relevant criterion being unsatisfactory for legal certificate photograph is wanted
Ask, described license camera suggestion user re-shoot, until shoot meet legal certificate photograph be correlated with
Till the photo of standard-required.
16. a kind of anti-tamper certificate photograph image pickup methods according to claim 11, its feature
It is: described method also includes:
The operand of the license camera user end of the described license camera access service all accesses of end record
According to;
The operation data of described license camera access service end monitoring license camera user end, different when occurring
Often operation behavior, then carry out forbidding or sending alarm.
17. a kind of anti-tamper certificate photograph image pickup methods according to claim 11, its feature
It is: described method also includes:
Described license cloud storage end verification camera arranges mandate access module;
Described license cloud storage end is the memory space that the distribution of each license camera client is independent;
Described license cloud storage end forbids that the certificate photograph of license cloud storage end is entered by the user of license camera
Row amendment operation, only allows user submitted to by license camera or delete license photograph.
18. a kind of anti-tamper certificate photograph image pickup methods according to claim 17, its feature
It is: described license cloud storage end verification camera arranges mandate access module, specifically includes:
Described license cloud storage end sets up an APP unique sequence numbers database, and preservation is authorized to
APP unique sequence numbers;
When the user agent developer of license camera is arrived to license cloud storage end application by exploitation code
After APP unique sequence numbers, described license cloud storage end passes through callback interface, distributes to license camera one
Individual access token, and arrange the time limit of losing efficacy.
19. a kind of anti-tamper certificate photograph image pickup methods according to claim 11, its feature
It is: described method also includes:
Described certificate photograph intelligent cloud processing system resolves the certificate photo that license camera access service end sends
Sheet processes required parameter;
After resolving certificate photograph process required parameter, described certificate photograph intelligent cloud processing system is to card
License artwork is extracted according to cloud storage end;
The authenticity of described certificate photograph intelligent cloud processing system checking license artwork, particularly as follows:
License artwork is carried out watermark extracting, and deciphers watermark information, use the watermark information certificate of inspection to shine
Whether artwork is passed through, the most then license artwork is not tampered with;If it is not, then license artwork is tampered
Cross;
Described certificate photograph intelligent cloud processing system completes license standard to the license artwork being not tampered with
The process of figure;
After license artwork has processed and obtains license standard drawing, described certificate photograph intelligent cloud processes system
The result completing to make by license standard drawing by license camera access service end of uniting feeds back to license phase
Machine.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510548572.8A CN105141842B (en) | 2015-08-31 | 2015-08-31 | A kind of anti-tamper license camera system and method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201510548572.8A CN105141842B (en) | 2015-08-31 | 2015-08-31 | A kind of anti-tamper license camera system and method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN105141842A CN105141842A (en) | 2015-12-09 |
CN105141842B true CN105141842B (en) | 2016-09-07 |
Family
ID=54727040
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201510548572.8A Active CN105141842B (en) | 2015-08-31 | 2015-08-31 | A kind of anti-tamper license camera system and method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN105141842B (en) |
Families Citing this family (14)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105915791B (en) * | 2016-05-03 | 2019-02-05 | Oppo广东移动通信有限公司 | Electronic apparatus control method and device, electronic device |
CN108093165A (en) * | 2016-11-23 | 2018-05-29 | 中兴通讯股份有限公司 | A kind of image processing method and device |
CN107690049A (en) * | 2017-02-20 | 2018-02-13 | 深圳红瓜子文化传媒科技有限公司 | The preparation method and system of panoramic pictures |
CN107451947A (en) * | 2017-08-03 | 2017-12-08 | 武汉远众科技有限公司 | A kind of enhancing evidence collection method based on picture watermark |
CN107632797B (en) * | 2017-08-14 | 2021-09-07 | 深圳百步印社科技有限公司 | Self-service printing method and device |
CN108269233B (en) * | 2018-03-15 | 2021-07-27 | 福州大学 | Text dithering method based on shading halftone |
CN108805001B (en) * | 2018-04-09 | 2019-12-24 | 平安科技(深圳)有限公司 | Electronic device, identity recognition method based on certificate picture and storage medium |
CN108848301A (en) * | 2018-05-23 | 2018-11-20 | 阿里巴巴集团控股有限公司 | A kind of bill shooting exchange method, device, processing equipment and client |
CN109636648A (en) * | 2018-12-13 | 2019-04-16 | 平安医疗健康管理股份有限公司 | Social security violation detection method, device, equipment and computer storage medium |
CN110992419B (en) * | 2019-10-13 | 2020-12-15 | 湛江市金蝶管理软件有限公司 | Target big data occupied area detection platform and method |
CN112199250A (en) * | 2020-09-15 | 2021-01-08 | 北京达佳互联信息技术有限公司 | Picture monitoring method and device, electronic equipment and storage medium |
CN114422652B (en) * | 2022-03-28 | 2022-06-03 | 北京中科飞鸿科技股份有限公司 | Large-angle imaging reconnaissance system |
CN115187222B (en) * | 2022-09-07 | 2023-04-07 | 艾斯特国际安全技术(深圳)有限公司 | Certificate acquisition control method, device and system and storage medium |
CN116074618B (en) * | 2023-03-31 | 2023-07-25 | 广州翼拍联盟网络技术有限公司 | Intelligent photographing service method, system and storage medium for preventing portrait information leakage |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7663670B1 (en) * | 2001-02-09 | 2010-02-16 | Digital Imaging Systems Gmbh | Methods and systems for embedding camera information in images |
CN102663668A (en) * | 2012-04-06 | 2012-09-12 | 王涛 | Digital watermarking system based on continuous vector graphics and implementation method of digital watermarking system based on continuous vector graphics |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2003046758A (en) * | 2001-07-31 | 2003-02-14 | Canon Inc | Imaging apparatus, information processing unit, image processing unit and method therefor, and image processing system |
US7120273B2 (en) * | 2002-05-31 | 2006-10-10 | Hewlett-Packard Development Company, Lp. | Apparatus and method for image group integrity protection |
WO2006064171A1 (en) * | 2004-12-14 | 2006-06-22 | Symbian Software Limited | A method of recording an image with a mobile phone |
US8842875B2 (en) * | 2011-05-26 | 2014-09-23 | Digimarc Corporation | Image related methods and systems |
-
2015
- 2015-08-31 CN CN201510548572.8A patent/CN105141842B/en active Active
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7663670B1 (en) * | 2001-02-09 | 2010-02-16 | Digital Imaging Systems Gmbh | Methods and systems for embedding camera information in images |
CN102663668A (en) * | 2012-04-06 | 2012-09-12 | 王涛 | Digital watermarking system based on continuous vector graphics and implementation method of digital watermarking system based on continuous vector graphics |
Also Published As
Publication number | Publication date |
---|---|
CN105141842A (en) | 2015-12-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN105141842B (en) | A kind of anti-tamper license camera system and method | |
CN105120167B (en) | A kind of license camera and license image pickup method | |
CN110889320B (en) | Periocular face recognition switching | |
US11256792B2 (en) | Method and apparatus for creation and use of digital identification | |
CN109325327B (en) | Process for updating templates used in face recognition | |
US10210343B2 (en) | Systems and methods for sharing verified identity documents | |
US20210034864A1 (en) | Iris liveness detection for mobile devices | |
WO2023064601A1 (en) | Method and system to autonomously authenticate and validate users using a node server and database | |
ES2858553T3 (en) | Systems and methods for electronically sharing private documents using pointers | |
EP0674295B1 (en) | System for verifying the identity | |
CN110555359B (en) | Automatic retry of facial recognition | |
JP4406547B2 (en) | ID card creation device, ID card, face authentication terminal device, face authentication device and system | |
CN110326001A (en) | The system and method for executing the user authentication based on fingerprint using the image captured using mobile device | |
US10403076B2 (en) | Method for securing and verifying a document | |
KR101810190B1 (en) | User authentication method and apparatus using face identification | |
JP2021517303A (en) | Remote user identity verification with threshold-based matching | |
CN107609364B (en) | User identity confirmation method and device | |
US20230041573A1 (en) | Image processing method and apparatus, computer device and storage medium | |
CN109492555A (en) | Newborn identity identifying method, electronic device and computer readable storage medium | |
CN114511915B (en) | Trusted certificate photo acquisition system and method based on mobile client | |
CA3149808C (en) | Method and apparatus for creation and use of digital identification | |
CN116074618B (en) | Intelligent photographing service method, system and storage medium for preventing portrait information leakage | |
WO2022222957A1 (en) | Method and system for identifying target | |
CN107491759A (en) | A kind of mixed mode register method and device | |
CN115114557B (en) | Page data acquisition method and device based on block chain |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |