CN104715478B  The method and system of exposure area in a kind of detection image picture  Google Patents
The method and system of exposure area in a kind of detection image picture Download PDFInfo
 Publication number
 CN104715478B CN104715478B CN201510098065.9A CN201510098065A CN104715478B CN 104715478 B CN104715478 B CN 104715478B CN 201510098065 A CN201510098065 A CN 201510098065A CN 104715478 B CN104715478 B CN 104715478B
 Authority
 CN
 China
 Prior art keywords
 row
 standard deviation
 gradient
 image picture
 obtained
 Prior art date
Links
 230000000694 effects Effects 0.000 description 5
 238000000034 methods Methods 0.000 description 1
Abstract
Description
Technical field
The present invention relates to image field, more particularly to a kind of method and system for detecting exposure area in image picture.
Background technology
During DR image collections, because improper, DR that the bat breath dosage that the experience level of doctor is selected is chosen are set The stability of standby hardware, difference of different film making patient density etc., the original image for causing to collect have apparent bright Difference is spent, if now post processing of image process is from identical parameters, the image of post processing cannot ensure brightness and contrast Effect, details and luminance proportion can not show well, and the diagnosis to doctor has a great impact.It is so adaptive The available grayscale information of analysis original image be very important, and analyze the available grayscale information of original image, human body group The detection for knitting (skin, muscle and bone portion) region is necessary, and tissue region detection is accurate in exposure area Carried out on the basis of detection.On the other hand, doctor can also cut after image is got to image, general Crop Area Domain can all elect exposure area as.
Therefore, it is necessary to it is a kind of can in quick detection image picture exposure area method, and then improve operating efficiency.
The content of the invention
The technical problems to be solved by the invention are：A kind of method of exposure area in detection image picture is provided and is System, being capable of the exposure area that goes out in image picture of quick detection.
In order to solve the abovementioned technical problem, the technical solution adopted by the present invention is：
The method of exposure area, comprises the following steps in a kind of detection image picture：
S100, obtain image picture to be detected；
S200, image picture obtained by step S100 is subjected to image scaling processing；
S300, marginal analysis is carried out to image picture obtained by step S200；
The marginal analysis includes step S301 to S305, specific as follows：
S301, image picture calculates row standard deviation and row standard deviation according to obtained by step S200；
S302, the row standard deviation according to obtained by step S301 calculate and obtain row gradient, the row standard deviation meter according to obtained by step S301 Calculate and obtain row gradient；
S303, the row gradient calculation according to obtained by step S302 obtain the weight coefficient array of row standard deviation gradient；According to step Row gradient calculation obtained by S302 obtains the weight coefficient array of row standard deviation gradient；
S304, the weight coefficient array meter of row gradient and step S303 gained row standard deviation gradients according to obtained by step S302 Calculate and obtain row standard deviation gradient weighting array；According to adding for row standard deviation gradient obtained by step S302 gained row gradients and step S303 Weight coefficient array, which calculates, obtains row standard deviation gradient weighting array；
S305, row standard deviation gradient weighting array and row standard deviation gradient weighting array determine just according to obtained by step S304 Initial line circle；
S400, row bound amendment is entered to image picture obtained by step S305；
S500, revised border obtained by step S400 as the exposure area of image picture, obtained into the striograph The exposure area scope of piece.
Another technical scheme that the present invention uses for：
The system of exposure area in a kind of detection image picture, including：Acquisition module, scaling processing module, marginal analysis Module, border correcting module and exposure area module；
The acquisition module, for obtaining image picture to be detected；
The scaling processing module, for image picture obtained by acquisition module to be carried out into image scaling processing；
The marginal analysis module includes the first computing unit, the second computing unit, the 3rd computing unit, the 4th calculating list Member and determining unit；
First computing unit, for calculating row standard deviation and row standard deviation according to gained image picture；
Second computing unit, calculated for the row standard deviation according to obtained by the first computing unit and obtain row gradient, according to step Row standard deviation obtained by rapid first computing unit, which calculates, obtains row gradient；
3rd computing unit, adding for row standard deviation gradient is obtained for the row gradient calculation according to obtained by the second computing unit Weight coefficient array；The row gradient calculation according to obtained by the second computing unit obtains the weight coefficient array of row standard deviation gradient；
4th computing unit, for calculating the weighting of standard deviation gradient to image picture obtained by the 3rd computing unit；Root Calculate capable according to the weight coefficient array of row standard deviation gradient obtained by row gradient obtained by the second computing unit and the 3rd computing unit Standard deviation gradient weights array；According to row standard deviation gradient obtained by the second computing unit gained row gradient and the 3rd computing unit Weight coefficient array, which calculates, obtains row standard deviation gradient weighting array；
The determining unit, for the row standard deviation gradient weighting array according to obtained by the 4th computing unit and row standard deviation ladder Degree weighting array determines initial boundary；
The border correcting module, for entering row bound amendment to image picture obtained by determining unit；
The exposure area module, for using revised border obtained by the correcting module of border as the exposure of image picture Region, obtain the exposure area scope of the image picture.
The beneficial effects of the present invention are：By the row standard deviation and row standard deviation of the image picture for calculating acquisition respectively, Row gradient corresponding to row gradient corresponding to the row standard deviation and the row standard deviation is calculated again, further according to row gradient calculation Obtain the weight coefficient array of row standard deviation gradient, row gradient calculation obtains the weight coefficient array of row standard deviation gradient, by row gradient Be multiplied by row standard deviation gradient weight coefficient array calculate obtain row standard deviation gradient weighting array and by row gradient be multiplied by row mark The weight coefficient array of accurate poor gradient, which calculates, obtains row standard deviation gradient weighting array, and array is weighted finally by row standard deviation gradient Coboundary, lower boundary, left margin and right margin are determined with row standard deviation gradient weighting array, so that it is determined that the image picture Final exposure area, being capable of the exposure area that goes out in image picture of quick detection by method and system provided by the invention.
Brief description of the drawings
Fig. 1 be the specific embodiment of the invention detection image picture in exposure area method step flow chart；
Fig. 2 be the specific embodiment of the invention detection image picture in exposure area system structural representation；
Fig. 3 is weight coefficient array schematic diagram in specific embodiment of the invention embodiment 1；
Label declaration：
10th, acquisition module；20th, processing module is scaled；30th, marginal analysis module；40th, border correcting module；50th, exposure region Domain module；301st, the first computing unit；302nd, the second computing unit；303rd, the 3rd computing unit；304th, the 4th computing unit； 305th, determining unit.
Embodiment
To describe the technology contents of the present invention, the objects and the effects in detail, below in conjunction with embodiment and coordinate attached Figure is explained.
The design of most critical of the present invention is：By 4 borders up and down for the effective coverage for determining image picture, from And determine the exposure area of image.
Fig. 1 is refer to, to be flowed in the detection image picture of the specific embodiment of the invention the step of method of exposure area Cheng Tu, it is specific as follows：
The method of exposure area, comprises the following steps in a kind of detection image picture：
S100, obtain image picture to be detected；
S200, image picture obtained by step S100 is subjected to image scaling processing；
S300, marginal analysis is carried out to image picture obtained by step S200；
The marginal analysis includes step S301 to S305, specific as follows：
S301, image picture calculates row standard deviation and row standard deviation according to obtained by step S200；
S302, the row standard deviation according to obtained by step S301 calculate and obtain row gradient, the row standard deviation meter according to obtained by step S301 Calculate and obtain row gradient；
S303, the row gradient calculation according to obtained by step S302 obtain the weight coefficient array of row standard deviation gradient；According to step Row gradient calculation obtained by S302 obtains the weight coefficient array of row standard deviation gradient；
S304, the weight coefficient array meter of row gradient and step S303 gained row standard deviation gradients according to obtained by step S302 Calculate and obtain row standard deviation gradient weighting array；According to adding for row standard deviation gradient obtained by step S302 gained row gradients and step S303 Weight coefficient array, which calculates, obtains row standard deviation gradient weighting array；
S305, row standard deviation gradient weighting array and row standard deviation gradient weighting array determine just according to obtained by step S304 Initial line circle；
S400, row bound amendment is entered to image picture obtained by step S305；
S500, revised border obtained by step S400 as the exposure area of image picture, obtained into the striograph The exposure area scope of piece.
It was found from foregoing description, the beneficial effects of the present invention are：By the rower for the image picture for calculating acquisition respectively Quasi difference and row standard deviation, then row gradient corresponding to row gradient corresponding to the row standard deviation and the row standard deviation is calculated, The weight coefficient array of row standard deviation gradient is obtained further according to row gradient calculation, row gradient calculation obtains the weighting system of row standard deviation gradient Number arrays, by row gradient be multiplied by row standard deviation gradient weight coefficient array calculate obtain row standard deviation gradient weighting array and will The weight coefficient array that row gradient is multiplied by row standard deviation gradient calculates and obtains row standard deviation gradient weighting array, accurate finally by rower Poor gradient weighting array and row standard deviation gradient weighting array determine coboundary, lower boundary, left margin and right margin, so as to really The final exposure area of the fixed image picture, by method provided by the invention, can quick detection go out in image picture Exposure area.
Further, described image scaling, which is handled, is specially：The gray value of gained image picture is extracted every row according to interlacing, Obtain the image picture after image scaling processing.
Further, the step S301 is specifically included：According to the gray value of gained image picture, image picture water is calculated Flat often capable standard deviation, calculate the standard deviation of the vertical each column of image picture.
Further, the step S302 is specifically included：The standard that the image picture level according to obtained by step S301 is often gone Difference, calculated level standard deviation gradient array, the standard deviation of the vertical each column of the image picture according to obtained by step S301, calculate vertical mark Accurate poor gradient array.
Further, the step S304 is specially：Each row gradient is multiplied by the row standard deviation gradient of correspondence position Weight coefficient obtains row standard deviation gradient weighting array；Each row gradient is multiplied by the weighting system of the row standard deviation gradient of correspondence position It is several to obtain row standard deviation gradient weighting array.
Further, the step S305 is specially：
Maximum in array is weighted by row standard deviation gradient, determines the left margin of initial boundary；Pass through row standard deviation Maximum in gradient weighting array, determine the coboundary of initial boundary；
Minimum value in array is weighted by row standard deviation gradient, determines the right margin of initial boundary；Pass through row standard deviation Minimum value in gradient weighting array, determine the lower boundary of initial boundary.
Further, the step S400 also includes：Judge that whether initial boundary is in default invalid border obtained by S305 In the range of, if not in the range of default invalid border, into step S500；If in the range of default invalid border, The second maximum or the second minimum value are obtained as revised ultimate bound.
Further, the step S400 also includes：Judge whether the second maximum is more than the first maximum preset multiple, If so, then using second maximum as revised ultimate bound；Judge whether the second minimum value is less than the first minimum value Preset multiple, if so, then using second minimum value as revised ultimate bound；The preset multiple scope arrives for 0.5 0.7；The optimal value of the preset multiple is 0.6.
Seen from the above description, by test of many times as shown by data, when A values are in the range of 0.5 to 0.7, detection knot The accuracy of fruit is up to more than 90%, and when A value is 0.6, the accuracy of testing result can reach 98%.
Further, the step S500 is specially：Coboundary, lower boundary, left margin and the right side are obtained according to step S400 Border, forms rectangular area, and the scope of the rectangular area is the scope of exposure area.
Referring to Fig. 2, the structure for the system of exposure area in the detection image picture of the specific embodiment of the invention is shown It is intended to, it is specific as follows：
The system of exposure area in a kind of detection image picture, including：Acquisition module 10, scaling processing module 20, border Analysis module 30, border correcting module 40 and exposure area module 50；
The acquisition module 10, for obtaining image picture to be detected；
The scaling processing module 20, for the gained image picture of acquisition module 10 to be carried out into image scaling processing；
The marginal analysis module 30 includes the first computing unit 301, the second computing unit 302, the 3rd computing unit 303rd, the 4th computing unit 304 and determining unit 305；
First computing unit 301, for calculating row standard deviation and row standard deviation according to gained image picture；
Second computing unit 302, row gradient is obtained for being calculated according to the gained row standard deviation of the first computing unit 301, Calculated according to the gained row standard deviation of step the first computing unit 301 and obtain row gradient；
3rd computing unit 303, for obtaining row standard deviation ladder according to the gained row gradient calculation of the second computing unit 302 The weight coefficient array of degree；The weight coefficient number of row standard deviation gradient is obtained according to the gained row gradient calculation of the second computing unit 302 Group；
4th computing unit 304, add for calculating standard deviation gradient to the gained image picture of the 3rd computing unit 303 Power；According to the weight coefficient number of the gained row gradient of the second computing unit 302 and the gained row standard deviation gradient of the 3rd computing unit 303 Group, which calculates, obtains row standard deviation gradient weighting array；According to the gained row gradient of the second computing unit 302 and the institute of the 3rd computing unit 303 Obtain row standard deviation gradient weight coefficient array calculate obtain row standard deviation gradient weighting array；
The determining unit 305, for weighting array and row mark according to the gained row standard deviation gradient of the 4th computing unit 304 Accurate poor gradient weighting array determines initial boundary；
The border correcting module 40, for entering row bound amendment to the gained image picture of determining unit 305；
The exposure area module 50, for using the revised border of the gained of border correcting module 40 as image picture Exposure area, obtain the exposure area scope of the image picture.
It was found from foregoing description, the beneficial effects of the present invention are：By the rower for the image picture for calculating acquisition respectively Quasi difference and row standard deviation, then row gradient corresponding to row gradient corresponding to the row standard deviation and the row standard deviation is calculated, The weight coefficient array of row standard deviation gradient is obtained further according to row gradient calculation, row gradient calculation obtains the weighting system of row standard deviation gradient Number arrays, by row gradient be multiplied by row standard deviation gradient weight coefficient array calculate obtain row standard deviation gradient weighting array and will The weight coefficient array that row gradient is multiplied by row standard deviation gradient calculates and obtains row standard deviation gradient weighting array, accurate finally by rower Poor gradient weighting array and row standard deviation gradient weighting array determine coboundary, lower boundary, left margin and right margin, so as to really The final exposure area of the fixed image picture, by system provided by the invention, can quick detection go out in image picture Exposure area.
Embodiment 1
A kind of method for detecting exposure area in image picture provided by the invention, it is specific as follows：
S100, obtain image picture to be detected；
S200, image picture obtained by step S100 is subjected to image scaling processing；Described image scaling is handled：Press The gray value of gained image picture is extracted every row according to interlacing, obtains the image picture after image scaling processing；
S300, marginal analysis is carried out to image picture obtained by step S200；
The marginal analysis includes step S301 to S305, specific as follows：
S301, image picture calculates row standard deviation and row standard deviation according to obtained by step S200；
The step for processing mode be：According to the gray value of gained image picture, calculate what image picture level was often gone Standard deviation, calculate the standard deviation of the vertical each column of image picture.
S302, the row standard deviation according to obtained by step S301 calculate and obtain row gradient, the row standard deviation meter according to obtained by step S301 Calculate and obtain row gradient；
The step for processing mode be：The standard deviation that the image picture level according to obtained by step S301 is often gone, calculate water Flat standard deviation gradient array, the standard deviation of the vertical each column of the image picture according to obtained by step S301, calculates vertical standard deviation gradient Array.
S303, the row gradient calculation according to obtained by step S302 obtain the weight coefficient array of row standard deviation gradient；According to step Row gradient calculation obtained by S302 obtains the weight coefficient array of row standard deviation gradient.
Due to edge, some is invalid border region to DR detectors, horizontal, vertical direction invalid border size point Yong not invalidBorderH, invalidBorderV.The weight coefficient array of horizontal, vertical standard deviation gradient is used respectively HWeight, vWeight are represented.RszHeight is the height of image after scaling, and rszWidth is the width of image after scaling.HA is water The slope of flat weighted direction oblique line, hB offset to be corresponding, and vA is the slope that vertical direction weights oblique line, and vB offsets to be corresponding, and x is Row coordinate or row coordinate.
Wherein hA, hB, vA, vB are calculated with below equation：
From figure 3, it can be seen that weighted value is since border, it is 1 just to start one section, and middle one section is by 1 linear decrease To 0, end up one section of weight coefficient all 0.Such as weight coefficient is：1、1、0.8、0.6、0.4、0.2、0.0、0、0、0、0.
S304, the weight coefficient array meter of row gradient and step S303 gained row standard deviation gradients according to obtained by step S302 Calculate and obtain row standard deviation gradient weighting array；According to adding for row standard deviation gradient obtained by step S302 gained row gradients and step S303 Weight coefficient array, which calculates, obtains row standard deviation gradient weighting array.
Abovementioned steps S304 is specially：Corresponding weight coefficient is multiplied by each Grad.1st Grad is multiplied by the 1st Individual weight coefficient, the 2nd Grad are multiplied by the 2nd weight coefficient, the like, Grad array and weight coefficient numerical value length It is equally long.
The weight coefficient for the row standard deviation gradient that each row gradient is multiplied by correspondence position obtains row standard deviation gradient weighting array； The weight coefficient for the row standard deviation gradient that each row gradient is multiplied by correspondence position obtains row standard deviation gradient weighting array；
S305, row standard deviation gradient weighting array and row standard deviation gradient weighting array determine just according to obtained by step S304 Initial line circle；
The position of maximum in row standard deviation gradient weighting array is the coboundary of initial boundary；Row standard deviation gradient adds The position of maximum in flexible strategy group is the left margin of initial boundary；
The position of minimum value in row standard deviation gradient weighting array is the lower boundary of initial boundary；Row standard deviation gradient adds The position of minimum value in flexible strategy group is the right margin of initial boundary；
S400, row bound amendment is entered to image picture obtained by step S305；
If not in the range of invalid border, it is not necessary to correct；
If the first maximum of left margin or coboundary in the range of invalid border, looks for left margin or coboundary respectively Second maximum, if the second maximum is more than A times of the first maximum, by the use of the position of the second maximum as revised Final left margin or coboundary.If the first minimum value of right margin or lower boundary in the range of invalid border, looks for the right respectively Boundary or the second minimum value of lower boundary, if the second minimum value is less than A times of the first minimum value, with the position of the second minimum value As revised final right margin or lower boundary.
A is the value between 0.5 to 0.7；A optimal value is 0.6；
By test of many times as shown by data, when A values are in the range of 0.5 to 0.7, the accuracy of testing result is up to 90% More than, when A value is 0.6, the accuracy of testing result can reach 98%.
S500, revised border obtained by step S400 as the exposure area of image picture, obtained into the striograph The exposure area scope of piece.
By 4 ultimate bounds up and down of determination, so that it is determined that the scope of exposure area.
In summary, a kind of method and system for detecting exposure area in image picture provided by the invention.Pass through difference The row standard deviation and row standard deviation of the image picture obtained are calculated, then calculates row gradient and institute corresponding to the row standard deviation Row gradient corresponding to row standard deviation is stated, weight coefficient array, the row gradiometer of row standard deviation gradient are obtained further according to row gradient calculation The weight coefficient array for obtaining row standard deviation gradient is calculated, the weight coefficient array that row gradient is multiplied by row standard deviation gradient calculates capable Standard deviation gradient weight array and by row gradient be multiplied by row standard deviation gradient weight coefficient array calculate obtain row standard deviation ladder Degree weighting array, array is weighted finally by row standard deviation gradient and row standard deviation gradient weighting array determines coboundary, following Boundary, left margin and right margin, so that it is determined that the final exposure area of the image picture, by method provided by the invention and System, being capable of the exposure area that goes out in image picture of quick detection.
Embodiments of the invention are the foregoing is only, are not intended to limit the scope of the invention, it is every to utilize this hair The equivalents that bright specification and accompanying drawing content are made, or the technical field of correlation is directly or indirectly used in, similarly include In the scope of patent protection of the present invention.
Claims (10)
 A kind of 1. method for detecting exposure area in image picture, it is characterised in that comprise the following steps：S100, obtain image picture to be detected；S200, image picture obtained by step S100 is subjected to image scaling processing；S300, marginal analysis is carried out to image picture obtained by step S200；The marginal analysis includes step S301 to S305, specific as follows：S301, image picture calculates row standard deviation and row standard deviation according to obtained by step S200；S302, the row standard deviation according to obtained by step S301 calculate and obtain row gradient, and the row standard deviation according to obtained by step S301 calculates Row gradient；S303, the row gradient calculation according to obtained by step S302 obtain the weight coefficient array of row standard deviation gradient；According to step S302 Gained row gradient calculation obtains the weight coefficient array of row standard deviation gradient；S304, the weight coefficient array of row gradient and step S303 gained row standard deviation gradients calculates according to obtained by step S302 Row standard deviation gradient weights array；The weighting system of row gradient and step S303 gained row standard deviation gradients according to obtained by step S302 Number array, which calculates, obtains row standard deviation gradient weighting array；S305, row standard deviation gradient weighting array and row standard deviation gradient weighting array determine initial edge according to obtained by step S304 Boundary；S400, row bound amendment is entered to image picture obtained by step S305；S500, revised border obtained by step S400 as the exposure area of image picture, obtained into the image picture Exposure area scope；Wherein, the step S400 also includes：Judge that initial boundary is whether in the range of default invalid border obtained by S305, if Not in the range of default invalid border, then into step S500；If in the range of default invalid border, second is obtained most Big value or the second minimum value are as revised ultimate bound.
 2. the method for exposure area in detection image picture according to claim 1, it is characterised in that described image scales Processing is specially：The gray value of gained image picture is extracted every row according to interlacing, obtains the image picture after image scaling processing.
 3. the method for exposure area in detection image picture according to claim 1, it is characterised in that the step S301 Specifically include：According to the gray value of gained image picture, the standard deviation that image picture level is often gone is calculated, image picture is calculated and hangs down The standard deviation of straight each column.
 4. the method for exposure area in detection image picture according to claim 3, it is characterised in that the step S302 Specifically include：The standard deviation that the image picture level according to obtained by step S301 is often gone, calculated level standard deviation gradient array, according to The standard deviation of the vertical each column of image picture obtained by step S301, calculates vertical standard deviation gradient array.
 5. the method for exposure area in detection image picture according to claim 1, it is characterised in that the step S304 Specially：The weight coefficient that each row gradient is multiplied by the row standard deviation gradient of correspondence position obtains row standard deviation gradient weighted number Group；The weight coefficient that each row gradient is multiplied by the row standard deviation gradient of correspondence position obtains row standard deviation gradient weighting array.
 6. the method for exposure area in detection image picture according to claim 1, it is characterised in that the step S305 Specially：Maximum in array is weighted by row standard deviation gradient, determines the left margin of initial boundary；Pass through row standard deviation gradient The maximum in array is weighted, determines the coboundary of initial boundary；Minimum value in array is weighted by row standard deviation gradient, determines the right margin of initial boundary；Pass through row standard deviation gradient The minimum value in array is weighted, determines the lower boundary of initial boundary.
 7. the method for exposure area in detection image picture according to claim 6, it is characterised in that the step S400 Also include：Judge whether the second maximum is more than the first maximum preset multiple, if so, then using second maximum as repairing Ultimate bound after just；Judge whether the second minimum value is less than the first minimum value preset multiple, if so, then minimum by described second Value is used as revised ultimate bound；The preset multiple scope is 0.5 to 0.7.
 8. the method for exposure area in detection image picture according to claim 7, it is characterised in that the preset multiple For 0.6.
 9. the method for exposure area in detection image picture according to claim 1, it is characterised in that the step S500 Specially：Coboundary, lower boundary, left margin and right margin are obtained according to step S400, form rectangular area, the rectangular area Scope be exposure area scope.
 A kind of 10. system for detecting exposure area in image picture, it is characterised in that including：Acquisition module, scaling processing mould Block, marginal analysis module, border correcting module and exposure area module；The acquisition module, for obtaining image picture to be detected；The scaling processing module, for image picture obtained by acquisition module to be carried out into image scaling processing；The marginal analysis module include the first computing unit, the second computing unit, the 3rd computing unit, the 4th computing unit and Determining unit；First computing unit, for calculating row standard deviation and row standard deviation according to gained image picture；Second computing unit, calculated for the row standard deviation according to obtained by the first computing unit and obtain row gradient, according to step the Row standard deviation obtained by one computing unit, which calculates, obtains row gradient；3rd computing unit, the weighting system of row standard deviation gradient is obtained for the row gradient calculation according to obtained by the second computing unit Number array；The row gradient calculation according to obtained by the second computing unit obtains the weight coefficient array of row standard deviation gradient；4th computing unit, for calculating the weighting of standard deviation gradient to image picture obtained by the 3rd computing unit；According to The weight coefficient array of row standard deviation gradient obtained by row gradient obtained by two computing units and the 3rd computing unit calculates to obtain rower standard Poor gradient weights array；The weighting of row gradient and the 3rd computing unit gained row standard deviation gradient according to obtained by the second computing unit Coefficient array, which calculates, obtains row standard deviation gradient weighting array；The determining unit, add for row standard deviation gradient weighting array and row standard deviation gradient according to obtained by the 4th computing unit Flexible strategy group determines initial boundary；The border correcting module, for entering row bound amendment to image picture obtained by determining unit；The exposure area module, for using revised border obtained by the correcting module of border as the exposure region of image picture Domain, obtain the exposure area scope of the image picture；Wherein, the border correcting module enters row bound amendment to image picture obtained by determining unit and specifically included：Judge to determine Initial boundary determined by unit whether in the range of default invalid border, if not in the range of default invalid border, It need not be modified；If in the range of default invalid border, the second maximum or the second minimum value are obtained as amendment Ultimate bound afterwards.
Priority Applications (1)
Application Number  Priority Date  Filing Date  Title 

CN201510098065.9A CN104715478B (en)  20150305  20150305  The method and system of exposure area in a kind of detection image picture 
Applications Claiming Priority (1)
Application Number  Priority Date  Filing Date  Title 

CN201510098065.9A CN104715478B (en)  20150305  20150305  The method and system of exposure area in a kind of detection image picture 
Publications (2)
Publication Number  Publication Date 

CN104715478A CN104715478A (en)  20150617 
CN104715478B true CN104715478B (en)  20171229 
Family
ID=53414772
Family Applications (1)
Application Number  Title  Priority Date  Filing Date 

CN201510098065.9A CN104715478B (en)  20150305  20150305  The method and system of exposure area in a kind of detection image picture 
Country Status (1)
Country  Link 

CN (1)  CN104715478B (en) 
Families Citing this family (2)
Publication number  Priority date  Publication date  Assignee  Title 

CN107977973A (en) *  20161025  20180501  北京东软医疗设备有限公司  The method and device on beamdefining clipper irradiation field border in a kind of acquisition medical diagnostic images 
CN106651858A (en) *  20170111  20170510  洛阳师范学院  Method and system for detecting exposure area in image picture 
Citations (6)
Publication number  Priority date  Publication date  Assignee  Title 

CN101064011A (en) *  20060426  20071031  电子科技大学  Vehicle registration extract method in complicated background based on wavelet transforming 
CN101872425A (en) *  20100729  20101027  哈尔滨工业大学  Empirical mode decomposition based method for acquiring image characteristics and measuring corresponding physical parameters 
CN102460471A (en) *  20090619  20120516  美国医软科技公司  Systems for computer aided lung nodule detection in chest tomosynthesis imaging 
CN102693535A (en) *  20110324  20120926  深圳市蓝韵实业有限公司  Method for detecting light bunching device region in DR image 
CN103034857A (en) *  20121218  20130410  深圳市安健科技有限公司  Method and system of automatic detection of exposure area in image picture 
CN103208106A (en) *  20120116  20130717  上海西门子医疗器械有限公司  Method and device for detecting collimation side and Xray imaging device 
Family Cites Families (2)
Publication number  Priority date  Publication date  Assignee  Title 

US6577752B2 (en) *  20010615  20030610  Arch Development Corporation  Automated method and system for the delineation of the chest wall in computed tomography scans for the assessment of pleural disease 
US7433507B2 (en) *  20030703  20081007  Ge Medical Systems Global Technology Co.  Imaging chain for digital tomosynthesis on a flat panel detector 

2015
 20150305 CN CN201510098065.9A patent/CN104715478B/en active IP Right Grant
Patent Citations (6)
Publication number  Priority date  Publication date  Assignee  Title 

CN101064011A (en) *  20060426  20071031  电子科技大学  Vehicle registration extract method in complicated background based on wavelet transforming 
CN102460471A (en) *  20090619  20120516  美国医软科技公司  Systems for computer aided lung nodule detection in chest tomosynthesis imaging 
CN101872425A (en) *  20100729  20101027  哈尔滨工业大学  Empirical mode decomposition based method for acquiring image characteristics and measuring corresponding physical parameters 
CN102693535A (en) *  20110324  20120926  深圳市蓝韵实业有限公司  Method for detecting light bunching device region in DR image 
CN103208106A (en) *  20120116  20130717  上海西门子医疗器械有限公司  Method and device for detecting collimation side and Xray imaging device 
CN103034857A (en) *  20121218  20130410  深圳市安健科技有限公司  Method and system of automatic detection of exposure area in image picture 
Also Published As
Publication number  Publication date 

CN104715478A (en)  20150617 
Similar Documents
Publication  Publication Date  Title 

EP2738741B1 (en)  Apparatus and method for tracking contour of moving object, and apparatus of and method for analyzing myocardial motion  
US9153022B2 (en)  Method and system for analyzing craniofacial complex images  
CN103608845B (en)  Respiratory movement determines device  
EP1904971B1 (en)  Method and computer program for spatial compounding of images  
Bookstein  Size and shape spaces for landmark data in two dimensions  
EP2505162B1 (en)  Method and apparatus for generating medical image of body organ by using 3D model  
US5742700A (en)  Quantitative dental caries detection system and method  
CN104173054B (en)  Measuring method and measuring device for height of human body based on binocular vision technique  
KR20120028109A (en)  3d ultrasound system for 3d modeling of tissue and method for operating 3d ultrasound system  
CN103829965B (en)  The method and apparatus of CT scan is guided using marked body  
CN104867225B (en)  A kind of bank note towards recognition methods and device  
JP5191240B2 (en)  Scene change detection apparatus and scene change detection program  
US9314161B2 (en)  Moving object contour extraction apparatus, left ventricle image segmentation apparatus, moving object contour extraction method and left ventricle image segmentation method  
CN102136142B (en)  Nonrigid medical image registration method based on selfadapting triangular meshes  
Soliman et al.  Quantification of left ventricular volumes and function in patients with cardiomyopathies by realtime threedimensional echocardiography: a headtohead comparison between two different semiautomated endocardial border detection algorithms  
EP2210557A1 (en)  Determining energy expenditure of a user  
US8676298B2 (en)  Medical image alignment apparatus, method, and program  
JP5054669B2 (en)  Method and system for characterization of knee joint morphology  
US9123101B2 (en)  Automatic quantification of asymmetry  
EP2391271B1 (en)  System for providing lung ventilation information  
US20160106520A1 (en)  Determining a dental treatment difficulty  
US20070083384A1 (en)  Method and system for posture awareness training  
JP5334692B2 (en)  Method and system for detecting 3D anatomical objects using constrained marginal space learning  
US8218849B2 (en)  Method and system for automatic landmark detection using discriminative joint context  
US8712133B2 (en)  Cardiac chamber volume computation from contours and base plane in cardiac MR Cine images 
Legal Events
Date  Code  Title  Description 

C06  Publication  
PB01  Publication  
C10  Entry into substantive examination  
SE01  Entry into force of request for substantive examination  
COR  Change of bibliographic data  
CB02  Change of applicant information 
Address after: 518000, A, Hua Han Innovation Park, 16 Lang Shan Road, North hi tech Industrial Park, Guangdong, Shenzhen, 3A Applicant after: SHENZHEN ANGELL TECHNOLOGY CO., LTD. Address before: 518000, A, Hua Han Innovation Park, 16 Lang Shan Road, North hi tech Industrial Park, Guangdong, Shenzhen, 3A Applicant before: Shenzhen Angell Technology Co., Ltd. 

GR01  Patent grant  
GR01  Patent grant 