CN104240180B - A kind of method and device for realizing image adjust automatically - Google Patents
A kind of method and device for realizing image adjust automatically Download PDFInfo
- Publication number
- CN104240180B CN104240180B CN201410390739.8A CN201410390739A CN104240180B CN 104240180 B CN104240180 B CN 104240180B CN 201410390739 A CN201410390739 A CN 201410390739A CN 104240180 B CN104240180 B CN 104240180B
- Authority
- CN
- China
- Prior art keywords
- image
- adjusted
- target object
- scaling
- centric
- 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
Landscapes
- Image Analysis (AREA)
- Apparatus For Radiation Diagnosis (AREA)
Abstract
The invention discloses a kind of method and devices for realizing image adjust automatically, and for the adjust automatically to reconstruction image, this method includes：Image to be adjusted is obtained, identifies the target object in image to be adjusted；Determine the place-centric of target object and the square boundary of target object；Translating image to be adjusted makes the place-centric of target object be overlapped with the place-centric of output image；And/or the scaling of image to be adjusted is determined according to the square boundary length of side of target object and the length of side of output image, image to be adjusted is zoomed in and out according to scaling.
Description
Technical field
The present invention relates to technical field of image processing, and in particular to a kind of method and device for realizing image adjust automatically.
Background technology
Reconstruction figure can be obtained after being scanned using CT (computed tomography, Computed Tomography)
Picture, each CT scan may will produce tens width to the reconstruction image of hundreds of width.After scanning is completed to lay equal stress on and builds out image, due to
The factors such as scan vision range selects and target object is put will appear the case where image display area less than normal or deviation, for just
It then needs to be adjusted reconstruction image in observation.
In the prior art, operator can use the software tool that CT system provides to be grasped by triggering mouse-keyboard
Make, manually the individual images in whole image sequence or image sequence are carried out with the adjustment of spatial position.But scheme due to rebuilding
The quantity of picture is more, is manually adjusted to image complicated for operation, and speed is slower, to reduce the effect of reconstruction image output
Rate.
Invention content
In view of this, the present invention provides a kind of method and device for realizing image adjust automatically, to solve in the prior art
Complicated for operation, slow technical problem manually is adjusted to image.
To solve the above problems, technical solution provided by the invention is as follows：
A method of realizing image adjust automatically, the method includes：
Image to be adjusted is obtained, identifies the target object in the image to be adjusted；
Determine the place-centric of the target object and the square boundary of the target object；
Translating the image to be adjusted makes the place-centric of the target object be overlapped with the place-centric of output image；
And/or it waits adjusting according to described in the square boundary length of side of the target object and the length of side determination of the output image
The scaling of whole image zooms in and out the image to be adjusted according to the scaling.
Correspondingly, before the target object in identifying the image to be adjusted, the method further includes：
Eliminate the background object in the image to be adjusted.
Correspondingly, the target object in the identification image to be adjusted, including：
The computer tomography CT value of each pixel in the image to be adjusted is obtained, identifies the image to be adjusted
Described in CT values pixel within a preset range form target object.
Correspondingly, the target object in the identification image to be adjusted, including：
Matching template image is obtained, the matching template image and the image to be adjusted are subjected to similarity mode, it will
The part to match with the matching template image in the image to be adjusted is determined as target object.
Correspondingly, the place-centric of the determination target object and the square boundary of the target object, including：
The minimum rectangle for obtaining and including the target object is calculated, the boundary of the minimum rectangle is determined as the target
The square boundary of object；
The place-centric of the minimum rectangle is determined as to the place-centric of the target object.
Correspondingly, the place-centric of the determination target object and the square boundary of the target object, including：
The actual boundary that the target object is obtained using image gradient recognizer calculates pixel in the actual boundary
The average value of point coordinates, the place-centric as the target object；
The square boundary for obtaining and including the target object is calculated according to the place-centric of the target object.
Correspondingly, when the image to be adjusted includes several images to be adjusted, the method further includes：
The average value for calculating the place-centric of target object in each image to be adjusted, as the target object
Place-centric.
Correspondingly, when the image to be adjusted includes several images to be adjusted, the method further includes：
A scaling for meeting image scaling range is chosen in the scaling of each image to be adjusted
Scaling as the image to be adjusted.
A kind of device for realizing image adjust automatically, described device include：
Acquiring unit, for obtaining image to be adjusted；
Recognition unit, for identification target object in the image to be adjusted；
Determination unit, the square boundary of place-centric and the target object for determining the target object；
Translation unit, the position for making the place-centric and output image of the target object for translating the image to be adjusted
Set center coincidence；
And/or unit for scaling, it is used for the length of side of the square boundary length of side and the output image according to the target object
The scaling for determining the image to be adjusted zooms in and out the image to be adjusted according to the scaling.
Correspondingly, described device further includes：
Unit is eliminated, for eliminating the background object in the image to be adjusted.
Correspondingly, the recognition unit includes：
First obtains subelement, the computer tomography CT for obtaining each pixel in the image to be adjusted
Value；
Identify subelement, the pixel of CT values described in the image to be adjusted within a preset range forms mesh for identification
Mark object.
Correspondingly, the recognition unit includes：
Second obtains subelement, for obtaining matching template image；
Coupling subelement, for the matching template image and the image to be adjusted to be carried out similarity mode；
First determination subelement, the part for will match with the matching template image in the image to be adjusted are true
It is set to target object.
Correspondingly, the determination unit includes：
First computation subunit, for calculating the minimum rectangle for obtaining and including the target object, by the minimum rectangle
Boundary be determined as the square boundary of the target object；
Second determination subelement, for the place-centric of the minimum rectangle to be determined as in the position of the target object
The heart.
Correspondingly, the determination unit includes：
Second computation subunit, the actual boundary for obtaining the target object using image gradient recognizer, meter
The average value for calculating pixel point coordinates in the actual boundary, the place-centric as the target object；
Third computation subunit is obtained for being calculated according to the place-centric of the target object comprising the target object
Square boundary.
Correspondingly, when the image to be adjusted includes several images to be adjusted, the determination unit is additionally operable to：
The average value for calculating the place-centric of target object in each image to be adjusted, as the target object
Place-centric.
Correspondingly, when the image to be adjusted includes several images to be adjusted, the unit for scaling is additionally operable to：
A scaling for meeting image scaling range is chosen in the scaling of each image to be adjusted
Scaling as the image to be adjusted.
It can be seen that the embodiment of the present invention has the advantages that：
The embodiment of the present invention is by identifying target object included in image to be adjusted, by image translation to be adjusted to mesh
The center for marking object is overlapped with the center of output image, and/or according to the square boundary length of side and output image of target object
The length of side determines the scaling of image to be adjusted, is zoomed in and out to image to be adjusted, and the target object that needs are observed can be made to exist
It is shown with position with suitable size in output image, to realize the adjust automatically to image to be adjusted, can be subtracted
Few artificial operation for carrying out Image Adjusting, accelerates the speed of Image Adjusting, further increases the efficiency of reconstruction image output.
Description of the drawings
Fig. 1 is the flow chart of the embodiment of the method one of the realization image adjust automatically provided in the embodiment of the present invention；
Fig. 2 is the flow chart of the embodiment of the method two of the realization image adjust automatically provided in the embodiment of the present invention；
Fig. 3 is the schematic diagram of the device embodiment of the realization image adjust automatically provided in the embodiment of the present invention；
Fig. 4 is the schematic diagram of the recognition unit embodiment one provided in the embodiment of the present invention；
Fig. 5 is the schematic diagram of the recognition unit embodiment two provided in the embodiment of the present invention；
Fig. 6 is the schematic diagram of the determination unit embodiment one provided in the embodiment of the present invention；
Fig. 7 is the schematic diagram of the determination unit embodiment two provided in the embodiment of the present invention.
Specific implementation mode
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with the accompanying drawings and specific real
Mode is applied to be described in further detail the embodiment of the present invention.
The method and device of the realization image adjust automatically provided in the embodiment of the present invention is to be directed to need in the prior art
Position adjustment and scaling manually are carried out to CT reconstruction images, complicated for operation, slow technical problem proposes that automatic identification waits for
The target object in image (such as CT reconstruction images) is adjusted, obtains the place-centric of target object and including target object
Circumscribed square boundary, so as to which image to be adjusted is carried out the position that translation makes the place-centric and output image of target object
Center overlaps, and allows target object in the center display of output image, utilizes the square boundary length of side and the output of target object
The length of side of image determines the scaling of image to be adjusted, is zoomed in and out to image to be adjusted, makes target object with suitable size
It is shown, to realize to the adjust automatically of image to be adjusted, accelerates the speed of Image Adjusting, also improve reconstruction image
The efficiency of output.
Shown in Figure 1 based on above-mentioned thought, the method for the realization image adjust automatically provided in the embodiment of the present invention is real
Example one is applied, may comprise steps of：
Step 101：Image to be adjusted is obtained, identifies the target object in image to be adjusted.
Image to be adjusted can be CT reconstruction images, i.e., carry out image reconstruction, obtained reconstruction according to CT scan data
Image before output, needs to be adjusted, and the adjustment in the present embodiment is primarily referred to as the adjustment on image space positions, can be with
It include the adjustment to image size and position.It is understood that CT reconstruction images are a sequence image, including several figures
Picture, then image to be adjusted can be the piece image in image sequence, or entire sequence image, i.e., image to be adjusted can
Think single width image to be adjusted, or several images to be adjusted.
Single width image to be adjusted is adjusted, the visual effect of single image is preferable after adjustment, but if image sequence
Individual images in row are adjusted, and each width image center location and size may be inconsistent；And to several images to be adjusted
It is carried out at the same time adjustment, multiple image shares a place-centric, it is ensured that each width image relative position and in the same size, specifically
Which kind of, using adjustment modes, can be pre-set according to actual demand.
Include target object in each image to be adjusted, such as the organs such as heart, liver are scanned, then waits adjusting
The organ shown in whole image (CT reconstruction images) is target object, needs to identify each wait in embodiments of the present invention
The target object in image is adjusted, to determine the orientation of subsequent image adjust automatically.
It in some embodiments of the invention, can be with before the target object in identifying image to be adjusted：Elimination waits for
Adjust the background object in image.
After obtaining image to be adjusted, the background object in image to be adjusted is first removed, then identify in image to be adjusted
Target object, so that recognition result is more accurate.
In the embodiment of the present invention, background object is primarily referred to as the unconcerned scanning object of user institute, example in image to be adjusted
Such as it is used for the object (such as bed board) to having scanned the effect of supporting and fixing.The elimination of background object can utilize image segmentation algorithm
Or other eliminate the image processing algorithm of image background to complete.
Step 102：Determine the place-centric of target object and the square boundary of target object.
The square boundary of target object is the boundary of the minimum rectangle comprising target object, and the place-centric of target object can
Think the geometric center of the minimum rectangle comprising target object.
Step 103：Translating image to be adjusted makes the place-centric of target object be overlapped with the place-centric of output image.
Step 104：The contracting of image to be adjusted is determined according to the length of side of the square boundary length of side of target object and output image
Ratio is put, image to be adjusted is zoomed in and out according to scaling.
Image adjustment parameter can be configured in advance, for example, Image Adjusting function whether open, whether to image into
Whether row move, zoomed in and out to image, image scaling range etc..It then can be according to image adjustment parameter to image to be adjusted
It is automatic to carry out translation and/or zoom operations, wherein translation refers to the position that translation image to be adjusted makes target object
Center is overlapped with the place-centric of output image, to make target object be shown in the center of output image, zoom operations
Then image to be adjusted is zoomed in and out according to scaling, can make in proper proportions to carry out target object in output image
Display.
In the present embodiment image scaling is carried out according to equal proportion, the length of the square boundary of target object and zoomed image
Length can determine that the first scaling, the width of the square boundary of target object and the width of zoomed image can be determined
Second scaling then generally determines that smaller value is the pantograph ratio of image to be adjusted in the first scaling and the second scaling
Example.When scaling exceeds image scaling range, then it can determine that the boundary value of image scaling range is image to be adjusted
Scaling.Operation can be zoomed in and out to image to be adjusted using various image difference Processing Algorithms after obtaining scaling.
Image after adjustment can be in desktop computer, pocket computer on knee, tablet computer, wearable intelligent equipment
Etc. show in the display device of terminals, can also print on the media such as film and be exported.
In this way, the embodiment of the present invention is put down image to be adjusted by identifying target object included in image to be adjusted
The center for moving to target object is overlapped with the center of output image, and/or the square boundary length of side according to target object and output
The length of side of image determines the scaling of image to be adjusted, is zoomed in and out to image to be adjusted, the target that needs can be made to observe
Object is shown with suitable size with position in the output image, to realize the adjust automatically to image to be adjusted,
The artificial operation for carrying out Image Adjusting can be reduced, the speed of Image Adjusting is accelerated, further increases reconstruction image output
Efficiency.
When image to be adjusted includes several images to be adjusted, difference lies in also wrap with adjustment single width image to be adjusted
It includes：
When determining the place-centric of target object, the place-centric of target object is flat in each image to be adjusted of calculating
Mean value, using the average value as the place-centric of target object；
When determining the scaling of image to be adjusted, in the scaling of each image to be adjusted choose one meet
Scaling of the scaling of image scaling range as image to be adjusted.
Such as in the scaling for meeting image scaling range, select maximum value or minimum value therein as common
The scaling of image to be adjusted can be flexibly arranged according to practical situations.
Shown in Figure 2, the embodiment of the method two of the realization image adjust automatically provided in the embodiment of the present invention can wrap
Include following steps：
Step 201：Image to be adjusted is obtained, image to be adjusted includes several images to be adjusted.
In the present embodiment, image to be adjusted can be entire reconstruction image sequence.
Step 202：Identify the target object in each image to be adjusted.
It is similar, it, can be with before the target object in identifying image to be adjusted：Eliminate the background in image to be adjusted
Object.
Step 203：Determine the place-centric of target object and the rectangular edges of target object in each image to be adjusted
Boundary.
Step 204：The average value for calculating the place-centric of target object in each image to be adjusted, which is made
For the place-centric of target object.
The place-centric of target object can be indicated by coordinate value, then calculated in each image target object position to be adjusted
The average value of heart coordinate value can obtain the place-centric of the target object in one group of image to be adjusted.In addition, target object
Place-centric can also be the weighted average of the place-centric of several images to be adjusted, such as entire image sequence two to be adjusted
The image at end, the target object area that scans is less can be arranged lower weight, entire image sequence center to be adjusted
Higher weight can be arranged in image, several picture position centers to be adjusted are weighted with average, the average value conduct of acquisition
The place-centric of target object.
Step 205：Translating each image to be adjusted makes the place-centric weight of place-centric and output image of target object
It closes.
Step 206：According to the length of side of the square boundary length of side of target object in each image to be adjusted and output image
Determine the scaling of each image to be adjusted.
Step 207：A scaling for meeting image scaling range is chosen in the scaling of each width image to be adjusted
Scaling of the ratio as image to be adjusted.
Step 208：Each image to be adjusted is zoomed in and out according to scaling.
The present embodiment is image to be adjusted when including several images to be adjusted, realizes the process of image adjust automatically.It can be with
Understand, when pre-setting progress image translation operation, then follow the steps 204-205, image contracting is carried out when pre-setting
When putting operation, 206-208 is thened follow the steps, step 204-205 may be performed simultaneously with step 206-208, to complete to more
It is adjusted while image to be adjusted.
Based on above-described embodiment, in some embodiments of the invention, the tool of the target object in image to be adjusted is identified
Body realization at least may include following several realization methods：
One, the CT values for obtaining each pixel in image to be adjusted, identify that CT values are within a preset range in image to be adjusted
Pixel form target object.
CT values are to measure a kind of measurement unit of a certain local organization of human body or organ density size, every in image to be adjusted
A pixel can correspond to a CT value.Using this recognition mode, then extracts CT values range in image to be adjusted and setting
Pixel in range can determine CT value preset ranges within the scope of the window width and window level in conjunction with current image setting to be adjusted.
Two, matching template image is obtained, matching template image and image to be adjusted are subjected to similarity mode, it will be to be adjusted
The part to match with matching template image in image is determined as target object.
The object of specific shape, such as head, heart, liver, kidney and other organs can be identified using matching template image.
The identification of specific shape object can be completed by images match recognizer, and input carries out matched matching template image,
Matching template image and image to be adjusted are subjected to similarity mode to judge whether to meet the requirements, then to image to be adjusted into
Row segmentation obtains target object.
Common image matching method is by extracting the feature of image for carrying out similarity calculation, such as SIFT
(Scale-Invariant Feature Transform, scale invariant feature conversion), SURF (Speed Up Robust
Feature, rapid robust feature) etc..It can be by precalculating the feature of matching template image, such as given exemplary head figure
As the feature extracted in feature, with image to be adjusted carries out matching completion.In addition neural network can also be taken by inputting just
True image and incorrect image carry out the training of inspection to identify target object to identifying system.
Three, the part that background object is removed in image to be adjusted is determined as target object.Utilizing image segmentation algorithm
Eliminate after the background object in image to be adjusted remaining part be effective object in image to be adjusted, which is determined
For target object.Using this recognition mode, it can facilitate and scanning object is integrally observed.
Based on above-described embodiment, in some embodiments of the invention, the place-centric and target of target object are determined
The specific implementation of the square boundary of object at least may include following several realization methods：
One, the minimum rectangle for obtaining and including target object is calculated, the boundary of minimum rectangle is determined as to the square of target object
Shape boundary；
The place-centric of minimum rectangle is determined as to the place-centric of target object.
Two, the actual boundary of target object is obtained using image gradient recognizer, is calculated pixel in actual boundary and is sat
Target average value, the place-centric as target object；
The square boundary for obtaining and including target object is calculated according to the place-centric of target object.
In this way, the embodiment of the present invention is put down image to be adjusted by identifying target object included in image to be adjusted
The center for moving to target object is overlapped with the center of output image, and/or the square boundary length of side according to target object and output
The length of side of image determines the scaling of image to be adjusted, is zoomed in and out to image to be adjusted, the target that needs can be made to observe
Object is shown with suitable size with position in the output image, to realize the adjust automatically to image to be adjusted,
The artificial operation for carrying out Image Adjusting can be reduced, the speed of Image Adjusting is accelerated, further increases reconstruction image output
Efficiency.
Correspondingly, it is shown in Figure 3, it is that the device of the realization image adjust automatically provided in the embodiment of the present invention is implemented
, may include：
Acquiring unit 301, for obtaining image to be adjusted.
In some embodiments of the invention, the device embodiment provided in an embodiment of the present invention for realizing image adjust automatically
Can also include：
Unit is eliminated, for eliminating the background object in image to be adjusted.
After obtaining image to be adjusted, the background object in image to be adjusted is first removed, then identify in image to be adjusted
Target object, so that recognition result is more accurate.
Recognition unit 302, for identification target object in image to be adjusted.
Determination unit 303, the square boundary of place-centric and target object for determining target object.
Translation unit 304 makes for translating image to be adjusted in the place-centric of target object and the position of output image
The heart overlaps.
And/or unit for scaling 305, for being determined according to the square boundary length of side and the length of side of output image of target object
The scaling of image to be adjusted zooms in and out image to be adjusted according to scaling.
Image adjustment parameter can be configured in advance, for example, Image Adjusting function whether open, whether to image into
Whether row move, zoomed in and out to image, image scaling range etc..It then can be according to image adjustment parameter to image to be adjusted
It is automatic to carry out translation and/or zoom operations, wherein translation unit 304 is used for translation, and unit for scaling 305 is for contracting
Put operation.
In some embodiments of the invention, when image to be adjusted includes several images to be adjusted, determination unit may be used also
For：The average value for calculating the place-centric of target object in each image to be adjusted, as in the position of target object
The heart.
In some embodiments of the invention, when image to be adjusted includes several images to be adjusted, unit for scaling may be used also
For：The scaling that selection one meets image scaling range in the scaling of each image to be adjusted is used as and waits for
Adjust the scaling of image.
Shown in Figure 4, in some embodiments of the invention, recognition unit embodiment one may include：
First obtains subelement 401, the computer tomography CT value for obtaining each pixel in image to be adjusted；
Identify subelement 402, the pixel of CT values within a preset range forms object in image to be adjusted for identification
Body.
Shown in Figure 5, in some embodiments of the invention, recognition unit embodiment two may include：
Second obtains subelement 501, for obtaining matching template image；
Coupling subelement 502, for matching template image and image to be adjusted to be carried out similarity mode；
First determination subelement 503, for the part to match with matching template image in image to be adjusted to be determined as
Target object.
Shown in Figure 6, in some embodiments of the invention, determination unit embodiment one may include：
First computation subunit 601, for calculating the minimum rectangle for obtaining and including target object, by the boundary of minimum rectangle
It is determined as the square boundary of target object；
Second determination subelement 602, the place-centric for the place-centric of minimum rectangle to be determined as to target object.
Shown in Figure 7, in some embodiments of the invention, determination unit embodiment two may include：
Second computation subunit 701, the actual boundary for being obtained target object using image gradient recognizer are calculated
The average value of pixel point coordinates in actual boundary, the place-centric as target object；
Third computation subunit 702, for calculating the square for obtaining and including target object according to the place-centric of target object
Shape boundary.
In this way, the embodiment of the present invention is put down image to be adjusted by identifying target object included in image to be adjusted
The center for moving to target object is overlapped with the center of output image, and/or the square boundary length of side according to target object and output
The length of side of image determines the scaling of image to be adjusted, is zoomed in and out to image to be adjusted, the target that needs can be made to observe
Object is shown with suitable size with position in the output image, to realize the adjust automatically to image to be adjusted,
The artificial operation for carrying out Image Adjusting can be reduced, the speed of Image Adjusting is accelerated, further increases reconstruction image output
Efficiency.
It should be noted that each embodiment is described by the way of progressive in this specification, each embodiment emphasis is said
Bright is all difference from other examples, and just to refer each other for identical similar portion between each embodiment.For reality
For applying system or device disclosed in example, since it is corresponded to the methods disclosed in the examples, so fairly simple, the phase of description
Place is closed referring to method part illustration.
It should also be noted that, herein, relational terms such as first and second and the like are used merely to one
Entity or operation are distinguished with another entity or operation, without necessarily requiring or implying between these entities or operation
There are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant are intended to contain
Lid non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
The step of method described in conjunction with the examples disclosed in this document or algorithm, can directly be held with hardware, processor
The combination of capable software module or the two is implemented.Software module can be placed in random access memory (RAM), memory, read-only deposit
Reservoir (ROM), electrically programmable ROM, electrically erasable ROM, register, hard disk, moveable magnetic disc, CD-ROM or technology
In any other form of storage medium well known in field.
The foregoing description of the disclosed embodiments enables those skilled in the art to implement or use the present invention.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, of the invention
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (14)
1. a kind of method for realizing image adjust automatically, which is characterized in that the method includes：
Image to be adjusted is obtained, identifies the target object in the image to be adjusted；
Determine the place-centric of the target object and the square boundary of the target object；
Translating the image to be adjusted makes the place-centric of the target object be overlapped with the place-centric of output image；According to mesh
The length of square boundary and the length of zoomed image for marking object determine the first scaling, according to the rectangular edges of target object
The width on boundary and the width of zoomed image determine the second scaling, determine that first scaling is scaled with described second
Smaller value is the scaling of the image to be adjusted in ratio, when the image to be adjusted includes several images to be adjusted,
It is chosen in the scaling of the image to be adjusted described in each width described in the scaling that one meets image scaling range is used as
The scaling of image to be adjusted；
The image to be adjusted is zoomed in and out according to the scaling, so that the target object is in the output image
With after adjustment position and size shown.
2. according to the method described in claim 1, it is characterized in that, target object in identifying the image to be adjusted it
Before, the method further includes：
Eliminate the background object in the image to be adjusted.
3. according to the method described in claim 1, it is characterized in that, target object in the identification image to be adjusted,
Including：
The computer tomography CT value of each pixel in the image to be adjusted is obtained, identifies institute in the image to be adjusted
State the pixel composition target object of CT values within a preset range.
4. according to the method described in claim 1, it is characterized in that, target object in the identification image to be adjusted,
Including：
Matching template image is obtained, the matching template image and the image to be adjusted are subjected to similarity mode, it will be described
The part to match with the matching template image in image to be adjusted is determined as target object.
5. according to the method described in claim 1, it is characterized in that, place-centric and the institute of the determination target object
The square boundary of target object is stated, including：
The minimum rectangle for obtaining and including the target object is calculated, the boundary of the minimum rectangle is determined as the target object
Square boundary；
The place-centric of the minimum rectangle is determined as to the place-centric of the target object.
6. according to the method described in claim 1, it is characterized in that, place-centric and the institute of the determination target object
The square boundary of target object is stated, including：
The actual boundary that the target object is obtained using image gradient recognizer is calculated pixel in the actual boundary and sat
Target average value, the place-centric as the target object；
The square boundary for obtaining and including the target object is calculated according to the place-centric of the target object.
7. according to 1,5,6 any one of them method of claim, which is characterized in that when the image to be adjusted includes that several are waited for
When adjusting image, the method further includes：
Calculate the average value of the place-centric of target object in each image to be adjusted, the position as the target object
Set center.
8. a kind of device for realizing image adjust automatically, which is characterized in that described device includes：
Acquiring unit, for obtaining image to be adjusted；
Recognition unit, for identification target object in the image to be adjusted；
Determination unit, the square boundary of place-centric and the target object for determining the target object；
Translation unit makes for translating the image to be adjusted in the place-centric of the target object and the position of output image
The heart overlaps；
Unit for scaling, for determining the first pantograph ratio according to the length of square boundary and the length of zoomed image of target object
Example, the second scaling is determined according to the width of the width of the square boundary of target object and zoomed image, determines described the
One scaling and the scaling that smaller value in second scaling is the image to be adjusted, when the figure to be adjusted
One, which is chosen, when as including several images to be adjusted, in the scaling of the image to be adjusted described in each width meets image scaling
Scaling of the scaling of range as the image to be adjusted；According to the scaling to the image to be adjusted into
Row scaling so that the target object it is described output image in after adjustment position and size shown.
9. device according to claim 8, which is characterized in that described device further includes：
Unit is eliminated, for eliminating the background object in the image to be adjusted.
10. device according to claim 8, which is characterized in that the recognition unit includes：
First obtains subelement, the computer tomography CT value for obtaining each pixel in the image to be adjusted；
Identify subelement, the pixel of CT values described in the image to be adjusted within a preset range forms object for identification
Body.
11. device according to claim 8, which is characterized in that the recognition unit includes：
Second obtains subelement, for obtaining matching template image；
Coupling subelement, for the matching template image and the image to be adjusted to be carried out similarity mode；
First determination subelement, for the part to match with the matching template image in the image to be adjusted to be determined as
Target object.
12. device according to claim 8, which is characterized in that the determination unit includes：
First computation subunit, for calculating the minimum rectangle for obtaining and including the target object, by the side of the minimum rectangle
Boundary is determined as the square boundary of the target object；
Second determination subelement, the place-centric for the place-centric of the minimum rectangle to be determined as to the target object.
13. device according to claim 8, which is characterized in that the determination unit includes：
Second computation subunit, the actual boundary for obtaining the target object using image gradient recognizer calculate institute
The average value for stating pixel point coordinates in actual boundary, the place-centric as the target object；
Third computation subunit, for calculating the square for obtaining and including the target object according to the place-centric of the target object
Shape boundary.
14. according to 8,12,13 any one of them device of claim, which is characterized in that when the image to be adjusted includes more
When image to be adjusted, the determination unit is additionally operable to：
Calculate the average value of the place-centric of target object in each image to be adjusted, the position as the target object
Set center.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410390739.8A CN104240180B (en) | 2014-08-08 | 2014-08-08 | A kind of method and device for realizing image adjust automatically |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410390739.8A CN104240180B (en) | 2014-08-08 | 2014-08-08 | A kind of method and device for realizing image adjust automatically |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104240180A CN104240180A (en) | 2014-12-24 |
| CN104240180B true CN104240180B (en) | 2018-11-06 |
Family
ID=52228192
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410390739.8A Active CN104240180B (en) | 2014-08-08 | 2014-08-08 | A kind of method and device for realizing image adjust automatically |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104240180B (en) |
Families Citing this family (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3465684A1 (en) * | 2016-05-27 | 2019-04-10 | IMINT Image Intelligence AB | System and method for a zoom function |
| CN108537794B (en) * | 2018-04-19 | 2021-09-21 | 上海联影医疗科技股份有限公司 | Medical image data processing method, apparatus and computer readable storage medium |
| US10950016B2 (en) | 2018-06-11 | 2021-03-16 | Shanghai United Imaging Healthcare Co., Ltd. | Systems and methods for reconstructing cardiac images |
| CN108898582B (en) * | 2018-06-11 | 2021-08-17 | 上海联影医疗科技股份有限公司 | Heart image reconstruction method and device and computer equipment |
| CN111767700B (en) * | 2019-04-01 | 2023-10-27 | 珠海金山办公软件有限公司 | Graph adjustment method and device |
| CN111078090A (en) * | 2019-11-29 | 2020-04-28 | 上海联影医疗科技有限公司 | Display method, device, equipment and storage medium |
| CN111062998B (en) * | 2019-12-11 | 2023-12-12 | 上海联影医疗科技股份有限公司 | Image reconstruction method, device, CT system and storage medium |
| CN111415332B (en) * | 2020-03-05 | 2023-10-24 | 北京深睿博联科技有限责任公司 | Mammary gland X-ray image linkage method and device |
| CN111385489B (en) * | 2020-03-20 | 2022-09-23 | 百度在线网络技术（北京）有限公司 | Method, device and equipment for manufacturing short video cover and storage medium |
| CN113762286A (en) * | 2021-09-16 | 2021-12-07 | 平安国际智慧城市科技股份有限公司 | Data model training method, device, equipment and medium |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20060239585A1 (en) * | 2005-04-04 | 2006-10-26 | Valadez Gerardo H | System and method for reducing artifacts in motion corrected dynamic image sequences |
| JP2010268441A (en) * | 2009-04-16 | 2010-11-25 | Sanyo Electric Co Ltd | Image processor, imaging device, and image reproducing device |
| JP5897273B2 (en) * | 2010-07-22 | 2016-03-30 | 株式会社東芝 | Medical image display apparatus and X-ray computed tomography apparatus |
| CN103732148A (en) * | 2012-02-02 | 2014-04-16 | 株式会社东芝 | Medical image-processing device, X-ray CT scanner, and medical image-processing method |
-
2014
- 2014-08-08 CN CN201410390739.8A patent/CN104240180B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN104240180A (en) | 2014-12-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104240180B (en) | A kind of method and device for realizing image adjust automatically | |
| CN107480677B (en) | Method and device for identifying interest region in three-dimensional CT image | |
| EP2856426B1 (en) | Body measurement | |
| US8270696B2 (en) | Image slice segmentation using midpoints of contour anchor points | |
| USRE47609E1 (en) | System for detecting bone cancer metastases | |
| CN107909622B (en) | Model generation method, medical imaging scanning planning method and medical imaging system | |
| JP2018530401A5 (en) | ||
| CN109544606B (en) | Rapid automatic registration method and system based on multiple Kinects | |
| WO2019062843A1 (en) | Ultrasound image processing method and system | |
| CN106611416B (en) | Method and device for segmenting lung in medical image | |
| CN104598871B (en) | A kind of facial age computational methods based on correlation regression | |
| US11954860B2 (en) | Image matching method and device, and storage medium | |
| US8554016B2 (en) | Image registration system and method for registering images for deformable surfaces | |
| CN105046641B (en) | Method and system for automatic pelvic expansion from 3D computed tomography images | |
| US10810738B1 (en) | Marker-less alignment of digital 3D face and jaw models | |
| CN109903277A (en) | A kind of scoliosis detection method based on polynomial curve fitting | |
| CN108764089A (en) | Human body back midspinal line recognition methods based on depth camera | |
| CN110782428A (en) | Method and system for constructing clinical brain CT image ROI template | |
| US20190392552A1 (en) | Spine image registration method | |
| CN111080658A (en) | Cervical MRI image segmentation method based on deformable registration and DCNN | |
| CN113034528A (en) | Target area and organ-at-risk delineation contour accuracy testing method based on image omics | |
| CN101504727A (en) | Image processing apparatus and method thereof | |
| US20110103654A1 (en) | Bone imagery segmentation method and apparatus | |
| CN113706514B (en) | Focus positioning method, device, equipment and storage medium based on template image | |
| CN105205784B (en) | Scale recognition methods and image splicing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: 110179 No. 177-1 Innovation Road, Hunnan District, Shenyang City, Liaoning Province Patentee after: DongSoft Medical System Co., Ltd. Address before: Hunnan New Century Road 110179 Shenyang city of Liaoning Province, No. 16 Patentee before: Dongruan Medical Systems Co., Ltd., Shenyang |