CN110415279A - Method for registering images, device and equipment - Google Patents
Method for registering images, device and equipment Download PDFInfo
- Publication number
- CN110415279A CN110415279A CN201910557242.3A CN201910557242A CN110415279A CN 110415279 A CN110415279 A CN 110415279A CN 201910557242 A CN201910557242 A CN 201910557242A CN 110415279 A CN110415279 A CN 110415279A
- Authority
- CN
- China
- Prior art keywords
- image
- registration
- reference picture
- level
- floating
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/30—Determination of transform parameters for the alignment of images, i.e. image registration
- G06T7/33—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods
- G06T7/337—Determination of transform parameters for the alignment of images, i.e. image registration using feature-based methods involving reference images or patches
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
This application discloses a kind of method for registering images, device and equipment, are related to technical field of image processing, and the efficiency and precision of image rigid registration can be improved.Wherein method includes: to carry out down-sampling processing to reference picture to be registered and floating image respectively, obtains the reference picture and floating image of different levels, and the corresponding image resolution ratio of image of different levels is different；According to the sequence of image resolution ratio from low to high, reference picture and floating image are successively registrated, wherein the initiation parameter when Optimal Parameters that upper level image registration obtains are as next level image registration.The application is suitable for image registration.
Description
Technical field
This application involves technical field of image processing, particularly with regard to a kind of method for registering images, device and equipment.
Background technique
With x-ray computer tomography (Computed Tomography, CT) and magnetic resonance imaging (Magnetic
Resonance Imaging, MRI) etc. medical imaging devices gradually apply and clinical diagnosis, the difference that multi-modality images are provided
Information is fused together, to build a simpler and practical display and analysis platform, becomes clinician and image
The common recognition of the researcher of process field.In order to reaching this purpose, first have to the registration for realizing two images, i.e., it will be different
Time, different modalities image space on point correspond get up.
Before carrying out image deformation registration, need first to carry out rigid registration make two images reach on the whole slightly match
Standard, rigid registration is based primarily upon the method for registering images of pixel grey scale at present, does not need to carry out any pretreatment work to image,
The raw information directly provided using image, the i.e. gray value of all pixels are registrated.
However, existing rigid registration mode needs biggish operand, Jin Erying during seeking optimum variation
The efficiency of image registration is rung, is in addition easy the presence of the phenomenon that largely mismatching, also needs to be further increased in registration accuracy.
Summary of the invention
In view of this, main purpose is to solve current this application provides a kind of method for registering images, device and equipment
Existing rigid registration mode needs biggish operand during seeking optimum variation, will affect the effect of image rigid registration
The technical issues of rate and precision.
According to the one aspect of the application, a kind of method for registering images is provided, this method comprises:
Down-sampling processing is carried out to reference picture to be registered and floating image respectively, obtains the reference picture of different levels
And floating image, and the corresponding image resolution ratio of image of different levels is different；
According to the sequence of image resolution ratio from low to high, reference picture and floating image are successively registrated, wherein on
The initiation parameter when Optimal Parameters that one level image registration obtains are as next level image registration.
According to the another aspect of the application, a kind of image registration device is provided, which includes:
Processing module obtains difference for carrying out down-sampling processing to reference picture to be registered and floating image respectively
The reference picture and floating image of level, and the corresponding image resolution ratio of image of different levels is different；
Registration module, for the sequence according to image resolution ratio from low to high, by reference picture and floating image carry out by
Layer registration, wherein the initiation parameter when Optimal Parameters that upper level image registration obtains are as next level image registration.
According to the application another aspect, a kind of storage medium is provided, computer program, described program are stored thereon with
Above-mentioned method for registering images is realized when being executed by processor.
According to the application another aspect, a kind of entity device of image registration, including storage medium, processor are provided
And the computer program that can be run on a storage medium and on a processor is stored, the processor is realized when executing described program
Above-mentioned method for registering images.
By above-mentioned technical proposal, a kind of method for registering images, device and equipment provided by the present application are and existing at present
Rigid registration mode is compared, and the application carries out down-sampling processing to reference picture to be registered and floating image respectively first, is obtained
To the image of multiple level different resolutions, the then sequence according to image resolution ratio from low to high, by reference picture and floating
Image is successively registrated, wherein when the obtained Optimal Parameters of upper level image registration are as next level image registration just
Beginningization parameter.Since most of registration iterative search procedures are completed in the lower thick scale layer of resolution ratio, pass through
The lower thick scale layer of this mode first search resolution ratio of the application, image become smaller, and improve convergence rate；Thick scale layer
Optimum results pass to the next layer of higher scale layer of resolution ratio, it is certain due to giving in the layer as initiation parameter
Initiation parameter, so improving the speed of search transformation space parameter, and then it is whole to improve image rigid registration algorithm
Convergence rate, to improve the efficiency and precision of image rigid registration.
Above description is only the general introduction of technical scheme, in order to better understand the technological means of the application,
And it can be implemented in accordance with the contents of the specification, and in order to allow above and other objects, features and advantages of the application can
It is clearer and more comprehensible, below the special specific embodiment for lifting the application.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present application, constitutes part of this application, this Shen
Illustrative embodiments and their description please are not constituted an undue limitation on the present application for explaining the application.In the accompanying drawings:
Fig. 1 shows a kind of flow diagram of method for registering images provided by the embodiments of the present application；
Fig. 2 shows the example schematics of image down sampling effect provided by the embodiments of the present application；
Fig. 3 shows the example schematic of image pyramid registration provided by the embodiments of the present application；
Fig. 4 shows the flow diagram of whole registration method provided by the embodiments of the present application；
Fig. 5 shows a kind of structural schematic diagram of image registration device provided by the embodiments of the present application；
Fig. 6 shows the structural schematic diagram of another image registration device provided by the embodiments of the present application.
Specific embodiment
The application is described in detail below with reference to attached drawing and in conjunction with the embodiments.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
Biggish operand is needed during seeking optimum variation for current existing rigid registration mode, will affect
The technical issues of efficiency and precision of image registration, a kind of method for registering images is present embodiments provided, as shown in Figure 1, the party
Method includes:
101, down-sampling processing is carried out to reference picture to be registered and floating image respectively, obtains the reference of different levels
Image and floating image, and the corresponding image resolution ratio of image of different levels is different.
Reference picture is the image remained stationary, and floating image is the image with punctual adjustment of floating.In this reality
It applies in example, can select the width in two images to be registered as reference picture according to actual needs, and another width is as floating
Motion video.The two images can be the image or other medical images of radiotherapy, and the format of the two images can be doctor
Learn digital imagery and communication (Digital Imaging and Communications in Medicine, DICOM) format.It needs
It is noted that the present embodiment method applies also for the scene of image registration in other industry, herein with the figure of radiotherapy
As being illustrated for registration, but any restriction of the present embodiment method application scenarios is not done.
For example, reducing the image resolution ratio of reference picture and floating image to be registered, obtains multiple level differences and differentiate
The reference picture and floating image of rate, wherein the reference picture of same level and the image resolution ratio of floating image can be identical
, to improve the registration accuracy of each level image.The level number divided can be specifically determined according to actual needs, and every
The corresponding image resolution ratio of a level, is equivalent to the smooth scale for changing to high resolution gradually from the low thick scale layer of resolution ratio
Layer.
It can be the device or equipment of image registration for the executing subject of the present embodiment, match for carrying out image rigid body
Standard, to improve the efficiency and precision of image rigid registration.
102, reference picture and floating image are successively registrated by the sequence according to image resolution ratio from low to high.
Wherein, the initialization ginseng when Optimal Parameters that upper level image registration obtains are as next level image registration
Number.
It is registrated for example, choosing the minimum level image of image resolution ratio first, in the reference picture of the level and floating
After the completion of motion video registration, the Optimal Parameters obtained after spatial alternations a series of in this level are passed into next level (figure
As resolution ratio increases), then initiation parameter when as next level image registration is completed in next level image registration
Afterwards, then by the new Optimal Parameters obtained after spatial alternations a series of in next level next level (image resolution ratio is passed to again
Increase again), initiation parameter when as next level image registration again；And so on, when the highest level of image resolution ratio
After the completion of image registration, determine that reference picture and the floating image rigid registration to be registered for starting input is completed.
Since most of registration iterative search procedures are completed in the lower thick scale layer of resolution ratio, pass through this
The lower thick scale layer of this method for registering images first search resolution ratio of embodiment, image become smaller, and improve convergence rate；
The optimum results of thick scale layer pass to the next layer of higher scale layer of resolution ratio, as initiation parameter, in the layer due to giving
Go out certain initiation parameter, so improving the speed of search transformation space parameter, and then improves image rigid registration
The convergence rate of algorithm entirety, to improve the efficiency and precision of image rigid registration.
Further, as the refinement and extension of above-described embodiment specific embodiment, scheme by reference picture and floating
As before be successively registrated, alternatively, the present embodiment method may also include that determines reference to be registered respectively
Specific markers in image and floating image；Correspondingly, be successively registrated reference picture and floating image in step 102,
Specifically can include: according to the specific markers in the reference picture and floating image of each level as the reference mark for match on time
Know, adjustment floating image is registrated.
Since the size of reference picture and floating image is possible to different, and matched by above-mentioned optional way
Standard is not limited by floating image and reference picture size, and then can realize that the different image of size can also carry out just
The adapting to image registration of body registration.
Optionally, specific markers can be reference picture to be registered and the corresponding reference frame unique identification of floating image.
For example, DICOM format image can be used the mark that the label that label in DICOM is (0020,0052) is registrated, be protected
Card is not limited by picture size size subject to registration, it can be achieved that accurately carrying out the adapting to image registration of rigid registration.
Since different image layered methods can influence the efficiency and precision of image registration to a certain extent, into one
Step is optional, in order to realize more optimal registration effect, can be counted in advance according to the original image resolution of image subject to registration
It is registrated efficiency and the optimal hierarchical rule of precision, so that the subsequent image directly using hierarchical rule progress quick high accuracy is rigid
Body registration process.Correspondingly, step 101 is specific can include: obtain the original of reference picture and floating image to be registered first
(corresponding image resolution ratio, the original image resolution can correspondence image layerings when i.e. image subject to registration inputs for image resolution ratio
The image resolution ratio of resolution ratio highest level afterwards)；According still further to original image resolution determine corresponding default layering number and
The pre-set image resolution ratio of each level；It is right referring next to default layering number and the pre-set image resolution ratio of each level
Reference picture and floating image to be registered carry out Image Adjusting, and then obtain the reference picture and floating image of different levels,
And the corresponding image resolution ratio of image of different levels is different.For example, as shown in Fig. 2, the effect handled for image down sampling
Fruit figure, sequence from left to right, image resolution ratio successively increase, and the image of the rightmost side is the original image of image subject to registration, i.e.,
Image subject to registration corresponding image when inputting.
After image layered, in order to which image illustrates the image registration mode of the present embodiment, as shown in figure 3, using similar
The registration mode of image pyramid, wherein left side pyramid is the image of the corresponding multiple level different resolutions of floating image,
Right side pyramid is the image of the corresponding multiple level different resolutions of reference picture；It is specific to be registrated from image pyramid
0 layer of Registration Level starts, and the resolution ratio of 0 tomographic image is minimum, and the lowest level of tower is original image.Registration process
In, 0 layer of Registration Level of image subject to registration is registrated first, 0 layer of Registration Level sets
Coarse initial parameter is set, then obtains Optimal Parameters after a series of spatial alternations, passes it on next layer
Registration Level 1 and the initial parameter that it is set；And so on, level Registration Level 1 is excellent
The result of change is used to initialize the parameter of level Registration Level 2, and level Registration Level 2 is excellent
The result of change is used to initialize the parameter of level Registration Level 3, and level Registration Level 3 is excellent
The result of change is used to initialize the parameter of level Registration Level 3.After the completion of the lowest level of tower registration, determine
Floating image and reference picture rigid registration are completed.
In specific each tomographic image registration process, in order to meet registration accuracy requirement, alternatively,
Step 102 is specific can include: after the reference picture of same level and floating image are registrated, if registration obtain it is mutual
The value of information is greater than or equal to preset threshold, then executes the image registration operation of next level corresponding with the level；If the level pair
The association relationship answered is less than preset threshold, then conversion process is carried out to the floating image of the level, so that newly counting after conversion process
Obtained association relationship is greater than or equal to preset threshold.
The above-mentioned floating image to the level carries out the process of conversion process, specifically can include: float first to the level
Motion video carries out spatial alternation, wherein spatial alternation may include one of rotation, translation, inclination, scaling or a variety of operations；
Then interpolation processing will be carried out by the floating image of spatial alternation.By this conversion process mode, image can be effectively realized
The process of registration can quickly carry out image according to the actual situation in such a way that suitable a variety of spatial alternations operation combines
Registration reduces the spent duration of single operation adjustment.
For example, can be as shown in figure 4, detailed process is as follows for the present embodiment method the whole series registration process:
(1) reference picture X1 and floating image X2 (DICOM format) is inputted；
(2) down-sampling processing is carried out to reference picture X1 and floating image X2 respectively；
(3) the minimum image of the resolution ratio of the X1 and X2 image after removing sampling respectively carries out first time registration；
(4) examine whether the association relationship of registration for the first time reaches maximum value with mutual information method；If reaching maximum value, take
Image of the slightly higher X1 and X2 image of resolution ratio as second registration, and it is registrated obtained Optimal Parameters for the first time as the
It is secondary to match punctual initiation parameter；If not reaching maximum value, spatial alternation is carried out to floating image, i.e., to floating image
The operation such as rotated, translated；
(5) interpolation processing is carried out to by the floating image of spatial alternation, then judges whether association relationship reaches again
Maximum value；
(6) (4) (5) are repeated until the highest image of resolution ratio completes registration.
Due to the original image that the image resolution ratio of resolution ratio highest level is image subject to registration；Therefore, in order to mention in time
User images rigid registration of waking up is completed, and optionally, completes registration in the reference picture and floating image of resolution ratio highest level
Afterwards, the rigid registration of exportable reference picture to be registered and floating image completes information.
The present embodiment method, which is equivalent to, provides a kind of automation adapting to image registration approach, passes through gaussian pyramid point
Two images subject to registration are solved, the image of many levels different resolution is obtained；The thick scale layer of Optimizing Search pyramid structure, figure
As becoming smaller, convergence rate is improved；The optimum results of thick scale layer are transmitted following scale layer, as initiation parameter, In
This layer is due to giving certain initiation parameter, so improving the speed of search transformation space parameter；Multiresolution gold word
Most of the iterative search procedures of tower registration are to complete on rough layer, and each layer all provides initialization for next layer
Parameter, therefore, the number of iterations in the smooth scale layer of high resolution are reduced, and have correspondinglyd increase the convergence rate of registration Algorithm.Separately
Outside, judge to use the mark that label is registrated in DICOM as the label of (0020,0052) to image, not by floating image
And the limitation of reference picture size, it is achieved that the different image of size can also carry out the adaptive of rigid registration
Image registration.
In short, the registration based on multiresolution optimisation strategy by coarse to completing in the way of smooth, combine down-sampled
And Gaussian smoothing filter, the valuable content of processing image is saved, locally optimal solution is eliminated in thick scale and improves registration Shandong
Stick reduces a possibility that mutual information measure falls into local extremum, improves registration success rate.
Further, the specific implementation as method shown in Fig. 1 present embodiments provides a kind of image registration device, such as
Shown in Fig. 5, which includes: processing module 21, registration module 22.
Processing module 21 can be used for carrying out down-sampling processing to reference picture to be registered and floating image respectively, obtain
The reference picture and floating image of different levels, and the corresponding image resolution ratio of image of different levels is different；
Registration module 22 can be used for the sequence from low to high according to image resolution ratio, by reference picture and floating image into
Row is successively registrated, wherein the initialization when Optimal Parameters that upper level image registration obtains are as next level image registration
Parameter.
In specific application scenarios, as shown in fig. 6, the present apparatus further include: determining module 23；
Determining module 23, for determining the specific markers in the reference picture to be registered and floating image respectively；
Registration module 22, the specific markers conduct being particularly used in the reference picture and floating image according to each level
It carries out with punctual reference identification, adjustment floating image is registrated.
In specific application scenarios, optionally, the specific markers can be the reference picture to be registered and float
The corresponding reference frame unique identification of motion video.
In specific application scenarios, registration module 22 specifically can also be used in by the reference picture of same level and floating
After motion video is registrated, if the association relationship that registration obtains is greater than or equal to preset threshold, execute corresponding with the level
The image registration of next level operates；If the association relationship is less than the preset threshold, to the floating image of the level into
Row conversion process, so that the association relationship being newly calculated after conversion process is greater than or equal to the preset threshold.
In specific application scenarios, optionally, the image resolution ratio of resolution ratio highest level is the original of image subject to registration
Beginning image；As shown in fig. 6, the present apparatus may also include that output module 24；
Output module 24 can be used for after the reference picture and floating image of resolution ratio highest level complete registration, defeated
Information is completed in the image registration of the reference picture to be registered and floating image out.
In specific application scenarios, registration module 22 specifically can also be used to carry out space to the floating image of the level
Transformation, the spatial alternation include one of rotation, translation, inclination, scaling or a variety of operations；It will be by the floating of spatial alternation
Motion video carries out interpolation processing.
In specific application scenarios, processing module 21 is particularly used in and obtains the reference picture to be registered and float
The original image resolution of motion video；Corresponding default layering number and each layer are determined according to the original image resolution
The pre-set image resolution ratio of grade；Referring to it is described it is default layering number and each level pre-set image resolution ratio, to it is described to
The reference picture and floating image of registration carry out Image Adjusting.
It should be noted that each functional unit involved by a kind of image registration device provided in this embodiment is other corresponding
Description, can be with reference to the corresponding description in Fig. 1, and details are not described herein.
It is stored thereon with based on above-mentioned method as shown in Figure 1 correspondingly, the present embodiment additionally provides a kind of storage medium
Computer program, the program realize above-mentioned method for registering images as shown in Figure 1 when being executed by processor.
Based on this understanding, the technical solution of the application can be embodied in the form of software products, this is to be identified
Software product can store in a non-volatile memory medium (can be CD-ROM, USB flash disk, mobile hard disk etc.), if including
Dry instruction is used so that a computer equipment (can be personal computer, server or the network equipment etc.) executes this Shen
It please method described in each implement scene.
It is above-mentioned in order to realize based on above-mentioned method and Fig. 5 as shown in Figure 1, virtual bench embodiment shown in fig. 6
Purpose, the present embodiment additionally provide a kind of entity device of image registration, are specifically as follows personal computer, medical supply, clothes
Business device, smart phone, tablet computer, smartwatch or other network equipments etc., which includes storage medium and place
Manage device；Storage medium, for storing computer program；Processor is realized above-mentioned as shown in Figure 1 for executing computer program
Method for registering images.
Optionally, which can also include user interface, network interface, camera, radio frequency (Radio
Frequency, RF) circuit, sensor, voicefrequency circuit, WI-FI module etc..User interface may include display screen
(Display), input unit such as keyboard (Keyboard) etc., optional user interface can also connect including USB interface, card reader
Mouthful etc..Network interface optionally may include standard wireline interface and wireless interface (such as WI-FI interface).
It will be understood by those skilled in the art that a kind of entity device structure of image registration provided in this embodiment not structure
The restriction of the pairs of entity device, may include more or fewer components, perhaps combine certain components or different components
Arrangement.
It can also include operating system, network communication module in storage medium.Operating system is the above-mentioned image registration of management
Entity device hardware and software resource to be identified program, support message handling program and other softwares to be identified and/or
The operation of program.Network communication module for realizing the communication between each component in storage medium inside, and with information processing reality
It is communicated between other hardware and softwares in body equipment.
Through the above description of the embodiments, those skilled in the art can be understood that the application can borrow
It helps software that the mode of necessary general hardware platform is added to realize, hardware realization can also be passed through.Pass through the skill of application the application
Art scheme, the registration based on multiresolution optimisation strategy to completing in the way of smooth, combine down-sampled and Gauss by coarse
Smothing filtering saves the valuable content of processing image, eliminates locally optimal solution in thick scale and improves registration robustness, drops
A possibility that low mutual information measure falls into local extremum, improves registration success rate.
It will be appreciated by those skilled in the art that the accompanying drawings are only schematic diagrams of a preferred implementation scenario, module in attached drawing or
Process is not necessarily implemented necessary to the application.It will be appreciated by those skilled in the art that the mould in device in implement scene
Block can according to implement scene describe be distributed in the device of implement scene, can also carry out corresponding change be located at be different from
In one or more devices of this implement scene.The module of above-mentioned implement scene can be merged into a module, can also be into one
Step splits into multiple submodule.
Above-mentioned the application serial number is for illustration only, does not represent the superiority and inferiority of implement scene.Disclosed above is only the application
Several specific implementation scenes, still, the application is not limited to this, and the changes that any person skilled in the art can think of is all
The protection scope of the application should be fallen into.
Claims (10)
1. a kind of method for registering images characterized by comprising
Down-sampling processing is carried out to reference picture to be registered and floating image respectively, obtain the reference picture of different levels and is floated
Motion video, and the corresponding image resolution ratio of image of different levels is different；
According to the sequence of image resolution ratio from low to high, reference picture and floating image are successively registrated, wherein upper one layer
The initiation parameter when Optimal Parameters that grade image registration obtains are as next level image registration.
2. the method according to claim 1, wherein reference picture and floating image are successively registrated it
Before, the method also includes:
The specific markers in the reference picture to be registered and floating image are determined respectively；
It is described to be successively registrated reference picture and floating image, it specifically includes:
According to the specific markers in the reference picture and floating image of each level as carrying out with punctual reference identification, adjustment
Floating image is registrated.
3. according to the method described in claim 2, it is characterized in that, it is described be specifically marked as the reference picture to be registered and
The corresponding reference frame unique identification of floating image.
4. according to the method in any one of claims 1 to 3, which is characterized in that it is described according to image resolution ratio from as low as
Reference picture and floating image are successively registrated, are specifically included by high sequence:
After being registrated the reference picture of same level and floating image, if the association relationship that registration obtains is greater than or waits
In preset threshold, then the image registration operation of next level corresponding with the level is executed；
If the association relationship is less than the preset threshold, conversion process is carried out to the floating image of the level, so that transformation
The association relationship being newly calculated after processing is greater than or equal to the preset threshold.
5. method according to claim 1 to 4, which is characterized in that the image resolution of resolution ratio highest level
Rate is the original image of image subject to registration, the sequence according to image resolution ratio from low to high, by reference picture and the figure that floats
As being successively registrated, specifically further include:
After the reference picture and floating image of resolution ratio highest level complete registration, the reference picture to be registered is exported
Information is completed with the rigid registration of floating image.
6. according to the method described in claim 4, it is characterized in that, the floating image of described pair of level carries out conversion process,
It specifically includes:
Spatial alternation is carried out to the floating image of the level, the spatial alternation includes one in rotating, translation, tilting, scale
Kind or a variety of operations；
Interpolation processing will be carried out by the floating image of spatial alternation.
7. the method according to claim 1, wherein described respectively to reference picture to be registered and floating image
Down-sampling processing is carried out, is specifically included:
Obtain the original image resolution of the reference picture to be registered and floating image；
The pre-set image resolution ratio of corresponding default layering number and each level is determined according to the original image resolution；
Referring to the default layering number and the pre-set image resolution ratio of each level, to the reference picture to be registered and
Floating image carries out Image Adjusting.
8. a kind of image registration device characterized by comprising
Processing module obtains different levels for carrying out down-sampling processing to reference picture to be registered and floating image respectively
Reference picture and floating image, and the corresponding image resolution ratio of image of different levels is different；
Registration module is successively matched reference picture and floating image for the sequence according to image resolution ratio from low to high
It is quasi-, wherein the initiation parameter when Optimal Parameters that upper level image registration obtains are as next level image registration.
9. a kind of storage medium, is stored thereon with computer program, which is characterized in that realization when described program is executed by processor
Method for registering images described in any one of claims 1 to 7.
10. a kind of image registration equipment, including storage medium, processor and storage can transport on a storage medium and on a processor
Capable computer program, which is characterized in that the processor realizes any one of claims 1 to 7 institute when executing described program
The method for registering images stated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910557242.3A CN110415279A (en) | 2019-06-25 | 2019-06-25 | Method for registering images, device and equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910557242.3A CN110415279A (en) | 2019-06-25 | 2019-06-25 | Method for registering images, device and equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110415279A true CN110415279A (en) | 2019-11-05 |
Family
ID=68359757
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910557242.3A Pending CN110415279A (en) | 2019-06-25 | 2019-06-25 | Method for registering images, device and equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110415279A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768393A (en) * | 2020-07-01 | 2020-10-13 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN112396640A (en) * | 2020-11-11 | 2021-02-23 | 广东拓斯达科技股份有限公司 | Image registration method and device, electronic equipment and storage medium |
| CN112561800A (en) * | 2020-12-23 | 2021-03-26 | 杭州群核信息技术有限公司 | Method and device for hierarchical loading and displaying of panoramic image, computer equipment and storage medium |
| CN114187337A (en) * | 2021-12-07 | 2022-03-15 | 推想医疗科技股份有限公司 | Image registration method, segmentation method, device, electronic equipment and storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101238993A (en) * | 2008-02-01 | 2008-08-13 | 哈尔滨工业大学 | Medical ultrasound image registration method based on integer lifting wavelet multiresolution analysis |
| CN101987019A (en) * | 2009-08-03 | 2011-03-23 | 徐子海 | Positron emission tomography (PET) and computed tomography (CT) cross-modality medical image fusion method based on wavelet transform |
| CN102592137A (en) * | 2011-12-27 | 2012-07-18 | 中国科学院深圳先进技术研究院 | Multi-modality image registration method and operation navigation method based on multi-modality image registration |
| CN103218811A (en) * | 2013-03-29 | 2013-07-24 | 中国资源卫星应用中心 | Statistical distribution-based satellite multi-spectral image waveband registration method |
| CN108549906A (en) * | 2018-04-10 | 2018-09-18 | 北京全域医疗技术有限公司 | Radiotherapy hooks target method for registering images and device |
| CN109215064A (en) * | 2018-08-03 | 2019-01-15 | 华南理工大学 | A kind of medical image registration method based on super-pixel guide |
| CN109754396A (en) * | 2018-12-29 | 2019-05-14 | 上海联影智能医疗科技有限公司 | Method for registering, device, computer equipment and the storage medium of image |
-
2019
- 2019-06-25 CN CN201910557242.3A patent/CN110415279A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101238993A (en) * | 2008-02-01 | 2008-08-13 | 哈尔滨工业大学 | Medical ultrasound image registration method based on integer lifting wavelet multiresolution analysis |
| CN101987019A (en) * | 2009-08-03 | 2011-03-23 | 徐子海 | Positron emission tomography (PET) and computed tomography (CT) cross-modality medical image fusion method based on wavelet transform |
| CN102592137A (en) * | 2011-12-27 | 2012-07-18 | 中国科学院深圳先进技术研究院 | Multi-modality image registration method and operation navigation method based on multi-modality image registration |
| CN103218811A (en) * | 2013-03-29 | 2013-07-24 | 中国资源卫星应用中心 | Statistical distribution-based satellite multi-spectral image waveband registration method |
| CN108549906A (en) * | 2018-04-10 | 2018-09-18 | 北京全域医疗技术有限公司 | Radiotherapy hooks target method for registering images and device |
| CN109215064A (en) * | 2018-08-03 | 2019-01-15 | 华南理工大学 | A kind of medical image registration method based on super-pixel guide |
| CN109754396A (en) * | 2018-12-29 | 2019-05-14 | 上海联影智能医疗科技有限公司 | Method for registering, device, computer equipment and the storage medium of image |
Non-Patent Citations (5)
| Title |
|---|
| 刘丽等: "基于小波变换和互信息的医学图像配准", 《中国图象图形学报》 * |
| 张恒: "基于递归标记的红外图像变分辨率相关匹配算法", 《系统仿真学报》 * |
| 张桂梅等: "基于 Nystrom 低阶近似和谱特征的图像非刚性配准", 《自动化学报》 * |
| 张桂梅等: "基于多分辨率和自适应分数阶的Active Demons算法", 《计算机研究与发展》 * |
| 金英: "优化的CT图像配准方法的研究与比较", 《黑龙江大学工程学报》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111768393A (en) * | 2020-07-01 | 2020-10-13 | 上海商汤智能科技有限公司 | Image processing method and device, electronic equipment and storage medium |
| CN112396640A (en) * | 2020-11-11 | 2021-02-23 | 广东拓斯达科技股份有限公司 | Image registration method and device, electronic equipment and storage medium |
| CN112396640B (en) * | 2020-11-11 | 2024-04-09 | 广东拓斯达科技股份有限公司 | Image registration method, device, electronic equipment and storage medium |
| CN112561800A (en) * | 2020-12-23 | 2021-03-26 | 杭州群核信息技术有限公司 | Method and device for hierarchical loading and displaying of panoramic image, computer equipment and storage medium |
| CN114187337A (en) * | 2021-12-07 | 2022-03-15 | 推想医疗科技股份有限公司 | Image registration method, segmentation method, device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2018211356B2 (en) | Image completion with improved deep neural networks | |
| US10600184B2 (en) | Automated segmentation utilizing fully convolutional networks | |
| CN110415279A (en) | Method for registering images, device and equipment | |
| EP3828825A1 (en) | Image segmentation method and apparatus, diagnosis system, storage medium, and computer device | |
| JP6993334B2 (en) | Automated cardiac volume segmentation | |
| CN110163876B (en) | Left ventricle segmentation method, system, device and medium based on multi-feature fusion | |
| CN111028242A (en) | Automatic tumor segmentation system and method and electronic equipment | |
| KR20220031695A (en) | Image recognition method and related devices and devices | |
| EP2979242B1 (en) | Method and apparatus for generating a super-resolved image from a single image | |
| US20190347847A1 (en) | View generation from a single image using fully convolutional neural networks | |
| CN107688783B (en) | 3D image detection method and device, electronic equipment and computer readable medium | |
| CN113256529B (en) | Image processing method, image processing device, computer equipment and storage medium | |
| CN109741395B (en) | Dual-chamber quantification method and device, electronic equipment and storage medium | |
| CN109903269B (en) | Method and computing device for determining abnormal type of spine cross-sectional image | |
| CN111080654A (en) | Image lesion region segmentation method and device and server | |
| US8948502B2 (en) | Image processing method, and image processor | |
| CN116580028B (en) | Object surface defect detection method, device, equipment and storage medium | |
| Choudhary et al. | Mathematical modeling and simulation of multi-focus image fusion techniques using the effect of image enhancement criteria: a systematic review and performance evaluation | |
| US10628698B1 (en) | Method for image stitching | |
| CN113989171A (en) | Subtraction map generation method and device, storage medium and computer equipment | |
| CN113989172A (en) | Subtraction map generation method, subtraction map generation device, storage medium, and computer apparatus | |
| CN116486090B (en) | Lung cancer spine metastasis image processing method, device, equipment and storage medium | |
| Zheng et al. | 3D consistent biventricular myocardial segmentation using deep learning for mesh generation | |
| Ali et al. | Breast tumor segmentation using neural cellular automata and shape guided segmentation in mammography images | |
| CN109961083A (en) | For convolutional neural networks to be applied to the method and image procossing entity of image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191105 |
|
| RJ01 | Rejection of invention patent application after publication |