CN108038863A - Image partition method and device - Google Patents
Image partition method and device Download PDFInfo
- Publication number
- CN108038863A CN108038863A CN201810085004.2A CN201810085004A CN108038863A CN 108038863 A CN108038863 A CN 108038863A CN 201810085004 A CN201810085004 A CN 201810085004A CN 108038863 A CN108038863 A CN 108038863A
- Authority
- CN
- China
- Prior art keywords
- image
- initial profile
- curve
- profile curve
- region
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of image partition method and device, this method includes：Initial profile curve is set in pending image；Determine the corresponding global energy of the initial profile curve and local energy, and according to the global energy and the local energy, determine the corresponding gross energy of the initial profile curve；According to the gross energy, the corresponding value of the corresponding level set movements equation of the initial profile curve is determined；Judge whether the corresponding value of the corresponding level set movements equation of the initial profile curve is consistent with predetermined threshold value；When the judgment result is No, according to the gross energy, evolution processing is carried out to the initial profile curve, until the corresponding value of the corresponding level set movements equation of contour curve after evolution processing is consistent with the predetermined threshold value, and using the contour curve after last time evolution processing as segmentation curve；Using curve is split, dividing processing is carried out from the pending image.
Description
Technical field
The present invention relates to technical field of image processing, more particularly, to a kind of image processing method and device.
Background technology
At present, the image section for meeting user demand is partitioned into from image, mainly passes through traditional active contour model.
Since traditional active contour model is the image processing model based on image global information so that traditional active contour model exists
Initial profile is more sensitive, and iterations is more in calculating process, the slow-footed shortcoming of curve convergence, especially for half-tone information
Changing little image cannot correctly split.
Accordingly, it is desirable to provide a kind of new technical method, is improved for above-mentioned technical problem of the prior art.
The content of the invention
It is an object of the present invention to provide the new solution of a kind of image partition method and device.
According to the first aspect of the invention, there is provided a kind of image partition method, including：
Initial profile curve is set in pending image；
Determine the corresponding global energy of the initial profile curve and local energy, and according to the global energy and described
Local energy, determines the corresponding gross energy of the initial profile curve；
According to the gross energy, the corresponding value of the corresponding level set movements equation of the initial profile curve is determined；
Judge whether the corresponding value of the corresponding level set movements equation of the initial profile curve is consistent with predetermined threshold value；
When the judgment result is No, according to the gross energy, evolution processing is carried out to the initial profile curve, until drilling
The corresponding value of the corresponding level set movements equation of contour curve after change processing is consistent with the predetermined threshold value, and will last time
Contour curve after evolution processing is as segmentation curve；
Using curve is split, to carrying out dividing processing in the pending image.
Optionally it is determined that the corresponding global energy of the initial profile curve, including：
According to the gray value of each pixel in the pending image, by all pixels point in the initial profile curve
The first grey parameter that gray average and gray scale intermediate value weighting are handled and by all pixels point outside the initial profile curve
Gray average and the second grey parameter for handling of gray scale intermediate value weighting, determine the corresponding overall situation of the initial profile curve
Energy；And/or
Determine the corresponding local energy of the initial profile curve, including：
Centered on each pixel in the initial profile curve, image-region is set up, wherein, in each image-region
In, using the initial profile curve as line of demarcation, each image-region is divided into the first image-region and the second image-region；
For the corresponding image-region of any pixel in the initial profile curve, corresponded to according to any pixel point
Image-region in the gray value of each pixel, the first gray scale intermediate value in described first image region and second image-region
The second gray scale intermediate value, determine the local energy of the corresponding image-region of any pixel point.
Alternatively, described image region is the circular diagram set up centered on each pixel in the initial profile curve
As region or square image-region.
Alternatively, the initial profile curve is any in circular curve, square curve, triangle curve.
According to the second aspect of the invention, there is provided a kind of image segmenting device, including：
Setup module, for setting initial profile curve in pending image；
First determining module, for determining the corresponding global energy of the initial profile curve and local energy, and according to
The global energy and the local energy, determine the corresponding gross energy of the initial profile curve；
Second determining module, for according to the gross energy, determining the corresponding level set movements of the initial profile curve
The corresponding value of equation；
Judgment module, for judge the corresponding value of the corresponding level set movements equation of the initial profile curve whether with advance
If threshold value is consistent；
Evolution processing module, for when the judgment result is No, according to the gross energy, to the initial profile curve into
Row evolution is handled, until the corresponding value of the corresponding level set movements equation of contour curve after evolution processing and the predetermined threshold value
Unanimously, the contour curve after and last time evolution is handled is as segmentation curve；
Split module, for using curve is split, dividing processing to be carried out from the pending image.
Alternatively, first determining module is additionally operable to：
According to the gray value of each pixel in the pending image, by all pixels point in the initial profile curve
The first grey parameter that gray average and gray scale intermediate value weighting are handled and by all pixels point outside the initial profile curve
Gray average and the second grey parameter for handling of gray scale intermediate value weighting, determine the corresponding overall situation of the initial profile curve
Energy；And/or
First determining module is additionally operable to：
Centered on each pixel in the initial profile curve, image-region is set up, wherein, in each image-region
In, using the initial profile curve as line of demarcation, each image-region is divided into the first image-region and the second image-region；
For the corresponding image-region of any pixel in the initial profile curve, corresponded to according to any pixel point
Image-region in the gray value of each pixel, the first gray scale intermediate value in described first image region and second image-region
The second gray scale intermediate value, determine the local energy of the corresponding image-region of any pixel point.
Alternatively, described image region is the circular diagram set up centered on each pixel in the initial profile curve
As region or square image-region.
Alternatively, the initial profile curve is any in circular curve, square curve, triangle curve.
According to the third aspect of the invention we, there is provided a kind of image segmenting device, including：Memory and processor, wherein,
The memory storage executable instruction, it is above-mentioned according to weighing to perform that the executable instruction controls the processor to be operated
Image partition method described in any one.
Image partition method and device provided in an embodiment of the present invention, by by the corresponding global energy drawn game of contour curve
Portion's energy carries out fusion treatment, obtains gross energy, and carries out evolution processing to contour curve using the gross energy, until at evolution
The corresponding value of the corresponding level set movements equation of contour curve after reason is consistent with predetermined threshold value, then, after being handled using evolution
Contour curve as segmentation curve, to pending image carry out dividing processing, extract target image from pending image,
Improve the accuracy of target image extraction.
By referring to the drawings to the present invention exemplary embodiment detailed description, further feature of the invention and its
Advantage will be made apparent from.
Brief description of the drawings
It is combined in the description and the attached drawing of a part for constitution instruction shows the embodiment of the present invention, and even
It is used to explain the principle of the present invention together with its explanation.
Fig. 1 shows the process chart of image partition method according to an embodiment of the invention.
Fig. 2 shows the structure diagram of image segmenting device according to an embodiment of the invention.
Fig. 3 shows the hardware structure diagram of image segmenting device according to an embodiment of the invention.
Embodiment
Carry out the various exemplary embodiments of detailed description of the present invention now with reference to attached drawing.It should be noted that：Unless in addition have
Body illustrates that the unlimited system of component and the positioned opposite of step, numerical expression and the numerical value otherwise illustrated in these embodiments is originally
The scope of invention.
The description only actually at least one exemplary embodiment is illustrative to be never used as to the present invention below
And its application or any restrictions that use.
It may be not discussed in detail for technology, method and apparatus known to person of ordinary skill in the relevant, but suitable
In the case of, the technology, method and apparatus should be considered as part for specification.
In shown here and discussion all examples, any occurrence should be construed as merely exemplary, without
It is as limitation.Therefore, other examples of exemplary embodiment can have different values.
It should be noted that：Similar label and letter represents similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined, then it need not be further discussed in subsequent attached drawing in a attached drawing.
An embodiment provides a kind of image partition method.Fig. 1 shows an implementation according to the present invention
The process chart of the image partition method of example.Referring to Fig. 1, this method includes at least following steps S101 to step S106.
Step S101, initial profile curve is set in pending image.
In one embodiment of the present of invention, initial profile curve is set up using the center of pending image as first center
Confined outline curve.Initial profile curve can be any in circular curve, square curve and triangle curve.For example, can root
According to the shape of the target image split from pending image, the type of initial profile curve is determined.
Step S102, determines the corresponding global energy of initial profile curve and local energy, and according to global energy drawn game
Portion's energy, determines the corresponding gross energy of initial profile curve.
In one embodiment of the present of invention, according to the gray value of each pixel in pending image, by initial profile curve
The first grey parameter that the gray average of interior all pixels point and gray scale intermediate value weighting are handled and by initial profile curve outside
The second grey parameter that the gray average of all pixels point and gray scale intermediate value weighting are handled, determines that initial profile curve corresponds to
Global energy.
The initial profile curve of setting is closed curve, and the pixel in pending image can be divided into two parts, one
It is the pixel in initial profile curve to divide, and another part is the pixel outside initial profile curve.
According to the number of pixel in the gray value of all pixels point in initial profile curve and initial profile curve,
Obtain the gray average of all pixels point in initial profile curve.By the gray value of all pixels point in initial profile curve according to
Descending or ascending order arrangement, using the gray value of centrally located pixel as initial profile curve
The gray scale intermediate value of interior all pixels point.According to the gray value and initial profile curve of all pixels point outside initial profile curve
The number of exterior pixel point, obtains the gray average of the outer all pixels point of initial profile curve.By all pictures outside initial profile curve
The gray value of vegetarian refreshments is arranged according to descending or ascending order, by the gray value of centrally located pixel
Gray scale intermediate value as all pixels point outside initial profile curve.
When determining the first grey parameter, in initial profile curve the gray average of all pixels point and gray scale intermediate value plus
Weight coefficient can depending on target image out to be split, and the gray average of the outer all pixels point of initial profile curve and
The weighting coefficient of gray scale intermediate value can be depending on target image out to be split.
For example, following calculating formula (1) can be based on, the corresponding global energy of initial profile curve is obtained,
Wherein, E1For the corresponding global energy of initial profile curve, Ωx1For the length in the x-axis direction of pending image,
Ωy1For the length in the y-axis direction of pending image, λ1、λ2For weight coefficient, I (x1,y1) it is (the x in pending image1,
y1) place pixel gray value, m1For by the gray average of all pixels point in initial profile curve and gray scale intermediate value weighting
Manage the first obtained grey parameter, m2For by the gray average of all pixels point outside initial profile curve and gray scale intermediate value weighting
Manage the second obtained grey parameter.Wherein, pending image is a rectangle diagram picture, with the lower left corner in the rectangle diagram picture
Point as origin, using the length direction of the rectangle diagram picture as x-axis direction, using the width of the rectangle diagram picture as
Y-axis direction.λ1、λ2It can be set depending on real image disposition, specifically by tester.
In one embodiment of the present of invention, centered on each pixel in initial profile curve, image-region is set up, its
In, in each image-region, using initial profile curve as line of demarcation, each image-region is divided into the first image-region and
Two image-regions；For the corresponding image-region of any pixel in initial profile curve, according to the corresponding figure of any pixel point
As in the second gray scale of the gray value of each pixel, the first gray scale intermediate value of the first image-region and the second image-region in region
Value, determines the local energy of the corresponding image-region of any pixel point.
The gray value of all pixels point in first image-region is arranged according to ascending or descending order,
The first gray scale intermediate value using the gray value of centrally located pixel as the first image-region.By in the second image-region
The gray value of all pixels point is arranged according to ascending or descending order, by centrally located pixel
Second gray scale intermediate value of the gray value as the second image-region.
In one embodiment of the present of invention, described image region is to be set centered on each pixel in initial profile curve
Vertical circular image regions or square image-region.
For example, following calculating formula (2) can be based on, the corresponding local energy of initial profile curve is obtained,
Wherein, E2For the corresponding local energy of initial profile curve, Ωx2For the x of the corresponding image-region of a certain pixel
The length of direction of principal axis, Ωy2For the length in the y-axis direction of the corresponding image-region of a certain pixel, γ is weight coefficient, specifically
Ground, γ can be set by tester.I′(x2,y2) it is (x in the corresponding image-region of a certain pixel2, y2) place pixel
The gray value of point, d1For the first gray scale intermediate value of the first image-region, d2For the second gray scale intermediate value of the second image-region, when
(x2, y2) pixel at place is when being located at the first image-region, B (x2,y2) 1 is taken, as (x2, y2) pixel at place is located at the second image
During region, B (x2,y2) take 0.Wherein, the corresponding image-region of a certain pixel is rectangular region, with positioned at the image-region
The point in the lower left corner, using the length direction of the image-region as x-axis direction, is made as origin with the width of the image-region
For y-axis direction.
Step S103, according to gross energy, determines the corresponding value of the corresponding level set movements equation of initial profile curve.
The present embodiments relate to the evolution principle of contour curve be contour curve along the energy made inside and outside contour curve
The direction that amount reaches balance develops.When energy inside and outside contour curve reaches balance, the evolution of contour curve terminates, at this time,
The corresponding value of the corresponding level set movements equation of contour curve obtained after evolution processing is 0.
For example, the corresponding level set movements equation expression formula of contour curve is as follows：
Wherein, Φ is level set function, and t is the time, and H (Φ) is Heaviside functions (Heaviside function), and η, ν are
Weight coefficient, div (divergence) are divergence function.Wherein, η, ν can depending on real image disposition, specifically,
It can be set by tester.
Step S104, judge the corresponding value of the corresponding level set movements equation of initial profile curve whether with predetermined threshold value one
Cause.
It should be noted that corresponding level set is drilled when predetermined threshold value as makes the energy inside and outside contour curve reach balance
Change the corresponding value of equation.
Step S105, when the judgment result is No, according to gross energy, evolution processing is carried out to initial profile curve, until
The corresponding value of the corresponding level set movements equation of contour curve after evolution processing is consistent with predetermined threshold value, and will drill for the last time
Contour curve after change processing is as segmentation curve.When the determination result is yes, can be using initial profile curve as pending figure
The segmentation curve of picture, then, using the initial profile curve, dividing processing is carried out to pending image.
After the contour curve after obtaining evolution processing, first, the corresponding total energy of contour curve after evolution processing is determined
Amount, wherein, the gross energy determination mode that the corresponding gross energy of contour curve after evolution processing can be provided according to above-described embodiment
It is determined.Then, the corresponding gross energy of contour curve after being handled according to evolution, determines the contour curve pair after evolution processing
The corresponding value of level set movements equation answered.The corresponding value of the corresponding level set movements equation of contour curve after evolution processing can
It is determined according to the corresponding value of level set movements equation that above-described embodiment provides.
Step S106, using curve is split, to carrying out dividing processing in pending image.
Image partition method provided in an embodiment of the present invention, by by the corresponding global energy of contour curve and local energy
Fusion treatment is carried out, obtains gross energy, and evolution processing is carried out to contour curve using the gross energy, until after evolution processing
The corresponding value of the corresponding level set movements equation of contour curve is consistent with predetermined threshold value, then, the profile after being handled using evolution
Curve carries out dividing processing to pending image, extracts target image from pending image, improve as segmentation curve
The accuracy of target image extraction.
Based on same inventive concept, one embodiment of the present of invention additionally provides a kind of image segmenting device.
Fig. 2 shows the structure diagram of image segmenting device according to an embodiment of the invention.Referring to Fig. 2, the dress
Put and include at least：Setup module 210, for setting initial profile curve in pending image；First determining module 220, is used
In the corresponding global energy of definite initial profile curve and local energy, and according to global energy and local energy, determine initial
The corresponding gross energy of contour curve；Second determining module 230, for according to gross energy, determining the corresponding water of initial profile curve
It is flat to collect the corresponding value of EVOLUTION EQUATION；Judgment module 240, for judging that the corresponding level set movements equation of initial profile curve corresponds to
Value it is whether consistent with predetermined threshold value；Evolution processing module 250, for when the judgment result is No, according to gross energy, to initial
Contour curve carries out evolution processing, until the corresponding value of the corresponding level set movements equation of contour curve after evolution processing with it is pre-
If threshold value is consistent, and using the contour curve after last time evolution processing as segmentation curve；Split module 260, for utilizing
Split curve, dividing processing is carried out from pending image.
In one embodiment of the present of invention, the first determining module 220 is additionally operable to：According to each pixel in pending image
Gray value, the first gray scale handled by the gray average of all pixels point in initial profile curve and gray scale intermediate value weighting are joined
Number and the second grey parameter handled by the gray average of all pixels point outside initial profile curve and gray scale intermediate value weighting,
Determine the corresponding global energy of initial profile curve；And/or first determining module be additionally operable to 220：With each in initial profile curve
Centered on pixel, image-region is set up, wherein,, will be each using initial profile curve as line of demarcation in each image-region
Image-region is divided into the first image-region and the second image-region；For the corresponding figure of any pixel in initial profile curve
As region, according to the first gray scale of the gray value of each pixel, the first image-region in the corresponding image-region of any pixel point
Second gray scale intermediate value of intermediate value and the second image-region, determines the local energy of the corresponding image-region of any pixel point.
In one embodiment of the present of invention, image-region is what is set up centered on each pixel in initial profile curve
Circular image regions or square image-region.
In one embodiment of the present of invention, initial profile curve is circular curve, any in square curve, triangle curve
Kind.
Fig. 3 shows the hardware structure diagram of image segmenting device according to an embodiment of the invention.Referring to figure
3, image segmenting device includes：Memory 320 and processor 310.Wherein, memory 320 stores executable instruction, can perform and refers to
Control processor 310 is made to be operated to perform the image partition method that any of the above-described embodiment of root provides.
The present invention can be system, method and/or computer program product.Computer program product can include computer
Readable storage medium storing program for executing, containing for making processor realize the computer-readable program instructions of various aspects of the invention.
Computer-readable recording medium can keep and store to perform the tangible of the instruction that uses of equipment by instruction
Equipment.Computer-readable recording medium for example can be-- but be not limited to-- storage device electric, magnetic storage apparatus, optical storage
Equipment, electromagnetism storage device, semiconductor memory apparatus or above-mentioned any appropriate combination.Computer-readable recording medium
More specifically example (non exhaustive list) includes：Portable computer diskette, hard disk, random access memory (RAM), read-only deposit
It is reservoir (ROM), erasable programmable read only memory (EPROM or flash memory), static RAM (SRAM), portable
Compact disk read-only storage (CD-ROM), digital versatile disc (DVD), memory stick, floppy disk, mechanical coding equipment, for example thereon
It is stored with punch card or groove internal projection structure and the above-mentioned any appropriate combination of instruction.Calculating used herein above
Machine readable storage medium storing program for executing is not interpreted instantaneous signal in itself, and the electromagnetic wave of such as radio wave or other Free propagations, lead to
Cross the electromagnetic wave (for example, the light pulse for passing through fiber optic cables) of waveguide or the propagation of other transmission mediums or transmitted by electric wire
Electric signal.
Computer-readable program instructions as described herein can be downloaded to from computer-readable recording medium it is each calculate/
Processing equipment, or outer computer or outer is downloaded to by network, such as internet, LAN, wide area network and/or wireless network
Portion's storage device.Network can include copper transmission cable, optical fiber is transmitted, is wirelessly transferred, router, fire wall, interchanger, gateway
Computer and/or Edge Server.Adapter or network interface in each calculating/processing equipment are received from network to be counted
Calculation machine readable program instructions, and the computer-readable program instructions are forwarded, for the meter being stored in each calculating/processing equipment
In calculation machine readable storage medium storing program for executing.
For perform the computer program instructions that operate of the present invention can be assembly instruction, instruction set architecture (ISA) instruction,
Machine instruction, machine-dependent instructions, microcode, firmware instructions, condition setup data or with one or more programming languages
The source code or object code that any combination is write, programming language of the programming language including object-oriented-such as
Smalltalk, C++ etc., and conventional procedural programming languages-such as " C " language or similar programming language.Computer
Readable program instructions fully can on the user computer perform, partly perform on the user computer, be only as one
Vertical software kit performs, part performs or completely in remote computer on the remote computer on the user computer for part
Or performed on server.In the situation of remote computer is related to, remote computer can pass through network-bag of any kind
LAN (LAN) or wide area network (WAN)-be connected to subscriber computer are included, or, it may be connected to outer computer (such as profit
Pass through Internet connection with ISP).In certain embodiments, by using computer-readable program instructions
Status information carry out personalized customization electronic circuit, such as programmable logic circuit, field programmable gate array (FPGA) or can
Programmed logic array (PLA) (PLA), the electronic circuit can perform computer-readable program instructions, so as to fulfill each side of the present invention
Face.
Referring herein to according to the method for the embodiment of the present invention, the flow chart of device (system) and computer program product and/
Or the block diagram various aspects that the invention has been described.It should be appreciated that each square frame and flow chart of flow chart and/or block diagram and/
Or in block diagram each square frame combination, can be realized by computer-readable program instructions.
These computer-readable program instructions can be supplied to all-purpose computer, special purpose computer or other programmable datas
The processor of processing unit, so as to produce a kind of machine so that these instructions are passing through computer or other programmable datas
When the processor of processing unit performs, generate and realize work(specified in one or more of flow chart and/or block diagram square frame
The device of energy/action.These computer-readable program instructions can also be stored in a computer-readable storage medium, these refer to
Order causes computer, programmable data processing unit and/or other equipment to work in a specific way, so that, it is stored with instruction
Computer-readable medium then includes a manufacture, it includes realizing in one or more of flow chart and/or block diagram square frame
The instruction of the various aspects of defined function/action.
Computer-readable program instructions can also be loaded into computer, other programmable data processing units or other
In equipment so that series of operation steps is performed on computer, other programmable data processing units or miscellaneous equipment, with production
Raw computer implemented process, so that performed on computer, other programmable data processing units or miscellaneous equipment
Function/action specified in one or more of flow chart and/or block diagram square frame is realized in instruction.
Flow chart and block diagram in attached drawing show system, method and the computer journey of multiple embodiments according to the present invention
Architectural framework in the cards, function and the operation of sequence product.At this point, each square frame in flow chart or block diagram can generation
One module of table, program segment or a part for instruction, the module, program segment or a part for instruction include one or more use
In the executable instruction of logic function as defined in realization.At some as the function of in the realization replaced, being marked in square frame
Can be with different from the order marked in attached drawing generation.For example, two continuous square frames can essentially be held substantially in parallel
OK, they can also be performed in the opposite order sometimes, this is depending on involved function.It is also noted that block diagram and/or
The combination of each square frame and block diagram in flow chart and/or the square frame in flow chart, can use function or dynamic as defined in performing
The dedicated hardware based system made is realized, or can be realized with the combination of specialized hardware and computer instruction.It is right
It is well known that, realized for those skilled in the art by hardware mode, realized by software mode and by software and
It is all of equal value that the mode of combination of hardware, which is realized,.
Various embodiments of the present invention are described above, described above is exemplary, and non-exclusive, and
It is not limited to disclosed each embodiment.In the case of without departing from the scope and spirit of illustrated each embodiment, for this skill
Many modifications and changes will be apparent from for the those of ordinary skill in art field.The selection of term used herein, purport
Best explain the principle of each embodiment, practical application or technological improvement to the technology in market, or lead this technology
Other those of ordinary skill in domain are understood that each embodiment disclosed herein.The scope of the present invention is limited by appended claims
It is fixed.
Claims (9)
- A kind of 1. image partition method, it is characterised in that including：Initial profile curve is set in pending image；Determine the corresponding global energy of the initial profile curve and local energy, and according to the global energy and the part Energy, determines the corresponding gross energy of the initial profile curve；According to the gross energy, the corresponding value of the corresponding level set movements equation of the initial profile curve is determined；Judge whether the corresponding value of the corresponding level set movements equation of the initial profile curve is consistent with predetermined threshold value；When the judgment result is No, according to the gross energy, evolution processing is carried out to the initial profile curve, until at evolution The corresponding value of the corresponding level set movements equation of contour curve after reason is consistent with the predetermined threshold value, and last time is developed Contour curve after processing is as segmentation curve；Using curve is split, to carrying out dividing processing in the pending image.
- 2. according to the method described in claim 1, it is characterized in that, determine the corresponding global energy of the initial profile curve, Including：According to the gray value of each pixel, the gray scale by all pixels point in the initial profile curve in the pending image The first grey parameter and the ash by all pixels point outside the initial profile curve that average and gray scale intermediate value weighting are handled The second grey parameter that degree average and gray scale intermediate value weighting are handled, determines the corresponding global energy of the initial profile curve Amount；And/orDetermine the corresponding local energy of the initial profile curve, including：Centered on each pixel in the initial profile curve, image-region is set up, wherein, in each image-region, with Each image-region is divided into the first image-region and the second image-region by the initial profile curve as line of demarcation；For the corresponding image-region of any pixel in the initial profile curve, according to the corresponding figure of any pixel point As the of the gray value of each pixel in region, the first gray scale intermediate value in described first image region and second image-region Two gray scale intermediate values, determine the local energy of the corresponding image-region of any pixel point.
- 3. according to the method described in claim 2, it is characterized in that, described image region is with the initial profile curve The circular image regions set up centered on each pixel or square image-region.
- 4. according to any method in claim 1-3, it is characterised in that the initial profile curve is circular curve, It is any in square curve, triangle curve.
- A kind of 5. image segmenting device, it is characterised in that including：Setup module, for setting initial profile curve in pending image；First determining module, for determining the corresponding global energy of the initial profile curve and local energy, and according to described Global energy and the local energy, determine the corresponding gross energy of the initial profile curve；Second determining module, for according to the gross energy, determining the corresponding level set movements equation of the initial profile curve Corresponding value；Judgment module, for judge the corresponding value of the corresponding level set movements equation of the initial profile curve whether with default threshold Value is consistent；Evolution processing module, for when the judgment result is No, according to the gross energy, drilling the initial profile curve Change is handled, until the corresponding value of the corresponding level set movements equation of contour curve after evolution processing and the predetermined threshold value one Cause, and using the contour curve after last time evolution processing as segmentation curve；Split module, for using curve is split, dividing processing to be carried out from the pending image.
- 6. device according to claim 5, it is characterised in that first determining module is additionally operable to：According to the gray value of each pixel, the gray scale by all pixels point in the initial profile curve in the pending image The first grey parameter and the ash by all pixels point outside the initial profile curve that average and gray scale intermediate value weighting are handled The second grey parameter that degree average and gray scale intermediate value weighting are handled, determines the corresponding global energy of the initial profile curve Amount；And/orFirst determining module is additionally operable to：Centered on each pixel in the initial profile curve, image-region is set up, wherein, in each image-region, with Each image-region is divided into the first image-region and the second image-region by the initial profile curve as line of demarcation；For the corresponding image-region of any pixel in the initial profile curve, according to the corresponding figure of any pixel point As the of the gray value of each pixel in region, the first gray scale intermediate value in described first image region and second image-region Two gray scale intermediate values, determine the local energy of the corresponding image-region of any pixel point.
- 7. device according to claim 6, it is characterised in that described image region is with the initial profile curve The circular image regions set up centered on each pixel or square image-region.
- 8. according to any device in claim 5-7, it is characterised in that the initial profile curve is circular curve, It is any in square curve, triangle curve.
- A kind of 9. image segmenting device, it is characterised in that including：Memory and processor, wherein, the memory storage can be held Row instruction, the executable instruction control the processor to be operated to perform any one in claim 1-4 The image partition method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810085004.2A CN108038863B (en) | 2018-01-29 | 2018-01-29 | Image segmentation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810085004.2A CN108038863B (en) | 2018-01-29 | 2018-01-29 | Image segmentation method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108038863A true CN108038863A (en) | 2018-05-15 |
| CN108038863B CN108038863B (en) | 2021-02-19 |
Family
ID=62096885
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810085004.2A Active CN108038863B (en) | 2018-01-29 | 2018-01-29 | Image segmentation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108038863B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335287A (en) * | 2019-07-15 | 2019-10-15 | 北华航天工业学院 | The extracting method and device of Architectural drawing data |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070122039A1 (en) * | 2005-11-29 | 2007-05-31 | Microsoft Corporation | Segmentation of objects by minimizing global-local variational energy |
| CN103093473A (en) * | 2013-01-25 | 2013-05-08 | 北京理工大学 | Multi-target picture segmentation based on level set |
| CN103093474A (en) * | 2013-01-28 | 2013-05-08 | 电子科技大学 | Three-dimensional mammary gland ultrasound image partition method based on homoplasmon and partial energy |
| CN104077778A (en) * | 2014-07-04 | 2014-10-01 | 南京通用电器有限公司 | Method for obtaining eye state on basis of distance-regular variational level set |
| CN104361613A (en) * | 2014-11-20 | 2015-02-18 | 安徽工业大学 | Method for extracting target area in inner scene video of oven on basis of level set |
| CN105631867A (en) * | 2015-12-25 | 2016-06-01 | 中国科学院深圳先进技术研究院 | Full-automatic contrast-enhanced ultrasonic image segmentation method |
| CN105989598A (en) * | 2015-02-13 | 2016-10-05 | 中国科学院沈阳自动化研究所 | Eye fundus image vessel segmentation method based on local enhancement active contour module |
| CN107103917A (en) * | 2017-03-17 | 2017-08-29 | 福建星网视易信息系统有限公司 | Music rhythm detection method and its system |
-
2018
- 2018-01-29 CN CN201810085004.2A patent/CN108038863B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070122039A1 (en) * | 2005-11-29 | 2007-05-31 | Microsoft Corporation | Segmentation of objects by minimizing global-local variational energy |
| CN103093473A (en) * | 2013-01-25 | 2013-05-08 | 北京理工大学 | Multi-target picture segmentation based on level set |
| CN103093474A (en) * | 2013-01-28 | 2013-05-08 | 电子科技大学 | Three-dimensional mammary gland ultrasound image partition method based on homoplasmon and partial energy |
| CN104077778A (en) * | 2014-07-04 | 2014-10-01 | 南京通用电器有限公司 | Method for obtaining eye state on basis of distance-regular variational level set |
| CN104361613A (en) * | 2014-11-20 | 2015-02-18 | 安徽工业大学 | Method for extracting target area in inner scene video of oven on basis of level set |
| CN105989598A (en) * | 2015-02-13 | 2016-10-05 | 中国科学院沈阳自动化研究所 | Eye fundus image vessel segmentation method based on local enhancement active contour module |
| CN105631867A (en) * | 2015-12-25 | 2016-06-01 | 中国科学院深圳先进技术研究院 | Full-automatic contrast-enhanced ultrasonic image segmentation method |
| CN107103917A (en) * | 2017-03-17 | 2017-08-29 | 福建星网视易信息系统有限公司 | Music rhythm detection method and its system |
Non-Patent Citations (6)
| Title |
|---|
| NHAT LINH BUI ET AL: "Automatic segmentation of the nasal cavity and paranasal sinuses from cone-beam CT images", 《INT J CARS》 * |
| 刘晨 等: "一种新的活动轮廓模型图像分割方法", 《工程科学与技术》 * |
| 唐利明 等: "结合L1拟合项的Chan-Vese模型", 《计算机辅助设计与图形学学报》 * |
| 张倩 等: "基于局部中值拟合C-V模型的SAR图像分割算法", 《中国科学技术大学学报》 * |
| 李守荣 等: "基于局部与全局信息的活动轮廓图像分割模型", 《系统工程与电子技术》 * |
| 江晓亮: "基于模糊聚类及活动轮廓模型的图像分割技术研究", 《中国博士学位论文全文数据库 信息科技辑》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110335287A (en) * | 2019-07-15 | 2019-10-15 | 北华航天工业学院 | The extracting method and device of Architectural drawing data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108038863B (en) | 2021-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107833209B (en) | X-ray image detection method and device, electronic equipment and storage medium | |
| US10062203B2 (en) | Voxelization of mesh representations | |
| CN109215080A (en) | 6D Attitude estimation network training method and device based on deep learning Iterative matching | |
| US9836879B2 (en) | Mesh skinning technique | |
| CN114008663A (en) | Real-time video super-resolution | |
| CN107239491A (en) | For realizing method, equipment, browser and electronic equipment that user behavior is followed the trail of | |
| CN109858138A (en) | Room finish component processing method, device, terminal and medium based on BIM | |
| US20150172627A1 (en) | Method of creating a parallax video from a still image | |
| WO2020218111A1 (en) | Learning method and device, program, learned model, and text generation device | |
| CN110460827A (en) | The determination method, apparatus and computer storage medium of galvanometer working condition | |
| EP4123595A2 (en) | Method and apparatus of rectifying text image, training method and apparatus, electronic device, and medium | |
| CN108664860A (en) | The recognition methods of room floor plan and device | |
| CN117058261A (en) | Image generation method and device, equipment, medium and product thereof | |
| CN107798675A (en) | The detection method and device of smear in display image | |
| CN110390344A (en) | Alternative frame update method and device | |
| CN109086790A (en) | A kind of alternative manner of disaggregated model, device and electronic equipment | |
| CN108038863A (en) | Image partition method and device | |
| CN114219804A (en) | Small sample tooth detection method based on prototype segmentation network and storage medium | |
| CN114140320A (en) | Image migration method and training method and device of image migration model | |
| CN117689772A (en) | Object background synthesis method and system based on latent space feature fusion | |
| CN108241404A (en) | A kind of method, apparatus and electronic equipment for obtaining the off-line operation time | |
| CN115812206A (en) | Machine learning for high quality image processing | |
| CN116612214A (en) | Vertex weight processing method, vertex weight processing device, electronic equipment and storage medium | |
| CN115953345A (en) | Method and device for synthesizing lesions of cerebral hemorrhage medical image and storage medium | |
| US11158059B1 (en) | Image reconstruction based on edge loss |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20210720 Address after: 264300 No. 699, Jiangjun South Road, Rongcheng City, Weihai City, Shandong Province Patentee after: Rongcheng goer Technology Co.,Ltd. Address before: 266104 Room 308, North Investment Street Service Center, Laoshan District, Qingdao, Shandong. Patentee before: GOERTEK TECHNOLOGY Co.,Ltd. |