CN106951895A - Determine the method and system of the profile of area-of-interest in image - Google Patents
Determine the method and system of the profile of area-of-interest in image Download PDFInfo
- Publication number
- CN106951895A CN106951895A CN201610009036.5A CN201610009036A CN106951895A CN 106951895 A CN106951895 A CN 106951895A CN 201610009036 A CN201610009036 A CN 201610009036A CN 106951895 A CN106951895 A CN 106951895A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel value
- value
- pixel
- profile
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of method and system for the profile for determining the area-of-interest in image.Methods described includes：Original image is transformed into HSV space, the first image is obtained；Extract second image of the described first image in channel S；The pixel Distribution value of second image is counted, pixel-value profile is obtained；Pixel value threshold value is determined according to the corresponding pixel value of trough in the pixel-value profile in centre in each trough；Binary conversion treatment generation binary image is carried out to second image according to the pixel value threshold value；The binary image is progressively scanned and record often go in the leftmost side pixel value non-zero points and the pixel value non-zero points of the rightmost side；And the pixel value non-zero points and the pixel value non-zero points of the rightmost side based on all leftmost sides recorded are fitted the profile for obtaining the area-of-interest.The method of the present invention and system can accurately and efficiently position the position of area-of-interest, it is easy to accomplish and computation complexity is low.
Description
Technical field
The present invention relates to the method and system for the profile for determining the area-of-interest in image, specifically relate to
And the outline perimeter of area-of-interest determines the area-of-interest in the picture in the case of there is shade
Profile method and system.
Background technology
At present, it is often necessary to bacterium is cultivated in culture dish, then need to count number of bacteria
To carry out follow-up bioanalysis.In order to save labour turnover, now usually using computer to number of bacteria
Counted.Specifically, culture dish image is obtained first, is then regarded using image procossing and computer
The method of feel is to the automatic counting of bacterium.Wherein it is critical that, to culture dish interior zone in image
It is accurately positioned, i.e., finds out the profile of culture dish interior zone exactly.
Due to the influence of ambient light, shade is there may be around the culture dish interior zone in image.By
In the presence of shade, the profile that traditional technique in measuring goes out has larger deviation.For example, typical method
It is after Canny rim detections, to follow the trail of continuous edge and detect continuous circle, by maximum
Circle output be used as culture dish.However, such method has many disadvantages：For example, sometimes
Because colored medium close to culture dish edge or culture dish edge there are discrete portions etc. to cause edge
It is discrete；It is sharp that culture dish periphery, which has the edge of shade and the shade, to follow-up place
Reason is adversely affected.Therefore, hatched culture dish interior zone is followed the trail of using conventional method
Edge, the culture dish interior zone exported can be offset slightly from the center of culture dish interior zone.
As can be seen here, existing scheme is influenceed by shade, it is impossible to region of interest in accurate output image
The profile in domain.Accordingly, it is desirable to provide it is a kind of determine image in area-of-interest profile method and
System, to determine the position of culture dish interior zone in image.
The content of the invention
The brief overview on the present invention is given below, to provide on some of the present invention
The basic comprehension of aspect.It should be appreciated that this general introduction is not the exhaustive general introduction on the present invention.
It is not intended to determine the key or pith of the present invention, nor the model of the intended limitation present invention
Enclose.Its purpose only provides some concepts in simplified form, more detailed in this, as what is discussed later
The preamble carefully described.
To solve the above problems, the present invention provides a kind of profile for determining the area-of-interest in image
Method and system.
There is provided a kind of profile for determining the area-of-interest in image according to an aspect of the present invention
Method, methods described includes：Original image is transformed into HSV space, the first image is obtained；Extract
Second image of the described first image in channel S；The pixel Distribution value of second image is counted,
Obtain pixel-value profile；According to the trough in the pixel-value profile in centre in each trough
Corresponding pixel value determines pixel value threshold value；Second image is carried out according to the pixel value threshold value
Binary conversion treatment generates binary image；The binary image is progressively scanned and recorded and is often gone
The pixel value non-zero points of the middle leftmost side and the pixel value non-zero points of the rightmost side；And based on the institute recorded
There are the pixel value non-zero points of the leftmost side and the pixel value non-zero points fitting of the rightmost side to obtain institute
State the profile of area-of-interest.
There is provided a kind of profile for determining the area-of-interest in image according to another aspect of the present invention
System, the system includes：Conversion equipment, the conversion equipment is used to original image being transformed into
HSV space, obtains the first image；Extraction element, the extraction element is used to extract first figure
As the second image in channel S；Statistic device, the statistic device is used to count second figure
The pixel Distribution value of picture, obtains pixel-value profile；Determining device, the determining device is used for basis
In the pixel-value profile pixel is determined in each trough in the middle corresponding pixel value of trough
It is worth threshold value；Binaryzation device, the binaryzation device is used for according to the pixel value threshold value to described the
Two images carry out binary conversion treatment generation binary image；Scanning means, the scanning means be used for pair
The binary image progressively scanned and record often go in the leftmost side pixel value non-zero points and most
The pixel value non-zero points on right side；And fitting device, the fitting device is for based on the institute recorded
There are the pixel value non-zero points of the leftmost side and the pixel value non-zero points fitting of the rightmost side to obtain institute
State the profile of area-of-interest.
Compared with prior art, method and system proposed by the present invention mainly has following benefit：1)
The position of area-of-interest (for example, culture dish interior zone) can accurately and efficiently be positioned；2)
It is easily achieved and computation complexity is well below existing scheme.
By the way that below in conjunction with accompanying drawing the following detailed description of the embodiment of the present invention, of the invention is above-mentioned
And other advantages will be apparent from.
Brief description of the drawings
In order to which the above and other advantages and features of the present invention are expanded on further, below in conjunction with the accompanying drawings to this
The embodiment of invention is described in further detail.The accompanying drawing is together with following detailed description
The part of this specification is included in this manual and formed together.With identical function and knot
The element of structure is denoted with the same reference numerals.It should be appreciated that these accompanying drawings only describe the allusion quotation of the present invention
Type example, and it is not to be taken as the restriction to the scope of the present invention.In the accompanying drawings：
Fig. 1 is the diagram according to an embodiment of the invention, shows schematically to determine in image
Area-of-interest profile method；
Fig. 2 is the diagram according to an embodiment of the invention, shows original image；
Fig. 3 is the diagram according to an embodiment of the invention, shows that original image is converted and arrives
Histogram after HSV space in channel S；
Fig. 4 is the diagram according to an embodiment of the invention, shows to determine the step of pixel value threshold value
Suddenly；
Fig. 5 be histogram as shown in Figure 3 it is smoothed after histogram smoothed curve；
Fig. 6 is the corresponding gradient curve of histogram smoothed curve as shown in Figure 5；
Fig. 7 is the diagram according to an embodiment of the invention, shows method as shown in Figure 1
Version；
Fig. 8 is the diagram according to an embodiment of the invention, shows to carry out background to original image
Image after filtering；
Fig. 9 is the diagram according to an embodiment of the invention, shows to carry out two to channel S image
Image after value processing；
Figure 10 is the diagram according to an embodiment of the invention, is shown to the image shown in Fig. 9
The profile point obtained after being progressively scanned；
Figure 11 is the diagram according to an embodiment of the invention, is shown to the profile shown in Figure 10
The diagram of the profile for the area-of-interest that point fitting is obtained；
Figure 12 is the diagram according to an embodiment of the invention, shows schematically to determine image
In area-of-interest profile system；
Figure 13 is the diagram according to an embodiment of the invention, shows schematical two-value makeup
Put；
Figure 14 is the diagram according to an embodiment of the invention, shows schematical determining unit；
Figure 15 is the diagram according to an embodiment of the invention, shows system as shown in figure 12
Version；
Figure 16 is shown available for the calculating for implementing method and system according to the embodiment of the present invention
The schematic block diagram of machine.
Embodiment
The one exemplary embodiment of the present invention is described hereinafter in connection with accompanying drawing.In order to clear and
For the sake of simplicity, all features of actual embodiment are not described in the description.However, should
Solution, must make many specific to embodiment during any this practical embodiments are developed
Determine, to realize the objectives of developer, for example, meeting that related to system and business
A little restrictive conditions, and these restrictive conditions may change with the difference of embodiment.
In addition, it also should be appreciated that, although development is likely to be extremely complex and time-consuming, but to benefiting
For those skilled in the art of present disclosure, this development is only routine task.
Herein, in addition it is also necessary to which explanation is a bit, in order to avoid having obscured this hair because of unnecessary details
It is bright, illustrate only in the accompanying drawings with according to the closely related device structure of the solution of the present invention and/or
Process step, and eliminate and the little other details of relation of the present invention.
" area-of-interest " refers to the image-region for wishing to obtain in the picture herein, in this hair
In bright preferred embodiment, " area-of-interest " refers in the culture dish image that is obtained by microscope
Culture dish interior zone.In the following description, by taking culture dish interior zone as an example, describe in detail
The method and system that the present invention is provided.
With reference first to Fig. 1 and Fig. 2, Fig. 1 is the diagram according to an embodiment of the invention, is shown
The method 1000 of the profile of the area-of-interest gone out in schematic determination image, Fig. 2 is according to this
The diagram of one embodiment of invention, shows original image.As shown in figure 1, method 1000 is wrapped
Include following steps：Original image is transformed into HSV space (step 1001)；It is extracted in channel S
On image (step 1002)；Obtain the pixel-value profile (step 1003) of the image in channel S；
Determine pixel value threshold value (step 1004)；Two are carried out to the image in channel S according to pixel value threshold value
Value processing generation binary image (step 1005)；(step is progressively scanned to binary image
It is rapid 1006)；And the recorded point (step 1007) of fitting scanning.
According to method 1000, it will be first transformed into as the original image of input signal (referring to Fig. 2)
HSV space (step 1001).In a preferred embodiment, original image refers to obtain using microscope
The culture dish image obtained.HSV space is a kind of conventional color of image space, and it includes 3 points
Amount, i.e. colourity (H), saturation degree (S) and brightness (V).Saturation degree refers to the purity of color of image
Or bright-coloured degree, purity is higher, then image appearance must be distincter, and S values are bigger；Purity is lower, then
Image appearance must be dulller, and S values are smaller.For black and white object, the value of saturation degree is 0.
Then, for the image in the image zooming-out channel S of HSV space, and count in channel S
Image pixel-value profile (step 1002 and 1003).In a preferred embodiment, utilize
Histogram characterizes foregoing pixel-value profile.Reference picture 3, Fig. 3 is an implementation according to the present invention
The diagram of mode, shows the converted histogram to after HSV space in channel S of original image.
Wherein, the histogrammic abscissa of channel S represents the pixel value of each pixel in channel S
(0-255), abbreviation S values after normalization, make S values fall between (0,1).Also, S
The ordinate of channel histogram represents the number of the pixel of each pixel value of correspondence.
In culture dish image as shown in Figure 2, image Outboard Sections include black background and white
Tray portion, this two parts image is practically free of colouring information, S value very littles, therefore, in Fig. 3 institutes
Correspond to S values less that part, i.e. S values in the channel S histogram shown to be more than 0 but be less than
0.1(0<S<0.1) image；The inside of culture dish image, is colored nutrient solution region, S
Value is larger, therefore, and that larger part of S values is corresponded in the channel S histogram shown in Fig. 3,
I.e. S values are more than 0.45 (S>0.45)；The outline portion of culture dish interior zone is mixed with outside culture dish
Side and the information of culture dish interior zone, correspond to middle area in the channel S histogram shown in Fig. 3
Domain, i.e. S values are more than 0.1 but less than 0.45 (0.1<S<0.45).
Next, pixel value threshold value is determined according to channel S histogram, that is, according to pixel Distribution value
In figure pixel value threshold value (step is determined in each trough in the middle corresponding pixel value of trough
1004).In a preferred embodiment, as shown in figure 4, determining the step 1004 of pixel value threshold value '
It may include steps of：Obtain histogram smoothed curve (step 1014)；Calculate gradient curve (step
It is rapid that 1024) and according to gradient curve pixel value threshold value (1034) is set.Specifically, first to S
Channel histogram enters column hisgram smoothly, obtains histogram smoothed curve, then calculates histogram smooth
The gradient curve of curve, then sets pixel value threshold value according to the zero crossing on gradient curve.Reference picture
5 and Fig. 6, Fig. 5 be histogram as shown in Figure 3 it is smoothed after histogram smoothed curve, Fig. 6
It is the corresponding gradient curve of histogram smoothed curve as shown in Figure 5.
It can be seen from foregoing teachings, with area-of-interest (i.e. culture dish inner area in channel S histogram
Domain) corresponding image is in the histogrammic center section of channel S, so as to for convenience of observing, such as scheme
In embodiment shown in 5, channel S histogram is entered column hisgram it is smooth when (step 1014),
The maximum of the ordinate of histogram smoothed curve is set to 1000, so as to omit more than 1000
Data.From Such analysis, the data that this part is omitted respectively correspond to culture dish Outboard Sections and
The image of culture dish inboard portion, does not include the wheel of our interested and concern culture dish interior zones
Exterior feature, so as to will not have a negative impact to subsequent operation.
Wherein it is possible to be carried out using prior arts such as mean filter or gaussian filterings to channel S histogram
Smoothly, the burr in histogram smoothed curve is removed.By taking mean filter as an example, for channel S Nogata
Every bit x on the histogram smoothed curve of figurei, with the value (x of N number of point before the pointi-1,…,xi-N)
With the value (x of N number of point after the pointi+1,…,xi+N) average as the point new value.Wherein,
N is empirical parameter, and those skilled in the art can select N value according to actual conditions.At this
In embodiment, N value is set as 5, obtain it is as shown in Figure 5 it is smoothed after histogram put down
Sliding curve.
When calculating gradient curve (step 1024) of histogram smoothed curve, obtained to smoothed
Any one point on histogram smoothed curve, the Grad of the point refers to N number of point after the point
Value and the point before N number of point value difference average.Wherein, N value is also this area
The numerical value that can be selected according to actual conditions and micro-judgment of technical staff.Here, still being taken with N
Illustrated exemplified by value 5, obtain gradient curve as shown in Figure 6.
Below, search the zero crossing on gradient curve and pixel value threshold value (step is set according to zero crossing
1034).So-called zero crossing, that is, refer on gradient curve from the occasion of changing to negative value or changed to just from negative value
The point of value.Zero crossing corresponds to the local maximum and local pole of the histogram smoothed curve shown in Fig. 5
Small value, that is, the histogrammic crest of channel S and trough shown in Fig. 3.In histogram smoothed curve
Value it is larger (part for being greater than 800), represent in original image (i.e. culture dish image)
Region than larger, corresponding to culture dish Outboard Sections and culture dish inboard portion, these regions are not
Belong to our target area.Therefore, in the histogram smoothed curve shown in Fig. 5, it is worth than larger
Region do not consider.
Also, on gradient curve from negative value change on the occasion of zero crossing (shown in the open circles in Fig. 6)
Corresponding to the trough in channel S histogram as shown in Figure 3, from the occasion of changing to negative value on gradient curve
Zero crossing (as shown in filled circles in Fig. 6) correspond to channel S histogram as shown in Figure 3 in
Crest.
It is all from negative value change on the occasion of zero crossing in, take centre the corresponding picture of a zero crossing
Element value is used as targets threshold.In other words, by find on gradient curve from negative value change on the occasion of zero passage
In point, the pixel value corresponding to a zero crossing in an intermediate position is used as pixel value threshold value.As before
It is described, on the gradient curve shown in Fig. 6 from negative value change on the occasion of zero crossing correspond to it is as shown in Figure 3
Channel S histogram in trough, that is to say, that selection channel S histogram in each trough in be in
The middle corresponding pixel value of trough is used as pixel value threshold value.In change mode, if channel S
Trough in histogram (correspond on gradient curve from negative value change on the occasion of zero crossing) sum be even
It is several, then select the corresponding pixel value of any one trough in two middle troughs in each trough
All it is feasible as pixel value threshold value.
Further, in a preferred embodiment, the second trough T2 in histogram is corresponding
Pixel value determines pixel value threshold value.
It is determined that after pixel value threshold value, binaryzation is carried out to the image in channel S according to pixel value threshold value
Processing generation binary image (step 1005), obtains image as shown in Figure 9.Specifically, exist
In preferred embodiment, the pixel value in the image in channel S higher than pixel value threshold value is set to
255, and will be equal in the image in channel S and be set to 0 less than the pixel value of pixel value threshold value.
After generation binary image, horizontal progressive scan is carried out to binary image and is recorded often to go
The pixel value non-zero points of the middle leftmost side and the pixel value non-zero points (step 1006) of the rightmost side, i.e., by
The first pixel value non-zero points and last pixel value non-zero points of often row are recorded in row scanning process.
After being progressively scanned to the image shown in Fig. 9 and recording the non-zero points information, obtain such as figure
Profile point shown in 10.
Next, pixel value non-zero points and the pixel value of the rightmost side based on all leftmost sides recorded
Non-zero points are fitted the profile (step 1007) for obtaining area-of-interest.In a preferred embodiment, it is sharp
The profile of area-of-interest, i.e., profile C as shown in figure 11 are obtained with least square fitting.
It is easily understood that the shape of area-of-interest is unrestricted, border circular areas, ellipse can be included
The various rules such as shape region and rectangular area or irregular shape.Those skilled in the art can root
According to the fit approach that the concrete shape selection of area-of-interest is suitable, herein without repeating.
Before original image is transformed into HSV space (step 1001), the sense in image is determined
The method of the profile in interest region can also be less than predetermined threshold including filtering pixel value in original image
Pixel.Reference picture 7, Fig. 7 is the diagram according to an embodiment of the invention, show as
The version of method 1000 shown in Fig. 1.In change mode as shown in Figure 7, with
The difference for determining the method 1000 of the profile of the area-of-interest in image is, method 1000 '
Before original image is transformed into HSV space (step 1001), also comprise the following steps：Filter
Except ambient noise (step 1101) and expansion process and corrosion treatment (step 1102).
Specifically, with continued reference to Fig. 2, in the original image shown in Fig. 2, four corner portions are deposited
In black region, because culture dish is in the central area of MIcrosope image, so that in image four
There is background area in weekly assembly.In order to exclude the influence of noise (i.e. surrounding black region), can first by
Four corners of image are removed.Specific way is to choose a threshold value according to experience, for example, can be with
Elect the threshold value as 20, or other filter the black region of surrounding close to 0 pixel value,
That is, the pixel value that will be less than 20 is set as 0, so as to obtain being carried out to original image shown in Fig. 8
Background filter after image.Then, the region for being filtered out pixel can be carried out well known in the art
Expansion process and corrosion treatment, herein without repeating.
The region of interest in the determination image that the present invention is provided is discussed in detail with reference to Figure 12-Figure 15
The system of the profile in domain.
First, reference picture 12, Figure 12 is the diagram according to an embodiment of the invention, is shown
The system 1200 of the schematical profile for determining the area-of-interest in image.As shown in figure 12, it is
System 1200 includes conversion equipment 1201, extraction element 1202, statistic device 1203, determining device
1204th, binaryzation device 1205, scanning means 1206 and fitting device 1207.
Wherein, conversion equipment 1201 is used to original image being transformed into HSV space.Extraction element
1202 image for being extracted in channel S.Statistic device 1203 is used to count in channel S
The pixel Distribution value of image, obtains pixel-value profile.Determining device 1204 is used for according to pixel value
Distribution map determines pixel value threshold value.In a preferred embodiment, determining device 1204 is according to pixel value
In distribution map pixel value threshold value is determined in each trough in the middle corresponding pixel value of trough.More enter
One step, pixel-value profile is characterized with histogram, and determining device 1204 is according in histogram
The corresponding pixel value of the second trough determine pixel value threshold value.
Binaryzation device 1205 is used to carry out binaryzation to the image in channel S according to pixel value threshold value
Processing generation binary image.Scanning means 1206 is used to progressively scan simultaneously binary image
The pixel value non-zero points and the pixel value non-zero points of the rightmost side of the leftmost side during record is often capable.It is fitted device
1207 is non-for pixel value non-zero points and the pixel value of the rightmost side based on all leftmost sides recorded
Zero point is fitted the profile for obtaining area-of-interest.
In preferred embodiment as shown in fig. 13 that, it is single that binaryzation device 1205 ' can include first
Member 1215 and second unit 1225.Wherein, first module 1215 will be high in the image in channel S
255 are set in the pixel value of pixel value threshold value, second unit 1225 is by the image in channel S
It is equal to and is set to 0 less than the pixel value of pixel value threshold value.
In preferred embodiment as shown in figure 14, determining device 1204 ' can include smooth unit
1214th, computing unit 1224, setting unit 1234.Wherein, smooth unit 1214 is used for Nogata
Figure carries out smoothly, obtaining histogram smoothed curve；Computing unit 1224 is smooth for calculating histogram
The gradient curve of curve；Setting unit 1234 be used for according on gradient curve Grad from negative value to
On the occasion of zero crossing in be located at middle zero crossing corresponding pixel value pixel value threshold value be set.
In preferred embodiment as shown in figure 15, system 1200 ' can also include filtering device
1208, filtering device 1208 is used to filter the pixel that pixel value in original image is less than predetermined threshold,
As it was previously stated, filtering the surrounding black in culture dish image by being positioned proximate to 0 pixel value threshold value
Region.In further preferred embodiment, system 1200 ' can also include servicing unit (figure
Do not show), servicing unit is used to carry out expansion process and corrosion treatment to the region for being filtered out pixel.
In a preferred embodiment, the profile of area-of-interest is obtained using least square fitting.
Figure 16 is shown available for the calculating for implementing method and system according to the embodiment of the present invention
The schematic block diagram of machine.
In figure 16, CPU (CPU) 1601 is according in read-only storage (ROM) 1602
The program of storage or the program that random access memory (RAM) 1603 is loaded into from storage part 1608
Perform various processing.In RAM 1603, always according to need store when CPU 1601 perform it is various
Required data during processing etc..CPU 1601, ROM 1602 and RAM 1603 are via bus
1604 are connected to each other.Input/output interface 1605 is also connected to bus 1604.
Components described below is connected to input/output interface 1605：Importation 1606 (including keyboard, mouse
Mark etc.), output par, c 1607 (including display, such as cathode-ray tube (CRT), liquid crystal
Show device (LCD) etc., and loudspeaker etc.), storage part 1608 (including hard disk etc.), communications portion
1609 (including NIC such as LAN cards, modem etc.).Communications portion 1609 is passed through
Communication process is performed by network such as internet.As needed, driver 1610 can be connected to defeated
Enter/output interface 1605.Detachable media 1611 such as disk, CD, magneto-optic disk, semiconductor are deposited
Reservoir etc. can be installed on driver 1610 as needed so that the computer read out
Program is installed in storage part 1608 as needed.
In the case where realizing above-mentioned series of processes by software, it is situated between from network such as internet or storage
Matter such as detachable media 1611 installs the program for constituting software.
It will be understood by those of skill in the art that this storage medium is not limited to its shown in Figure 16
In have program stored therein, separately distribute to provide a user the detachable media of program with equipment
1611.The example of detachable media 1611 (is included comprising disk (including floppy disk (registration mark)), CD
Compact disc read-only memory (CD-ROM) and digital universal disc (DVD)), magneto-optic disk (include mini-disk
(MD) (registration mark)) and semiconductor memory.Or, storage medium can be ROM 1602,
Hard disk for including etc., wherein computer program stored in storage part 1608, and with setting comprising them
It is standby to be distributed to user together.
The present invention also provides a kind of program product of the instruction code for the machine-readable that is stored with.It is described to refer to
When making the code be read and be performed by machine, the side realized according to the principle and design of the present invention can perform
Method.
Correspondingly, the program product for the instruction code that carries the above-mentioned machine-readable that is stored with is deposited
Storage media is intended to be included within the scope of the present invention.The storage medium include but is not limited to floppy disk, CD,
Flash memory, magneto-optic disk, storage card, memory stick etc..
It may also be noted that in the device, method and system of the present invention, each part or each step
It can decompose and/or reconfigure.These, which decompose and/or reconfigured, be considered as the present invention's
Equivalents.Also, perform above-mentioned series of processes the step of can order naturally following the instructions press
Time sequencing is performed, but and necessarily need not be performed in chronological order.Some steps can parallel or
Perform independently of one another.
Finally, in addition it is also necessary to explanation, term " comprising ", "comprising" or its any other variant
Including for nonexcludability is intended to, so that process, method, article including a series of key elements
Or equipment not only includes those key elements, but also other key elements including being not expressly set out, or
It is also to include for this process, method, article or the intrinsic key element of equipment.In addition, not having
In the case of more limitations, the key element limited by sentence "including a ...", it is not excluded that in bag
Also there is other identical element in the process, method, article or the equipment that include the key element.
Although embodiments of the invention are described in detail with reference to accompanying drawing above, it is to be understood that above
Described embodiment is only intended to the explanation present invention, and is not construed as limiting the invention.It is right
For those skilled in the art, above-mentioned embodiment can be made various changes and modifications and do not had
Have away from the spirit and scope of the invention.Therefore, the scope of the present invention only by appended claim and
Its equivalents is limited.
Note
A kind of 1. methods for the profile for determining the area-of-interest in image are attached, methods described includes：
Original image is transformed into HSV space, the first image is obtained；
Extract second image of the described first image in channel S；
The pixel Distribution value of second image is counted, pixel-value profile is obtained；
According to the corresponding pixel value of trough in the pixel-value profile in centre in each trough
Determine pixel value threshold value；
Binary conversion treatment generation binary picture is carried out to second image according to the pixel value threshold value
Picture；
The binary image is progressively scanned and record often go in the leftmost side pixel value non-zero
Point and the pixel value non-zero points of the rightmost side；And
Pixel value non-zero points and the pixel of the rightmost side based on all leftmost sides recorded
Value non-zero points are fitted the profile for obtaining the area-of-interest.
Method of the note 2. as described in note 1, wherein according to the pixel value threshold value to described second
Image, which carries out binary conversion treatment generation binary image, to be included：
Pixel value in second image higher than the pixel value threshold value is set to 255；And
It will be equal in second image and be set to 0 less than the pixel value of the pixel value threshold value.
Method of the note 3. as described in note 1, wherein the pixel-value profile includes histogram.
Method of the note 4. as described in note 3, wherein determining that pixel value threshold value includes：
The histogram is carried out smoothly, to obtain histogram smoothed curve；
Calculate the gradient curve of the histogram smoothed curve；And
According on the gradient curve Grad from negative value on the occasion of zero crossing in be located at it is middle
The corresponding pixel value of zero crossing sets the pixel value threshold value.
Method of the note 5. as described in note any one of 1 to 4, wherein determining pixel value threshold value
Including：
The corresponding pixel value of the second trough in the pixel-value profile determines the pixel value
Threshold value.
Method of the note 6. as described in note any one of 1 to 4, wherein turning by original image
Change to before HSV space, methods described also includes：
Filter the pixel that pixel value in the original image is less than predetermined threshold.
Method of the note 7. as described in note 6, also includes：
Expansion process and corrosion treatment are carried out to the region for being filtered out pixel.
Note 8. as be attached any one of 1 to 4 as described in methods, wherein the original image by
Microscope is obtained.
Method of the note 9. as described in note any one of 8, wherein the sense in the original image
Interest region includes the culture dish interior zone in the culture dish image that is obtained by the microscope.
Method of the note 10. as described in any one of note 1-4, wherein being intended using least square method
Close the profile for obtaining the area-of-interest.
It is attached a kind of 11. systems for the profile for determining the area-of-interest in image, the system bag
Include：
Conversion equipment, the conversion equipment is used to original image being transformed into HSV space, obtains the
One image；
Extraction element, the extraction element is used to extract second figure of the described first image in channel S
Picture；
Statistic device, the statistic device is used for the pixel Distribution value for counting second image, obtains
Pixel-value profile；
Determining device, the determining device be used for according in the pixel-value profile in each trough locate
Pixel value threshold value is determined in the middle corresponding pixel value of trough；
Binaryzation device, the binaryzation device is used for according to the pixel value threshold value to second figure
As carrying out binary conversion treatment generation binary image；
Scanning means, the scanning means is used to the binary image is progressively scanned and recorded
The pixel value non-zero points and the pixel value non-zero points of the rightmost side of the leftmost side in often going；And
Device is fitted, the fitting device is used for the pixel value based on all leftmost sides recorded
Non-zero points and the fitting of the pixel value non-zero points of the rightmost side obtain the profile of the area-of-interest.
System of the note 12. as described in note 11, wherein the binaryzation device includes：
First module, the first module will be higher than the picture of the pixel value threshold value in second image
Plain value is set to 255；And
Second unit, the second unit will be equal in second image and less than the pixel value threshold
The pixel value of value is set to 0.
System of the note 13. as described in note 11, wherein the pixel-value profile includes histogram.
System of the note 14. as described in note 13, wherein the determining device includes：
Smooth unit, the smooth unit is used to the histogram is carried out smoothly, to obtain histogram and put down
Sliding curve；
Computing unit, the computing unit is used for the gradient curve for calculating the histogram smoothed curve；
And
Setting unit, the setting unit be used for according on the gradient curve Grad from negative value to
On the occasion of zero crossing in be located at middle zero crossing corresponding pixel value the pixel value threshold value be set.
System of the note 15. as described in note any one of 11 to 14, wherein the determining device
The corresponding pixel value of the second trough in the pixel-value profile determines the pixel value threshold value.
System of the note 16. as described in note any one of 11 to 14, wherein the system is also wrapped
Include：
Filtering device, the filtering device is used to filter pixel value in the original image and is less than predetermined threshold
The pixel of value.
System of the note 17. as described in note 16, also includes：
Servicing unit, the servicing unit be used for be filtered out pixel region carry out expansion process and
Corrosion treatment.
System of the note 18. as described in note any one of 11 to 14, wherein the original image
Obtained by microscope.
System of the note 19. as described in note any one of 18, wherein in the original image
Area-of-interest includes the culture dish interior zone in the culture dish image that is obtained by the microscope.
System of the note 20. as described in any one of note 11-14, wherein utilizing least square method
Fitting obtains the profile of the area-of-interest.
Claims (10)
1. a kind of method for the profile for determining the area-of-interest in image, methods described includes：
Original image is transformed into HSV space, the first image is obtained；
Extract second image of the described first image in channel S；
The pixel Distribution value of second image is counted, pixel-value profile is obtained；
According to the corresponding pixel value of trough in the pixel-value profile in centre in each trough
Determine pixel value threshold value；
Binary conversion treatment generation binary picture is carried out to second image according to the pixel value threshold value
Picture；
The binary image is progressively scanned and record often go in the leftmost side pixel value non-zero
Point and the pixel value non-zero points of the rightmost side；And
Pixel value non-zero points and the pixel of the rightmost side based on all leftmost sides recorded
Value non-zero points are fitted the profile for obtaining the area-of-interest.
2. the method as described in claim 1, wherein according to the pixel value threshold value to described second
Image, which carries out binary conversion treatment generation binary image, to be included：
Pixel value in second image higher than the pixel value threshold value is set to 255；And
It will be equal in second image and be set to 0 less than the pixel value of the pixel value threshold value.
3. the method as described in claim 1, wherein the pixel-value profile includes histogram.
4. method as claimed in claim 3, wherein determining that pixel value threshold value includes：
The histogram is carried out smoothly, to obtain histogram smoothed curve；
Calculate the gradient curve of the histogram smoothed curve；And
According on the gradient curve Grad from negative value on the occasion of zero crossing in be located at it is middle
The corresponding pixel value of zero crossing sets the pixel value threshold value.
5. the method as described in any one of Claims 1-4, wherein determining pixel value threshold value
Including：
The corresponding pixel value of the second trough in the pixel-value profile determines the pixel value
Threshold value.
6. the method as described in any one of Claims 1-4, wherein turning by original image
Change to before HSV space, methods described also includes：
Filter the pixel that pixel value in the original image is less than predetermined threshold.
7. method as claimed in claim 6, also includes：
Expansion process and corrosion treatment are carried out to the region for being filtered out pixel.
8. the method as described in any one of Claims 1-4, wherein in the original image
Area-of-interest include the culture dish interior zone in the culture dish image that is obtained by microscope.
9. the method as described in any one of Claims 1-4, wherein utilizing least square method
Fitting obtains the profile of the area-of-interest.
10. a kind of system for the profile for determining the area-of-interest in image, the system includes：
Conversion equipment, the conversion equipment is used to original image being transformed into HSV space, obtains the
One image；
Extraction element, the extraction element is used to extract second figure of the described first image in channel S
Picture；
Statistic device, the statistic device is used for the pixel Distribution value for counting second image, obtains
Pixel-value profile；
Determining device, the determining device be used for according in the pixel-value profile in each trough locate
Pixel value threshold value is determined in the middle corresponding pixel value of trough；
Binaryzation device, the binaryzation device is used for according to the pixel value threshold value to second figure
As carrying out binary conversion treatment generation binary image；
Scanning means, the scanning means is used to the binary image is progressively scanned and recorded
The pixel value non-zero points and the pixel value non-zero points of the rightmost side of the leftmost side in often going；And
Device is fitted, the fitting device is used for the pixel value based on all leftmost sides recorded
Non-zero points and the fitting of the pixel value non-zero points of the rightmost side obtain the profile of the area-of-interest.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610009036.5A CN106951895A (en) | 2016-01-07 | 2016-01-07 | Determine the method and system of the profile of area-of-interest in image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610009036.5A CN106951895A (en) | 2016-01-07 | 2016-01-07 | Determine the method and system of the profile of area-of-interest in image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106951895A true CN106951895A (en) | 2017-07-14 |
Family
ID=59465687
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610009036.5A Pending CN106951895A (en) | 2016-01-07 | 2016-01-07 | Determine the method and system of the profile of area-of-interest in image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106951895A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107797517A (en) * | 2017-09-30 | 2018-03-13 | 湖南文理学院 | The method and system detected using realizing of Robot Vision steel band punching processing |
| CN107907063A (en) * | 2017-11-14 | 2018-04-13 | 湖南文理学院 | A kind of the steel band punching processing detecting system and method for view-based access control model measurement |
| CN109978773A (en) * | 2017-12-27 | 2019-07-05 | 浙江宇视科技有限公司 | Image processing method and device |
| CN111242062A (en) * | 2020-01-17 | 2020-06-05 | 于兴虎 | Image processing method and system for detecting skin position of zebra fish juvenile fish |
| CN111242963A (en) * | 2018-11-29 | 2020-06-05 | 合肥泰禾光电科技股份有限公司 | Container contour detection method and device |
| CN112686840A (en) * | 2020-12-16 | 2021-04-20 | 广州大学 | Method, system and device for detecting straw on surface of beverage packaging box and storage medium |
| CN114820591A (en) * | 2022-06-06 | 2022-07-29 | 北京医准智能科技有限公司 | Image processing method, image processing apparatus, electronic device, and medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100061655A1 (en) * | 2008-09-05 | 2010-03-11 | Digital Business Processes, Inc. | Method and Apparatus for Despeckling an Image |
| CN102938053A (en) * | 2011-08-16 | 2013-02-20 | 汪建 | Sugarcane characteristic extraction and recognition method based on computer vision |
| CN103033134A (en) * | 2013-01-07 | 2013-04-10 | 上海理工大学 | Detection system and detection method aiming at damaged optical fiber geometry parameters |
| CN104616275A (en) * | 2013-11-04 | 2015-05-13 | 北京兆维电子(集团)有限责任公司 | Defect detecting method and defect detecting device |
| CN105091756A (en) * | 2015-08-31 | 2015-11-25 | 中国烟草总公司广东省公司 | Tobacco leaf length detection method for grading tobacco leaves |
-
2016
- 2016-01-07 CN CN201610009036.5A patent/CN106951895A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20100061655A1 (en) * | 2008-09-05 | 2010-03-11 | Digital Business Processes, Inc. | Method and Apparatus for Despeckling an Image |
| CN102938053A (en) * | 2011-08-16 | 2013-02-20 | 汪建 | Sugarcane characteristic extraction and recognition method based on computer vision |
| CN103033134A (en) * | 2013-01-07 | 2013-04-10 | 上海理工大学 | Detection system and detection method aiming at damaged optical fiber geometry parameters |
| CN104616275A (en) * | 2013-11-04 | 2015-05-13 | 北京兆维电子(集团)有限责任公司 | Defect detecting method and defect detecting device |
| CN105091756A (en) * | 2015-08-31 | 2015-11-25 | 中国烟草总公司广东省公司 | Tobacco leaf length detection method for grading tobacco leaves |
Non-Patent Citations (7)
| Title |
|---|
| GANESAN P ET AL: "HSV Color Space Based Segmentation of Region of Interest in Satellite Images", 《2014 INTERNATIONAL CONFERENCE ON CONTROL, INSTRUMENTATION, COMMUNICATION AND COMPUTATIONAL TECHNOLOGIES》 * |
| LIN LIN XIONG ET AL: "Research of Double-threshold Segmentation of Brazing-area Defect of Saw Based on Otsu and HSV Color Space", 《2009 2ND INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING》 * |
| SALEM SALEH AL-AMRI ET AL: "Image Segmentation by Using Thershod Techniques", 《JOURNAL OF COMPUTING》 * |
| 张艳彬等: "实用化图像式油液污染实时检测系统研究", 《南京航空航天大学学报》 * |
| 彭真明: "《光电图像处理及应用》", 31 January 2013 * |
| 李刚等: "基于图像直方图的车牌图像二值化方法研究", 《交通运输系统工程与信息》 * |
| 王磊等: "批量图像采集中数字标识自动识别系统的构建", 《武汉船舶职业技术学院学报》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107797517A (en) * | 2017-09-30 | 2018-03-13 | 湖南文理学院 | The method and system detected using realizing of Robot Vision steel band punching processing |
| CN107907063A (en) * | 2017-11-14 | 2018-04-13 | 湖南文理学院 | A kind of the steel band punching processing detecting system and method for view-based access control model measurement |
| CN109978773A (en) * | 2017-12-27 | 2019-07-05 | 浙江宇视科技有限公司 | Image processing method and device |
| CN111242963A (en) * | 2018-11-29 | 2020-06-05 | 合肥泰禾光电科技股份有限公司 | Container contour detection method and device |
| CN111242963B (en) * | 2018-11-29 | 2024-02-13 | 合肥泰禾光电科技股份有限公司 | Container contour detection method and device |
| CN111242062A (en) * | 2020-01-17 | 2020-06-05 | 于兴虎 | Image processing method and system for detecting skin position of zebra fish juvenile fish |
| CN111242062B (en) * | 2020-01-17 | 2023-05-09 | 于兴虎 | Image processing method and system for detecting skin position of juvenile zebra fish |
| CN112686840A (en) * | 2020-12-16 | 2021-04-20 | 广州大学 | Method, system and device for detecting straw on surface of beverage packaging box and storage medium |
| CN114820591A (en) * | 2022-06-06 | 2022-07-29 | 北京医准智能科技有限公司 | Image processing method, image processing apparatus, electronic device, and medium |
| CN114820591B (en) * | 2022-06-06 | 2023-02-21 | 北京医准智能科技有限公司 | Image processing method, image processing apparatus, electronic device, and medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106951895A (en) | Determine the method and system of the profile of area-of-interest in image | |
| Hayakawa et al. | Computational nuclei segmentation methods in digital pathology: a survey | |
| CN111145209B (en) | Medical image segmentation method, device, equipment and storage medium | |
| CN105719243B (en) | Image processing apparatus and method | |
| US8073233B2 (en) | Image processor, microscope system, and area specifying program | |
| Bozorgtabar et al. | Sparse coding based skin lesion segmentation using dynamic rule-based refinement | |
| US20090290795A1 (en) | Geodesic Image and Video Processing | |
| EP1510969A1 (en) | Subject image extraction method and apparatus | |
| CN104751187A (en) | Automatic meter-reading image recognition method | |
| KR20040050909A (en) | Method and apparatus for discriminating between different regions of an image | |
| CN110930427B (en) | Image segmentation method, device and storage medium based on semantic contour information | |
| CN101593277A (en) | A kind of complicated color image Chinese version zone automatic positioning method and device | |
| JP2006260401A (en) | Image processing device, method, and program | |
| CN103632361A (en) | An image segmentation method and a system | |
| CN110517273B (en) | Cytology image segmentation method based on dynamic gradient threshold | |
| CN112465852A (en) | Improved region growing method for infrared image segmentation of power equipment | |
| CN104598907A (en) | Stroke width figure based method for extracting Chinese character data from image | |
| Chang et al. | Optimizing the decomposition for multiple foreground cosegmentation | |
| CN114067114A (en) | Area nucleus segmentation counting method based on algae cell morphology | |
| CN112949378A (en) | Bacterial microscopic image segmentation method based on deep learning network | |
| Roberts et al. | Chan–vese reformulation for selective image segmentation | |
| CN113673541A (en) | Image sample generation method for target detection and application | |
| KR20180067909A (en) | Apparatus and method for segmenting image | |
| CN115439456A (en) | Method and device for detecting and identifying object in pathological image | |
| CN114463173A (en) | Hyperspectral remote sensing image subgraph reconstruction method based on superpixel segmentation |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20170714 |