CN106504252A - A kind of color segmentation method and device of coloured image - Google Patents
A kind of color segmentation method and device of coloured image Download PDFInfo
- Publication number
- CN106504252A CN106504252A CN201610854745.3A CN201610854745A CN106504252A CN 106504252 A CN106504252 A CN 106504252A CN 201610854745 A CN201610854745 A CN 201610854745A CN 106504252 A CN106504252 A CN 106504252A
- Authority
- CN
- China
- Prior art keywords
- color
- image
- original image
- single channel
- span
- 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
Landscapes
- Facsimile Image Signal Circuits (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a kind of color segmentation method and device of coloured image, the method includes:Colour original picture to be split is decomposed into multiple single channel images corresponding with the color space for setting;According to intrinsic value distribution of the color in color space is extracted, determine and extract span of the color in each single channel image;The pixel that value in original image in each single channel component meets span is converted to the first gray scale, the rest of pixels in original image is converted to the second gray scale, generating only includes the mask image of the first gray areas and the second gray areas;Be partitioned in original image and the parts of images corresponding to the first gray areas, obtain the parts of images for only including that color is extracted in original image.The accuracy that image segmentation is carried out for color is higher, it is not necessary to carries out Coordinate Conversion to extracting the image corresponding to color, it is to avoid the detection mistake occurred due to manual operation or error, reduces the complexity of color segmentation, with preferable versatility.
Description
Technical field
The present invention relates to technical field of image processing, the color segmentation method and device of espespecially a kind of coloured image.
Background technology
Image segmentation refers to and image is divided into according to the uniform criterion of phase Sihe the image sets for not overlapping mutually, being connected in itself
The process of unit, is the committed step from image procossing to graphical analyses, and the quality of image segmentation quality, after largely decide
The effect of continuous graphical analyses.Coloured image provides the information of more horn of plenty, the therefore segmentation to coloured image than gray level image
Increasingly draw attention.
The color corresponding image labelling for extracting will be wanted usually manually to the color segmentation of coloured image at this stage
Out, the coordinate system that the image for marking is located with image is being changed, so that it is determined that going out to extract corresponding to color
The position coordinateses of image, the feature further according to the coordinate pair region are analyzed process.But determined by way of Freehandhand-drawing
Image-region still suffer from larger error, the precision of the stability and imaging system of image capturing system is also had higher
Require, its versatility is simultaneously little, is easy to be interfered and detection mistake occur.
Content of the invention
The embodiment of the present invention provides a kind of color segmentation method and device of coloured image, in order to improve the standard of color segmentation
Exactness, reduces the complexity of color segmentation.
In a first aspect, the embodiment of the present invention provides a kind of color segmentation method of coloured image, including:
Colour original picture to be split is decomposed into multiple single channel images corresponding with the color space for setting;
According to intrinsic value distribution of the color in the color space is extracted, determine the extraction color in each single-pass
Span in road image;
The pixel that value in the original image in each single channel component meets the span is converted to
Rest of pixels in the original image is converted to the second gray scale by one gray scale, and generating only includes first gray areas and institute
State the mask image of the second gray areas;
It is partitioned in the original image and the parts of images corresponding to first gray areas, obtains the original image
In only include described extract color parts of images.
In a kind of possible implementation, in said method provided in an embodiment of the present invention, described will be to be split
Colour original picture is decomposed into multiple single channel images corresponding with the color space for setting, including:
Colour original picture to be split is decomposed into the single channel image corresponding to tri- passages of X, Y, Z.
The intrinsic value according to extraction color in the color space is distributed, and determines the extraction color each described
Span in single channel image, including:
According to intrinsic distribution characteristicss of the color in XYZ color space are extracted, determine the extraction color in X, Y, Z respectively
Span in single channel image.
In a kind of possible implementation, in said method provided in an embodiment of the present invention, described by the artwork
Value in each single channel component as in meets the pixel of the span and is converted to the first gray scale, by the original image
In rest of pixels be converted to the second gray scale, generating only includes first gray areas with the mask of second gray areas
Image, including:
The pixel that value in the original image in each single channel component meets the span is converted to white
Rest of pixels in the original image is converted to black by color, and generating only includes the mask image of black region and white portion.
In a kind of possible implementation, in said method provided in an embodiment of the present invention, in the original image
It is partitioned into and the parts of images corresponding to first gray areas, obtaining only includes the extraction color in the original image
Parts of images, including:
The mask image is done with the original image and computing, obtaining in the original image only includes the extraction color
Parts of images.
In a kind of possible implementation, in said method provided in an embodiment of the present invention, the extraction color exists
The span of each single channel component corresponding to the intrinsic value distribution of the color space at least covers the extraction color
Span in each single channel component.
Second aspect, the embodiment of the present invention provide a kind of color segmentation device of coloured image, including:
Image conversion unit, corresponding multiple with the color space for setting for colour original picture to be split to be decomposed into
Single channel image;
Threshold value determination unit, is distributed for the intrinsic value according to extraction color in the color space, carries described in determination
Take span of the color in each single channel image;
Mask image signal generating unit, for will take described in the value satisfaction in the original image in each single channel component
The pixel of value scope is converted to the first gray scale, and the rest of pixels in the original image is converted to the second gray scale, and generating only includes
The mask image of first gray areas and second gray areas;
Color segmentation unit, for being partitioned into and the part figure corresponding to first gray areas in the original image
Picture, obtaining only includes the parts of images for extracting color in the original image.
In a kind of possible implementation, in said apparatus provided in an embodiment of the present invention, described image conversion is single
Unit, specifically for being decomposed into the single channel image corresponding to tri- passages of X, Y, Z by colour original picture to be split;
The threshold value determination unit, specifically for according to intrinsic distribution characteristicss of the color in XYZ color space are extracted, dividing
Do not determine the extraction span of the color in X, Y, Z single channel image.
In a kind of possible implementation, in said apparatus provided in an embodiment of the present invention, the mask image life
Into unit, turn specifically for the value in the original image in each single channel component to be met the pixel of the span
White is changed to, the rest of pixels in the original image is converted to black, generating only includes covering for black region and white portion
Film image.
In a kind of possible implementation, in said apparatus provided in an embodiment of the present invention, the color segmentation list
Unit, specifically for doing and computing the mask image with the original image, obtaining in the original image only includes the extraction
The parts of images of color.
In a kind of possible implementation, in said apparatus provided in an embodiment of the present invention, the extraction color exists
The span of each single channel component corresponding to the intrinsic value distribution of the color space at least covers the extraction color
Span in each single channel component.
The present invention has the beneficial effect that:
The color segmentation method and device of coloured image provided in an embodiment of the present invention, by by colour original to be split
As being decomposed into multiple single channel images corresponding with the color space of setting;According to extract color color space intrinsic value
Distribution, determines and extracts span of the color in each single channel image;Will be full for the value in original image in each single channel component
The pixel of sufficient span is converted to the first gray scale, and the rest of pixels in original image is converted to the second gray scale, and generating only includes
First gray areas and the mask image of the second gray areas;It is partitioned in original image and the portion corresponding to the first gray areas
Partial image, obtains the parts of images for only including extracting color in original image.As coloured image is transformed into color space, and root
Carry out threshold value scope according to color is extracted in the distribution characteristicss of color space, so as to generate the mask figure corresponding with color is extracted
Picture, therefore, the accuracy for carrying out image segmentation for color is higher, and need not sit to extracting the image corresponding to color
Mark conversion, it is to avoid the detection mistake occurred due to manual operation or error, reduces the complexity of color segmentation, makes the party
Method has preferable versatility.
Description of the drawings
Fig. 1 is the flow chart of the color segmentation method of coloured image in the embodiment of the present invention;
Fig. 2 a are the design sketch for arranging the threshold range for extracting color in the embodiment of the present invention;
Fig. 2 b are the schematic diagram of original image to be split in the embodiment of the present invention;
Fig. 2 c are the schematic diagram of mask image corresponding with color is extracted in the embodiment of the present invention;
Fig. 3 is the structural representation of the color segmentation device of coloured image in the embodiment of the present invention.
Specific embodiment
For problems of the prior art, the embodiment of the present invention provide a kind of color segmentation method of coloured image and
Device, in order to improve the accuracy of color segmentation, reduces the complexity of color segmentation.
In order that the object, technical solutions and advantages of the present invention are clearer, below in conjunction with accompanying drawing the present invention is made into
One step ground is described in detail, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole enforcement
Example.Embodiment in based on the present invention, those of ordinary skill in the art are obtained under the premise of creative work is not made
All other embodiment, belongs to the scope of protection of the invention.
As shown in figure 1, the color segmentation method of coloured image provided in an embodiment of the present invention, specifically may include following step
Suddenly:
S101, colour original picture to be split is decomposed into and the corresponding multiple single channel images of color space for setting;
S102, the intrinsic value according to extraction color in color space are distributed, and determine and extract color in each single channel image
In span;
S103, the pixel that the value in original image in each single channel component meets span is converted to the first gray scale,
Rest of pixels in original image is converted to the second gray scale, generating only includes the mask of the first gray areas and the second gray areas
Image;
S104, it is partitioned in original image and the parts of images corresponding to the first gray areas, obtains and only wrap in original image
Include the parts of images for extracting color.
In the specific implementation, coloured image is usually the digital picture with colouring information, before color segmentation is carried out,
First the coloured image can be changed to suitable color space.For example, digital picture can be changed to RGB color, the face
The colour space is the most frequently used color space, and any one color can be produced by the weighted superposition of Red Green Blue, but
RGB color is visually heterogeneous, and there is very strong dependency between three components, is unsuitable for being directly used in three
The image segmentation of individual component operation independent.Therefore, in said method provided in an embodiment of the present invention, HSI colors can be adopted empty
Between as set color space, image is described in terms of tone, brightness and saturation three.In addition, may be used also
Coloured image to be split is changed to CIE XYZ color spaces, so as to can be according to color mutually to be extracted in color space
Intrinsic value distribution characteristicss arrange the threshold value of entering line parameter to original image, so as to be partitioned into only comprising the part for extracting color
Image.
As coloured image is transformed into color space, and according to extracting distribution characteristicss of the color in color space determining
Threshold range, so as to generate the mask image corresponding with color is extracted, therefore, for the accuracy that color carries out image segmentation
Higher, and Coordinate Conversion need not be carried out to extracting the image corresponding to color, it is to avoid the detection occurred due to manual operation
Mistake or error, reduce the complexity of color segmentation, make the method that there is preferable versatility.
Below to said method provided in an embodiment of the present invention in each step be specifically described.
Specifically, in above-mentioned step S101, colour original picture to be split is changed to the color space for setting, tool
Body can include:
Colour original picture to be split is decomposed into the single channel image corresponding to tri- passages of X, Y, Z.
Correspondingly, above-mentioned step S102, can specifically include:
According to intrinsic distribution characteristicss of the color in XYZ color space are extracted, determine respectively and color is extracted in X, Y, Z single-pass
Span in road image.
Specifically, during using CIE XYZ color spaces as the color space for setting, original image can be decomposed into three single-passes
The corresponding image of road image, i.e. X passage, the corresponding image of Y passages and the corresponding image of Z passages.Now, in single channel image only
Comprising characteristics of image corresponding with the passage, original image taking under the corresponding component of the passage can be obtained in single channel image
Value scope and distribution situation.Three single channel images are overlapped original image is obtained.
It will be appreciated that any one color all has corresponding and unique distribution characteristicss in color space,
A corresponding span on each component in color space.Therefore, after the color for wanting to extract is determined, can be in face
A span is determined on each component in the colour space so that the original image within the span is extracted for only including
The parts of images of color.Specifically, after above-mentioned original image to be decomposed into tri- single channel images of X, Y, Z, can basis
The intrinsic value distribution characteristicss in color XYZ color space are extracted, and determine the value model for color being extracted in each component channel
Enclose, the span should be less than intrinsic span of the extraction color in the color space.
In a kind of mode of possible enforcement, also original image can be transformed into HSI color spaces, be partitioned in original image
During yl moiety image, each component of yellow in HSI can determine that according to intrinsic value distribution of the yellow in HSI color spaces
On span as shown in Figure 2 a.After each span is determined, figure that can be according to original image in the span
As determining the segmentation figure picture corresponding with color is extracted.
Further, in above-mentioned step S103, value model will be met in the value of each single channel component in original image
The pixel that encloses is converted to the first gray scale, and the rest of pixels in original image is converted to the second gray scale, and generating only includes the first gray scale
Region and the mask image of the second gray areas, can specifically include:
The pixel that value in original image in each single channel component meets span is converted to white, by original image
Rest of pixels be converted to black, generating only includes the mask image of black region and white portion.
In the specific implementation, all pixels of original image can be traveled through according to the span that determines, will can be fallen in value
Enter the original image pixel in above-mentioned span and be converted into the white image that gray scale is 255, and value is not fallen within span
Interior original image pixel is converted into the black image that gray scale is 0.Thus, can be directed to color generation one is extracted only comprising two ashes
The image of degree, wherein, is white comprising the image for extracting color part, is black not comprising other images for extracting color.With
Color is extracted for, as a example by yellow, after judging through above-mentioned value, original image is that image as shown in Figure 2 b can be generated such as
Shown in Fig. 2 c with extract color yellow corresponding to mask image.Can be seen that by the contrast images of Fig. 2 b and Fig. 2 c
White portion in the mask image of generation has yellow for only including the part of yellow, that is, the mask image for generating in original image
The profile of image and not have yellow image image information.Can after the mask image of generation and original image are done image operation
Only included the parts of images for extracting color.
Specifically, in above-mentioned step S104, it is partitioned in original image and the part corresponding to the first gray areas
Image, obtains the parts of images for only including extracting color in original image, can specifically include:
Mask image and original image are done and computing, obtain the parts of images for only including that color is extracted in original image.Due to
The mask image of generation has the profile information for extracting color corresponding image, therefore, mask image and original image is done and fortune
After calculation, the parts of images for only including extracting color is obtained in original image, and in the parts of images, includes extraction color institute
All images information in corresponding parts of images.
It should be noted that the above-mentioned extraction color that determines is according to the extraction in the span of each single channel component
Intrinsic value of the color in color space is announced and is determined, as in practical application, to be fetched color is needed
The various visual impacts to color such as background to be considered, light, therefore, extract color taking in each single channel component determining
During value scope, span can be adjusted according to practical situation and make the span that determines be suitable for being actually needed, so
And, which kind of adjustment no matter is made, color taking in the corresponding each single channel component of the intrinsic value distribution of color space is extracted
Value scope all should at least cover the span for extracting color in each single channel component.The span that determines not over
Extraction color is outside the intrinsic value of the color space.
Compared with color segmentation method of the prior art, above-mentioned color segmentation method provided in an embodiment of the present invention will
Coloured image is transformed into color space, and according to extracting distribution characteristicss of the color in color space determining span, so as to
The mask image corresponding with color is extracted is generated, and therefore, the accuracy for image segmentation being carried out for color is higher, and need not
Coordinate Conversion is carried out to extracting the image corresponding to color, it is to avoid the detection mistake occurred due to manual operation or error, drop
The low complexity of color segmentation, makes the method that there is preferable versatility.
Same inventive concept is based on, the embodiment of the present invention provides a kind of color segmentation device of coloured image, due to the dress
The principle for putting solve problem is similar to the color segmentation method of above-mentioned coloured image provided in an embodiment of the present invention, therefore the device
Enforcement may refer to the enforcement of method, repeat part and repeat no more.
As shown in figure 3, the color segmentation device of coloured image provided in an embodiment of the present invention, including:
Image conversion unit 31 is corresponding more with the color space for setting for colour original picture to be split to be decomposed into
Individual single channel image;
Threshold value determination unit 32, for according to intrinsic value distribution of the color in color space is extracted, determining and extracting color
Span in each single channel image;
Mask image signal generating unit 33, for the value in original image in each single channel component to be met the picture of span
Element is converted to the first gray scale, and the rest of pixels in original image is converted to the second gray scale, generate only include the first gray areas with
The mask image of the second gray areas;
Color segmentation unit 34, for being partitioned in original image and the parts of images corresponding to the first gray areas, obtains
Obtain the parts of images for only including that color is extracted in original image.
Coloured image is transformed into color space by the color segmentation device of coloured image provided in an embodiment of the present invention, and
According to distribution characteristicss of the color in color space are extracted come threshold value scope, so as to generate the mask corresponding with color is extracted
Image, therefore, the accuracy for carrying out image segmentation for color is higher, and need not carry out to extracting the image corresponding to color
Coordinate Conversion, it is to avoid the detection mistake occurred due to manual operation or error, reduces the complexity of color segmentation, makes this
Method has preferable versatility.
Alternatively, image conversion unit 31, specifically for being decomposed into tri- passages of X, Y, Z by colour original picture to be split
Corresponding single channel image.
Correspondingly, threshold value determination unit 32, specifically for special according to intrinsic distribution of the color in XYZ color space is extracted
Levy, determine respectively and extract span of the color in X, Y, Z single channel image.
Alternatively, mask image signal generating unit 33, specifically for meeting the value in original image in each single channel component
The pixel of span is converted to white, and the rest of pixels in original image is converted to black, generate only include black region and
The mask image of white portion.
Alternatively, color segmentation unit 34, specifically for doing and computing mask image and original image, obtains in original image
Only include the parts of images for extracting color.
The present invention is the flow process with reference to method according to embodiments of the present invention, equipment (system) and computer program
Figure and/or block diagram are describing.It should be understood that can be by computer program instructions flowchart and/or each stream in block diagram
Journey and/or the combination of square frame and flow chart and/or the flow process in block diagram and/or square frame.These computer programs can be provided
Instruct the processor of general purpose computer, special-purpose computer, Embedded Processor or other programmable data processing devices so that
A stream in flow chart is can achieve by the instruction of the computing device of the computer or other programmable data processing devices
The function of specifying in journey or one square frame of multiple flow processs and/or block diagram or multiple square frames.
These computer program instructions may be alternatively stored in and can guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works so that the instruction being stored in the computer-readable memory is produced to be included referring to
Make the manufacture of device, the command device realize in one flow process of flow chart or one square frame of multiple flow processs and/or block diagram or
The function of specifying in multiple square frames.
These computer program instructions can be also loaded in computer or other programmable data processing devices so that in meter
Series of operation steps is executed on calculation machine or other programmable devices to produce computer implemented process, so as in computer or
The instruction executed on other programmable devices provides a flow process or multiple flow processs and/or the block diagram for realization in flow chart
A square frame or multiple square frames in specify function the step of.
, but those skilled in the art once know basic creation although preferred embodiments of the present invention have been described
Property concept, then can make other change and modification to these embodiments.So, claims are intended to be construed to include excellent
Select embodiment and fall into the had altered of the scope of the invention and change.
Obviously, those skilled in the art can carry out the essence of various changes and modification without deviating from the present invention to the present invention
God and scope.So, if these modifications of the present invention and modification belong to the scope of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to comprising these changes and modification.
Claims (10)
1. a kind of color segmentation method of coloured image, it is characterised in that include:
Colour original picture to be split is decomposed into multiple single channel images corresponding with the color space for setting;
According to intrinsic value distribution of the color in the color space is extracted, determine the extraction color in each single channel figure
Span as in;
The pixel that value in the original image in each single channel component meets the span is converted to the first ash
Rest of pixels in the original image is converted to the second gray scale by degree, and generating only includes first gray areas with described the
The mask image of two gray areas;
It is partitioned in the original image and the parts of images corresponding to first gray areas, only obtains in the original image
Including the parts of images for extracting color.
2. the method for claim 1, it is characterised in that described by colour original to be split as being decomposed into and setting
The corresponding multiple single channel images of color space, including:
Colour original picture to be split is decomposed into the single channel image corresponding to tri- passages of X, Y, Z.
The intrinsic value according to extraction color in the color space is distributed, and determines the extraction color in each single-pass
Span in road image, including:
According to intrinsic distribution characteristicss of the color in XYZ color space are extracted, determine the extraction color in X, Y, Z single-pass respectively
Span in road image.
3. the method for claim 1, it is characterised in that described by the original image in each single channel component
Value meets the pixel of the span and is converted to the first gray scale, and the rest of pixels in the original image is converted to the second ash
Degree, generating only includes first gray areas and the mask image of second gray areas, including:
The pixel that value in the original image in each single channel component meets the span is converted to white, will
Rest of pixels in the original image is converted to black, and generating only includes the mask image of black region and white portion.
4. method as claimed in claim 3, it is characterised in that be partitioned in the original image and first gray areas
Corresponding parts of images, obtaining only includes the parts of images for extracting color in the original image, including:
The mask image is done with the original image and computing, obtaining only includes the portion for extracting color in the original image
Partial image.
5. the method for claim 1, it is characterised in that intrinsic value point of the extraction color in the color space
The span of each single channel component corresponding to cloth at least covers the value for extracting color in each single channel component
Scope.
6. the color segmentation device of a kind of coloured image, it is characterised in that include:
Image conversion unit, for being decomposed into multiple single-passes corresponding with the color space for setting by colour original picture to be split
Road image;
Threshold value determination unit, for according to intrinsic value distribution of the color in the color space is extracted, determining the extraction face
Span of the color in each single channel image;
Mask image signal generating unit, for will meet the value model in the value of each single channel component in the original image
The pixel that encloses is converted to the first gray scale, and the rest of pixels in the original image is converted to the second gray scale, generates described in only including
The mask image of the first gray areas and second gray areas;
Color segmentation unit, for being partitioned in the original image and the parts of images corresponding to first gray areas,
Obtaining only includes the parts of images for extracting color in the original image.
7. device as claimed in claim 6, it is characterised in that described image converting unit, specifically for by coloured silk to be split
Chromogen picture breakdown is the single channel image corresponding to tri- passages of X, Y, Z;
The threshold value determination unit, specifically for according to intrinsic distribution characteristicss of the color in XYZ color space are extracted, true respectively
The fixed extraction span of the color in X, Y, Z single channel image.
8. device as claimed in claim 6, it is characterised in that the mask image signal generating unit, specifically for by the original
Value in image in each single channel component meets the pixel of the span and is converted to white, by the original image
Rest of pixels be converted to black, generating only includes the mask image of black region and white portion.
9. device as claimed in claim 8, it is characterised in that the color segmentation unit, specifically for by the mask figure
As doing with the original image and computing, obtaining only includes the parts of images for extracting color in the original image.
10. device as claimed in claim 6, it is characterised in that intrinsic value of the extraction color in the color space
The span of the corresponding each single channel component of distribution at least covers extraction color the taking in each single channel component
Value scope.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610854745.3A CN106504252A (en) | 2016-09-27 | 2016-09-27 | A kind of color segmentation method and device of coloured image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610854745.3A CN106504252A (en) | 2016-09-27 | 2016-09-27 | A kind of color segmentation method and device of coloured image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106504252A true CN106504252A (en) | 2017-03-15 |
Family
ID=58291151
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610854745.3A Pending CN106504252A (en) | 2016-09-27 | 2016-09-27 | A kind of color segmentation method and device of coloured image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106504252A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110146509A (en) * | 2019-05-07 | 2019-08-20 | 无锡先导智能装备股份有限公司 | Battery detection method and battery detection equipment |
CN110738651A (en) * | 2019-10-17 | 2020-01-31 | 国网四川省电力公司电力科学研究院 | multi-mode multi-target dynamic indicator lamp batch detection method |
CN112560929A (en) * | 2020-12-09 | 2021-03-26 | 中国石油大学(华东) | Oil spilling area determining method and device and storage medium |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101859437A (en) * | 2010-06-13 | 2010-10-13 | 上海交通大学 | Vector image splitting method |
CN104952066A (en) * | 2015-05-11 | 2015-09-30 | 国网安徽省电力公司芜湖供电公司 | Method for identifying phase signboards of power transmission lines on basis of HSV (hue, saturation and value) color spaces |
-
2016
- 2016-09-27 CN CN201610854745.3A patent/CN106504252A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101859437A (en) * | 2010-06-13 | 2010-10-13 | 上海交通大学 | Vector image splitting method |
CN104952066A (en) * | 2015-05-11 | 2015-09-30 | 国网安徽省电力公司芜湖供电公司 | Method for identifying phase signboards of power transmission lines on basis of HSV (hue, saturation and value) color spaces |
Non-Patent Citations (2)
Title |
---|
李刚 等: "基于字符边缘颜色多分量信息的车牌定位方法", 《计算机工程》 * |
陈再良 等: "基于显著点的感兴趣区域提取及评价", 《华中科技大学(自然科学版)》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110146509A (en) * | 2019-05-07 | 2019-08-20 | 无锡先导智能装备股份有限公司 | Battery detection method and battery detection equipment |
CN110738651A (en) * | 2019-10-17 | 2020-01-31 | 国网四川省电力公司电力科学研究院 | multi-mode multi-target dynamic indicator lamp batch detection method |
CN110738651B (en) * | 2019-10-17 | 2022-07-01 | 国网四川省电力公司电力科学研究院 | Method for detecting dynamic indicator lamps in batches under multi-mode and multi-target conditions |
CN112560929A (en) * | 2020-12-09 | 2021-03-26 | 中国石油大学(华东) | Oil spilling area determining method and device and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
DE102019106252A1 (en) | Method and system for light source estimation for image processing | |
CN108293092A (en) | Parameter adjustment based on Strength Changes | |
CN105122306B (en) | Region segmentation method and check device | |
CN104504722B (en) | Method for correcting image colors through gray points | |
JP2001014456A (en) | Image processing device and program recording medium | |
JP2006229990A (en) | Video apparatus for automatically adjusting white balance and white balance adjustment method therefor | |
KR900012497A (en) | Color image processing method | |
US10878300B2 (en) | Adjusting a colour in an image | |
CN106504252A (en) | A kind of color segmentation method and device of coloured image | |
CN106407919A (en) | Image processing-based text separation method, device and image forming device | |
CN106020120A (en) | Method for generating G code by using image based on ios system | |
EP1302896A1 (en) | Process of identification of sky in an image and image obtained using this process | |
KR20200054299A (en) | Color gamut mapping method and color gamut mapping device | |
CN112529808A (en) | Image color adjusting method, device, equipment and medium | |
CN104680518A (en) | Blue screen image matting method based on chroma overflowing processing | |
CN113888534A (en) | Image processing method, electronic device and readable storage medium | |
KR101932182B1 (en) | A method and an arrangement for pseudo coloring of a digital image | |
CN108322723A (en) | A kind of compensation method of color distortion, device and television set | |
CN105321153A (en) | Video monitor low-illumination image color restoration method and device | |
US10083516B2 (en) | Method for segmenting a color image and digital microscope | |
CN102800061A (en) | High-illuminance digital image fast adaptive optimization method | |
JP2756047B2 (en) | Color image color adjustment method and apparatus, and image synthesis method | |
KR100539940B1 (en) | Method for displaying an image of sketch effect in portable terminal | |
JPH077442B2 (en) | Image processing method | |
JP4159917B2 (en) | Image reading device |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170315 |