CN101231757A - Apparatus and method for analyzing picture dominant hue as well as application in picture searching thereof - Google Patents
Apparatus and method for analyzing picture dominant hue as well as application in picture searching thereof Download PDFInfo
- Publication number
- CN101231757A CN101231757A CNA2007101789838A CN200710178983A CN101231757A CN 101231757 A CN101231757 A CN 101231757A CN A2007101789838 A CNA2007101789838 A CN A2007101789838A CN 200710178983 A CN200710178983 A CN 200710178983A CN 101231757 A CN101231757 A CN 101231757A
- Authority
- CN
- China
- Prior art keywords
- color
- picture
- dominant hue
- block
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Landscapes
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a picture dominant hue analytical method, a device thereof and application thereof in search of a picture. The invention solves the problem that prior picture dominant hue analytical method determines picture dominant hue inaccurately. The method comprises the following steps: a color space is divided into x<n> color blocks, and each color block has corresponding color value scope; a predefined color is marked on each color block; color value of each pixel in a picture is acquired, and the color of each pixel point is determined according to the color value scope and the predefined color of each color block; the picture dominant hue is determined according to the ratio of the number of pixels contained in each color in the picture to the number of all of the pixels in the picture. As the color of each pixel is determined more accurately, the dominant hue of the entire picture is determined more accurately. When a search engine according to the dominant hue filtration search result is established, information of the dominant hue can be added into index information as an attribute of the picture, and the picture results meeting requirement of a user are filtered.
Description
Technical field
The present invention relates to network technology, particularly relate to a kind of picture dominant hue analytical approach, device and the application in picture searching thereof.
Background technology
In the application of picture searching, some searching methods provide the service of searching for according to the picture color.For example, the user imports the picture searching keyword, and the dominant hue of input picture, and search engine will rescreen the picture of selecting respective color and offer the user from the picture that meets searching key word.Such search is more accurate hunting zone, the user can search the picture of same colour system more easily.
In above-mentioned application, need carry out the dominant hue analysis to each width of cloth picture of search engine system storage, which kind of color the dominant hue of judging a width of cloth picture belongs to, thus the dominant hue that in search service, helps user filtering to go out to need.Because being the pixels by different colours, the various colors that comprise of a pictures constitute, therefore the judgement of dominant hue is by judging the color of each pixel, then the color of pixel is added up, the pixel quantity that comprises according to every kind of color is judged the dominant hue of picture.And wherein the judgement of each pixel color is crucial, and existing method is the color that the space length distance of utilizing pixel to arrive Standard Colors point in color space is judged this pixel.For example, Standard Colors point redness is [255:0:0] in color space, and Standard Colors point blueness is [0:0:255] in color space, and pixel [255:0:3] is nearer than blue from the space length of redness, just determines that this pixel is red.
But, there is following shortcoming in above-mentioned dominant hue determination methods: judge the color that draws by the calculating pixel point and the space length distance of Standard Colors point, sometimes with human eye to the judgement of color and misfit, promptly human eye is not complete corresponding for the sensation of color with distance in the color space.For example at RGB (Red, Green, Blue, represent red, green, blue respectively) in the color space, for predefined Standard Colors: red [255:0:0], yellow [255:255:0], blue [0:0:255], green [0:255:0], purple [255:0:255] etc., the color that pixel [150:255:0] is seen by naked eyes is green, but it is nearest from yellow in color space.Therefore, the actual color of a pixel in naked eyes always do not equal color nearest in color space.Thisly when judging the naked eyes color of a pixel, be inaccurate, cause finally deviation is appearred in the judgement of putting in order the pictures dominant hue and the judgement of human eye by weighing with the far and near method of Standard Colors point distance.In the application of picture searching, this dominant hue analytical approach causes having occurred in the Search Results picture of other tones, can not satisfy user's search need fully.
Summary of the invention
Technical matters to be solved by this invention provides a kind of picture dominant hue analytical approach, device and the application in picture searching thereof, to solve existing picture dominant hue analytical approach to the inaccurate problem of the judgement of picture dominant hue.
For solving the problems of the technologies described above,, the invention discloses following according to specific embodiment provided by the invention
Technical scheme:
A kind of picture dominant hue analytical approach comprises:
Color space is divided into x
nIndividual color block, each color block have corresponding color value scope, and wherein n is the number of dimensions of color space, the umber that x is divided for each dimension;
Each color block is marked predefined color;
Obtain the color value of each pixel in the picture, and, determine the color of each pixel according to the color value scope and the predefined color of each color block;
The ratio of all the pixel quantity of the shared picture of pixel quantity that comprise according to every kind of color in the picture is determined the picture dominant hue.
Preferably, determine the picture dominant hue according to following steps: the ratio of calculating in the picture all pixel quantity of the shared picture of pixel quantity that every kind of color comprises; When ratio met threshold condition, the color that ratio is the highest was defined as the dominant hue of picture.
Preferably, according to following steps each color block is marked predefined color: the dominant hue candidate color is defined as the predefine color; Corresponding each color block utilizes the center color value of color block to generate a monochromatic picture; Monochromatic picture and predefined color are compared, and immediate predefine color is labeled as the color of this monochromatic picture.
Wherein, can also utilize any one color value in the color block to generate a monochromatic picture.
Preferably, described method also comprises: the picture dominant hue is preserved as the attribute information of picture, and the various attribute informations of picture is applied in the picture searching as indexing key words, during search according to picture dominant hue retrieving image.
A kind of picture dominant hue analytical equipment comprises:
The color block division unit is used for color space is divided into x
nIndividual color block, each color block have corresponding color value scope, and wherein n is the number of dimensions of color space, the umber that x is divided for each dimension;
Color mark unit is used for each color block is marked predefined color;
Picture pixel analysis unit is used for obtaining the color value of each pixel of picture, and according to the color value scope and the predefined color of each color block, determines the color of each pixel;
Picture dominant hue judging unit, the ratio that is used for all pixel quantity of the shared picture of pixel quantity of comprising according to every kind of color of picture is determined the picture dominant hue.
Preferably, described device also comprises: applying unit, be used for the picture dominant hue is preserved as the attribute information of picture, and the various attribute informations of picture be applied in the picture searching as indexing key words, during search according to picture dominant hue retrieving image.
Wherein, described picture dominant hue judging unit calculates in the picture ratio of all pixel quantity of the shared picture of pixel quantity that every kind of color comprises, and when ratio met threshold condition, the color that ratio is the highest was defined as the dominant hue of picture.
Wherein, described color marks the unit dominant hue candidate color is defined as the predefine color; Corresponding each color block utilizes the center color value of color block to generate a monochromatic picture; Monochromatic picture and predefined color are compared, and immediate predefine color is labeled as the color of this monochromatic picture.
Wherein, described color mark unit further utilizes any one color value in the color block to generate a monochromatic picture.
According to specific embodiment provided by the invention, the invention discloses following technique effect:
The embodiment of the invention is divided into x with color space
nIndividual color block, and each color block marked predefined color; When judging the dominant hue of a width of cloth picture, color value scope and predefined color according to each color block, color block under each pixel of picture sought is also determined color, and the ratio of all the pixel quantity of the shared picture of pixel quantity that comprise according to every kind of color in the picture is determined the picture dominant hue then.Because each color block is enough little, the different colours in each color block can't feel difference substantially in naked eyes, and it is very accurate therefore to judge on the level of naked eyes identification for the color of each pixel.Because the judgement of each pixel color is more accurate, so the judgement of whole picture dominant hue is also corresponding more accurate.
Above-mentioned picture dominant hue determination methods is applied in the picture searching, can preserves dominant hue information as the attribute of picture, then the various attributes of picture as searching key word, in search, be used to filter the picture result.When the user selected the picture of certain dominant hue, the picture that only meets the dominant hue requirement just can be used as the result and return, and remaining result can be filtered, and satisfies the dominant hue demand of user for the picture result.
Description of drawings
Fig. 1 is the flow chart of steps of a kind of picture dominant hue analytical approach embodiment of the present invention;
Fig. 2 is the described color block tabulation of an embodiment of the invention synoptic diagram;
Fig. 3 is the structured flowchart of a kind of picture dominant hue analytical equipment embodiment of the present invention.
Embodiment
For above-mentioned purpose of the present invention, feature and advantage can be become apparent more, the present invention is further detailed explanation below in conjunction with the drawings and specific embodiments.
Judge the inaccurate problem of picture dominant hue at utilizing the color space distance, the embodiment of the invention provides a kind of determination methods of picture dominant hue, at first color space is divided into enough little color block, and manually mark the color of each color block, then each pixel of picture is sought affiliated color block, and obtain the dominant hue of a pictures by statistical computation.Described method is applied to be provided in the picture searching in the search service that dominant hue filters, and the accuracy that can improve picture search result is met the picture of user's request more.
With reference to Fig. 1, be the flow chart of steps of the described a kind of picture dominant hue analytical approach of embodiment.
Color space is divided into x
nIndividual color block, wherein n is the number of dimensions of color space, the umber that x is divided for each dimension.For example n is 3 in the RGB color space, represents Red Green Blue respectively; N is 4 in the CMYK color space, represents blue or green, pinkish red, yellow, black four kinds of colors respectively.Promptly under different color space models, the value of n is also different.
Simultaneously, each color block has corresponding color value scope.With the RGB color space is example, general three color dimensions of red, green, blue all have the individual value in 256 (0~255) in the practical application, if x gets 16, then each color block has 256/16=16 color value in each dimension (first color block is 0~15 at the color value of this dimension, second color block is 16~31 at the color value of this dimension,, the 16 color block is 240~255 at the color value of this dimension).Therefore, comprise 16 in each color block
3=4096 color values, whole color space is divided into 16 simultaneously
3=4096 color block.
In the present embodiment, selection to color space does not limit, can select RGB (Red, Green, Blue, represent red respectively, green, blue), CMYK (Cyan, Magenta, Yellow, Black, expression is blue or green respectively, pinkish red, yellow, black), HSI (Hue, Saturation, Intensity, represent tone respectively, color saturation and brightness), (Y represents luminance signal to YUV, U and V represent two carrier chrominance signals) etc. multiple color space, or CIE (Commission Intemationale de L ' Eclairage/InternationalCommission on Illumination, International Commission on Illumination, the cie color model is one of model that uses the earliest, it is a three-dimensional model, wherein, x and y bidimensional define color, the 3rd dimension definition brightness) colourity model such as.Wherein, what use in display video picture and photography is exactly RGB color space model, will be that example describes with the RGB color space hereinafter.
And, dividing on the quantity of color block, also unqualified to the value of x and n, but being different colours in the same color block, the principle of division can reach the degree that naked eyes are very difficult to differentiate, the color block that promptly marks off is enough little, and human eye can't feel difference substantially to different colours.Hereinafter also only with n value 3, x value 16, always to have 4096 color block be that example describes.
At first, present embodiment is chosen red, yellow, green, blue in the RGB color space, purple, black, white 7 kinds of colors as predefined color, and these colors may be as the dominant hue candidate color in picture searching is used.Certainly, also can other colors of predefine.Described 7 kinds of predefine colors will be used for 4096 color block are marked, and promptly these color block will be selected the color of a kind of conduct oneself from described 7 kinds of predefine colors.
Secondly, each color block in the color space all has corresponding color value scope, be that each color block all comprises multiple color, present embodiment will utilize the center color value of each color block to generate the color that monochromatic picture comes the representative color piece, manually mark the color of each monochromatic picture then.For example the RGB scope is the color block of (0~15,240~255,160~176), and the center color value is [7:247:167].To generating a monochromatic picture by color value, judge that by manual type any color in this monochromatic picture and the above-mentioned 7 kinds of predefine colors is the most approaching, immediate a kind of color is labeled as the color of this color block.Because predefined color is fewer, therefore the boundary between every kind of predefine color is easy to distinguish by naked eyes, so the color of final mark can feel consistent to color with human eye.
Need to prove, the generation of monochromatic picture not necessarily must be used the center color value of color block, because division principle according to color space, the color block that marks off is enough little, human eye can't feel difference substantially to the different colours in the same color block, so any one color value in the color block can use.At this, the purpose that generates monochromatic picture is exactly with the naked eye to provide corresponding color block should belong to which kind of predefine color.
Through the processing of step 101 and 102, the corresponding color space will obtain a tabulation.With reference to shown in Figure 2, list content is the color value scope of each color block and the predefine color of mark.
When calculating the dominant hue of a pictures, at first need to judge the color of each pixel that constitutes picture.Therefore, at first need to obtain the color value of each pixel in the picture, normally utilize image processing software to obtain, the kind of present this image processing software is many, for example open source software ImageMagick etc.Then, utilize above-mentioned color block tabulation to judge that the color value of each pixel belongs in the color value scope of which color block, for example with reference to tabulation shown in Figure 2, color value just belongs to the color block that the color value scope is (r0-15_g80-95_b0-15) for the pixel of [14:82:8].At last, according to the predefine color that color block marked in the tabulation, the color of affiliated color block is defined as the color of this pixel.
After obtaining the color of each pixel in the picture,, much has identical predefine color pixel point so can exist because predefined color is limited.Each color that a corresponding pictures is comprised is added up the pixel quantity that every kind of predefine color is comprised, and is used for the analysis of subsequent step picture dominant hue.
In actual applications, owing to reasons such as the difference of the choosing of computing formula, reference factor, criterions, it is a variety of that the pixel quantity of utilizing every kind of color to comprise judges that the mode of picture dominant hue has.And present embodiment is simultaneously with reference to two factor of judgment, and one is the ratio of all pixel quantity of the shared picture of pixel quantity that every kind of color comprises in the picture, and another is the height of ratio.Concrete determination methods is as follows:
At first calculate the ratio of all pixel quantity of the shared picture of pixel quantity that every kind of color comprises, judge then whether these ratio values meet threshold condition, if meet, continue relatively to meet which value maximum in the ratio value of threshold condition again, the color of proportion maximum is defined as the dominant hue of picture.And empirical value is got in the setting of threshold condition usually.
For example, when the ratio of certain color pixel quantity and total pixel number amount reaches more than the threshold value θ, and this kind color is when having the maximum color of pixel quantity, to judge that this color is the picture dominant hue.If the ratio of the pixel quantity of all colours and total pixel number amount is all less than θ, then this picture is judged to be dereliction tone picture.
Above-mentioned steps has promptly been finished the dominant hue of a width of cloth picture and has been judged, in this process, because each color block is enough little, the different colours in each color block can't feel difference substantially in naked eyes, and it is very accurate therefore to judge on the level of naked eyes identification for the color of each pixel.Because the judgement of each pixel color is more accurate, so the judgement of whole picture dominant hue is also corresponding more accurate.
Above-mentioned picture dominant hue determination methods is applied in the picture searching, can improves the accuracy that the picture dominant hue is judged, thereby improve the quality of Search Results.In photographic search engine, usually can join information such as the length of picture, width, byte number in the index, be used to filter the picture result during search, make the result in length that the user needs, width, byte number scope.Therefore, when the search engine that makes up according to the dominant hue filter search results, need join the attribute of dominant hue information in the index information, if comprise that whether having dominant hue to have is what color etc. as picture.When the user selected the picture of certain dominant hue, the figure sector-meeting that only meets the dominant hue requirement was used as the result and returns, and remaining result can be filtered, and satisfied the dominant hue demand of user for the picture result.For example, the user wants to look for one to be that the picture of major part is done desktop with yellow maple, can import keyword " maple ", selects mass-tone to be adjusted to " yellow " simultaneously and searches for, and the yellow maple that searches out is the yellow maple that is near the mark most; And if utilize original implementation, can comprise the maple of other colors among the result.
In search engine system, need to analyze the dominant hue of every pictures, after the dominant hue calculating of every width of cloth picture is finished, only need storage dominant hue information in the index of search, directly use the dominant hue information of storage when searching for, do not need to calculate in real time the picture dominant hue.
At above-mentioned picture dominant hue analytical approach, the present invention also provides a kind of picture dominant hue analytical equipment.With reference to Fig. 3, be the structured flowchart of described device, described device mainly comprises color block division unit 301, color mark unit 302, picture pixel analysis unit 303 and picture dominant hue judging unit 304.Wherein, the output of each unit is as the input of next unit, and the process that described four unit are carried out by an order is finished the judgement of picture dominant hue.
Described color block division unit 301 is used for color space is divided into x
nIndividual color block, each color block have corresponding color value scope, and wherein n is the number of dimensions of color space, the umber that x is divided for each dimension.The principle of dividing is that the different colours in the same color block can reach the degree that naked eyes are very difficult to differentiate, and the color block that promptly marks off is enough little, and human eye can't feel difference substantially to different colours.
Described color mark unit 302 is used for each color block is marked predefined color.At first get colors several colors in the space as predefined color, these colors may be as the dominant hue candidate color in picture searching is used, and the color block that color block division unit 301 marks off will be selected the color of a kind of conduct oneself from described predefine color.Then, utilize center color value or other color values of each color block to generate the color that a monochromatic picture is represented this color block, and judge that by manual type any color in this monochromatic picture and the above-mentioned predefine color is the most approaching, immediate a kind of color is labeled as the color of this color block.At last, a tabulation will be exported in color mark unit 302, and list content is the color value scope of each color block and the predefine color of mark.
Because predefined color is fewer, therefore the boundary between every kind of predefine color is easy to distinguish by naked eyes, so the color of final mark can feel consistent to color with human eye.And because the color block that marks off is enough little, human eye can't feel difference substantially to the different colours in the same color block, so any one color value in the color block can be with generating monochromatic picture.
Described picture pixel analysis unit 303 is used for obtaining the color value of each pixel of picture, and according to the color value scope and the predefined color of each color block, determines the color of each pixel.At first utilize image processing software to obtain the color value of all pixels that picture comprises, which color block the color value that utilizes above-mentioned tabulation to search each pixel then belongs to, and determines the color of pixel according to the corresponding relation of color block and predefine color.At last, also need to add up the pixel quantity that every kind of color comprises, statistics will be exported in picture pixel analysis unit 303.
Described picture dominant hue judging unit 304 is used for the ratio of all pixel quantity of the shared picture of pixel quantity of comprising according to every kind of color of picture and determines the picture dominant hue.In the present embodiment, picture dominant hue judging unit 304 is defined as the color that meets following two conditions simultaneously the dominant hue of picture: the ratio that condition is certain color pixel quantity and total pixel number amount meets threshold condition, and another condition is that the ratio of ratio of this color pixel quantity and total pixel number amount is the highest.
When being applied to above-mentioned picture dominant hue analytical equipment in the picture searching, preferably, also comprise applying unit 305, be used for when the search engine that makes up according to the dominant hue filter search results, the attribute of dominant hue information as picture being joined in the index information.When the user selected the picture of certain dominant hue, the figure sector-meeting that only meets the dominant hue requirement was used as the result and returns, and remaining result can be filtered, and satisfied the dominant hue demand of user for the picture result.After picture dominant hue judging unit 304 had been analyzed the dominant hue of every pictures, 305 need of applying unit are storage dominant hue information in the index of search, directly uses the dominant hue information of storage when searching for, and does not need to calculate in real time the picture dominant hue.
The division of unit is not unique in the said apparatus, in actual applications, usually a unit merged in color block division unit 301 and color mark unit 302 and is provided with, and the present invention does not limit at this.
The part that does not describe in detail in the device shown in Figure 3 can be considered for length referring to the relevant portion of method shown in Figure 1, is not described in detail in this.And instructions of the present invention only illustrates the RGB color space, and uses other color spaces or colourity model and RGB color space in like manner, all falls within protection scope of the present invention.
More than to a kind of picture dominant hue analytical approach provided by the present invention, device and the application in picture searching thereof, be described in detail, used specific case herein principle of the present invention and embodiment are set forth, the explanation of above embodiment just is used for helping to understand method of the present invention and core concept thereof; Simultaneously, for one of ordinary skill in the art, according to thought of the present invention, part in specific embodiments and applications all can change.In sum, this description should not be construed as limitation of the present invention.
Claims (10)
1. a picture dominant hue analytical approach is characterized in that, comprising:
Color space is divided into x
nIndividual color block, each color block have corresponding color value scope, and wherein n is the number of dimensions of color space, the umber that x is divided for each dimension;
Each color block is marked predefined color;
Obtain the color value of each pixel in the picture, and, determine the color of each pixel according to the color value scope and the predefined color of each color block;
The ratio of all the pixel quantity of the shared picture of pixel quantity that comprise according to every kind of color in the picture is determined the picture dominant hue.
2. method according to claim 1 is characterized in that, determines the picture dominant hue according to following steps:
Calculate in the picture ratio of all pixel quantity of the shared picture of pixel quantity that every kind of color comprises;
When ratio met threshold condition, the color that ratio is the highest was defined as the dominant hue of picture.
3. method according to claim 1 is characterized in that, according to following steps each color block is marked predefined color:
The dominant hue candidate color is defined as the predefine color;
Corresponding each color block utilizes the center color value of color block to generate a monochromatic picture;
Monochromatic picture and predefined color are compared, and immediate predefine color is labeled as the color of this monochromatic picture.
4. method according to claim 3 is characterized in that: can also utilize any one color value in the color block to generate a monochromatic picture.
5. method according to claim 1, it is characterized in that, also comprise: the picture dominant hue is preserved as the attribute information of picture, and the various attribute informations of picture is applied in the picture searching as indexing key words, during search according to picture dominant hue retrieving image.
6. a picture dominant hue analytical equipment is characterized in that, comprising:
The color block division unit is used for color space is divided into x
nIndividual color block, each color block have corresponding color value scope, and wherein n is the number of dimensions of color space, the umber that x is divided for each dimension;
Color mark unit is used for each color block is marked predefined color;
Picture pixel analysis unit is used for obtaining the color value of each pixel of picture, and according to the color value scope and the predefined color of each color block, determines the color of each pixel;
Picture dominant hue judging unit, the ratio that is used for all pixel quantity of the shared picture of pixel quantity of comprising according to every kind of color of picture is determined the picture dominant hue.
7. device according to claim 6, it is characterized in that, also comprise: applying unit is used for the picture dominant hue is preserved as the attribute information of picture, and the various attribute informations of picture are applied in the picture searching as indexing key words, during search according to picture dominant hue retrieving image.
8. device according to claim 6, it is characterized in that: described picture dominant hue judging unit calculates in the picture ratio of all pixel quantity of the shared picture of pixel quantity that every kind of color comprises, when ratio met threshold condition, the color that ratio is the highest was defined as the dominant hue of picture.
9. device according to claim 6 is characterized in that: described color mark unit is defined as the predefine color with the dominant hue candidate color; Corresponding each color block utilizes the center color value of color block to generate a monochromatic picture; Monochromatic picture and predefined color are compared, and immediate predefine color is labeled as the color of this monochromatic picture.
10. device according to claim 9 is characterized in that: described color mark unit further utilizes any one color value in the color block to generate a monochromatic picture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2007101789838A CN100568283C (en) | 2007-12-07 | 2007-12-07 | A kind of picture dominant hue analytical approach and device thereof |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2007101789838A CN100568283C (en) | 2007-12-07 | 2007-12-07 | A kind of picture dominant hue analytical approach and device thereof |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101231757A true CN101231757A (en) | 2008-07-30 |
CN100568283C CN100568283C (en) | 2009-12-09 |
Family
ID=39898201
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2007101789838A Active CN100568283C (en) | 2007-12-07 | 2007-12-07 | A kind of picture dominant hue analytical approach and device thereof |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN100568283C (en) |
Cited By (28)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101877137A (en) * | 2009-04-30 | 2010-11-03 | 国际商业机器公司 | Method for highlighting thematic element and system thereof |
CN102592272A (en) * | 2011-01-12 | 2012-07-18 | 腾讯科技(深圳)有限公司 | Extracting method and device of picture dominant tone |
CN102736920A (en) * | 2012-06-11 | 2012-10-17 | 广东欧珀移动通信有限公司 | Adaptive color matching method of desktop icon background mask |
CN102819821A (en) * | 2012-07-24 | 2012-12-12 | 浙江大学 | Method for rapidly rematching colors of product appearance based on color style transfer |
WO2013117110A1 (en) * | 2012-02-10 | 2013-08-15 | 华为终端有限公司 | Image hue determination method and wireless handheld device |
US8515164B2 (en) | 2009-07-02 | 2013-08-20 | Alibaba Group Holding Limited | Non-product image identification |
CN103268338A (en) * | 2013-05-16 | 2013-08-28 | 北京京东尚科信息技术有限公司 | Method and server device for providing images and terminal device |
CN103366178A (en) * | 2012-03-30 | 2013-10-23 | 北京百度网讯科技有限公司 | Method and device for carrying out color classification on target image |
CN103577993A (en) * | 2012-08-07 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Color selecting method and device |
CN103955952A (en) * | 2014-05-04 | 2014-07-30 | 电子科技大学 | Extraction and description method for garment image color features |
CN104636194A (en) * | 2013-11-11 | 2015-05-20 | 中兴通讯股份有限公司 | Terminal and method for terminal to achieve ranking of applications |
CN104657482A (en) * | 2015-02-26 | 2015-05-27 | 深圳市中兴移动通信有限公司 | Method for displaying application interface and terminal |
CN105469107A (en) * | 2015-11-17 | 2016-04-06 | 小米科技有限责任公司 | Image classification method and image classification device |
CN105488820A (en) * | 2016-02-25 | 2016-04-13 | 曹溯 | Color comparing method and device |
CN105551011A (en) * | 2014-10-29 | 2016-05-04 | 阿里巴巴集团控股有限公司 | Method and apparatus for setting dominant tone |
CN105761283A (en) * | 2016-02-14 | 2016-07-13 | 广州神马移动信息科技有限公司 | Picture dominant color extraction method and device |
CN106295659A (en) * | 2016-08-15 | 2017-01-04 | 惠州Tcl移动通信有限公司 | Taking pictures of a kind of smart machine takes color application process and system |
CN106780634A (en) * | 2016-12-27 | 2017-05-31 | 努比亚技术有限公司 | Picture dominant tone extracting method and device |
CN106898026A (en) * | 2017-03-15 | 2017-06-27 | 腾讯科技(深圳)有限公司 | The dominant hue extracting method and device of a kind of picture |
CN107025464A (en) * | 2017-04-13 | 2017-08-08 | 深圳市金立通信设备有限公司 | A kind of colour selecting method and terminal |
CN107563745A (en) * | 2017-09-19 | 2018-01-09 | 成都猫道科技有限公司 | Fruits and vegetables class commodity self-service is weighed and accounting device, system and application method |
CN108334531A (en) * | 2017-09-19 | 2018-07-27 | 平安普惠企业管理有限公司 | Picture tone extracting method, equipment and computer readable storage medium |
CN110083735A (en) * | 2019-04-22 | 2019-08-02 | 广州华多网络科技有限公司 | Method, apparatus, electronic equipment and the computer readable storage medium of optical sieving |
CN110648371A (en) * | 2018-06-27 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Method and device for determining mapping relation between RGB value and color number information |
CN110674329A (en) * | 2019-09-23 | 2020-01-10 | 北京百度网讯科技有限公司 | Picture filtering method and device, electronic equipment and storage medium |
CN111369431A (en) * | 2020-03-12 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Image processing method and device, readable medium and electronic equipment |
CN111862244A (en) * | 2020-07-16 | 2020-10-30 | 安徽慧视金瞳科技有限公司 | Plastic sheet intelligent color sorting method based on image processing |
CN117202451A (en) * | 2023-11-07 | 2023-12-08 | 深圳市千岩科技有限公司 | Atmosphere lamp equipment, and light-emitting control method, device and medium thereof |
-
2007
- 2007-12-07 CN CNB2007101789838A patent/CN100568283C/en active Active
Cited By (45)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101877137A (en) * | 2009-04-30 | 2010-11-03 | 国际商业机器公司 | Method for highlighting thematic element and system thereof |
CN101877137B (en) * | 2009-04-30 | 2013-01-02 | 国际商业机器公司 | Method for highlighting thematic element and system thereof |
US8515164B2 (en) | 2009-07-02 | 2013-08-20 | Alibaba Group Holding Limited | Non-product image identification |
CN102592272B (en) * | 2011-01-12 | 2017-01-25 | 深圳市世纪光速信息技术有限公司 | Extracting method and device of picture dominant tone |
CN102592272A (en) * | 2011-01-12 | 2012-07-18 | 腾讯科技(深圳)有限公司 | Extracting method and device of picture dominant tone |
WO2013117110A1 (en) * | 2012-02-10 | 2013-08-15 | 华为终端有限公司 | Image hue determination method and wireless handheld device |
US8948504B2 (en) | 2012-02-10 | 2015-02-03 | Huawei Device Co., Ltd. | Device and machine readable medium for determining image hue |
US8577133B2 (en) | 2012-02-10 | 2013-11-05 | Huawei Device Co., Ltd | Method and wireless handheld device for determining image hue |
CN103366178B (en) * | 2012-03-30 | 2017-12-29 | 北京百度网讯科技有限公司 | A kind of method and apparatus for being used to carry out target image color classification |
CN103366178A (en) * | 2012-03-30 | 2013-10-23 | 北京百度网讯科技有限公司 | Method and device for carrying out color classification on target image |
CN102736920A (en) * | 2012-06-11 | 2012-10-17 | 广东欧珀移动通信有限公司 | Adaptive color matching method of desktop icon background mask |
CN102736920B (en) * | 2012-06-11 | 2015-09-09 | 广东欧珀移动通信有限公司 | A kind of self-adaptation color matching method of desktop icon background mask |
CN102819821B (en) * | 2012-07-24 | 2015-01-28 | 浙江大学 | Method for rapidly rematching colors of product appearance based on color style transfer |
CN102819821A (en) * | 2012-07-24 | 2012-12-12 | 浙江大学 | Method for rapidly rematching colors of product appearance based on color style transfer |
CN103577993A (en) * | 2012-08-07 | 2014-02-12 | 阿里巴巴集团控股有限公司 | Color selecting method and device |
CN103577993B (en) * | 2012-08-07 | 2017-06-09 | 阿里巴巴集团控股有限公司 | Color choosing method and device |
CN103268338B (en) * | 2013-05-16 | 2016-03-30 | 北京京东尚科信息技术有限公司 | A kind of image is provided method and server unit and end device |
CN103268338A (en) * | 2013-05-16 | 2013-08-28 | 北京京东尚科信息技术有限公司 | Method and server device for providing images and terminal device |
CN104636194A (en) * | 2013-11-11 | 2015-05-20 | 中兴通讯股份有限公司 | Terminal and method for terminal to achieve ranking of applications |
CN103955952A (en) * | 2014-05-04 | 2014-07-30 | 电子科技大学 | Extraction and description method for garment image color features |
CN105551011B (en) * | 2014-10-29 | 2019-01-29 | 阿里巴巴集团控股有限公司 | A kind of setting method and device of dominant hue |
CN105551011A (en) * | 2014-10-29 | 2016-05-04 | 阿里巴巴集团控股有限公司 | Method and apparatus for setting dominant tone |
CN104657482A (en) * | 2015-02-26 | 2015-05-27 | 深圳市中兴移动通信有限公司 | Method for displaying application interface and terminal |
CN105469107B (en) * | 2015-11-17 | 2019-09-17 | 小米科技有限责任公司 | Image classification method and device |
CN105469107A (en) * | 2015-11-17 | 2016-04-06 | 小米科技有限责任公司 | Image classification method and image classification device |
CN105761283A (en) * | 2016-02-14 | 2016-07-13 | 广州神马移动信息科技有限公司 | Picture dominant color extraction method and device |
CN105761283B (en) * | 2016-02-14 | 2018-12-25 | 广州神马移动信息科技有限公司 | A kind of picture key color extraction method and device |
CN105488820B (en) * | 2016-02-25 | 2018-04-06 | 曹溯 | Color comparison method and device |
CN105488820A (en) * | 2016-02-25 | 2016-04-13 | 曹溯 | Color comparing method and device |
CN106295659A (en) * | 2016-08-15 | 2017-01-04 | 惠州Tcl移动通信有限公司 | Taking pictures of a kind of smart machine takes color application process and system |
CN106780634B (en) * | 2016-12-27 | 2019-06-18 | 努比亚技术有限公司 | Picture dominant tone extracting method and device |
CN106780634A (en) * | 2016-12-27 | 2017-05-31 | 努比亚技术有限公司 | Picture dominant tone extracting method and device |
CN106898026A (en) * | 2017-03-15 | 2017-06-27 | 腾讯科技(深圳)有限公司 | The dominant hue extracting method and device of a kind of picture |
CN106898026B (en) * | 2017-03-15 | 2019-02-05 | 腾讯科技(深圳)有限公司 | A kind of the dominant hue extracting method and device of picture |
CN107025464A (en) * | 2017-04-13 | 2017-08-08 | 深圳市金立通信设备有限公司 | A kind of colour selecting method and terminal |
CN108334531A (en) * | 2017-09-19 | 2018-07-27 | 平安普惠企业管理有限公司 | Picture tone extracting method, equipment and computer readable storage medium |
CN107563745A (en) * | 2017-09-19 | 2018-01-09 | 成都猫道科技有限公司 | Fruits and vegetables class commodity self-service is weighed and accounting device, system and application method |
CN110648371A (en) * | 2018-06-27 | 2020-01-03 | 阿里巴巴集团控股有限公司 | Method and device for determining mapping relation between RGB value and color number information |
CN110648371B (en) * | 2018-06-27 | 2023-05-09 | 阿里巴巴集团控股有限公司 | Method and device for determining mapping relation between RGB value and color number information |
CN110083735A (en) * | 2019-04-22 | 2019-08-02 | 广州华多网络科技有限公司 | Method, apparatus, electronic equipment and the computer readable storage medium of optical sieving |
CN110674329A (en) * | 2019-09-23 | 2020-01-10 | 北京百度网讯科技有限公司 | Picture filtering method and device, electronic equipment and storage medium |
CN111369431A (en) * | 2020-03-12 | 2020-07-03 | 北京字节跳动网络技术有限公司 | Image processing method and device, readable medium and electronic equipment |
CN111862244A (en) * | 2020-07-16 | 2020-10-30 | 安徽慧视金瞳科技有限公司 | Plastic sheet intelligent color sorting method based on image processing |
CN117202451A (en) * | 2023-11-07 | 2023-12-08 | 深圳市千岩科技有限公司 | Atmosphere lamp equipment, and light-emitting control method, device and medium thereof |
CN117202451B (en) * | 2023-11-07 | 2024-01-30 | 深圳市千岩科技有限公司 | Atmosphere lamp equipment, and light-emitting control method, device and medium thereof |
Also Published As
Publication number | Publication date |
---|---|
CN100568283C (en) | 2009-12-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN100568283C (en) | A kind of picture dominant hue analytical approach and device thereof | |
CN104636759B (en) | A kind of method and picture filter information recommendation system for obtaining picture and recommending filter information | |
CN101911118B (en) | Skin color evaluation method, skin color evaluation apparatus, skin color evaluation program, and recording medium with the program recorded thereon | |
US8594420B2 (en) | Color naming, color categorization and describing color composition of images | |
US20100271513A1 (en) | Selection of decorative picture suitable for input picture | |
CN112598761B (en) | Collaborative design and intelligent recommendation method for color matching of textile and clothing | |
CN104899586A (en) | Method for recognizing character contents included in image and device thereof | |
CN104636726A (en) | Method and device for identifying image colors and terminal | |
CN103310201B (en) | The recognition methods of target blend color | |
CN102592272A (en) | Extracting method and device of picture dominant tone | |
CN101213576A (en) | Album creating apparatus, album creating method and program therefor | |
CN101882315A (en) | Method for detecting skin color areas | |
CN110120034A (en) | A kind of image quality evaluating method relevant to visual perception | |
CN104637425A (en) | Assembly-line LED (light emitting diode) display unit uniformity detection method, system and device | |
RU2510935C2 (en) | Method of indexing and searching digital images | |
CN101316328A (en) | News anchor lens detection method based on space-time strip pattern analysis | |
EP2672719A2 (en) | Color calibration of a image capture device in a way that is adaptive to the scene to be captured | |
CN111340818B (en) | Hair dyeing effect graph generation method, device and computer readable storage medium | |
CN115731320A (en) | Color matching method, device and computer readable storage medium | |
EP3671754A1 (en) | Method for determining a coloration product recommendation | |
CN110097070A (en) | A kind of Chinese painting feature collection acquisition methods based on human eye visual perception | |
Foster et al. | Information limits on identification of natural surfaces by apparent colour | |
KR100243351B1 (en) | Image similarity measurement using color distribution feature in yuv color domain | |
CN104766301B (en) | A kind of monochromatic gathering algorithm based on image | |
KR100618341B1 (en) | image color analysis method based on image processing |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant |