CN106611431A - An image detection method and apparatus - Google Patents
An image detection method and apparatus Download PDFInfo
- Publication number
- CN106611431A CN106611431A CN201510695116.6A CN201510695116A CN106611431A CN 106611431 A CN106611431 A CN 106611431A CN 201510695116 A CN201510695116 A CN 201510695116A CN 106611431 A CN106611431 A CN 106611431A
- Authority
- CN
- China
- Prior art keywords
- picture
- color
- detected
- pixel
- value
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
Abstract
The application brings forward an image detection method and apparatus. The image detection method comprises the following steps: conducting image segmenting of an image to be detected to obtain a plurality of image sub-blocks; obtaining color values of the image sub-blocks in a preset scope, conducting clustering according to the color values and determining a background color of the image to be detected according to the clustering result; selecting one or more image sub-blocks, the distances between whose color values and the background color are smaller than a preset distance value in the plurality of image sub-blocks obtained after the image segmenting; calculating a ratio of the total number of pixels of the selected image sub-block to the total number of pixels contained in the image to be detected; and judging whether the image to be detected is a background image of a pure color according to the ratio. The method can effectively detect the background image of a pure color, and can also detect an image of a specific color.
Description
Technical field
The application is related to technical field of image processing, more particularly to a kind of picture detection method and device.
Background technology
The solid background of picture refers to that the background color of picture is single, without complicated texture or color change.In practical application
Under scene, the background color for detecting picture is needed, and whether be that pure color carries out subsequent treatment according to background color.
Lack the detection method of effective solid background picture in prior art.
The content of the invention
The application is intended at least to solve to a certain extent one of technical problem in correlation technique.
For this purpose, a purpose of the application is to propose a kind of picture detection method, the method can effectively detect pure color
Background picture.
Further object is to propose a kind of picture detection means.
To reach above-mentioned purpose, the picture detection method that the application first aspect embodiment is proposed, including：To picture to be detected
Image segmentation is carried out, multiple images sub-block is obtained；The color value of the image subblock in preset range is obtained, and according to color
Value is clustered, and according to cluster result the background colour of picture to be detected is determined；The multiple images sub-block obtained after image segmentation
In, select color value to be less than one or more image subblocks of predeterminable range value with the distance of the background colour；Calculate the choosing
The ratio of the total pixel sum included with picture to be detected of pixel that the image subblock selected is included；Sentenced according to the ratio
Whether the picture to be detected that breaks is solid background picture.
The picture detection method that the application first aspect embodiment is proposed, by carrying out image segmentation, cluster and ratio calculated,
Solid background picture can be effectively detected, facilitates subsequent treatment.
To reach above-mentioned purpose, the picture detection means that the application second aspect embodiment is proposed, including：Segmentation module, uses
In image segmentation is carried out to picture to be detected, multiple images sub-block is obtained；Cluster module, for obtaining in preset range
The color value of image subblock, and clustered according to color value, the background colour of picture to be detected is determined according to cluster result；Choosing
Module is selected, in the multiple images sub-block that obtains after image segmentation, selecting color value to be less than with the distance of the background colour
One or more image subblocks of predeterminable range value；Computing module, the pixel that the image subblock for calculating the selection is included
The ratio of the total pixel sum included with picture to be detected of point；First judge module, for being treated according to the ratio in judgement
Whether detection picture is solid background picture.
The picture detection means that the application second aspect embodiment is proposed, by carrying out image segmentation, cluster and ratio calculated,
Solid background picture can be effectively detected, facilitates subsequent treatment.
The aspect and advantage that the application is added will be set forth in part in the description, and partly will from the following description become bright
It is aobvious, or recognized by the practice of the application.
Description of the drawings
The above-mentioned and/or additional aspect of the application and advantage will be apparent from from the following description of the accompanying drawings of embodiments
With it is easy to understand, wherein：
Fig. 1 is the schematic flow sheet of the picture detection method that the embodiment of the application one is proposed；
Fig. 2 is to judge that whether the background color of picture to be detected is the schematic flow sheet of particular color in the embodiment of the present application；
Fig. 3 is the schematic flow sheet of the picture detection method that another embodiment of the application is proposed；
Fig. 4 be the background color detected in the embodiment of the present application be particular color picture schematic diagram；
Fig. 5 is the schematic flow sheet that solid background fraction is calculated in the embodiment of the present application；
Fig. 6 is the schematic diagram of the solid background picture detected in the embodiment of the present application；
Fig. 7 is the schematic diagram of the ninsolid color background picture detected in the embodiment of the present application；
Fig. 8 is the structural representation of the picture detection means that another embodiment of the application is proposed；
Fig. 9 is the structural representation of the picture detection means that another embodiment of the application is proposed.
Specific embodiment
Embodiments herein is described below in detail, the example of the embodiment is shown in the drawings, wherein identical from start to finish
Or similar label represents same or similar module or the module with same or like function.Retouch below with reference to accompanying drawing
The embodiment stated is exemplary, is only used for explaining the application, and it is not intended that the restriction to the application.Conversely, this Shen
Embodiment please includes all changes, modification and the equivalent fallen in the range of the spirit and intension of attached claims.
Fig. 1 is the schematic flow sheet of the picture detection method that the embodiment of the application one is proposed, the method includes：
S11：Image segmentation is carried out to picture to be detected, multiple images sub-block is obtained.
Before image segmentation, whether the background color that can first judge picture to be detected is particular color, be not special
Carry out image segmentation when determining color again.
Wherein, particular color can pre-set.
In some embodiments, referring to Fig. 2, whether the background color for judging picture to be detected is particular color, can be included：
S21：Whether the color for judging each edge in the four edges of picture to be detected respectively is particular color.
Referring to Fig. 3, whether the color for judging each edge is particular color, can be included：
S31：Respectively each edge in the four edges of picture to be detected is corresponded to into current detection as the side of current detection
Side, scans the pixel value of the corresponding N rows pixel in side of current detection, wherein, N is preset value.
For example, N is 3, then scan the pixel value of 3 row pixels of each edge in 4 sides respectively.
S32：The pixel value of the pixel obtained according to scanning, it is determined that the ratio shared by the pixel in the range of particular color
Example.
Wherein it is possible to threshold value T is pre-set, if between the pixel value of a pixel and the numerical value of particular color
Difference absolute value be less than or equal to T, it is determined that the pixel is in the range of particular color.Afterwards, can calculate
The sum M 1 of the pixel on each side in the range of particular color, and, all pixels point for obtaining is scanned on the side
Sum M 2, then the ratio shared by the pixel in the range of particular color is M1/M2.
S33：If the ratio is more than or equal to preset ratio value, it is determined that the side of current detection is particular color.
For example, preset ratio value is 75%, then the ratio shared by the pixel in the range of particular color is more than or equal to
When 75%, then the side that can determine current detection is particular color.
S22：The number on the side of particular color is determined according to judged result, when the number is more than or equal to predetermined number value
When, the background color for judging picture to be detected is particular color.
For example, predetermined number value is 3, then when the number on the side of particular color is 3 or 4, judge picture to be detected
Background color be particular color.Otherwise, when the number on the side of particular color is less than predetermined number value, determine to be checked
The background color of mapping piece is not particular color.
For example, with reference to Fig. 4, be a background color be particular color, and particular color is the picture of white.
Referring to Fig. 3, judge current detection side whether be particular color after, it may be determined that the number on the side of particular color
(S34), and according to the number judge whether the background color of picture to be detected is particular color (S35).
So that image segmentation is super-pixel segmentation as an example, in super-pixel segmentation, can be clustered using simple linear iteration
(Simple linear iterative clustering, SLIC) method carries out super-pixel segmentation, or, also may be used
To carry out super-pixel segmentation using SEEDS methods, Turbopixel methods etc..The present embodiment using SLIC methods being entered
As a example by row super-pixel segmentation.
When super-pixel segmentation is carried out using SLIC methods, first view data is switched to into CIELAB by primary color space
Color space, adds pixel position after normalization, forms 5 dimension data spaces；Regulation grid is selected apart from the K of S
Individual cluster centre Ck=[lk,ak,bk,xk,yk]T；Data point is calculated around cluster centre in the range of 2S × 2S in cluster
The distance of the heart, data point is put under in nearest cluster.
Wherein, l, a, b are value of the pixel in Lab color spaces, and x, y are the abscissas and vertical coordinate of pixel.
In the above process, apart from DsComputing formula be：
Wherein, m is tight factor.
S12：The color value of the image subblock in preset range is obtained, and is clustered according to color value, it is true according to cluster result
The background colour of fixed picture to be detected；
Wherein, so that image subblock is the super-pixel block obtained after super-pixel segmentation as an example, the super-pixel block in preset range is for example
It is the super-pixel block on four sides of neighbouring picture to be detected.
The color value of super-pixel block can specifically refer to lab color averages, and the computing formula of lab color averages is：
Clustering algorithm is, for example, kmeans clusters, and kmeans clusters for example select k=2, and data dimension is 3.
Determine that the background colour of picture to be detected for example includes according to cluster result：To count out most cluster centres comprising data
Color value be defined as the background colour (L of picture to be detectedB,aB,bB)。
S13：In the multiple images sub-block obtained after image segmentation, color value is selected to be less than with the distance of the background colour default
One or more image subblocks of distance value.
S14：Calculate the total ratio total with picture to be detected is included pixel of pixel that the image subblock of the selection is included
Value.For example, with reference to Fig. 5, by taking super-pixel block as an example, S13-S14 can be specifically included：
S51：Obtain in the super-pixel block obtained after super-pixel segmentation and meet pre-conditioned super-pixel block, and it is pre- to obtain satisfaction
If pixel that the super-pixel block of condition is included sum, wherein, pre-conditioned is color value with the distance of background colour less than default
Distance value.
For example, meet pre-conditioned super-pixel block and refer to the super-pixel block for meeting equation below：
Wherein θ is predeterminable range value, if the lab color averages of super-pixel block are little with the distance of the background colour of picture to be detected
In θ, then judge that the super-pixel block color is identical with the background colour of picture to be detected.For example, threshold θ is set to 100.
After acquisition meets pre-conditioned super-pixel block, the pixel that these super-pixel block are included can be added, be obtained
To meeting the pixel sum p that pre-conditioned super-pixel block is includedθ。
S52：Calculating meets the total pixel sum included with picture to be detected of pixel that pre-conditioned super-pixel block is included
Ratio.
For example, the ratio is properly termed as solid background fraction, therefore, the calculating of the solid background fraction pr of picture to be detected is public
Formula is：
Pr=pθ/pall
Wherein, pallFor the pixel sum that picture to be detected is included.
S15：Whether it is solid background picture according to ratio in judgement picture to be detected.
For example, when the ratio is more than preset fraction value, it is determined that picture to be detected is solid background picture, otherwise, it determines
Picture to be detected is not solid background picture.
For example, preset fraction value selects to be 0.3.
It is a solid background picture for example, with reference to Fig. 6, is a ninsolid color background picture referring to Fig. 7.
Further, referring to Fig. 3, can also include：
It is that the picture of particular color carries out filtration treatment (S36) to background color, and/or, solid background picture is filtered
Process (S37).In addition, when the background color of picture is not particular color, and picture is not when being solid background picture, then may be used
To process (S38) according to normal picture, normal picture is such as preserved.
In the present embodiment, by carrying out image segmentation, cluster and ratio calculated, solid background picture can be effectively detected,
Facilitate subsequent treatment.Furthermore it is also possible to detect the picture of particular color.
Fig. 8 is the structural representation of the picture detection means that another embodiment of the application is proposed, the device 80 includes：Segmentation mould
Block 81, cluster module 82, selecting module 83, the judge module 85 of computing module 84 and first.
Segmentation module 81, for carrying out image segmentation to picture to be detected, obtains multiple images sub-block；
In some embodiments, referring to Fig. 9, the device can also include：
Second judge module 86, for judging whether the background color of picture to be detected is particular color, not to be specific
During color, triggering segmentation module carries out image segmentation to picture to be detected.
Wherein, particular color can pre-set.
Referring to Fig. 9, second judge module includes：
First module 861, whether the color for each edge in the four edges for judging picture to be detected respectively is specific face
Color；
Optionally, the first module specifically for：
Respectively each edge in the four edges of picture to be detected is corresponded to into the side of current detection as the side of current detection,
The pixel value of the corresponding N rows pixel in side of scanning current detection, wherein, N is preset value；
For example, N is 3, then scan the pixel value of 3 row pixels of each edge in 4 sides respectively.
The pixel value of the pixel obtained according to scanning, it is determined that the ratio shared by the pixel in the range of particular color；
Wherein it is possible to threshold value T is pre-set, if between the pixel value of a pixel and the numerical value of particular color
Difference absolute value be less than or equal to T, it is determined that the pixel is in the range of particular color.Afterwards, can calculate
The sum M 1 of the pixel on each side in the range of particular color, and, all pixels point for obtaining is scanned on the side
Sum M 2, then the ratio shared by the pixel in the range of particular color is M1/M2.
If the ratio is more than or equal to preset ratio value, it is determined that the side of current detection is particular color.
For example, preset ratio value is 75%, then the ratio shared by the pixel in the range of particular color is more than or equal to
When 75%, then the side that can determine current detection is particular color.
Second unit 862, for determining the number on the side of particular color according to judged result, when the number is more than or waits
When predetermined number value, the background color for judging picture to be detected is particular color.
For example, predetermined number value is 3, then when the number on the side of particular color is 3 or 4, judge picture to be detected
Background color be particular color.
So that image segmentation is super-pixel segmentation as an example, in super-pixel segmentation, can be clustered using simple linear iteration
(Simple linear iterative clustering, SLIC) method carries out super-pixel segmentation, or, also may be used
To carry out super-pixel segmentation using SEEDS methods, Turbopixel methods etc..The present embodiment using SLIC methods being entered
As a example by row super-pixel segmentation.
When super-pixel segmentation is carried out using SLIC methods, first view data is switched to into CIELAB by primary color space
Color space, adds pixel position after normalization, forms 5 dimension data spaces；Regulation grid is selected apart from the K of S
Individual cluster centre Ck=[lk,ak,bk,xk,yk]T；Data point is calculated around cluster centre in the range of 2S × 2S in cluster
The distance of the heart, data point is put under in nearest cluster.Wherein, l, a, b are value of the pixel in Lab color spaces,
X, y are the abscissas and vertical coordinate of pixel.
In the above process, apart from DsComputing formula be：
Wherein, m is tight factor.
Cluster module 82, for obtaining the color value of the image subblock in preset range, and is clustered, root according to color value
Determine the background colour of picture to be detected according to cluster result；
Wherein, so that image subblock is the super-pixel block obtained after super-pixel segmentation as an example, the super-pixel block in preset range is for example
It is the super-pixel block on four sides of neighbouring picture to be detected.
The color value of super-pixel block can specifically refer to lab color averages, and the computing formula of lab color averages is：
Clustering algorithm is, for example, kmeans clusters, and kmeans clusters for example select k=2, and data dimension is 3.
Optionally, cluster module is used to determine the background colour of picture to be detected according to cluster result, including：
The background colour of picture to be detected will be defined as comprising the count out color value of most cluster centres of data.
Selecting module 83, in the multiple images sub-block that obtains after image segmentation, selecting color value and the background colour
One or more image subblocks of distance less than predeterminable range value；
Computing module 84, the total picture included with picture to be detected of the pixel that the image subblock for calculating the selection is included
The ratio of vegetarian refreshments sum；
For example, by taking super-pixel block as an example, selecting module specifically for：
Obtain in the super-pixel block obtained after super-pixel segmentation and meet pre-conditioned super-pixel block, and obtain the default bar of satisfaction
The pixel sum that the super-pixel block of part is included, wherein, pre-conditioned is that color value is less than predeterminable range with the distance of background colour
Value；
For example, meet pre-conditioned super-pixel block and refer to the super-pixel block for meeting equation below：
Wherein θ is predeterminable range value, if the lab color averages of super-pixel block are little with the distance of the background colour of picture to be detected
In θ, then judge that the super-pixel block color is identical with the background colour of picture to be detected.For example, threshold θ is set to 100.
After acquisition meets pre-conditioned super-pixel block, the pixel that these super-pixel block are included can be added, be obtained
To meeting the pixel sum p that pre-conditioned super-pixel block is includedθ。
Accordingly, computing module specifically for：Calculating meet pixel that pre-conditioned super-pixel block includes it is total with it is to be checked
The ratio of the pixel sum that mapping piece is included.
For example, the ratio is properly termed as solid background fraction, therefore, the calculating of the solid background fraction pr of picture to be detected is public
Formula is：
Pr=pθ/pall
Wherein, pallFor the pixel sum that picture to be detected is included.
Second judge module 85, for whether being solid background picture according to ratio in judgement picture to be detected.
For example, the second judge module specifically for：
When the ratio is more than preset fraction value, determine that picture to be detected is solid background picture.
For example, when solid background fraction is more than preset fraction value, it is determined that picture to be detected is solid background picture, otherwise,
Determine that picture to be detected is not solid background picture.
For example, preset fraction value selects to be 0.3.
In some embodiments, referring to Fig. 9, the device also includes：
Processing module 87, the picture for background color being particular color carries out filtration treatment, and/or, to solid background
Picture carries out filtration treatment.
In addition, when the background color of picture is not particular color, and picture is not when being solid background picture, then can be according to just
Often picture processing, such as preserves normal picture.
In the present embodiment, by carrying out image segmentation, cluster and ratio calculated, solid background picture can be effectively detected,
Facilitate subsequent treatment.Furthermore it is also possible to detect the picture of particular color.
It should be noted that in the description of the present application, term " first ", " second " etc. are only used for describing purpose, and
It is not intended that indicating or implying relative importance.Additionally, in the description of the present application, unless otherwise stated, " multiple "
Implication refer at least two.
In flow chart or here any process described otherwise above or method description are construed as, expression includes one
Or more module, fragment or parts for being used for the code of executable instruction the step of realize specific logical function or process,
And the scope of the preferred implementation of the application includes other realization, wherein order that is shown or discussing can not be pressed,
Including according to involved function by it is basic simultaneously in the way of or in the opposite order, carry out perform function, this should be by the application's
Embodiment person of ordinary skill in the field understood.
It should be appreciated that each several part of the application can be realized with hardware, software, firmware or combinations thereof.In above-mentioned reality
In applying mode, software that multiple steps or method can in memory and by suitable instruction execution system be performed with storage or
Firmware is realizing.For example, if realized with hardware, and in another embodiment, can be with well known in the art
Any one of row technology or their combination are realizing：With for realizing the logic gates of logic function to data signal
Discrete logic, the special IC with suitable combinational logic gate circuit, programmable gate array (PGA) is existing
Field programmable gate array (FPGA) etc..
Those skilled in the art be appreciated that to realize all or part of step that above-described embodiment method is carried is can
Completed with the hardware that correlation is instructed by program, described program can be stored in a kind of computer-readable recording medium,
The program upon execution, including one or a combination set of the step of embodiment of the method.
Additionally, each functional unit in the application each embodiment can be integrated in a processing module, or each
Individual unit is individually physically present, it is also possible to which two or more units are integrated in a module.Above-mentioned integrated module was both
Can be realized in the form of hardware, it would however also be possible to employ the form of software function module is realized.If the integrated module with
The form of software function module is realized and as independent production marketing or when using, it is also possible to be stored in a computer-readable
In taking storage medium.
Storage medium mentioned above can be read only memory, disk or CD etc..
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specific example ",
Or the description of " some examples " etc. means to combine specific features, structure, material or feature that the embodiment or example are described
In being contained at least one embodiment of the application or example.In this manual, the schematic representation of above-mentioned term is differed
Surely identical embodiment or example are referred to.And, the specific features of description, structure, material or feature can be any
One or more embodiments or example in combine in an appropriate manner.
Although embodiments herein has been shown and described above, it is to be understood that above-described embodiment be it is exemplary,
It is not intended that the restriction to the application, one of ordinary skill in the art within the scope of application can be to above-described embodiment
It is changed, changes, replacing and modification.
Claims (10)
1. a kind of picture detection method, it is characterised in that include：
Image segmentation is carried out to picture to be detected, multiple images sub-block is obtained；
The color value of the image subblock in preset range is obtained, and is clustered according to color value, determined according to cluster result and treated
The background colour of detection picture；
In the multiple images sub-block obtained after image segmentation, color value is selected to be less than predeterminable range with the distance of the background colour
One or more image subblocks of value；
Calculate the total ratio total with picture to be detected is included pixel of pixel that the image subblock of the selection is included；
Whether it is solid background picture according to ratio in judgement picture to be detected.
2. method according to claim 1, it is characterised in that also include：
Whether the background color for judging picture to be detected is particular color, so as to when not being particular color, to picture to be detected
Carry out image segmentation.
3. method according to claim 2, it is characterised in that whether the background color for judging picture to be detected be
Particular color, including：
Whether the color for judging each edge in the four edges of picture to be detected respectively is particular color；
The number on the side of particular color is determined according to judged result, when the number is more than or equal to predetermined number value,
The background color for judging picture to be detected is particular color.
4. method according to claim 3, it is characterised in that in the four edges for judging picture to be detected respectively
The color of each edge whether be particular color, including：
Respectively each edge in the four edges of picture to be detected is corresponded to into the side of current detection as the side of current detection,
The pixel value of the corresponding N rows pixel in side of scanning current detection, wherein, N is preset value；
The pixel value of the pixel obtained according to scanning, it is determined that the ratio shared by the pixel in the range of particular color；
If the ratio is more than or equal to preset ratio value, it is determined that the side of current detection is particular color.
5. method according to claim 1, it is characterised in that the back of the body that picture to be detected is determined according to cluster result
Scenery, including：
The background colour of picture to be detected will be defined as comprising the count out color value of most cluster centres of data.
6. method according to claim 1, it is characterised in that it is described according to ratio in judgement picture to be detected whether
For solid background picture, including：
When the ratio is more than preset fraction value, determine that picture to be detected is solid background picture.
7. the method according to any one of claim 1-6, it is characterised in that also include：
It is that the picture of particular color carries out filtration treatment to background color, and/or, filtration treatment is carried out to solid background picture.
8. a kind of picture detection means, it is characterised in that include：
Segmentation module, for carrying out image segmentation to picture to be detected, obtains multiple images sub-block；
Cluster module, for obtaining the color value of the image subblock in preset range, and is clustered according to color value, according to
Cluster result determines the background colour of picture to be detected；
Selecting module, in the multiple images sub-block that obtains after image segmentation, select color value and the background colour away from
From one or more image subblocks less than predeterminable range value；
Computing module, the total pixel included with picture to be detected of the pixel that the image subblock for calculating the selection is included
The ratio of point sum；
First judge module, for whether being solid background picture according to ratio in judgement picture to be detected.
9. device according to claim 8, it is characterised in that also include：
Second judge module, for judging whether the background color of picture to be detected is particular color, so as not to being particular color
It is that triggering segmentation module carries out image segmentation to picture to be detected.
10. device according to claim 8 or claim 9, it is characterised in that also include：
Processing module, the picture for background color being particular color carries out filtration treatment, and/or, to solid background picture
Carry out filtration treatment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510695116.6A CN106611431A (en) | 2015-10-22 | 2015-10-22 | An image detection method and apparatus |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510695116.6A CN106611431A (en) | 2015-10-22 | 2015-10-22 | An image detection method and apparatus |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106611431A true CN106611431A (en) | 2017-05-03 |
Family
ID=58613190
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510695116.6A Pending CN106611431A (en) | 2015-10-22 | 2015-10-22 | An image detection method and apparatus |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106611431A (en) |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107577654A (en) * | 2017-09-14 | 2018-01-12 | 掌阅科技股份有限公司 | E-book color matching method, electronic equipment and storage medium based on front cover analysis |
| CN109272526A (en) * | 2017-07-17 | 2019-01-25 | 北京京东尚科信息技术有限公司 | Image processing method, system and electronic equipment |
| CN109903210A (en) * | 2019-01-04 | 2019-06-18 | 阿里巴巴集团控股有限公司 | Minimizing technology, device and the server of watermark |
| CN110084801A (en) * | 2019-04-28 | 2019-08-02 | 深圳回收宝科技有限公司 | A kind of detection method of terminal screen, device, portable terminal and storage medium |
| CN110717865A (en) * | 2019-09-02 | 2020-01-21 | 苏宁云计算有限公司 | Picture detection method and device |
| CN112199131A (en) * | 2019-07-08 | 2021-01-08 | 腾讯科技（深圳）有限公司 | Page detection method, device and equipment |
| CN112784854A (en) * | 2020-12-30 | 2021-05-11 | 成都云盯科技有限公司 | Method, device and equipment for segmenting and extracting clothing color based on mathematical statistics |
| CN112991470A (en) * | 2021-02-08 | 2021-06-18 | 上海通办信息服务有限公司 | Method and system for checking photo background color of certificate under complex background |
| CN113240649A (en) * | 2021-05-19 | 2021-08-10 | 姚坚超 | Building component detection method and system based on image analysis |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334835A (en) * | 2008-07-28 | 2008-12-31 | 上海高德威智能交通系统有限公司 | Color recognition method |
| CN102842135A (en) * | 2012-07-17 | 2012-12-26 | 杭州淘淘搜科技有限公司 | Method of detecting main body area of product image |
| CN103176994A (en) * | 2011-12-21 | 2013-06-26 | 阿里巴巴集团控股有限公司 | Method and system for issuing advertising data on advertising areas |
| CN104103082A (en) * | 2014-06-06 | 2014-10-15 | 华南理工大学 | Image saliency detection method based on region description and priori knowledge |
| CN104537679A (en) * | 2015-01-16 | 2015-04-22 | 厦门大学 | Cartoon picture saliency detecting method based on superpixel topology analysis |
-
2015
- 2015-10-22 CN CN201510695116.6A patent/CN106611431A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101334835A (en) * | 2008-07-28 | 2008-12-31 | 上海高德威智能交通系统有限公司 | Color recognition method |
| CN103176994A (en) * | 2011-12-21 | 2013-06-26 | 阿里巴巴集团控股有限公司 | Method and system for issuing advertising data on advertising areas |
| CN102842135A (en) * | 2012-07-17 | 2012-12-26 | 杭州淘淘搜科技有限公司 | Method of detecting main body area of product image |
| CN104103082A (en) * | 2014-06-06 | 2014-10-15 | 华南理工大学 | Image saliency detection method based on region description and priori knowledge |
| CN104537679A (en) * | 2015-01-16 | 2015-04-22 | 厦门大学 | Cartoon picture saliency detecting method based on superpixel topology analysis |
Non-Patent Citations (2)
| Title |
|---|
| 司永胜等: ""基于K-均值聚类的绿色苹果识别技术"", 《农业机械学报》 * |
| 李宗等: ""一种基于图像内容的图像评价方法"", 《通信技术》 * |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109272526A (en) * | 2017-07-17 | 2019-01-25 | 北京京东尚科信息技术有限公司 | Image processing method, system and electronic equipment |
| CN107577654A (en) * | 2017-09-14 | 2018-01-12 | 掌阅科技股份有限公司 | E-book color matching method, electronic equipment and storage medium based on front cover analysis |
| CN109903210A (en) * | 2019-01-04 | 2019-06-18 | 阿里巴巴集团控股有限公司 | Minimizing technology, device and the server of watermark |
| CN109903210B (en) * | 2019-01-04 | 2024-02-06 | 创新先进技术有限公司 | Watermark removal method, watermark removal device and server |
| CN110084801A (en) * | 2019-04-28 | 2019-08-02 | 深圳回收宝科技有限公司 | A kind of detection method of terminal screen, device, portable terminal and storage medium |
| CN112199131B (en) * | 2019-07-08 | 2024-04-16 | 腾讯科技（深圳）有限公司 | Page detection method, device and equipment |
| CN112199131A (en) * | 2019-07-08 | 2021-01-08 | 腾讯科技（深圳）有限公司 | Page detection method, device and equipment |
| CN110717865B (en) * | 2019-09-02 | 2022-07-29 | 苏宁云计算有限公司 | Picture detection method and device |
| CN110717865A (en) * | 2019-09-02 | 2020-01-21 | 苏宁云计算有限公司 | Picture detection method and device |
| CN112784854A (en) * | 2020-12-30 | 2021-05-11 | 成都云盯科技有限公司 | Method, device and equipment for segmenting and extracting clothing color based on mathematical statistics |
| CN112991470A (en) * | 2021-02-08 | 2021-06-18 | 上海通办信息服务有限公司 | Method and system for checking photo background color of certificate under complex background |
| CN112991470B (en) * | 2021-02-08 | 2023-12-26 | 上海通办信息服务有限公司 | Certificate photo background color checking method and system under complex background |
| CN113240649A (en) * | 2021-05-19 | 2021-08-10 | 姚坚超 | Building component detection method and system based on image analysis |
| CN113240649B (en) * | 2021-05-19 | 2023-12-19 | 姚坚超 | Building component detection method and system based on image analysis |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106611431A (en) | An image detection method and apparatus | |
| US8498482B2 (en) | Image segmentation | |
| US8781249B2 (en) | Image processing apparatus and image processing method | |
| JP5458905B2 (en) | Apparatus and method for detecting shadow in image | |
| JP3114668B2 (en) | Object detection / background removal method, apparatus, and recording medium recording program | |
| US8379975B2 (en) | Image processing device and method, and program recording medium | |
| CN1260680C (en) | Method and appts. for digital image segmentation | |
| KR102356372B1 (en) | White balance processing method, electronic device and computer readable storage medium | |
| KR20090101911A (en) | Detecting block artifacts in coded image and video | |
| CN115311277B (en) | Pit defect identification method for stainless steel product | |
| CN107292828B (en) | Image edge processing method and device | |
| KR20050067438A (en) | Image segmentation using template prediction | |
| CN109308711A (en) | Object detection method, device and image processing equipment | |
| US20120242792A1 (en) | Method and apparatus for distinguishing a 3d image from a 2d image and for identifying the presence of a 3d image format by image difference determination | |
| US20150302595A1 (en) | Method and apparatus for generating depth information | |
| CN112862832B (en) | Dirt detection method based on concentric circle segmentation positioning | |
| CN111179291A (en) | Edge pixel point extraction method and device based on neighborhood relationship | |
| US20070086658A1 (en) | Image processing apparatus and method of image processing | |
| CN115937186A (en) | Textile defect identification method and system | |
| CN110223241A (en) | A kind of histogram equalizing method based on block statistics | |
| CN106415596B (en) | image conversion based on segmentation | |
| US20130259373A1 (en) | Image processing device capable of determining types of images accurately | |
| CN113176270A (en) | Dimming method, device and equipment | |
| CN110717910A (en) | CT image target detection method and CT scanner | |
| Huang et al. | Image segmentation using edge detection and region distribution |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170503 |
|
| RJ01 | Rejection of invention patent application after publication |