CN105701773A - Method and device for processing image rapidly - Google Patents
Method and device for processing image rapidly Download PDFInfo
- Publication number
- CN105701773A CN105701773A CN201410714750.5A CN201410714750A CN105701773A CN 105701773 A CN105701773 A CN 105701773A CN 201410714750 A CN201410714750 A CN 201410714750A CN 105701773 A CN105701773 A CN 105701773A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- whitening
- value
- color balance
- 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
Abstract
An embodiment of the invention relates to the field of image processing technologies, in particular to a method and a device for processing image rapidly. The method comprises the steps of: carrying out whitening processing on an image to be processed to obtain a whitened image; carrying out color balance processing on pixel points in the whitened image to obtain a color-balanced image; and adjusting contrast and brightness of the pixel points in the color-balanced image to obtain an adjusted image. According to the method, the image to be processed is subjected to whitening processing to achieve initial whitening of the image to be processed, then the whitened image is subjected to color balance processing, so that image color distribution is balanced, factuality of the image is increased, and the contrast and brightness of the color-balanced image are adjusted at the same time, thereby improving the influence of insufficient light on processing effect.
Description
Technical field
The present embodiments relate to technical field of image processing, particularly relate to method and the device of a kind of quick process image。
Background technology
In recent years, along with developing rapidly of smart mobile phone, people were more and more diversified to the demand of cell-phone function。Wherein, one important function of smart mobile phone is to autodyne。The photo that mobile phone is filmed is utilized to can be applicable to numerous areas such as making head portrait, social networks is shared。The U.S. face realizing auto heterodyne image on smart mobile phone processes, and is the emphasis paid close attention to of people more, and wherein most basic U.S. face processes and must comprise image mill skin and process, and image whitening processes。
Image mill skin method comparison is ripe, more successfully has Gaussian Blur and bilateral filtering algorithm。But the image whitening method comparison of maturation is few, whitening is not a feature description of image, the simple brightness improving image or other parameters can not realize good whitening effect, and the whitening effect of the whitening algorithm existed now is not good, and treatment effect is excessively stiff。
Summary of the invention
The purpose of the present invention is to propose to a kind of method of quick process image and device, to realize the landscaping treatment of image, and ensure the nature for the treatment of effect and true。
On the one hand, a kind of method that the invention provides quick process image, including:
Pending image is carried out whitening process, it is thus achieved that whitening image；
Pixel in described whitening image is carried out color balance process, it is thus achieved that color balance image；
Regulate contrast and the brightness of pixel in described color balance image, it is thus achieved that the image after adjustment。
On the other hand, the invention provides the device of a kind of quick process image, including:
Whitening processing unit, for carrying out whitening process to pending image, it is thus achieved that whitening image；
Color balance unit, for carrying out color balance process to the pixel in described whitening image, it is thus achieved that color balance image；
Brightness adjusting unit, for regulating contrast and the brightness of pixel in described color balance image, it is thus achieved that the image after adjustment。
The method and the device that quickly process image provided in the embodiment of the present invention, it is achieved that the U.S. face of image is processed, and ensure the nature for the treatment of effect and true。In the embodiment of the present invention, pending image is carried out whitening and processes the preliminary whitening realized pending image, again whitening image is carried out color balance process, make image color distributing equilibrium, increase the verity of image, and regulate contrast and the brightness of color balance image simultaneously, improve because insufficient light causes the impact for the treatment of effect。
Accompanying drawing explanation
Accompanying drawing described herein is used for providing being further appreciated by the embodiment of the present invention, constitutes a part for the embodiment of the present invention, is not intended that the restriction to the embodiment of the present invention。In the accompanying drawings:
Fig. 1 is the flowchart of the method quickly processing image provided in first embodiment of the invention；
Fig. 2 is the flowchart of the method quickly processing image provided in second embodiment of the invention；
Fig. 3 is the flowchart of the method quickly processing image provided in third embodiment of the invention；
Fig. 4 is the flow chart of the method quickly processing image provided in third embodiment of the invention；
Fig. 5 is the schematic diagram of the parameter value scope provided in third embodiment of the invention；
Fig. 6 is the structural representation of the device quickly processing image provided in fourth embodiment of the invention。
Detailed description of the invention
Below in conjunction with drawings and the specific embodiments the embodiment of the present invention carried out in further detail with complete explanation。It is understood that specific embodiment described herein is only used for explaining the embodiment of the present invention, but not the restriction to the embodiment of the present invention。It also should be noted that, for the ease of describing, accompanying drawing illustrate only the part relevant to the embodiment of the present invention but not full content。
First embodiment:
Fig. 1 is the flowchart of the method quickly processing image provided in first embodiment of the invention, the method can be performed by the device quickly processing image, wherein this device can be realized by software and/or hardware, can be built in inside intelligent terminal as the part of intelligent terminal。Include as it is shown in figure 1, this realizes flow process:
Step 11, pending image is carried out whitening process, it is thus achieved that whitening image。
Wherein, pending image can be the image that intelligent terminal's (such as smart mobile phone and panel computer etc.) shoots。Intelligent terminal can adopt whitening algorithm to carry out the pixel value of pixel in pending image processing acquisition whitening image。Whitening image, compared to pending image, improves the colour of skin of personage in image, increases whitening degree, to eliminate skin dark yellow or partially black etc., improves the picture quality of pending image。
Step 12, the pixel in described whitening image is carried out color balance process, it is thus achieved that color balance image。
Pixel in the whitening image obtained in step 11 is carried out color balance process, as the pixel value of the pixel in whitening image is carried out conversion process, obtain the pixel value after conversion process, and the pixel value of pixel in whitening image is set to the pixel value that conversion process obtains, it is thus achieved that color balance image。
By pixel in whitening image is carried out color balance process, the COLOR COMPOSITION THROUGH DISTRIBUTION making color balance image is balanced, it is ensured that the verity of color balance image, as, it is possible to make the skin of personage in color balance image have fair and tender effect。
Step 13, the contrast regulating pixel in described color balance image and brightness, it is thus achieved that the image after adjustment。
Regulate the pixel value of pixel in color balance image, to regulate contrast and the brightness of pixel in color balance image, making image detail in the image after regulating clearly true, raising brightness improving causes the impact on image effect such as the shooting effect not good grade because of insufficient light。
Wherein, contrast and the brightness of pixel in described color balance image are regulated, it is thus achieved that the image after adjustment, it is possible to including:
A, according to equation below, calculate pixel in described color balance image pixel value Output (i, j):
Output (i, j)=alph × image (i, j)+bata
Wherein alph is for presetting contrast level parameter, and bata is predetermined luminance parameter value, and (i, j) for coordinate in described color balance image (i, j) pixel value of place's pixel for image。
For coordinate in color balance image (i, j) place's pixel pixel value image (i, j), by equation below calculate this pixel new pixel value Output (i, j):
Output (i, j)=alph × image (i, j)+bata
Wherein, the span presetting contrast level parameter can be 0-3, and the span of predetermined luminance parameter value can be 0-100。The value presetting contrast level parameter represents the contrast adjustment degree to color equilibrium figures picture, and when default contrast level parameter is 1.4, the image after adjustment has good contrast。
B, the pixel value of pixel in described color balance image is set to the pixel value calculated, it is thus achieved that the image after adjustment。
Concrete, by coordinate in color balance image (i, pixel value Output that j) pixel value of place's pixel is set to calculate (and i, j), it is thus achieved that the image after adjustment。
Wherein, the value of predetermined luminance parameter value a degree of can characterize the brightness of the image after adjustment, and the more big explanation of the value of predetermined luminance parameter value is more big to the raising degree of color equilibrium figures picture, as, when predetermined luminance parameter value is 0, represents and color equilibrium figures picture is not highlighted；When predetermined luminance parameter value takes 1-10, represent and color equilibrium figures picture minuent is highlighted；When predetermined luminance parameter value takes 11-40, represent and color equilibrium figures is highlighted as moderate；And predetermined luminance parameter value is when taking 41-100, represents and color equilibrium figures image height degree is highlighted。
The method quickly processing image provided in first embodiment of the invention, pending image is carried out whitening process, obtain whitening image, also the pixel in whitening image is carried out color balance process, it is thus achieved that color balance image, then regulate contrast and the brightness of pixel in color balance image, obtain the image after regulating, that is, the method processes by pixel in each image carries out whitening process, color balance process, brightness and contrast, improves the quality of image。
Second embodiment:
Fig. 2 is the flowchart of the method quickly processing image provided in second embodiment of the invention, the method can be performed by the device quickly processing image, wherein this device can be realized by software and/or hardware, can be built in inside intelligent terminal as the part of intelligent terminal。Include as in figure 2 it is shown, this realizes flow process:
Step 21, the noise spot in described pending image is carried out mill skin process, it is thus achieved that remove the mill skin image of described noise spot。
Noise spot in described pending image can be the freckle in pending image, mottle, wrinkle and black eye etc.。Intelligent terminal can adopt image mill skin algorithm, such as Gaussian Blur algorithm and bilateral filtering algorithm etc., the noise spot in pending image carries out mill skin and processes, remove the noise spot in described pending image, it is achieved the U.S. face of pending image processes function。
Adopt bilateral filtering algorithm to carry out mill skin when processing, according to equation below, calculate coordinate in pending image (i, j) place's pixel pixel value g (i, j):
Wherein, (k, l) for coordinate in pending image, (i, j) the neighborhood territory pixel value of place's pixel, the radius of neighbourhood is that (i, j, k, l) for weight coefficient, the size of weight coefficient depends on the product of definition territory core and codomain core for d, w to f。
Wherein, foundation equation below, calculating weight coefficient w (i, j, k, l):
Wherein, σdAnd σrThe respectively variance of spatial domain and codomain, neighborhood of pixels diameter when d is for filtering。This example arranges mill skin parameter I, definition: d=I；σd=I*2；σr=I/2。The value being arranged mill skin parameter I by outside changes mill skin degree, and the span of mill skin parameter can be 0-31, and wherein 0-10 represents low mill skin；11-18 represents moderate mill skin；19-31 represents and highly grinds skin。
Step 22, for described pending image increase gray channel, and the opacity of described pending image is set to preset opacity value, it is thus achieved that the four-way image after arranging。
Increase gray scale (Alpha) passage for described pending image, pending image is converted into four-way image by triple channel image, i.e. the form of pending image is converted into RGBA from RGB。Gray channel represents the opacity of pending image, it is possible to by the equal equipment of opacity of pixel each in pending image for presetting opacity value。
Preferably, described default opacity value is 20%。
Step 23, adopt described mill skin image corresponding first preset the second default weighted value that weighted value is corresponding with described four-way image, pixel in described mill skin image and the pixel in described four-way image are carried out corresponding weighted superposition, it is thus achieved that whitening image。
Concrete, it is possible to according to equation below calculate coordinate in whitening image (i, j) place's pixel pixel value RGB (i, j):
RGB (i, j)=J1*RGB1(i,j)+J2*RGB2(i, j),
Wherein, RGB1(i, j) for coordinate (i, j) pixel value of place's pixel, RGB in mill skin image2(i, j) for coordinate in four-way image (i, j) pixel value of place's pixel, J1It is the first default weighted value, J2It it is the second default weighted value。
Definition whitening dynamics parameter J=J2/J1。Wherein, the span of whitening dynamics parameter J is 0-1。Whitening dynamics parameter value is more big, illustrates that the whitening degree to image is more high, and e.g., 0 represents not whitening, and 1 represents height whitening。
Preferably, first presets weighted value takes 0.7, and second presets weighted value takes 1.5, the best results of the whitening image now obtained。
It should be noted that, the effect of whitening image and the default opacity value of gray channel and to superpose arranging of coefficient relevant, in order to convenient with post processing, it is possible to the whitening image after superposition is re-set as triple channel image, that is, whitening image is arranged to rgb format。
Step 24, the pixel in described whitening image is carried out color balance process, it is thus achieved that color balance image。
Step 25, the contrast regulating pixel in described color balance image and brightness, it is thus achieved that the image after adjustment。
The method quickly processing image provided in second embodiment of the invention, adopt bilateral filtering algorithm that noise spot in pending image carries out mill skin to process, obtain the mill skin image removing described noise spot, and pending image is set to four-way image, whitening image is obtained again through to mill skin image and four-way image weighted superposition, can improve the colour of skin of personage in pending image, increase whitening degree and eliminate the situations such as skin is dark yellow and partially black。The method processes also by whitening image carries out color balance process, brightness and contrast, improves the quality of image。
3rd embodiment:
Fig. 3 is the flowchart of the method quickly processing image provided in third embodiment of the invention, the method can be performed by the device quickly processing image, wherein this device can be realized by software and/or hardware, can be built in inside intelligent terminal as the part of intelligent terminal。Include as it is shown on figure 3, this realizes flow process:
Step 31, pending image is carried out whitening process, it is thus achieved that whitening image。
Wherein, pending image is carried out whitening process, it is thus achieved that whitening image may include that the noise spot in described pending image carries out mill skin to be processed, it is thus achieved that removes the mill skin image of described noise spot；Increase gray channel for described pending image, and be set to the opacity of described pending image preset opacity value, it is thus achieved that the four-way image after arranging；Adopt described mill skin image corresponding first presets the second default weighted value that weighted value is corresponding with described four-way image, the pixel in described mill skin image and the pixel in described four-way image carries out corresponding weighted superposition, it is thus achieved that whitening image。
Wherein, default opacity value can be 20%。
Step 32, the redness of described whitening image, yellow and green channel are carried out image separate, obtain red single channel image, yellow single channel image and green single channel image。
Wherein, in red single channel image coordinate (i, j) pixel value of the pixel at place is equal to coordinate (i, j) pixel value of the red channel of the pixel at place in whitening image；In yellow single channel image, (i, j) pixel value of the pixel at place is equal to coordinate (i, j) pixel value of the yellow channels of the pixel at place in whitening image for coordinate；And in green single channel image coordinate (i, j) pixel value of the pixel at place is equal to coordinate (i, j) pixel value of the green channel of the pixel at place in whitening image。
Step 33, foundation equation below, calculate pixel value f (x) after the affine transformation of pixel in each single channel image:
F (x)=(x-Vmin)×(max-min)/(Vmax-Vmin)+min,
Wherein, x is the pixel value before the affine transformation of pixel, and max is for presetting maximum gradation value, and min is for presetting minimum gradation value, Vmin=NS/2, Vmax=N (1-S/2)-1, treatment radius S are natural number and belong to [0,100], and N is the number of pixel in each single channel image。
Wherein, default maximum gradation value can take the max pixel value of pixel in corresponding single channel image, presets maximum gradation value and can take 255 in the present embodiment；Default minimum gradation value can take the minimum pixel value of pixel in corresponding single channel image, presets minimum gradation value and can take 0 in the present embodiment。
It should be noted that the statistics with histogram of each single channel image can be passed through to set up, treatment radius S is set according to statistics with histogram。Preferably, treatment radius S is 0.1。
Step 34, according to the pixel value after the affine transformation of pixel in calculated each single channel image, update the pixel value of pixel in described whitening image。
Wherein, can by coordinate (i in described whitening image, j) the red channel pixel value of place's pixel is set to coordinate (i in the red single channel image after affine transformation, j) pixel value of place's pixel, the yellow channels pixel value of this pixel is set in the yellow single channel image after affine transformation the pixel value of this pixel, and the green channel pixel value of this pixel is set in the green single channel image after affine transformation the pixel value of this pixel, obtain color balance image。
Step 35, the contrast regulating pixel in described color balance image and brightness, it is thus achieved that the image after adjustment。
Wherein, regulate contrast and the brightness of pixel in described color balance image, it is thus achieved that the image after adjustment, it is possible to including: according to equation below, calculate pixel in described color balance image pixel value Output (i, j):
Output (i, j)=alph × image (i, j)+bata
, wherein alph is for presetting contrast level parameter, and bata is predetermined luminance parameter value, and (i, j) for coordinate in described color balance image (i, j) pixel value of place's pixel for image；The pixel value of pixel in described color balance image is set to the pixel value calculated, it is thus achieved that the image after adjustment。
Fig. 4 is the flow chart of the method quickly processing image provided in third embodiment of the invention, as shown in Figure 4, mainly through following flow processing image: receive pending image；Adopt bilateral filtering algorithm that pending image carries out mill skin and process proper mill skin image；Increase gray channel for pending image, and by arranging gray channel, regulate the opacity of pending image, proper four-way image；Mill skin image and four-way image weighted superposition are obtained whitening image；Whitening image is carried out color balance process, obtains color balance image；Color equilibrium figures picture is carried out contrast and brightness regulation, obtains and output processing result。
Fig. 5 is the schematic diagram of the parameter value scope provided in third embodiment of the invention, as shown in Figure 5, mill skin parameter in the present embodiment, whitening dynamics parameter and predetermined luminance parameter can be set by the user, and preset opacity value, treatment radius and default contrast level parameter and can fix in advance, wherein, the meaning of each parameter and span do not repeat them here。
The method quickly processing image provided in third embodiment of the invention, by pending image carries out two-way process, mill skin processes on the one hand, and conversion image data form arranges gray channel parameter on the one hand, regulate the opacity of image, it can be used as mask image。Then image and masking-out image after mill skin being processed are weighted superposition and obtain whitening image, add color balanceization to process, with contrast and brightness processed, realize intelligent terminal to autodyne the landscaping treatment of image, as ground skin speckle dispelling, Vitamin K, image whitening, the U.S. face achieving auto heterodyne image processes function, and ensures that treatment effect is natural, true。
Fourth embodiment of the invention is device embodiment, and the inventive method embodiment and device embodiment belong to same design, the detail content of not detailed description in device embodiment, it is possible to reference to said method embodiment。
4th embodiment:
Fig. 6 is the structural representation of the device quickly processing image provided in fourth embodiment of the invention, and this device can be arranged on inside intelligent terminal。As shown in Figure 6, this device may include that whitening processing unit 41, for pending image is carried out whitening process, it is thus achieved that whitening image；Color balance unit 42, for carrying out color balance process to the pixel in described whitening image, it is thus achieved that color balance image；Brightness adjusting unit 43, for regulating contrast and the brightness of pixel in described color balance image, it is thus achieved that the image after adjustment。
Wherein, whitening processing unit 41 may include that mill leather unit, processes for the noise spot in described pending image carries out mill skin, it is thus achieved that remove the mill skin image of described noise spot；Transparency subelement, for increasing gray channel for described pending image, and is set to the opacity of described pending image preset opacity value, it is thus achieved that the four-way image after arranging；Image overlay subelement, for adopting described mill skin image corresponding first presets the second default weighted value that weighted value is corresponding with described four-way image, pixel in described mill skin image and the pixel in described four-way image are carried out corresponding weighted superposition, it is thus achieved that whitening image。
Wherein, color balance unit 41 may include that image segregant unit, separates for the redness of described whitening image, yellow and green channel are carried out image, obtains red single channel image, yellow single channel image and green single channel image；First pixel computation subunit, for according to equation below, calculating pixel value f (x) after the affine transformation of pixel in each single channel image:
F (x)=(x-Vmin)×(max-min)/(Vmax-Vmin)+min,
Wherein, x is the pixel value before the affine transformation of pixel, and max is for presetting maximum gradation value, and min is for presetting minimum gradation value, Vmin=NS/2, Vmax=N (1-S/2)-1, treatment radius S are natural number and belong to [0,100], and N is the number of pixel in each single channel image；First pixel arranges subelement, for according to the pixel value after the affine transformation of pixel in calculated each single channel image, updating the pixel value of pixel in described whitening image。
Wherein, brightness adjusting unit 43 may include that the second pixel computation subunit, for according to equation below, calculate pixel in described color balance image pixel value Output (i, j):
Output (i, j)=alph × image (i, j)+bata
Wherein alph is for presetting contrast level parameter, and bata is predetermined luminance parameter value, and (i, j) for coordinate in described equilibrium figures picture (i, j) pixel value of place's pixel for image；Second pixel arranges subelement, for the pixel value of pixel in described color balance image is set to the pixel value calculated, it is thus achieved that the image after adjustment。
Wherein, default opacity value can be 20%。
Wherein, the span presetting contrast level parameter can be 0-3, and the span of predetermined luminance parameter value can be 0-100。
The device quickly processing image provided in fourth embodiment of the invention, by pending image carries out two-way process, mill skin processes on the one hand, and conversion image data form arranges gray channel parameter on the one hand, regulate the opacity of image, it can be used as mask image。Then image and masking-out image after mill skin being processed are weighted superposition and obtain whitening image, add color balanceization to process, with contrast and brightness processed, realize intelligent terminal to autodyne the landscaping treatment of image, as ground skin speckle dispelling, Vitamin K, image whitening, the U.S. face achieving auto heterodyne image processes function, and ensures that treatment effect is natural, true。
Being only the preferred embodiment of the embodiment of the present invention described in upper, be not limited to the embodiment of the present invention, to those skilled in the art, the embodiment of the present invention can have various change and change。Any amendment of making within all spirit in the embodiment of the present invention and principle, equivalent replacement, improvement etc., should be included within the protection domain of the embodiment of the present invention。
Claims (10)
1. the method for a quick process image, it is characterised in that including:
Pending image is carried out whitening process, it is thus achieved that whitening image；
Pixel in described whitening image is carried out color balance process, it is thus achieved that color balance image；
Regulate contrast and the brightness of pixel in described color balance image, it is thus achieved that the image after adjustment。
2. method according to claim 1, it is characterised in that pending image is carried out whitening process, it is thus achieved that whitening image, including:
Noise spot in described pending image carries out mill skin process, it is thus achieved that remove the mill skin image of described noise spot；
Increase gray channel for described pending image, and be set to the opacity of described pending image preset opacity value, it is thus achieved that the four-way image after arranging；
Adopt described mill skin image corresponding first presets the second default weighted value that weighted value is corresponding with described four-way image, the pixel in described mill skin image and the pixel in described four-way image carries out corresponding weighted superposition, it is thus achieved that whitening image。
3. method according to claim 1, it is characterised in that the pixel in described whitening image is carried out color balance process, it is thus achieved that color balance image, including:
The redness of described whitening image, yellow and green channel are carried out image separate, obtain red single channel image, yellow single channel image and green single channel image；
According to equation below, calculate pixel value f (x) after the affine transformation of pixel in each single channel image:
F (x)=(x-Vmin)×(max-min)/(Vmax-Vmin)+min, wherein, x is the pixel value before the affine transformation of pixel, and max is for presetting maximum gradation value, and min is for presetting minimum gradation value, Vmin=NS/2, Vmax=N (1-S/2)-1, treatment radius S are natural number and belong to [0,100], and N is the number of pixel in each single channel image；
According to the pixel value after the affine transformation of pixel in calculated each single channel image, update the pixel value of pixel in described whitening image。
4. method according to claim 1, it is characterised in that regulate contrast and the brightness of pixel in described color balance image, it is thus achieved that the image after adjustment, including:
According to equation below, calculate pixel in described color balance image pixel value Output (i, j):
Output (i, j)=alph × image (i, j)+bata
, wherein alph is for presetting contrast level parameter, and bata is predetermined luminance parameter value, and (i, j) for coordinate in described color balance image (i, j) pixel value of place's pixel for image；
The pixel value of pixel in described color balance image is set to the pixel value calculated, it is thus achieved that the image after adjustment。
5. method according to claim 2, it is characterised in that default opacity value is 20%。
6. method according to claim 4, it is characterised in that the span presetting contrast level parameter is 0-3, and the span of predetermined luminance parameter value is 0-100。
7. the device of a quick process image, it is characterised in that including:
Whitening processing unit, for carrying out whitening process to pending image, it is thus achieved that whitening image；
Color balance unit, for carrying out color balance process to the pixel in described whitening image, it is thus achieved that color balance image；
Brightness adjusting unit, for regulating contrast and the brightness of pixel in described color balance image, it is thus achieved that the image after adjustment。
8. device according to claim 7, it is characterised in that whitening processing unit includes:
Mill leather unit, processes for the noise spot in described pending image carries out mill skin, it is thus achieved that remove the mill skin image of described noise spot；
Transparency subelement, for increasing gray channel for described pending image, and is set to the opacity of described pending image preset opacity value, it is thus achieved that the four-way image after arranging；
Image overlay subelement, for adopting described mill skin image corresponding first presets the second default weighted value that weighted value is corresponding with described four-way image, pixel in described mill skin image and the pixel in described four-way image are carried out corresponding weighted superposition, it is thus achieved that whitening image。
9. device according to claim 7, it is characterised in that color balance unit includes:
Image segregant unit, separates for the redness of described whitening image, yellow and green channel are carried out image, obtains red single channel image, yellow single channel image and green single channel image；
First pixel computation subunit, for according to equation below, calculating pixel value f (x) after the affine transformation of pixel in each single channel image:
F (x)=(x-Vmin)×(max-min)/(Vmax-Vmin)+min, wherein, x is the pixel value before the affine transformation of pixel, and max is for presetting maximum gradation value, and min is for presetting minimum gradation value, Vmin=NS/2, Vmax=N (1-S/2)-1, treatment radius S are natural number and belong to [0,100], and N is the number of pixel in each single channel image；
First pixel arranges subelement, for according to the pixel value after the affine transformation of pixel in calculated each single channel image, updating the pixel value of pixel in described whitening image。
10. device according to claim 7, it is characterised in that brightness adjusting unit includes:
Second pixel computation subunit, for according to equation below, calculate pixel in described color balance image pixel value Output (i, j):
Output (i, j)=alph × image (i, j)+bata
, wherein alph is for presetting contrast level parameter, and bata is predetermined luminance parameter value, and (i, j) for coordinate in described equilibrium figures picture (i, j) pixel value of place's pixel for image；
Second pixel arranges subelement, for the pixel value of pixel in described color balance image is set to the pixel value calculated, it is thus achieved that the image after adjustment。
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410714750.5A CN105701773B (en) | 2014-11-28 | 2014-11-28 | A kind of method and device of quick processing image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410714750.5A CN105701773B (en) | 2014-11-28 | 2014-11-28 | A kind of method and device of quick processing image |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105701773A true CN105701773A (en) | 2016-06-22 |
| CN105701773B CN105701773B (en) | 2018-08-17 |
Family
ID=56231156
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410714750.5A Active CN105701773B (en) | 2014-11-28 | 2014-11-28 | A kind of method and device of quick processing image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105701773B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780299A (en) * | 2016-11-30 | 2017-05-31 | 努比亚技术有限公司 | The processing method and processing device of picture |
| CN107609485A (en) * | 2017-08-16 | 2018-01-19 | 中国科学院自动化研究所 | The recognition methods of traffic sign, storage medium, processing equipment |
| CN109767385A (en) * | 2018-12-20 | 2019-05-17 | 深圳市资福医疗技术有限公司 | A kind of method and apparatus removing image chroma noise |
| CN110286415A (en) * | 2019-07-12 | 2019-09-27 | 广东工业大学 | Safety check contraband detecting method, apparatus, equipment and computer readable storage medium |
| CN110288570A (en) * | 2019-05-31 | 2019-09-27 | 东南大学 | A kind of weak iridescent image detection method of the rotor winding of view-based access control model attention mechanism |
| CN110738625A (en) * | 2019-10-21 | 2020-01-31 | Oppo广东移动通信有限公司 | Image resampling method, device, terminal and computer readable storage medium |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584153A (en) * | 2018-12-06 | 2019-04-05 | 北京旷视科技有限公司 | Modify the methods, devices and systems of eye |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404082A (en) * | 2008-11-14 | 2009-04-08 | 深圳市迅雷网络技术有限公司 | Portrait buffing method and apparatus |
| CN103093203A (en) * | 2013-01-21 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Human body re-recognition method and human body re-recognition system |
| CN103617638A (en) * | 2013-12-05 | 2014-03-05 | 北京京东尚科信息技术有限公司 | Image processing method and device |
| CN103745430A (en) * | 2013-06-25 | 2014-04-23 | 厦门美图网科技有限公司 | Rapid beautifying method of digital image |
| US20140369554A1 (en) * | 2013-06-18 | 2014-12-18 | Nvidia Corporation | Face beautification system and method of use thereof |
-
2014
- 2014-11-28 CN CN201410714750.5A patent/CN105701773B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101404082A (en) * | 2008-11-14 | 2009-04-08 | 深圳市迅雷网络技术有限公司 | Portrait buffing method and apparatus |
| CN103093203A (en) * | 2013-01-21 | 2013-05-08 | 信帧电子技术（北京）有限公司 | Human body re-recognition method and human body re-recognition system |
| US20140369554A1 (en) * | 2013-06-18 | 2014-12-18 | Nvidia Corporation | Face beautification system and method of use thereof |
| CN103745430A (en) * | 2013-06-25 | 2014-04-23 | 厦门美图网科技有限公司 | Rapid beautifying method of digital image |
| CN103617638A (en) * | 2013-12-05 | 2014-03-05 | 北京京东尚科信息技术有限公司 | Image processing method and device |
Non-Patent Citations (1)
| Title |
|---|
| 小洲实验室: "学习OpenCV范例（五）——改变图像的对比度和亮度", 《HTTP://BLOG.CSDN.NET/CHENJIAZHOU12/ARTICLE/DETAILS/21119031》 * |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106780299A (en) * | 2016-11-30 | 2017-05-31 | 努比亚技术有限公司 | The processing method and processing device of picture |
| CN107609485A (en) * | 2017-08-16 | 2018-01-19 | 中国科学院自动化研究所 | The recognition methods of traffic sign, storage medium, processing equipment |
| CN109767385A (en) * | 2018-12-20 | 2019-05-17 | 深圳市资福医疗技术有限公司 | A kind of method and apparatus removing image chroma noise |
| CN110288570A (en) * | 2019-05-31 | 2019-09-27 | 东南大学 | A kind of weak iridescent image detection method of the rotor winding of view-based access control model attention mechanism |
| CN110286415A (en) * | 2019-07-12 | 2019-09-27 | 广东工业大学 | Safety check contraband detecting method, apparatus, equipment and computer readable storage medium |
| CN110286415B (en) * | 2019-07-12 | 2021-03-16 | 广东工业大学 | Security inspection contraband detection method, device, equipment and computer readable storage medium |
| CN110738625A (en) * | 2019-10-21 | 2020-01-31 | Oppo广东移动通信有限公司 | Image resampling method, device, terminal and computer readable storage medium |
| CN110738625B (en) * | 2019-10-21 | 2022-03-11 | Oppo广东移动通信有限公司 | Image resampling method, device, terminal and computer readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105701773B (en) | 2018-08-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105701773A (en) | Method and device for processing image rapidly | |
| CN104182947B (en) | Low-illumination image enhancement method and system | |
| CN103714520B (en) | Digital video image strengthening system and its method are realized based on FPGA | |
| CN104182949B (en) | Image inking and fusing method and system based on histogram feature point registration | |
| CN106897981A (en) | A kind of enhancement method of low-illumination image based on guiding filtering | |
| CN104618700B (en) | Enhanced display method for color high dynamic range image | |
| DE102018119625A1 (en) | Reduction of structured IR patterns in stereoscopic depth sensor imaging | |
| CN101540832B (en) | Methods for matching dynamic range of image signals | |
| CN102663741B (en) | Method for carrying out visual stereo perception enhancement on color digit image and system thereof | |
| CN103248793B (en) | The colour of skin optimization method of gamut conversion system and device | |
| CN107038680A (en) | The U.S. face method and system that adaptive optical shines | |
| CN104809694B (en) | Digital image processing method and device | |
| CN102750671B (en) | A kind of Image color noise minimizing technology | |
| DE112017000500T5 (en) | Motion-adaptive flow processing for temporal noise suppression | |
| CN108022223B (en) | Tone mapping method based on logarithm mapping function blocking processing fusion | |
| CN106530309A (en) | Video matting method and system based on mobile platform | |
| CN107895350B (en) | HDR image generation method based on self-adaptive double gamma transformation | |
| CN104392425B (en) | A kind of image enchancing method of the adjust automatically contrast based on face | |
| CN113297937B (en) | Image processing method, device, equipment and medium | |
| CN111915508B (en) | Image texture detail enhancement method for color vision disorder | |
| CN107194884A (en) | A kind of several LDR image acquisition methods with different exposure values | |
| CN105354801A (en) | HSV color space based image enhancement method | |
| CN111105359A (en) | Tone mapping method for high dynamic range image | |
| CN105763747A (en) | Mobile terminal for achieving high-quality real-time facial beautification | |
| CN105976309A (en) | High-efficiency and easy-parallel implementation beauty mobile terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| EE01 | Entry into force of recordation of patent licensing contract |
Application publication date: 20160622 Assignee: Shanghai Li Ke Semiconductor Technology Co., Ltd. Assignor: Leadcore Technology Co., Ltd. Contract record no.: 2018990000159 Denomination of invention: Method and device for processing image rapidly License type: Common License Record date: 20180615 |
|
| EE01 | Entry into force of recordation of patent licensing contract | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |