CN101478629A - Image processing process for regulating human face ratio - Google Patents
Image processing process for regulating human face ratio Download PDFInfo
- Publication number
- CN101478629A CN101478629A CNA2008100000792A CN200810000079A CN101478629A CN 101478629 A CN101478629 A CN 101478629A CN A2008100000792 A CNA2008100000792 A CN A2008100000792A CN 200810000079 A CN200810000079 A CN 200810000079A CN 101478629 A CN101478629 A CN 101478629A
- Authority
- CN
- China
- Prior art keywords
- convergent
- adjustment
- image
- divergent block
- human face
- 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 Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses an image processing method for adjusting the proportion of human face. The method is executed through a microprocessor of digital camera for adjusting the proportion of human face part in the image. The microprocessor executes a human face detection for finding out the human face position in the image and sets a zooming area according to the complete line (row) which includes the position of human face for zooming the proportion of human face. When the position of human face is adjusted, the whole line of pixels is added/deleted proportionally through two sides of zooming area for mending the pixel altered in the human face rooming and causing that the whole image is not distorted. According to the invention, the human face position is accurately found out and simultaneously the pixel of the human face position is adjusted, thereby effectively adjusting the human face proportion and avoiding the distortion of proportion between the human face and body of image.
Description
Technical field
The present invention relates to a kind of image processing method, particularly relate to a kind of image processing method of adjusting human face ratio in a certain image.
Background technology
When digital camera carries out scene shot at present, except functions such as automatic focusing that shooting environmental is provided, ambient brightness detection, screening-mode switching, the part camera also provides and carries out digitized processing to taking imaging, for example goes to make function behind the images such as blood-shot eye illness, adding framing mask.The digital camera of minority also provides the portrait to shooting picture to carry out " reducing " or special effect processing such as " becoming fat ", makes the people in the photographic images seem can not cross fat or thin excessively.In fact, when this class digital camera carries out image special effect processing (portrait reduces or becomes fat), be not the processing of carrying out " amplification " or " dwindling " at the people face part in the image.The composition custom that most users take is for putting the people mid portion at image.Therefore, the processing of contracting in carrying out at the pixel of the mid portion of image, and the pixel of the left and right sides is extended out, can reach effect to people face part " amplification " or " dwindling ".
This type of image special effect is handled the phenomenon that but is easy to generate metamorphopsic distortion.Figure 1A, Figure 1B are human face ratio schematic diagram in the known adjustment image.Please also refer to Figure 1A, Figure 1B, behind photographic images, compression middle body image is so as to allowing people's face 110 of central authorities produce the sensation of " reducing ".Yet, directly behind the compressed image mid portion (be among Figure 1A between two dotted lines image), find that by Figure 1B the drum 120 in the image also can produce tangible deformation, cause whole image fault inharmonious.In addition, and nonowner's face all is positioned at the image middle body, if people's face is arranged in the image both sides, then not only do not reduce through the people face part in the image after the special effect processing, can cause people's face to seem fat more because of extending out the pixel of handling the image both sides on the contrary.
Summary of the invention
The object of the present invention is to provide a kind of image processing method of adjusting human face ratio.In wanting zoomed image during human face ratio, the convergent-divergent block at convergent-divergent people face place only, and adjust convergent-divergent block both sides simultaneously, to repair the pixel that the convergent-divergent block changes, avoid the anamorphose distortion.
To achieve these goals, the invention provides a kind of image processing method of adjusting facial image, may further comprise the steps: at first, image is carried out the detection of people's face, and find out the people's face in the image.Then, according to people's face position the convergent-divergent block is set.Afterwards, a scaling is set, and according to this this convergent-divergent block of scaling geometric ratio adjustment.Then, according to this scaling, the both sides of this convergent-divergent block of geometric ratio adjustment are so as to keeping the pixel summation of this image.
According to the image processing method of the described adjustment human face ratio of preferred embodiment of the present invention, people's face wherein detects and comprises that step is as follows: earlier image is carried out rim detection to obtain edge image.Afterwards, with a plurality of face characteristic contrast fringes images in the face database, and take out the people's face that conforms to face characteristic in the database in the edge image.Then, in record this person face position.
According to the image processing method of the described adjustment human face ratio of preferred embodiment of the present invention, the permutation of wherein said convergent-divergent block behaviour face position.
According to the image processing method of the described adjustment human face ratio of preferred embodiment of the present invention, the full line of wherein said convergent-divergent block behaviour face position.
According to the image processing method of the described adjustment human face ratio of preferred embodiment of the present invention, wherein also comprise providing a personal-machine interface (adjustment) aforesaid scaling to be set for the user.This scaling is the length percent of convergent-divergent block before the shared adjustment of adjusted convergent-divergent block.In addition, the scaling of the both sides of convergent-divergent block (being the relation before and after the both sides adjustment of convergent-divergent block), can following mathematical notation as follows:
γ’＝γ+γ*X/(γ+δ)；
δ’＝δ+δ*X/(γ+δ)；
Wherein, the γ indication in the above-mentioned mathematical expression is that pixel head office (row) number, pixel head office (row) number after the side adjustment that γ ' indication is the convergent-divergent block, the pixel head office (row) after the opposite side adjustment that pixel head office (row) counts, δ ' indication is the convergent-divergent block before the opposite side adjustment that the δ indication is the convergent-divergent block before the one side adjustment of convergent-divergent block counts and the X indication is that the pixel head office (row) of the required adjustment of convergent-divergent block counts.
From the above mentioned, the image processing method of adjusting human face ratio selects the convergent-divergent block according to people's face position, in wanting zoomed image during human face ratio, only adjust the convergent-divergent block and do not need whole image of convergent-divergent, and after the convergent-divergent block carries out zoom action, equal proportion is adjusted convergent-divergent block both sides so as to repairing image, provides the function of adjusting human face ratio in the image to reach, and guarantees that image can be because of not adjusting the phenomenon that human face ratio causes image fault.
Describe the present invention below in conjunction with the drawings and specific embodiments, but not as a limitation of the invention.
Description of drawings
Figure 1A, 1B are human face ratio schematic diagram in the known adjustment image;
Fig. 2 is the image processing method flow chart of adjustment facial image of the present invention;
Fig. 3 A, 3B are human face ratio schematic diagram in the adjustment image of the present invention.
Wherein, Reference numeral:
110 people's faces
120 drums
α, β convergent-divergent distance
Embodiment
Fig. 2 is the image processing method flow chart of adjustment facial image of the present invention.In the present embodiment, after utilizing the digital camera photographic images, take the photograph image can be by digital camera microprocessor or the whole photographic images of digital processing (DSP) in the ratio of people's face.At first, image is carried out the detection of people's face, and find out at least one people's face (step S210) in the image; Then, according to people's face position convergent-divergent block (step S220) is set; Afterwards, scaling is set, and according to this scaling geometric ratio adjustment convergent-divergent block (step S230); Then, according to this scaling, the both sides of geometric ratio adjustment convergent-divergent block are to keep the pixel summation (step S240) of input picture.
To accurately adjust human face ratio in the image, then must need to find out earlier people's face position in the image, just earlier image executor face be detected to find out people's face in the image.People's face detects and comprises the following steps: step 1, input picture, and carries out rim detection, to obtain edge image.For example use gradient magnitude (Gradient Magnitude) method to try to achieve edge image in the present embodiment, the formed matrix of each pixel of image be multiplied by a horizontal direction gradient calculation value:
And vertical gradient calculation value:
Afterwards, can draw out edge image according to the matrix of gained.Other such as Laplce (Laplacian) method, greatest gradient (Tengengrad) method, and one dimension horizontal filtering (1D HorizontalFilter) method all can not limit its scope at this in order to obtain edge image.Obtain (step 2) after the edge image, a plurality of face characteristics in this edge image and the face database are compared, finding out the people's face in the image, and recorder's face position information (step 3).
Behind people's face in finding out image, begin human face ratio is carried out adjustment.Yet for allowing the unlikely generation of portrait " top-heavy " in the image or the phenomenon (the health ratio that is portrait does not conform to normality) of " head is light and feet are heavy ", select a convergent-divergent block in the present embodiment, and this convergent-divergent block of equal proportion adjustment, to avoid adjusting separately the phenomenon of the portrait health ratio inequality that the people face part produces.Put (portrait is perpendicular to the horizon) or laterally put (the portrait level is in the horizon) according to portrait forward in the image, decision is chosen the full line of people's face position or permutation image as the convergent-divergent block.If the portrait in the image is that forward is put, the full line of then choosing people's face position is the convergent-divergent block; Otherwise the portrait in the image is for laterally putting, and the permutation of then choosing people's face position is as the convergent-divergent block.
The user can set the scaling of convergent-divergent block by a personal-machine interface.In certain embodiments, man-machine interface for example is physical button on the digital camera or the virtual key on the digital camera screen (touch screen).After the microprocessor (or dsp chip) of digital camera receives the scaling of user's input, promptly adjust the convergent-divergent block according to this scaling.Described scaling is the length percent of adjusting the preceding convergent-divergent block of the shared adjustment of back convergent-divergent block; And pixel head office (row) number of the required adjustment of convergent-divergent block can be following the mathematical notation formula present:
The number * (1-scaling) of number=convergent-divergent block of pixel head office of pixel head office (row) (row) of convergent-divergent block adjustment.
What deserves to be mentioned is, if in the picture for homo erectus picture then the convergent-divergent block be the full line adjustment, by increasing/delete the fat or thin of people's face in the entire row of pixels adjustment picture; If the portrait of picture be laterally to place, then the convergent-divergent block is the permutation adjustment, by increasing/delete the fat or thin of people's face in the column of pixels adjustment picture.
In one embodiment, the portrait in the picture is uprightly placed.If the convergent-divergent block width of setting is 100 pixels and scaling that the user sets is 80%, when then carrying out the adjustment of convergent-divergent block, can calculate the total line number of pixel of the required adjustment of convergent-divergent block earlier.After the microprocessor computing convergent-divergent block of digital camera needs equal proportion to remove 20 row pixels, promptly from a left side and the right unnecessary pixel (promptly every 5 wide entire row of pixels that remove of pixel) that equidistantly removes can remaining 80 capable pixels be integrated into a convergent-divergent block after the adjustment afterwards.Width after the adjustment of convergent-divergent block is 80 pixels, and what this moment, the people's face in the image seemed to become is thinner.Because the body part of portrait is also elected as the convergent-divergent block by circle, so behind the adjustment human face ratio, can not think that also the portrait in the image has factitious impression.Accept above-mentioned example, comparatively plump if the user will allow the people face part of image it seems, then can set scaling is 120%.The width of the convergent-divergent block after the adjustment then becomes 120 pixels.
For allowing image keep life size and make the image impression comparatively natural, after the convergent-divergent block dwindled (inwardly compression), the both sides image of convergent-divergent block also needed equal proportion to amplify, with repair convergent-divergent block adjustment (inwardly compression) back short pixel.With regard to above-mentioned example, the convergent-divergent block dwindles 20 row pixels, and then 20 row pixels just must be filled in convergent-divergent block both sides.The mathematical notation formula of the scaling of convergent-divergent block both sides is:
γ’＝γ+γ*X/(γ+δ)；
δ’＝δ+δ*X/(γ+δ)；
Wherein, the γ indication in the above-mentioned mathematical expression is that the total line number of pixel, γ ' indication before the one side adjustment of convergent-divergent block are the total line number of pixel that the total line number of pixel, the total line number of pixel before the opposite side adjustment that the δ indication is the convergent-divergent block, the total line number of pixel after the opposite side adjustment that δ ' indication is the convergent-divergent block and X indication after the side adjustment of convergent-divergent block are the required adjustment of convergent-divergent block.The previous examples that continues is 300 pixels if the pixel wide in the left side of convergent-divergent block is the pixel wide on the right side of 200 pixels, convergent-divergent block, and then 8 row pixels need be filled in the left side of convergent-divergent block, and 12 row pixels need be filled in the left side of convergent-divergent block.One-row pixels (value of each pixel in this row pixel on filling up is directly got adjacent pixels average of each pixel) right is filled every 25 row from a left side in the left side of convergent-divergent block, and the right side of convergent-divergent block is from a left side and one-row pixels is also filled up every 25 row in the right side.So just, can allow image keep life size, and can make whole image impression comparatively natural.
In another embodiment, the portrait in the picture is laterally placed.If will carry out adjustment to the ratio of the people's face in the picture, its execution in step is similar to the adjustment mode of the picture of aforementioned homo erectus's picture.The user also need be provided with scaling, find out people's face position in the picture again, and the permutation that people's face position is set is the convergent-divergent block, afterwards the column of pixels of the adjustment convergent-divergent block of equal proportion again, and the both sides of adjustment convergent-divergent block (both sides up and down), so as to allowing image keep life size.Detailed steps in last embodiment narration, does not repeat them here.
In order more to clearly demonstrate present embodiment, below paragraph will adjust the image processing method of facial image with graphic explanation.Fig. 3 A, Fig. 3 B are human face ratio schematic diagram in the adjustment image of the present invention.Please also refer to Fig. 3 A, Fig. 3 B, the user take the photograph behind the image (as shown in Figure 3A), handle the image special effect that the people's face in the image 110 carry out " reducing ".It is 60% that the user sets scaling by the man-machine interface on the digital camera (physical button other as camera screen).Then, find out people's face 110 by microprocessor (hereinafter to be referred as microprocessor) the executor face detection of digital camera, and set convergent-divergent block (being two blocks that dotted line surrounds among Fig. 3 A) according to people's face 110 positions.Afterwards, microprocessor calculates the width that the convergent-divergent block need dwindle according to scaling, and dwindles this convergent-divergent block.Simultaneously, also fill up the required pixel of filling in convergent-divergent block both sides.Microprocessor calculates that convergent-divergent block left side need fill up that the capable pixel of α is wide, convergent-divergent block right side need fill up the capable pixel of β wide after, (pixel of convergent-divergent block both sides is filled up mode as described above, and equidistant intervals is filled up entire row of pixels) fills the pixel that lacks to repair image shown in Fig. 3 B to scale promptly.Can find by Fig. 3 B,, can guarantee that facial image fixes in the convergent-divergent block, and the drum 120 that portrait is held can be because of not adjusting the outdoor scene that facial image causes deformation, distortion to take yet by the image processing method of adjustment facial image of the present invention.
In sum, the present invention detects by people's face and determines people's face position, and the full line or the permutation of setting people face position are the block that needs adjustment.Via this block of adjustment, can reach simultaneously whole portrait is carried out the ratio adjustment, and then make the health of portrait and face harmonious.In addition, behind the convergent-divergent block at adjustment people face place, the pixel (entire row of pixels that adds/remove) of changing when facial image is adjusted then can be repaired in the both sides of this convergent-divergent block of the adjustment of equal proportion, because of the human face ratio adjustment distortion phenomenon is arranged to guarantee that image is unlikely.
Certainly; the present invention also can have other various embodiments; under the situation that does not deviate from spirit of the present invention and essence thereof; those of ordinary skill in the art work as can make various corresponding changes and distortion according to the present invention, but these corresponding changes and distortion all should belong to the protection range of the appended claim of the present invention.
Claims (9)
1, a kind of image processing method of adjusting human face ratio, the ratio by the microprocessor or the digital processing chip of digital camera are adjusted people's face in the captured image is characterized in that this image processing method comprises:
This image is carried out the detection of people's face, and find out at least one people's face in this image;
According to this people's face position one convergent-divergent block is set;
One scaling is set, and according to this this convergent-divergent block of scaling geometric ratio adjustment; And
According to this scaling, the both sides of this convergent-divergent block of geometric ratio adjustment are to keep the pixel summation of this image.
2, the image processing method of adjustment human face ratio according to claim 1 is characterized in that, this people's face detects and may further comprise the steps:
This image is carried out rim detection to obtain an edge image;
Contrast several face characteristics in this edge image and the face database, to find out the people's face in the image; And
Write down this people's face position.
3, the image processing method of adjustment human face ratio according to claim 1 is characterized in that, this convergent-divergent block is the full line of this people's face position in this image.
4, the image processing method of adjustment human face ratio according to claim 1 is characterized in that, this convergent-divergent block is the permutation of this people's face position in this image.
5, the image processing method of adjustment human face ratio according to claim 1 is characterized in that, also comprising provides a man-machine interface, uses for the user this scaling is set.
6, the image processing method of adjustment human face ratio according to claim 1 is characterized in that, this scaling is the length percent of this convergent-divergent block before the shared adjustment of adjusted this convergent-divergent block.
7, the image processing method of adjustment human face ratio according to claim 1 is characterized in that, this convergent-divergent block of geometric ratio adjustment comprises:
Calculate the number row pixel of the required adjustment in both sides of this convergent-divergent block and this convergent-divergent block according to this scaling;
Equidistant insertion/remove the pixel of this full line to this convergent-divergent block; And
The equidistant pixel that removes/insert this full line is to the both sides of this convergent-divergent block.
8, the image processing method of adjustment human face ratio according to claim 1 is characterized in that, this convergent-divergent block of geometric ratio adjustment comprises:
Calculate the ordered series of numbers pixel of the required adjustment in both sides of this convergent-divergent block and this convergent-divergent block according to this scaling;
Equidistant insertion/remove the pixel of this permutation to this convergent-divergent block; And
The equidistant pixel that removes/insert this permutation is to the both sides of this convergent-divergent block.
9, the image processing method of adjustment human face ratio according to claim 1 is characterized in that, the mathematical notation formula of the scaling of these convergent-divergent block both sides is:
γ’＝γ+γ*X/(γ+δ)；
δ '=δ+δ * X/ (γ+δ); Wherein
Before γ is adjustment, the pixel head office/columns of a side of convergent-divergent block;
After γ ' is adjustment, the pixel head office/columns of a side of convergent-divergent block;
Before δ is adjustment, the pixel head office/columns of the opposite side of convergent-divergent block;
After δ ' is adjustment, the pixel head office/columns of the opposite side of convergent-divergent block; And
X is the pixel head office/columns of convergent-divergent block adjustment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100000792A CN101478629B (en) | 2008-01-04 | 2008-01-04 | Image processing process for regulating human face ratio |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2008100000792A CN101478629B (en) | 2008-01-04 | 2008-01-04 | Image processing process for regulating human face ratio |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101478629A true CN101478629A (en) | 2009-07-08 |
| CN101478629B CN101478629B (en) | 2010-09-22 |
Family
ID=40839256
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2008100000792A Expired - Fee Related CN101478629B (en) | 2008-01-04 | 2008-01-04 | Image processing process for regulating human face ratio |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101478629B (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393951A (en) * | 2011-06-30 | 2012-03-28 | Tcl集团股份有限公司 | Deformation method of human face model |
| CN103929565A (en) * | 2013-01-10 | 2014-07-16 | 柯尼卡美能达株式会社 | Image processing device and image processing method |
| CN104754217A (en) * | 2015-03-06 | 2015-07-01 | 深圳市欧珀通信软件有限公司 | Shooting method and terminal |
| CN105678251A (en) * | 2015-12-31 | 2016-06-15 | Tcl海外电子（惠州）有限公司 | Face image processing method and device |
| CN106454481A (en) * | 2016-09-30 | 2017-02-22 | 广州华多网络科技有限公司 | Live broadcast interaction method and apparatus of mobile terminal |
| CN106558040A (en) * | 2015-09-23 | 2017-04-05 | 腾讯科技（深圳）有限公司 | Character image treating method and apparatus |
| CN107172347A (en) * | 2017-05-12 | 2017-09-15 | 维沃移动通信有限公司 | A kind of photographic method and terminal |
| CN107181913A (en) * | 2017-05-25 | 2017-09-19 | 维沃移动通信有限公司 | A kind of photographic method and mobile terminal |
| CN107820007A (en) * | 2017-11-09 | 2018-03-20 | 维沃移动通信有限公司 | The picture processing method and mobile terminal of a kind of camera |
| CN107977927A (en) * | 2017-12-14 | 2018-05-01 | 北京奇虎科技有限公司 | Stature method of adjustment and device, computing device based on view data |
| CN112288623A (en) * | 2020-06-09 | 2021-01-29 | 北京沃东天骏信息技术有限公司 | Picture scaling method, device, equipment and storage medium |
| CN113822804A (en) * | 2021-09-23 | 2021-12-21 | 深圳万兴软件有限公司 | Gray scale map optimization method and device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1842125A (en) * | 2005-04-02 | 2006-10-04 | 奥多比公司 | Extraction and scaled display of objects in an image |
| US7184167B1 (en) * | 1999-09-30 | 2007-02-27 | Brother Kogyo Kabushiki Kaisha | Data processing for arranging text and image data on a substrate |
-
2008
- 2008-01-04 CN CN2008100000792A patent/CN101478629B/en not_active Expired - Fee Related
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7184167B1 (en) * | 1999-09-30 | 2007-02-27 | Brother Kogyo Kabushiki Kaisha | Data processing for arranging text and image data on a substrate |
| CN1842125A (en) * | 2005-04-02 | 2006-10-04 | 奥多比公司 | Extraction and scaled display of objects in an image |
Cited By (17)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393951B (en) * | 2011-06-30 | 2014-10-29 | Tcl集团股份有限公司 | Deformation method of human face model |
| CN102393951A (en) * | 2011-06-30 | 2012-03-28 | Tcl集团股份有限公司 | Deformation method of human face model |
| CN103929565A (en) * | 2013-01-10 | 2014-07-16 | 柯尼卡美能达株式会社 | Image processing device and image processing method |
| CN103929565B (en) * | 2013-01-10 | 2017-03-01 | 柯尼卡美能达株式会社 | Image processing apparatus and image processing method |
| CN104754217A (en) * | 2015-03-06 | 2015-07-01 | 深圳市欧珀通信软件有限公司 | Shooting method and terminal |
| CN106558040A (en) * | 2015-09-23 | 2017-04-05 | 腾讯科技（深圳）有限公司 | Character image treating method and apparatus |
| CN106558040B (en) * | 2015-09-23 | 2019-07-19 | 腾讯科技（深圳）有限公司 | Character image treating method and apparatus |
| CN105678251A (en) * | 2015-12-31 | 2016-06-15 | Tcl海外电子（惠州）有限公司 | Face image processing method and device |
| CN105678251B (en) * | 2015-12-31 | 2019-10-01 | Tcl海外电子（惠州）有限公司 | Face image processing process and device |
| CN106454481A (en) * | 2016-09-30 | 2017-02-22 | 广州华多网络科技有限公司 | Live broadcast interaction method and apparatus of mobile terminal |
| CN107172347A (en) * | 2017-05-12 | 2017-09-15 | 维沃移动通信有限公司 | A kind of photographic method and terminal |
| CN107172347B (en) * | 2017-05-12 | 2020-04-14 | 维沃移动通信有限公司 | Photographing method and terminal |
| CN107181913A (en) * | 2017-05-25 | 2017-09-19 | 维沃移动通信有限公司 | A kind of photographic method and mobile terminal |
| CN107820007A (en) * | 2017-11-09 | 2018-03-20 | 维沃移动通信有限公司 | The picture processing method and mobile terminal of a kind of camera |
| CN107977927A (en) * | 2017-12-14 | 2018-05-01 | 北京奇虎科技有限公司 | Stature method of adjustment and device, computing device based on view data |
| CN112288623A (en) * | 2020-06-09 | 2021-01-29 | 北京沃东天骏信息技术有限公司 | Picture scaling method, device, equipment and storage medium |
| CN113822804A (en) * | 2021-09-23 | 2021-12-21 | 深圳万兴软件有限公司 | Gray scale map optimization method and device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101478629B (en) | 2010-09-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101478629B (en) | Image processing process for regulating human face ratio | |
| CN104992408B (en) | For the panorama image generation method and device of user terminal | |
| US7356254B2 (en) | Image processing method, apparatus, and program | |
| EP2987134B1 (en) | Generation of ghost-free high dynamic range images | |
| US7612804B1 (en) | Methods and apparatuses for image processing | |
| CN101329732B (en) | Face detection method and digital camera | |
| US20050243350A1 (en) | Image processing method, apparatus, and program | |
| CN101212702B (en) | Image scoring method | |
| CN105049728A (en) | Method and device for acquiring shot image | |
| JP6720881B2 (en) | Image processing apparatus and image processing method | |
| WO2012149772A1 (en) | Method and apparatus for generating morphing animation | |
| EP3070930B1 (en) | Methods for generating high dynamic range hdr images and apparatuses using the same | |
| KR101756548B1 (en) | Methods for awb(automatic white balance) compensation and apparatuses using the same | |
| CN101256764A (en) | Frame region filters | |
| CN104867125B (en) | Obtain the method and device of image | |
| JP2008083820A (en) | Image processor, image processing method, and image processing program | |
| CN105989574A (en) | Image processing device and image field-depth processing method | |
| US20020164082A1 (en) | Image processing apparatus | |
| CN105574813A (en) | Image processing method and device | |
| CN105812672A (en) | Method and device for photographing processing | |
| EP3179716B1 (en) | Image processing method, computer storage medium, device, and terminal | |
| JP4851505B2 (en) | Image processing apparatus and image processing method | |
| JP2005332381A (en) | Image processing method, device and program | |
| TWI364002B (en) | ||
| CN106791351A (en) | Panoramic picture treating method and apparatus |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20100922 Termination date: 20160104 |
|
| EXPY | Termination of patent right or utility model |