CN104851114B - A kind of method and terminal for realizing image local discoloration - Google Patents
A kind of method and terminal for realizing image local discoloration Download PDFInfo
- Publication number
- CN104851114B CN104851114B CN201510200800.2A CN201510200800A CN104851114B CN 104851114 B CN104851114 B CN 104851114B CN 201510200800 A CN201510200800 A CN 201510200800A CN 104851114 B CN104851114 B CN 104851114B
- Authority
- CN
- China
- Prior art keywords
- image
- target location
- haar
- rgb value
- classifier
- 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.)
- Expired - Fee Related
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Color Image Communication Systems (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of method and terminal for realizing image local discoloration.Method therein includes：Identify the target location that local discolouration is treated in the image of generation；Detect the rgb value for the target location identified；The rgb value of the target location is converted, obtains the colour switching of the target location into the image of pre-set color.Also disclose corresponding terminal.The target location of local discolouration is treated in image by identifying generation, colour switching then is carried out to the target location, the same target location in same image can be allow to take different colors, increase the interest of shooting.
Description
Technical field
The present invention relates to picture imaging techniques field, more particularly to a kind of method and terminal for realizing image local discoloration.
Background technology
Current intelligent terminal such as mobile phone, tablet computer etc. all have camera function, however, using present intelligent terminal
Take pictures, be all that what color subject be that what color takes pictures out in itself is exactly, even being post-processed by photo,
Also simply increase and decrease saturation degree etc. in terms of color, and cannot change colour to the local location of subject, i.e., can not allow and take
Photo different colors is taken to same target location.
The content of the invention
The present invention provides a kind of method and terminal for realizing image local discoloration, so that same in same image
Target location can take different colors, increase the interest of shooting.
On the one hand, there is provided a kind of method for realizing image local discoloration, including：
Identify the target location that local discolouration is treated in the image of generation；
Detect the rgb value for the target location identified；
The rgb value of the target location is converted, obtains the colour switching of the target location into pre-set color
Image.
On the other hand, there is provided a kind of terminal, including：
First recognition unit, the target location of local discolouration is treated for identifying in the image generated；
Detection unit, for detecting the rgb value for the target location identified；
First converter unit, for being converted to the rgb value of the target location, obtains the color of the target location
It is transformed into the image of pre-set color.
As it can be seen that a kind of method and terminal for realizing image local discoloration provided according to the present invention, by identifying generation
The target location of local discolouration is treated in image, colour switching then is carried out to the target location, can be made in same image
Same target location can take different colors, increase the interest of shooting.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is attached drawing needed in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of flow diagram of method for realizing image local discoloration provided in an embodiment of the present invention；
Fig. 2 is the exemplary image for treating local discolouration；
Fig. 3 is the flow diagram for the method that another kind provided in an embodiment of the present invention realizes image local discoloration；
Fig. 4 is the schematic diagram of the original rectangular feature of exemplary acquisition Haar-like features；
Fig. 5 is a kind of structure diagram of terminal provided in an embodiment of the present invention；
Fig. 6 is the structure diagram of another terminal provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the attached drawing in the embodiment of the present invention, the technical solution in the embodiment of the present invention is carried out clear, complete
Site preparation describes, it is clear that described embodiment is only part of the embodiment of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment, belongs to the scope of protection of the invention.
If user can make the different photo of the color for appearing in same position select storage for user upon taking a picture, that will
It is an interesting experience.The present invention provides a kind of method and terminal for realizing image local discoloration, by the figure for identifying generation
The target location of local discolouration is treated as in, colour switching then is carried out to the target location, can be made same in same image
One target location can take different colors, increase the interest of shooting.
With reference to Fig. 1-Fig. 4, the method provided in an embodiment of the present invention for realizing image local discoloration is retouched in detail
State：
Referring to Fig. 1, be a kind of flow diagram for the method for realizing image local discoloration provided in an embodiment of the present invention,
This method comprises the following steps：
Step S101, identifies the target location that local discolouration is treated in the image of generation.
The present embodiment is changed colour to the local location of the image of generation, it is important to identify the target for treating local discolouration
Position.The image of local discolouration is treated as Fig. 2 is exemplary, to carry out the target location of local discolouration or target object is this tree,
And the color on sky and meadow does not change.For example, image can be identified using Haar classifier algorithm, obtain and wait to become
The target location of color.
Step S102, detects the rgb value for the target location identified.
The change of color be to red (R), green (G), blue (B) three Color Channels change and they are mutual
It is superimposed to obtain miscellaneous color.Before turn colors, first have to detection and identify that the target location of image is original
Rgb value.
Step S103, converts the rgb value of the target location, obtains the colour switching of the target location into pre-
If the image of color.
According to the color wanted, the calculating of rgb value is carried out, then the rgb value of target location is converted, that is, is become
Get the color wanted in return, and to the rgb value outside the target location of the image without changing, so as to fulfill image
Local discolouration.For example, the tree in Fig. 2 can be transformed into the green of script in a variety of colors, rather than image, and sky and grass
The color on ground does not change, and user can select the different photo of the color for preserving one or more tree therein, increase shooting
It is interesting.
A kind of method for realizing image local discoloration provided according to embodiments of the present invention, by identifying in the image generated
Treat the target location of local discolouration, colour switching then is carried out to the target location, can be made same in same image
Target location can take different colors, increase the interest of shooting.
Referring to Fig. 3, the flow signal of the method for image local discoloration is realized for another kind provided in an embodiment of the present invention
Figure, this method comprise the following steps：
Step S201, obtains distinguishing the target location and non-after the Haar features using AdaBoost Algorithm for Training samples
The strong classifier of target location, it is Haar classifier that screening, which cascades all strong classifiers,.
Step S202, the identification of the target location is carried out using the Haar features of the Haar classifier.
Step S203, in identification process, using integrating calculating of the nomography to the Haar features of the Haar classifier
Accelerated.
Step S201-S203 obtains target location to be changed colour for image is identified using Haar classifier algorithm
Specific steps.
HAAR characteristic methods are by using the local feature data sample obtained under the external conditions such as various different scenes
Cultivate, the grader of obtained corresponding topical feature, when carrying out local feature detection, pass through the lookup in grader
Match somebody with somebody, determine whether corresponding feature, so as to fulfill detection local feature.Overall operating procedure is as follows：
Haar classifier=Haar-like features+integrogram method+AdaBoost+ cascades.
1.Haar-like features：
Any one rectangle in Fig. 4 is put on the region of detection object, then, by the pixel of white area and is subtracted
The pixel of black region and, for obtained value we term it object features value, this rectangle is put into a non-detection object by you
Region, then the characteristic value calculated should be different with object features value.
2. integrogram method:
A picture sample is often run into, often runs into a sub- video in window, we all suffer from how calculating current subgraph
As the problem of characteristic value, how a Haar-like feature arranges in a window can preferably embody detection target
Feature, this is unknown, so just to train, and we can only be exhaustive all such special by permutation and combination before training
Sign, only by taking most basic four features as an example, arbitrary arrangement can at least produce number with 10 in the window of a 24 × 24size
The feature of ten thousand meters, the calculation amount to these feature evaluations is very big.And integrogram is exactly that only image of traversal can
The fast algorithm of all areas pixel sum in image is obtained, greatly improves the efficiency of image feature value calculating.
Wherein, step S203 may include following steps：
A：Calculate the cumulative of pixel line direction；
B：Progressively scan described image, the cumulative integral image that obtains of each pixel line direction of recursive calculation
Value；
C：Described image is scanned according to the value of the integral image and constructs integral image；
D：The Haar features of the Haar classifier are calculated by the integral image.
3.AdaBoost：
Come determine which type of rectangular characteristic what kind of be combined to one piece can preferably distinguish target to be detected and
It is non-targeted.
4. cascade：
Exactly the Adaboost combinations formed are all cascaded up, improve accuracy rate.
Step S204, detects the rgb value for the target location identified.
The change of color be to red (R), green (G), blue (B) three Color Channels change and they are mutual
It is superimposed to obtain miscellaneous color.Before turn colors, first have to detection and identify that the target location of image is original
Rgb value.
Step S205, is transformed to the rgb value of the corresponding data in target location in the yuv data of the image of the generation
Rgb value corresponding with pre-set color, the yuv data after being converted.
Step S206, according to the yuv data after the conversion, the image of output setting form.
Before output picture or image, the RGB for being yuv data, converting target location of the sensor output of camera
Value, is that the rgb value of the corresponding data in target location in yuv data is converted.According to the color wanted, carry out
The calculating of rgb value, then converts the rgb value of target location, i.e. conversion obtains the color wanted, and to the image
Target location outside rgb value without change, so as to fulfill the local discolouration of image.For example, the tree in Fig. 2 can be become
Change the green of script in a variety of colors, rather than image into, and the color on sky and meadow does not change, user can select to preserve
The different photo of the color of one or more tree therein, increases the interest of shooting.Converted in the RGB to target location
Afterwards, the yuv data after conversion rgb value is obtained, yuv data is pressed into the image of setting form, is output to photograph album.
A kind of method for realizing image local discoloration provided according to embodiments of the present invention, by identifying in the image generated
Treat the target location of local discolouration, colour switching then is carried out to the target location, can be made same in same image
Target location can take different colors, increase the interest of shooting；The identification of target location is carried out using Haar classifier,
Screening type cascade system improves the accuracy rate of grader, and the use for integrating nomography accelerates the speed of algorithm.
With reference to Fig. 5-Fig. 6, the terminal provided in an embodiment of the present invention for realizing image local discoloration is retouched in detail
State：
Referring to Fig. 5, for a kind of structure diagram of terminal provided in an embodiment of the present invention, which includes：
First recognition unit 11, the target location of local discolouration is treated for identifying in the image generated.
The present embodiment is changed colour to the local location of the image of generation, it is important to which the first recognition unit 11, which will identify, to be treated
The target location of local discolouration.The image of local discolouration is treated as Fig. 2 is exemplary, to carry out target location or the target of local discolouration
Object is this tree, and the color on sky and meadow does not change.For example, Haar classifier algorithm can be applied to carry out image
Identification, obtains target location to be changed colour.
Detection unit 12, detects the rgb value for the target location identified.
The change of color be to red (R), green (G), blue (B) three Color Channels change and they are mutual
It is superimposed to obtain miscellaneous color.Before turn colors, detection unit 12 first has to the mesh that detection identifies image
The original rgb value of cursor position.
First converter unit 13, for being converted to the rgb value of the target location, obtains the face of the target location
Discoloration changes the image of pre-set color into.
First converter unit 13 carries out the calculating of rgb value, then to the RGB of target location according to the color wanted
Value is converted, i.e. conversion obtains the color wanted, and to the rgb value outside the target location of the image without changing
Become, so as to fulfill the local discolouration of image.For example, the tree in Fig. 2 can be transformed into a variety of colors, rather than image originally
Green, and the color on sky and meadow does not change, and user can select the color for preserving one or more tree therein different
Photo, increase the interest of shooting.
A kind of terminal provided according to embodiments of the present invention, the target position of local discolouration is treated by identifying in the image generated
Put, colour switching then is carried out to the target location, the same target location in same image can be allow to take not
Same color, increases the interest of shooting.
Referring to Fig. 6, for the structure diagram of another terminal provided in an embodiment of the present invention, which includes：
First recognition unit 21, for image to be identified using Haar classifier algorithm, obtains target to be changed colour
Position.
Specifically, the first recognition unit 21 includes Haar classifier training unit 211, the second recognition unit 212 and accelerates
Recognition unit 213.
Haar classifier training unit 211, for application AdaBoost Algorithm for Training samples Haar features after obtain area
Divide the strong classifier of the target location and non-targeted position, it is Haar classifier that screening, which cascades all strong classifiers,.
Second recognition unit 212, the Haar features for the application Haar classifier carry out the knowledge of the target location
Not.
Accelerate recognition unit 213, in identification process, using integrating Haar of the nomography to the Haar classifier
The calculating of feature is accelerated.
HAAR characteristic methods are by using the local feature data sample obtained under the external conditions such as various different scenes
Cultivate, the grader of obtained corresponding topical feature, when carrying out local feature detection, pass through the lookup in grader
Match somebody with somebody, determine whether corresponding feature, so as to fulfill detection local feature.Overall operation is as follows：
Haar classifier=Haar-like features+integrogram method+AdaBoost+ cascades.
1.Haar-like features：
Any one rectangle in Fig. 4 is put on the region of detection object, then, by the pixel of white area and is subtracted
The pixel of black region and, for obtained value we term it object features value, this rectangle is put into a non-detection object by you
Region, then the characteristic value calculated should be different with object features value.
2. integrogram method:
A picture sample is often run into, often runs into a sub- video in window, we all suffer from how calculating current subgraph
As the problem of characteristic value, how a Haar-like feature arranges in a window can preferably embody detection target
Feature, this is unknown, so just to train, and we can only be exhaustive all such special by permutation and combination before training
Sign, only by taking most basic four features as an example, arbitrary arrangement can at least produce number with 10 in the window of a 24 × 24size
The feature of ten thousand meters, the calculation amount to these feature evaluations is very big.And integrogram is exactly that only image of traversal can
The fast algorithm of all areas pixel sum in image is obtained, greatly improves the efficiency of image feature value calculating.
Wherein, recognition unit 213 is accelerated to may include the first computing unit, the second computing unit, integral image structural unit
With the 3rd computing unit.Wherein：
First computing unit：For calculating the cumulative of pixel line direction；
Second computing unit：For progressively scanning described image, each pixel line direction of recursive calculation it is cumulative
Obtain the value of integral image；
Integral image structural unit, integral image is constructed for scanning described image according to the value of the integral image；
3rd computing unit, for being calculated by the integral image the Haar features of the Haar classifier.
3.AdaBoost：
Come determine which type of rectangular characteristic what kind of be combined to one piece can preferably distinguish target to be detected and
It is non-targeted.
4. cascade：
Exactly the Adaboost combinations formed are all cascaded up, improve accuracy rate.
Detection unit 22, for detecting the rgb value for the target location identified.
The change of color be to red (R), green (G), blue (B) three Color Channels change and they are mutual
It is superimposed to obtain miscellaneous color.Before turn colors, first have to detection and identify that the target location of image is original
Rgb value.
First converter unit 23, for being converted to the rgb value of the target location, obtains the face of the target location
Discoloration changes the image of pre-set color into.
In the present embodiment, the first converter unit 23 includes the second converter unit 231 and output unit 232.
Second converter unit 231, for the corresponding data in target location in the yuv data of the image to the generation
Rgb value is transformed to rgb value corresponding with pre-set color, the yuv data after being converted.
Output unit 232, for according to the yuv data after the conversion, the image of output setting form.
Before output picture or image, the RGB for being yuv data, converting target location of the sensor output of camera
Value, is that the rgb value of the corresponding data in target location in yuv data is converted.According to the color wanted, carry out
The calculating of rgb value, then converts the rgb value of target location, i.e. conversion obtains the color wanted, and to the image
Target location outside rgb value without change, so as to fulfill the local discolouration of image.For example, the tree in Fig. 2 can be become
Change the green of script in a variety of colors, rather than image into, and the color on sky and meadow does not change, user can select to preserve
The different photo of the color of one or more tree therein, increases the interest of shooting.Converted in the RGB to target location
Afterwards, the yuv data after conversion rgb value is obtained, yuv data is pressed into the image of setting form, is output to photograph album.
A kind of terminal provided according to embodiments of the present invention, the target position of local discolouration is treated by identifying in the image generated
Put, colour switching then is carried out to the target location, the same target location in same image can be allow to take not
Same color, increases the interest of shooting；The identification of target location is carried out using Haar classifier, screening type cascade system improves
The accuracy rate of grader, the use for integrating nomography accelerate the speed of algorithm.
It should be noted that for foregoing each method embodiment, in order to be briefly described, therefore it is all expressed as a series of
Combination of actions, but those skilled in the art should know, the present invention and from the limitation of described sequence of movement because
According to the present invention, some steps can use other orders or be carried out at the same time.Secondly, those skilled in the art should also know
Know, embodiment described in this description belongs to preferred embodiment, and involved action and module are not necessarily of the invention
It is necessary.
In the above-described embodiments, the description to each embodiment all emphasizes particularly on different fields, and does not have the portion being described in detail in some embodiment
Point, it may refer to the associated description of other embodiment.
Through the above description of the embodiments, it is apparent to those skilled in the art that the present invention can be with
Realized with hardware realization, or firmware realization, or combinations thereof mode.When implemented in software, can be by above-mentioned function
It is stored in computer-readable medium or is transmitted as one or more instructions on computer-readable medium or code.Meter
Calculation machine computer-readable recording medium includes computer storage media and communication media, and wherein communication media includes being easy to from a place to another
Any medium of a place transmission computer program.Storage medium can be any usable medium that computer can access.With
Exemplified by this but it is not limited to：Computer-readable medium can include random access memory (Random Access Memory,
RAM), read-only storage (Read-Only Memory, ROM), Electrically Erasable Programmable Read-Only Memory (Electrically
ErasableProgrammable Read-Only Memory, EEPROM), read-only optical disc (Compact Disc Read-
OnlyMemory, CD-ROM) or other optical disc storages, magnetic disk storage medium or other magnetic storage apparatus or can be used in
Carry or storage with instruction or data structure form desired program code simultaneously can by computer access any other
Medium.In addition.Any connection can be suitably become computer-readable medium.For example, if software is using coaxial cable, light
Fine optical cable, twisted-pair feeder, Digital Subscriber Line (Digital SubscriberLine, DSL) or such as infrared ray, radio and micro-
The wireless technology of ripple etc is transmitted from website, server or other remote sources, then coaxial cable, optical fiber cable, multiple twin
The wireless technology of line, DSL or such as infrared ray, wireless and microwave etc be included in belonging to medium it is fixing in.Such as the present invention
Used, disk (Disk) and dish (disc) include compression laser disc (CD), laser disc, laser disc, Digital Versatile Disc (DVD), soft
Disk and Blu-ray Disc, the usually magnetic replicate data of which disk, and dish is then with laser come optical replicate data.Above combination above
It should also be as being included within the protection domain of computer-readable medium.
In short, the foregoing is merely the preferred embodiment of technical solution of the present invention, it is not intended to limit the present invention's
Protection domain.Within the spirit and principles of the invention, any modification, equivalent replacement, improvement and so on, should be included in
Within protection scope of the present invention.
Claims (2)
- A kind of 1. method for realizing image local discoloration, it is characterised in that including：Identify the target location that local discolouration is treated in the image of generation；Detect the rgb value for the target location identified；The rgb value of the target location is converted, obtains the colour switching of the target location into the image of pre-set color；The target location of local discolouration is treated in the image of the identification generation, including：Described image is identified using Haar classifier algorithm, target location to be changed colour described in acquisition；Described image is identified in the application Haar classifier algorithm, target location to be changed colour described in acquisition, including：Calculate the cumulative of pixel line direction；Described image is progressively scanned, each the cumulative of the pixel line direction obtains the value of integral image to recursive calculation；Described image is scanned according to the value of the integral image and constructs integral image；The Haar features of the Haar classifier are calculated by the integral image；Obtain distinguishing the strong of the target location and non-targeted position after Haar features using AdaBoost Algorithm for Training samples Grader, it is Haar classifier that screening, which cascades all strong classifiers,；The identification of the target location is carried out using the Haar features of the Haar classifier；The rgb value to the target location converts, and obtains the colour switching of the target location into pre-set color Image, including：The rgb value of the corresponding data in target location in the yuv data of the image of the generation is transformed to and pre-set color pair The rgb value answered, the yuv data after being converted；According to the yuv data after the conversion, the image of output setting form.
- A kind of 2. terminal, it is characterised in that including：First recognition unit, the target location of local discolouration is treated for identifying in the image generated；Detection unit, for detecting the rgb value for the target location identified；First converter unit, for being converted to the rgb value of the target location, obtains the colour switching of the target location Into the image of pre-set color；First recognition unit is specifically used for：Described image is identified using Haar classifier algorithm, target location to be changed colour described in acquisition；First recognition unit includes：Accelerate recognition unit, in identification process, using integrating nomography to the Haar features of the Haar classifier Calculating is accelerated；Haar classifier training unit, for application AdaBoost Algorithm for Training samples Haar features after obtain distinguishing the mesh Cursor position and the strong classifier of non-targeted position, it is Haar classifier that screening, which cascades all strong classifiers,；Second recognition unit, the Haar features for the application Haar classifier carry out the identification of the target location；The acceleration recognition unit includes：First computing unit, for calculating the cumulative of pixel line direction；Second computing unit, for progressively scanning described image, each the cumulative of pixel line direction obtains recursive calculation The value of integral image；Integral image structural unit, integral image is constructed for scanning described image according to the value of the integral image；3rd computing unit, for being calculated by the integral image the Haar features of the Haar classifier；First converter unit includes：Second converter unit, the rgb value for the corresponding data in target location in the yuv data of the image to the generation become It is changed to rgb value corresponding with pre-set color, the yuv data after being converted；Output unit, for according to the yuv data after the conversion, the image of output setting form.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510200800.2A CN104851114B (en) | 2015-04-24 | 2015-04-24 | A kind of method and terminal for realizing image local discoloration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510200800.2A CN104851114B (en) | 2015-04-24 | 2015-04-24 | A kind of method and terminal for realizing image local discoloration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104851114A CN104851114A (en) | 2015-08-19 |
| CN104851114B true CN104851114B (en) | 2018-05-01 |
Family
ID=53850741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510200800.2A Expired - Fee Related CN104851114B (en) | 2015-04-24 | 2015-04-24 | A kind of method and terminal for realizing image local discoloration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104851114B (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105488819B (en) * | 2015-12-04 | 2018-09-18 | 小米科技有限责任公司 | Generation method, image processing method and the device of color template |
| CN106642003B (en) * | 2016-11-15 | 2019-04-12 | 广州视源电子科技股份有限公司 | Method for automatically changing color of jewelry and jewelry |
| CN109166162A (en) * | 2018-10-08 | 2019-01-08 | 苏州仙峰网络科技股份有限公司 | 2D color changing method based on fixed form and aspect |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1181569A (en) * | 1996-10-08 | 1998-05-13 | 夏普公司 | INformation processing apparatus |
| EP0852041A1 (en) * | 1995-09-14 | 1998-07-08 | Bently Mills, Inc. | Method and systems for manipulation of images of floor coverings or other fabrics |
| CN101043578A (en) * | 2006-03-21 | 2007-09-26 | 晨星半导体股份有限公司 | Hue regulation system and its regulation method |
| CN102567974A (en) * | 2010-12-16 | 2012-07-11 | 方正国际软件(北京)有限公司 | Method and system for adjusting local color of image |
| CN104519238A (en) * | 2013-09-26 | 2015-04-15 | 天津书生软件技术有限公司 | Color correction method |
-
2015
- 2015-04-24 CN CN201510200800.2A patent/CN104851114B/en not_active Expired - Fee Related
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP0852041A1 (en) * | 1995-09-14 | 1998-07-08 | Bently Mills, Inc. | Method and systems for manipulation of images of floor coverings or other fabrics |
| CN1181569A (en) * | 1996-10-08 | 1998-05-13 | 夏普公司 | INformation processing apparatus |
| CN101043578A (en) * | 2006-03-21 | 2007-09-26 | 晨星半导体股份有限公司 | Hue regulation system and its regulation method |
| CN102567974A (en) * | 2010-12-16 | 2012-07-11 | 方正国际软件(北京)有限公司 | Method and system for adjusting local color of image |
| CN104519238A (en) * | 2013-09-26 | 2015-04-15 | 天津书生软件技术有限公司 | Color correction method |
Non-Patent Citations (3)
| Title |
|---|
| 基于Adaboost算法的人脸检测分类器的设计与实现;兰胜坤;《电脑知识与技术》;20101105;第6卷(第31期);8828-8830 * |
| 基于类Haar特征与级联AdaBoost算法的防震锤识别;金立军 等;《系统仿真学报》;20120815;第24卷(第9期);1806-1809 * |
| 数码影像技术操作篇之六十三 图像色彩调整的基本方法(上);齐欣;《照相机》;20090301(第3期);60-63 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104851114A (en) | 2015-08-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107424123B (en) | Moire pattern removing method and device | |
| CN108335306B (en) | Image processing method and device, electronic equipment and storage medium | |
| US10204432B2 (en) | Methods and systems for color processing of digital images | |
| CN107204034B (en) | A kind of image processing method and terminal | |
| US20160155241A1 (en) | Target Detection Method and Apparatus Based On Online Training | |
| Mi et al. | Single image dehazing via multi‐scale gradient domain contrast enhancement | |
| CN108154086B (en) | Image extraction method and device and electronic equipment | |
| CN111833340A (en) | Image detection method, image detection device, electronic equipment and storage medium | |
| CN111385640B (en) | Video cover determining method, device, equipment and storage medium | |
| CN111144337B (en) | Fire detection method and device and terminal equipment | |
| CN112967180B (en) | Training method for generating countermeasure network, image style conversion method and device | |
| CN104851114B (en) | A kind of method and terminal for realizing image local discoloration | |
| JP6779688B2 (en) | Image processing equipment, image processing method, computer program | |
| CN113538223B (en) | Noise image generation method, device, electronic equipment and storage medium | |
| CN114372931A (en) | Target object blurring method and device, storage medium and electronic equipment | |
| WO2023011280A1 (en) | Image noise degree estimation method and apparatus, and electronic device and storage medium | |
| CN110838088A (en) | Multi-frame noise reduction method and device based on deep learning and terminal equipment | |
| CN110310341B (en) | Method, device, equipment and storage medium for generating default parameters in color algorithm | |
| Sheng et al. | Multi-scale residual attention network for single image dehazing | |
| WO2015189369A1 (en) | Methods and systems for color processing of digital images | |
| CN112489144A (en) | Image processing method, image processing apparatus, terminal device, and storage medium | |
| Riaz et al. | Single image dehazing with bright object handling | |
| CN112995666B (en) | Video horizontal and vertical screen conversion method and device combined with scene switching detection | |
| CN104463898A (en) | Image identification counting system for logistics platform | |
| Kim et al. | Information measure based tone mapping of outdoor LDR image for maximum scale‐invariant feature transform extraction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: Changan town in Guangdong province Dongguan 523860 usha Beach Road No. 18 Patentee before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20180501 |