CN108446705A - The method and apparatus of image procossing - Google Patents
The method and apparatus of image procossing Download PDFInfo
- Publication number
- CN108446705A CN108446705A CN201710082941.8A CN201710082941A CN108446705A CN 108446705 A CN108446705 A CN 108446705A CN 201710082941 A CN201710082941 A CN 201710082941A CN 108446705 A CN108446705 A CN 108446705A
- Authority
- CN
- China
- Prior art keywords
- brightness
- foreground
- colour system
- subdivision
- adjustment
- 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
- 238000000034 method Methods 0.000 title claims abstract description 90
- 238000012545 processing Methods 0.000 claims abstract description 72
- 238000012937 correction Methods 0.000 claims description 56
- 238000006243 chemical reaction Methods 0.000 claims description 15
- 238000004422 calculation algorithm Methods 0.000 claims description 6
- 230000008859 change Effects 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 4
- 238000005286 illumination Methods 0.000 description 29
- 241001183271 Verrucomicrobiaceae Species 0.000 description 8
- 239000003086 colorant Substances 0.000 description 7
- 238000010586 diagram Methods 0.000 description 7
- 241000930965 Spartobacteria Species 0.000 description 6
- 241000936928 Verrucomicrobia subdivision 3 Species 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000000463 material Substances 0.000 description 3
- 238000013139 quantization Methods 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008878 coupling Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 1
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000010894 electron beam technology Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003702 image correction Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- G06T5/94—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/56—Extraction of image or video features relating to colour
-
- 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
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20004—Adaptive image processing
- G06T2207/20012—Locally adaptive
Abstract
This application provides a kind of methods and apparatus of processing image, can accurately obtain the brightness of target object, reduce the difference of the target object color caused by brightness of image changes, and then be conducive to the retrieval or identification of target object.This method includes:Target image is transformed into tone saturation degree brightness HSV space from RGB rgb space, wherein the target image includes foreground part and background parts;According to the brightness of the background parts and the brightness of the foreground part, the colour system of the foreground part is determined;According to the colour system of the foreground part, the brightness of the foreground part is adjusted;According to the brightness after the adjustment of the foreground part, which is transformed into the rgb space from the HSV space.
Description
Technical field
This application involves image processing fields, and more particularly, to the method and apparatus of image procossing.
Background technology
In the prior art, the imaging device based on optics, image quality are all influenced by illumination.With image
In many applications based on content analysis, for example, recognition of face, iris recognition, image retrieval and video monitoring etc., exterior light
According to the brightness of often change image, and then change the color of image, brings very big difficulty to Target Acquisition, affect and depend on
The validity for the system that color is retrieved or identified.
Therefore, the brightness of target object how is accurately obtained, the target object face caused by brightness of image changes is reduced
The difference of color improves the validity for the system retrieved or identified dependent on color, is a urgent problem to be solved.
Invention content
The application provides a kind of method of processing image, can accurately obtain the brightness of target object, reduce brightness of image
The difference of the target object color caused by change, and then be conducive to the retrieval or identification of target object.
In a first aspect, a kind of method of processing image is provided, including:Target image is converted from RGB rgb space
To tone saturation degree brightness HSV space, wherein the target image includes foreground part and background parts;According to the background parts
Brightness and the foreground part brightness, determine the colour system of the foreground part;According to the colour system of the foreground part, before adjusting this
The brightness of scape part;According to the brightness after the adjustment of the foreground part, which is transformed into the rgb space from the HSV space.
Therefore, in this application, image processing equipment is satisfied by the way that target image is transformed into tone from RGB rgb space
With degree brightness HSV space, according to the brightness of the background parts of the target image and the brightness of the foreground part of the target image,
Determine the colour system of the foreground part;According to the colour system of the foreground part, the brightness of the foreground part is adjusted;The foreground portion will be adjusted
The target image of brightness is divided to be transformed into the rgb space from the HSV space.This is determined by the brightness in conjunction with the background parts
The colour system of foreground part increases the condition of the colour system of determining foreground part, improves the standard for the colour system for determining the foreground part
True rate to adjust the brightness of the foreground part according to the colour system of the foreground part, and will adjust being somebody's turn to do for the foreground part brightness
Target image is transformed into the rgb space from the HSV space, reduces the mesh caused by the brightness of image difference under different illumination
The difference of object color is marked, and then is conducive to the retrieval or identification of target object.
Optionally, in a kind of realization method of first aspect, according to the brightness of the background parts and the foreground part
Brightness, determine the colour system of the foreground part, including:According to the brightness of the background parts, determine that the brightness of the foreground part is repaiied
Positive coefficient;According to the brightness correction coefficient of the foreground part, the brightness of the foreground part is adjusted;According to the adjustment of the foreground part
Brightness afterwards determines the colour system of the foreground part.
Optionally, in a kind of realization method of first aspect, which is mainly the target line in target image
People's image, the background parts are the picture materials in addition to the foreground part in the target image.
Optionally, in a kind of realization method of first aspect, which can be divided into entire background parts and foot
Lower background parts.A part for background where the underfooting background parts can choose the target image lower part in proportion.
At this point, by carrying out background parts to be divided into underfooting background parts, the illumination level of underfooting background parts is with before
Scape part is more nearly, and is conducive to obtain more accurately brightness correction coefficient.
Optionally, in a kind of realization method of first aspect, according to the brightness of the background parts, the foreground part is determined
Brightness correction coefficient, including:According to the interval range of the brightness of the background parts and background luminance, the background parts institute is determined
The interval range of the background luminance of category;Determine the corresponding brightness correction system of the interval range of the background luminance belonging to the background parts
Number is the brightness correction coefficient of the foreground part.
Optionally, in a kind of realization method of first aspect, according to the brightness of entire background parts, the background portion is determined
The interval range of background luminance belonging to point;Determine the interval range of the background luminance belonging to the entire background parts;It determines whole
The corresponding brightness correction coefficient of interval range of background luminance belonging to a background parts is the brightness correction system of the foreground part
Number.
Optionally, in a kind of realization method of first aspect, according to the brightness of underfooting background parts, the background portion is determined
The interval range of background luminance belonging to point;Determine the interval range of the background luminance belonging to the entire background parts;It determines whole
The corresponding brightness correction coefficient of interval range of background luminance belonging to a background parts is the brightness correction system of the foreground part
Number.
At this point, the brightness correction coefficient of the background parts by repeatedly compare the background luminance under the illumination condition with it is normal
The ratio of background luminance under illumination condition obtains, which reflects under the illumination condition, it should to foreground image
Brightness adjustment, the brightness which is adjusted by the corresponding brightness correction coefficient of the background parts so that the foreground
Closer to the brightness under normal illumination, the brightness after being adjusted according to the foreground part determines the color of the foreground part for partial brightness
System improves the accuracy rate for the colour system for determining the foreground part.
Optionally, in a kind of realization method of first aspect, brightness and the underfooting background portion of entire background parts are calculated
The mean value of the brightness divided, the interval range of the background luminance belonging to the background parts is determined according to the mean value;Determine the entire back of the body
The interval range of background luminance belonging to scape part;Determine that the interval range of the background luminance belonging to entire background parts is corresponding
Brightness correction coefficient is the brightness correction coefficient of the foreground part.
Optionally, in a kind of realization method of first aspect, which determines the foreground portion
The brightness correction coefficient divided, including:The average value of the brightness of the background parts of the multiple images in image storage database is calculated,
Multiple image and the image that the image is under same capturing scenes;By the background of the target image where the foreground part
The ratio that partial brightness stores the average value of the brightness of the background parts of the multiple images in database with the image is determined as
The brightness correction coefficient of the foreground part.
At this point, the brightness correction coefficient is the back of the body of the brightness and the multiple images under the same capturing scenes of the background parts
The ratio of the brightness of scape part avoids light by reference to the brightness of the background parts of the multiple images under the same capturing scenes
According to the influence of the brightness of the foreground part to the target image, adjusted by the corresponding brightness correction coefficient of the background parts
The brightness of the foreground part so that the brightness of the foreground part is closer to the brightness under normal illumination, according to the foreground part tune
Brightness after whole determines the colour system of the foreground part, improves the accuracy rate for the colour system for determining the foreground part.
Optionally, in a kind of realization method of first aspect, according to the brightness after the adjustment of the foreground part, determining should
The colour system of foreground part, including:The brightness range for comparing the brightness and multiple colour systems of the adjustment of the foreground part, determines the foreground
Partial colour system.
Optionally, in a kind of realization method of first aspect, this compare the brightness of the adjustment of the foreground part with it is multiple
The brightness range of colour system determines the colour system of the foreground part, including:The brightness after adjustment of the foreground part belongs to multiple colors
The brightness range of the first colour system in system, and it is less than first with the absolute difference of the critical value of the brightness range of first colour system
When threshold value, according to the foreground part in the tone and saturation degree of the HSV space, the colour system of the foreground part is determined;Or when described
Brightness after the adjustment of foreground part belongs to the brightness range of the first colour system in multiple colour systems, and bright with first colour system
Spend range critical value absolute difference be greater than or equal to the first threshold when, by first colour system be determined as it is described before
The colour system of scape subdivision.
At this point, belong to the brightness range of the first colour system in multiple colour systems by the foreground part brightness after the adjustment,
And when being less than first threshold with the absolute difference of the critical value of the brightness range of first colour system, according to the foreground part at this
The tone and saturation degree of HSV space, determine the colour system of the foreground part, avoid the colour system for judging the foreground part by accident and lead to figure
As inquiry failure.
Optionally, in a kind of realization method of first aspect, this compare the brightness of the adjustment of the foreground part with it is multiple
The brightness range of colour system determines the colour system of the foreground part, including:The brightness after adjustment of the foreground part belongs to multiple colors
The brightness range of the first colour system in system, and it is less than first with the absolute difference of the critical value of the brightness range of first colour system
When threshold value, which can be done to two classification processing, using the foreground subdivision as the first colour system and the second color
System is handled, wherein second colour system and the first colour system are adjacent.
Optionally, in a kind of realization method of first aspect, this is according to the brightness of the background parts and the foreground portion
The brightness divided, determines that the colour system of the foreground part includes:The foreground part is divided into multiple foreground subdivisions;According to the background
Partial brightness is adjusted the brightness of each foreground subdivision in multiple foreground subdivision;According to each foreground
Brightness after partial adjustment determines the colour system of each foreground subdivision;Brightness after the adjustment according to the foreground part, really
The colour system of the foreground part includes calmly:According to the colour system of each foreground subdivision, the brightness of each foreground subdivision is adjusted.
At this point, by the way that the foreground part is divided into multiple foreground subdivisions, and to every in multiple foreground subdivision
A foreground sub-portion is allocated as different processing, avoids the interference between different foreground subdivisions, is conducive to more accurately judge that
The colour system of each foreground subdivision in multiple foreground subdivision and according in multiple foreground subdivision each foreground son
Partial colour system adjusts the brightness of each foreground subdivision.
Optionally, in a kind of realization method of first aspect, multiple foreground subdivision includes the first foreground subdivision
With the second foreground subdivision, the brightness category after brightness and the second foreground subdivision adjustment after the first foreground subdivision adjustment
In the brightness range of the first colour system, brightness after the first foreground subdivision adjustment is critical with the brightness range of first colour system
The absolute difference of value is greater than or equal to second threshold, and the brightness after the second foreground subdivision adjustment is bright with first colour system
The absolute difference for spending the critical value of range is less than the second threshold;
This determines the colour system of each foreground subdivision according to the brightness after each foreground subdivision adjustment, including:
First colour system is determined as to the colour system of the first foreground subdivision;
The difference of brightness and the brightness after the first foreground subdivision adjustment after the second foreground subdivision adjusts is exhausted
When being greater than or equal to third threshold value to value, according to the second foreground subdivision in the tone and saturation degree of the HSV space, determining should
The colour system of second foreground subdivision;Or, brightness after the second foreground subdivision adjusts is adjusted with the first foreground subdivision
When the absolute difference of brightness afterwards is greater than or equal to third threshold value, by the adjacent model of the brightness of the second foreground subdivision adjustment
Enclose the colour system that corresponding colour system is determined as the second foreground subdivision;Or, brightness after the second foreground subdivision adjusts with
When the absolute difference of the brightness of the second foreground subdivision is less than the third threshold value, which is determined as this before second
The colour system of scape subdivision.
Optionally, in a kind of realization method of first aspect, which is divided into multiple first foreground sub-portions
Timesharing, the brightness after the first foreground subdivision adjustment can be the brightness after wherein any one first foreground subdivision adjustment
Or the mean value of the brightness after multiple first foreground subdivision adjustment.
Optionally, in a kind of realization method of first aspect, according to the brightness of the background parts and the foreground part
Brightness, determine the colour system of the foreground part, including:By the tone of the foreground part, saturation degree and brightness and the Background
The brightness input parameter model of picture, and obtain the label value of parameter model output, wherein the parameter model is used to indicate at this
Under the capturing scenes of target image, the label value of multiple colour systems, the tone with foreground part, saturation degree and brightness and background portion
The correspondence of the brightness divided;According to the label value of the output of the parameter model, the colour system of the foreground part is determined.
Optionally, in a kind of realization method of first aspect, tone, saturation degree and the brightness by the foreground part with
And before the brightness input parameter model of the background parts, this method further includes:According to each colour system setting in multiple colour system
Label value and image storage database in multiple images in foreground part tone, saturation degree and brightness and this is every
The brightness of background parts in a image carries out algorithm training, determines that the parameter model, multiple image are with the target image
Image under same capturing scenes.
Optionally, it is bright in the corresponding brightness set of colour system of the foreground part by the brightness adjustment of the foreground part
Degree.
Optionally, according to the colour system of the foreground part, the corresponding brightness set of the colour system of the foreground part is determined;According to this
Brightness set adjusts the brightness of the foreground part.
Optionally, which is a kind of colour system in dark colour system, coloured colour system and white light tone system, which corresponds to
Brightness set in element be a;The corresponding brightness collection of the coloured colour system is combined into the brightness model more than or equal to b and less than or equal to c
It encloses;The white light tone is that the element in corresponding brightness set is d,
Wherein, a, the b, the c and the d meet relational expression:
D≤1 0≤a < b≤c <
A, b, c and the d are constant.
Second aspect provides a kind of method of processing image, including:Target image is converted from RGB rgb space
To tone saturation degree brightness HSV space;When the brightness of the target image belongs to the brightness range of the first colour system in multiple colour systems,
And when being less than first threshold with the absolute difference of the critical value of the brightness range of first colour system, according to the target image at this
The tone and saturation degree of HSV space, determine the colour system of the foreground part;According to the colour system of the target image, the target figure is adjusted
The brightness of picture;According to the brightness after the adjustment of the target image, which is transformed into the rgb space from the HSV space.
The third aspect provides a kind of method of processing head portrait, including:Target image is converted from RGB rgb space
To tone saturation degree brightness HSV space, which includes first part and second part;
The brightness of the first part and the brightness of the second part belong to the brightness range of the first colour system, and described first
The absolute difference of partial brightness and the critical value of the brightness range of first colour system is greater than or equal to first threshold, described
The brightness of second part and the absolute difference of the critical value of the brightness range of first colour system are less than the first threshold, will
First colour system is determined as the colour system of the first part;
When the absolute difference of the brightness of the brightness and first part of the second part is greater than or equal to the second threshold
When value, according to the second part in the tone and saturation degree of the HSV space, the colour system of the second part is determined;Or work as
It, will be described when the brightness of the second part and the absolute difference of the brightness of the first part are greater than or equal to second threshold
The adjacent corresponding colour system of range of the brightness of second part is determined as the colour system of the second part;Or, working as the second part
The absolute difference of brightness of brightness and second part when being less than the second threshold, first colour system is determined as
The colour system of the second part;
According to the colour system of the first part and the second part, the brightness of the first part and second part is adjusted;
According to the brightness after the adjustment of the target image, which is transformed into the rgb space from the HSV space.
Fourth aspect provides a kind of image processing equipment, including conversion module, first processing module and adjustment module,
The method in any possible realization method of above-mentioned first aspect or first aspect can be executed.
5th aspect provides a kind of image processing equipment, including conversion module, first processing module and adjustment module,
The method in any possible realization method of above-mentioned second aspect or second aspect can be executed.
6th aspect provides a kind of image processing equipment, including conversion module, first processing module and adjustment module,
The method in any possible realization method of the above-mentioned third aspect or the third aspect can be executed.
7th aspect, provides a kind of image processing equipment, including memory, transceiver and processor, the memory
On be stored with the program code that can serve to indicate that and execute above-mentioned first or its arbitrary optional realization method, transceiver is used for
Specific signal transmitting and receiving is executed under the driving of processor, when the code is performed, the processor may be implemented in method
Terminal device executes each operation.
Eighth aspect provides a kind of image processing equipment, including memory, transceiver and processor, the memory
On be stored with the program code that can serve to indicate that and execute above-mentioned second or its arbitrary optional realization method, transceiver is used for
Specific signal transmitting and receiving is executed under the driving of processor, when the code is performed, the processor may be implemented in method
Terminal device executes each operation.
9th aspect, provides a kind of image processing equipment, including memory, transceiver and processor, the memory
On be stored with the program code that can serve to indicate that and execute above-mentioned third or its arbitrary optional realization method, transceiver is used for
Specific signal transmitting and receiving is executed under the driving of processor, when the code is performed, the processor may be implemented in method
Terminal device executes each operation.
Tenth aspect, provides a kind of computer-readable medium, for storing computer program, which includes
Any of any possible realization method for executing above-mentioned first aspect or first aspect, second aspect or second aspect
The instruction of method in any possible realization method of the possible realization method of kind, the third aspect or the third aspect.
Description of the drawings
Fig. 1 is the schematic diagram using a kind of image processing system of the application.
Fig. 2 is the schematic flow chart according to a kind of method of image procossing of the application.
Fig. 3 is the schematic figure according to the brightness mapping range of the application.
Fig. 4 is the schematic flow chart according to a kind of method of image procossing of the application.
Fig. 5 is the schematic flow chart according to a kind of method of image procossing of the application.
Fig. 6 is the schematic block diagram according to the image processing equipment of the application.
Fig. 7 is the schematic block diagram according to the image processing equipment of the application.
Fig. 8 is the schematic block diagram according to the image processing equipment of the application.
Specific implementation mode
Below in conjunction with attached drawing, the technical solution in the application is described.
Fig. 1 is a kind of schematic diagram of the image processing system of the method and apparatus of processing image of the application.Such as Fig. 1 institutes
Show, which includes server 110, client 120, transmission device 130, image processing equipment 140 and storage
Equipment 150.Storage needs the picture by image procossing in the server 110, and the client 120 to the image procossing for setting
Standby 140 send retrieval request, and the transmission device 130 is for the client 120 and the image processing equipment 140 or the client
Information between 120 and the server 110 is transmitted, which can be interchanger.The storage device 150 is passed through for storing
Cross the picture of image procossing.The image processing equipment 140 is mainly used for handling the brightness of image, and will treated figure
In picture storage to storage device 140, and the retrieval request of the client 120 is received, schemed to treated in storage device
As being retrieved, and the result of retrieval is returned into the client 120.
Optionally, in this application, which can be video content manager.
The application in order to better understand, below with reference to Fig. 2-Fig. 8, with same or analogous with system shown in FIG. 1
The application is illustrated for system.
Fig. 2 is the schematic flow chart according to a kind of method 200 of processing image of the application.As shown in Fig. 2, this method
200 include the following contents.
In 210, target image is transformed into tone saturation degree brightness HSV by image processing equipment from RGB rgb space
Space, wherein the target image includes foreground part and background parts.
It should be understood that computer color display shows that color uses the principle of R, G, B additive color mixture, by launching three kinds
The electron beam of varying strength makes the red, green, blue phosphor material covered on the inside of screen shine and generate color.The table of this color
Show that method is known as rgb color space representation, wherein R indicates red, and G indicates that green, Blue indicate blue.Tone saturation degree is bright
Degree (Hue Saturation Value, HSV) color model is user oriented more intuitive color model, and wherein H is indicated
The tone of image, S indicates the saturation degree of image, and V indicates the brightness of image.
Optionally, which is mainly the target pedestrian image in target image, which is the target figure
The facilities such as the picture material in addition to the foreground part as in, such as ground, building in the target image.
Optionally, which can be all images content in the image in addition to the foreground part, the background
Parts of images content in part or the image in addition to the foreground part.The background parts include that the target image is caught
The information of the illumination brightness under scene is obtained, in some cases, the illumination level and foreground part of the image of part background parts
It is closer, such as underfooting background parts can be selected as with reference to the brightness for adjusting the foreground part.The underfooting background parts can
To choose a part for the target image lower part in proportion, it is somebody's turn to do for example, choosing the 15%~20% of the target image lower part and being used as
The underfooting background parts of target image.
In 220, according to the brightness of the background parts and the brightness of the foreground part, the color of the foreground part is determined
System.
It is alternatively possible to be divided to different colors according to the tone of different color, saturation degree and the rule of brightness characteristic
Colour system, the tone of the different color in identical colour system, saturation degree are consistent with the changing rule of brightness, therefore, can be according to color
System is adjusted the brightness of target object.For example, color is divided into three colour systems, respectively dark colour system, coloured colour system and
Bai Liangse systems.The dark colour system refers to black, grey black, dark blue and hide colors and its similar color such as black, belongs to the dark colour system
One of the main feature of image be that the image is remained unchanged in H values and either varied less (or inexcessive in intensity of illumination)
In the case of, V variation ranges are smaller, and the value of V is also smaller, such as V values are from 0.02 to 0.18.Coloured colour system refers to
The colors such as red, orange, yellow, green, green, blue and purple and its similar color, belonging to one of the main feature of image of coloured colour system is
For the image in the case where H values are remained unchanged or varied less, V value variation ranges are very big, and the value of V can be smaller
Can be larger, such as V values are from 0.2 to 0.8.Bai Liangse systems refer to white or with its similar color, belong to white light tone system
One of the main feature of image be the image in the case where H values are remained unchanged or varied less, the variation range of V component
Smaller (for relatively coloured colour system), but V values are larger, such as V values are from 0.7 to 0.9.
Optionally, according to the brightness of background parts, the brightness correction coefficient of the foreground part is determined;According to the foreground part
Brightness correction coefficient, adjust the brightness of the foreground part;According to the brightness after the adjustment of the foreground part, the foreground portion is determined
The colour system divided.
Optionally, according to the interval range of the brightness of the background parts and background luminance, the background parts institute is determined
The interval range of the background luminance of category;Determine the corresponding brightness correction of the interval range of the background luminance belonging to the background parts
Coefficient is the brightness correction coefficient of the foreground part.
For example, storing the observation for calculating the image sample data in library based on image, the brightness V of background parts is divided into
5 ranges, respectively secretly, dark, normal, brighter and bright, each range in 5 ranges correspond to a brightness correction system
Number, as shown in table 1.
1 background V values of table determine range and corresponding brightness correction coefficient
The brightness correction coefficient is used to adjust the brightness of the foreground part of the target image belonging to the background parts, makes it more
Close to the V values of normal illumination situation.For example, if current background part V values are 0.4, background parts brightness is judged according to table 1
To be dark, corresponding illumination tensor is 1.4.If the brightness of current foreground part is V0, then it is adjusted to 1.4*V0。
Optionally, the average value of the brightness of the background parts of the multiple images in image storage database is calculated, it is described more
A image and the image that the target image is under same capturing scenes;According to the target image where the foreground part
The brightness of the background parts and the brightness of background parts of the multiple images in described image storage database be averaged
Value, determines the brightness correction coefficient of the foreground part.
Specifically, the same capturing scenes are constant for the physical environment residing for the target person, for example, the target person exists
Multiple pictures or the target person are had taken under one crossroad has taken multiple pictures on market doorway.Calculate image storage
The average value of the background luminance of multiple images in database, such as the average value of the background luminance of multiple image is 0.491,
Then the ratio of the background luminance of the target image and the average value 0.491 of background luminance is calculated, which is the target
The brightness correction coefficient of image.
Optionally, the brightness range of the brightness of the adjustment of the foreground part and multiple colour systems determines the foreground
Partial colour system.
Optionally, the brightness after adjustment of the foreground part belongs to the brightness model of the first colour system in multiple colour systems
When enclosing, and being less than first threshold with the absolute difference of the critical value of the brightness range of first colour system, according to the foreground
Part determines the colour system of the foreground part in the tone and saturation degree of the HSV space;Or
The brightness after adjustment of the foreground part belongs to the brightness range of the first colour system in multiple colour systems, and with institute
When stating the absolute difference of the critical value of the brightness range of the first colour system more than or equal to the first threshold, by first color
System is determined as the colour system of the foreground subdivision.
Specifically, judging the affiliated colour system of the foreground part according to the V values of the foreground part after adjustment.In general,
For dark colour system, under normal illumination, V values are not more than 0.18.Under dark or dark illumination, V values are possibly less than
0.10.V values mentioned herein are all the values after normalization.And for non-black system, under normal illumination, V values are usually big
In 0.23.But under dark or dark illumination, V values can also be less than 0.16 or even smaller, be less than 0.10.Below with blue
It is illustrated for the judgement of (coloured colour system) and black (dark colour system) two kinds of colour systems.
Under same capturing scenes, ten photos under the different illumination of the target object are handled.The target pair
As for foreground part, obtaining the HSV value and background luminance of the target person, data as listed in table 2 are obtained, R, G in table 2,
B, H, S, V indicate R, G, B, H, S and V value of foreground part, V respectively1And V2The respectively foreground part corresponding background parts
The brightness of brightness underfooting background parts corresponding with the foreground part.
RGB the and HSV parameters of 2 image of table
Optionally, according to every image background part V1Brightness determine the foreground of every image according to the relationship of table 1
Partial brightness correction coefficient.
Optionally, according to every image background part V2Brightness determine the foreground of every image according to the relationship of table 1
Partial brightness correction coefficient.
Optionally, every image background part V is calculated1And V2Mean value V, determine every according to the relationship of table 1 according to V
The brightness correction coefficient of the foreground part of image.
For example, in this application, with according to every image background part V1Brightness determine every according to the relationship of table 1
The brightness correction coefficient of the foreground part of image is illustrated.According to every image background part V1Brightness, according to the pass of table 1
System, determines the brightness correction coefficient of the foreground part of every image, according to the brightness of the foreground part of every of determination image
Correction factor, the brightness of the foreground part of this every image of pre-adjustment.It is bright after the pre-adjustment of the foreground part of this every image
Degree is as shown in table 3.
Brightness value after 3 image pre-adjustment of table
Serial number | V1 | V2 | V3 | V4 | V5 | V6 | V7 | V8 | V9 | V10 |
V | 0.224 | 0.196 | 0.177 | 0.192 | 0.181 | 0.178 | 0.176 | 0.254 | 0.216 | 0.198 |
Optionally, according to the brightness of the background parts, the brightness to each foreground subdivision in multiple foreground subdivision
It is adjusted;According to the brightness after each foreground subdivision adjustment, the colour system of each foreground subdivision is determined.
Optionally, the brightness after adjustment of the foreground part belongs to the brightness model of the first colour system in multiple colour systems
When enclosing, and being less than first threshold with the absolute difference of the critical value of the brightness range of first colour system, according to the foreground
Part determines the colour system of the foreground part in the tone and saturation degree of the HSV space;Or
The brightness after adjustment of the foreground part belongs to the brightness range of the first colour system in multiple colour systems, and with institute
When stating the absolute difference of the critical value of the brightness range of the first colour system more than or equal to the first threshold, by first color
System is determined as the colour system of the foreground subdivision.
Specifically, the critical value of the brightness of dark colour system is 0.18, and first threshold 0.01, in table 3, image V1,
The difference of V2, V4, V8, V9 and V10 and the critical value of the brightness of dark colour system is more than 0.01, thus image V1, V2, V4, V8, V9 and
V10 belongs to dark colour system, and the difference of picture V3, V5 and V7 and the critical value of the brightness of dark colour system is less than 0.01, needs basis
The foreground part determines the colour system of the foreground part in the tone and saturation degree of the HSV space.
Optionally, the foreground part is divided into multiple foreground subdivisions;According to the brightness of the background parts, to institute
The brightness for stating each foreground subdivision in multiple foreground subdivisions is adjusted;After each foreground subdivision adjustment
Brightness determines the colour system of each foreground subdivision;
The colour system according to the foreground part adjusts the brightness of the foreground part, including:According to it is described it is each before
The colour system of scape subdivision adjusts the brightness of each foreground subdivision.
Optionally, which can pass through the semi-structured data (Extensible of automatic or manual generation
Markup Language, XML) the methods of the foreground part is divided into multiple sub- foreground parts.
Optionally, multiple foreground subdivision includes the first foreground subdivision and the second foreground subdivision, first foreground
The brightness after brightness and the second foreground subdivision adjustment after subdivision adjustment belongs to the brightness range of the first colour system, this first
The absolute difference of the critical value of the brightness range of brightness and first colour system after the adjustment of foreground subdivision is greater than or equal to the
Two threshold values, the absolute difference of brightness and the critical value of the brightness range of first colour system after the second foreground subdivision adjustment
Less than the second threshold;
This determines the colour system of each foreground subdivision according to the brightness after each foreground subdivision adjustment, including:
First colour system is determined as to the colour system of the first foreground subdivision;
The difference of brightness and the brightness after the first foreground subdivision adjustment after the second foreground subdivision adjusts is exhausted
When being greater than or equal to third threshold value to value, according to the second foreground subdivision in the tone and saturation degree of the HSV space, determining should
The colour system of second foreground subdivision;Or, brightness after the second foreground subdivision adjusts is adjusted with the first foreground subdivision
When the absolute difference of brightness afterwards is greater than or equal to third threshold value, by the adjacent model of the brightness of the second foreground subdivision adjustment
Enclose the colour system that corresponding colour system is determined as the second foreground subdivision;Or, brightness after the second foreground subdivision adjusts with
When the absolute difference of the brightness of the second foreground subdivision is less than the third threshold value, which is determined as this before second
The colour system of scape subdivision.
Specifically, brightness after the second foreground subdivision adjusts and the brightness after the first foreground subdivision adjustment
Absolute difference be greater than or equal to third threshold value when, by the second foreground subdivision adjust brightness it is adjacent range it is corresponding
Colour system is determined as the colour system of the second foreground subdivision.First colour system is adjacent with the second colour system, the second foreground subdivision adjustment
The absolute difference of brightness afterwards and the critical value of the brightness range of first colour system is less than the second threshold, and second foreground
The absolute difference of brightness and the brightness after the first foreground subdivision adjustment after subdivision adjustment is greater than or equal to third threshold
When value, determine that the second foreground sub-portion is divided into the second colour system.
When first colour system is respectively at the second colour system and adjacent third colour system, i.e. the first colour system is in the second colour system and
The centre of three colour systems, wherein the brightness of second colour system is less than the brightness of first colour system, and the brightness of first colour system is less than should
The brightness of third colour system, for first colour system there are two critical value, respectively the first critical value and the second critical value, this is first critical
Value is adjacent with the second colour system, and second critical value is adjacent with third colour system.Brightness after the first foreground subdivision adjusts and
Brightness after second foreground subdivision adjustment belongs to the brightness range of the first colour system, bright after the first foreground subdivision adjustment
Degree and the absolute difference of the first critical value of the brightness range of first colour system are greater than or equal to second threshold, second foreground
When brightness and the absolute difference of the critical value of the brightness range of first colour system after subdivision adjustment are less than the second threshold,
First colour system is determined as to the colour system of the first foreground subdivision;Brightness after the second foreground subdivision adjusts with this first
When the absolute difference of brightness after the adjustment of foreground subdivision is greater than or equal to third threshold value, which is adjusted
The adjacent corresponding colour system of range of brightness, i.e. the second colour system is determined as the colour system of the second foreground subdivision;Or, when this second
It, will when the absolute difference of brightness and the brightness of the second foreground subdivision after the adjustment of foreground subdivision is less than the third threshold value
First colour system is determined as the colour system of the second foreground subdivision.
The brightness after brightness and the second foreground subdivision adjustment after the first foreground subdivision adjusts belongs to first
The brightness range of colour system, the second critical value of brightness and the brightness range of first colour system after the first foreground subdivision adjustment
Absolute difference be greater than or equal to second threshold, the second foreground subdivision adjustment after brightness and first colour system brightness
When the absolute difference of the critical value of range is less than the second threshold, the first colour system is determined as to the color of the first foreground subdivision
System;The absolute difference of brightness and the brightness after the first foreground subdivision adjustment after the second foreground subdivision adjusts is big
When third threshold value, by the adjacent corresponding colour system of range of the brightness of the second foreground subdivision adjustment, i.e. third color
System is determined as the colour system of the second foreground subdivision;Or, brightness after the second foreground subdivision adjusts and second foreground
When the absolute difference of the brightness of subdivision is less than the third threshold value, which is determined as the second foreground subdivision
Colour system.
For example, under same capturing scenes, ten photos under the different illumination of same target person are handled.The mesh
Mark personage is foreground part, which is divided into the upper part of the body and the lower part of the body, obtains the upper part of the body of the target person under
Half body HSV value and background value, obtain the data as listed by table 4, R1, G1 in table 2, B1, H1, S1, V1, R2, G2, B2,
H2, S2, V2 are respectively the upper part of the body of foreground part and R, G, B, H, S and V value of the lower part of the body, V1And V2The respectively foreground part
The brightness of the brightness of corresponding background parts underfooting background parts corresponding with the foreground part.
RGB the and HSV parameters of 4 image of table
Optionally, according to every image background part V1Brightness determine the foreground of every image according to the relationship of table 1
The brightness correction coefficient of the partial upper part of the body and the lower part of the body.
Optionally, according to every image background part V2Brightness determine the foreground of every image according to the relationship of table 1
The brightness correction coefficient of the partial upper part of the body and the lower part of the body.
Optionally, every image background part V is calculated1And V2Mean value V, determine every according to the relationship of table 1 according to V
The upper part of the body of the foreground part of image and the brightness correction coefficient of the lower part of the body.
For example, in this application, with according to every image background part V1Brightness determine every according to the relationship of table 1
The upper part of the body of the foreground part of image and the brightness correction coefficient of the lower part of the body are illustrated.According to every image background part V1's
Brightness determines the upper part of the body of the foreground part of every image and the brightness correction coefficient of the lower part of the body according to the relationship of table 1, according to
The upper part of the body of the foreground part of every image of the determination and the brightness correction coefficient of the lower part of the body, before this every image of pre-adjustment
The brightness of the upper part of the body and the lower part of the body of scape part.The upper part of the body of the foreground part of this every image and bright after lower part of the body pre-adjustment
Degree is as shown in table 5.
Brightness value after 5 image pre-adjustment of table
For example, by the brightness value after the upper part of the body of the foreground part of every image and lower part of the body pre-adjustment compared with 0.18,
It may determine that the lower part of the body of 10 images belongs to dark colour system, the upper part of the body of the foreground part of picture 1,2,4,5,8,9 and 10
For coloured colour system, and the upper part of the body brightness of the foreground part of picture 3,6 and 7 is in critical value, needs further to judge.At this point,
It can be judged in conjunction with the corresponding lower part of the body.Because the light environment residing for upper and lower half body is substantially close, and lower part of the body brightness
Value is judged as the brightness value still very little after dark colour system and adjustment, under same illumination, the target image of same colour system
Brightness value can not possibly differ too big, it is possible to judge that picture 3,6 and 7 is not dark colour system, be consequently belonging to coloured colour system.Such as
Fruit combines the lower part of the body of the foreground part still can not determine colour system belonging to the upper part of the body of the foreground part, judges by accident in order to prevent,
The upper part of the body of the foreground part can be done to two classification processing, that is, judge that it is both dark colour system and coloured colour system, then distinguish
It is handled by two kinds of colour systems, avoids erroneous judgement that processing mistake is caused to lead to subsequent query or retrieval failure.
Optionally, the difference of the brightness and the critical value of the brightness range of first colour system after the second foreground subdivision adjustment
It is worth absolute value and is less than the first threshold, the target image belonging to the second foreground subdivision includes multiple first foreground sub-portions
Point, brightness and the brightness belonged to after the adjustment of the second foreground subdivision after multiple first foreground subdivision adjustment belong to first
The brightness range of colour system, the critical value of brightness and the brightness range of first colour system after multiple first foreground subdivision adjustment
Absolute difference be greater than or equal to first threshold, can be according to the brightness of multiple first foreground subdivision and second foreground
The difference of the brightness of subdivision and the relationship of second threshold determine the colour system of the second foreground subdivision.
Specifically, according to after any foreground subdivision adjustment in multiple first foreground subdivision brightness with this
The relationship of the difference and second threshold of the brightness of two foreground subdivisions determines the colour system of the second foreground subdivision, when this second
Foreground subdivision adjustment after brightness with it is bright after any foreground subdivision brightness adjustment in multiple first foreground subdivision
When the absolute difference of degree is greater than or equal to second threshold, the adjacent range of the brightness of the second foreground subdivision adjustment is corresponded to
Colour system be determined as the colour system of the second foreground subdivision;Or, this is more for brightness and this after the second foreground subdivision adjusts
The value absolute value of the luminance difference after any foreground subdivision brightness adjustment in a first foreground subdivision is less than the second threshold
When, which is determined as to the colour system of the second foreground subdivision.
For example, multiple first foreground subdivision is respectively the first foreground subdivision 1, the first foreground subdivision 2 and first
Foreground subdivision 3, the difference of brightness and the brightness of the second foreground subdivision after being adjusted according to the first foreground subdivision 1
With the relationship of second threshold, the colour system of the second foreground subdivision is determined.Brightness after the second foreground subdivision adjusts with
When the absolute difference of brightness after the first foreground subdivision 1 adjustment is greater than or equal to second threshold, by second foreground
The adjacent corresponding colour system of range of the brightness of partial adjustment is determined as the colour system of the second foreground subdivision;Or, when this is before second
Brightness and the value absolute value of the luminance difference after the first foreground subdivision 1 adjustment after the adjustment of scape subdivision are less than the second threshold
When, which is determined as to the colour system of the second foreground subdivision.Before can also be according to the first foreground subdivision 2 or the first
Scape subdivision 3 adjust after brightness and the second foreground subdivision brightness difference and second threshold relationship, determine this
The colour system of two foreground subdivisions.
Specifically, according to after each foreground subdivision adjustment in multiple first foreground subdivision brightness with this
The relationship of the average value and second threshold of the difference of the brightness of two foreground subdivisions determines the colour system of the second foreground subdivision,
Brightness after the second foreground subdivision adjusts and each foreground subdivision brightness tune in multiple first foreground subdivision
When the average value absolute value of the difference of brightness after whole is greater than or equal to second threshold, by the bright of the second foreground subdivision adjustment
Spend the colour system that the corresponding colour system of adjacent range is determined as the second foreground subdivision;Or, when the second foreground subdivision adjusts
Brightness afterwards and the average value of the luminance difference after each foreground subdivision brightness adjustment in multiple first foreground subdivision are small
When the second threshold, which is determined as to the colour system of the second foreground subdivision.
For example, multiple first foreground subdivision is respectively the first foreground subdivision 1, the first foreground subdivision 2 and first
Foreground subdivision 3, by the first foreground subdivision 1, the first foreground subdivision 2 and the first foreground subdivision 3 and the second foreground
The average value of the difference of partial brightness compares the absolute value of the difference and the relationship of second threshold, determines the second foreground subdivision
Colour system.Brightness and the average value absolute value of the difference after the second foreground subdivision adjusts are greater than or equal to second threshold
When, the adjacent corresponding colour system of range of the brightness of the second foreground subdivision adjustment is determined as to the color of the second foreground subdivision
System;Or, when the brightness and the average value of the difference after the second foreground subdivision adjustment are less than the second threshold, by first color
System is determined as the colour system of the second foreground subdivision.
Specifically, the average value of the brightness after being adjusted according to multiple first foreground subdivision and the second foreground sub-portion
The relationship of the difference and second threshold of the brightness divided, determines the colour system of the second foreground subdivision, when the second foreground subdivision
Brightness and the absolute difference of the average brightness after multiple first foreground subdivision brightness adjustment after adjustment are greater than or equal to
When second threshold, the adjacent corresponding colour system of range of the brightness of the second foreground subdivision adjustment is determined as second foreground
Partial colour system;Or, brightness after the second foreground subdivision adjusts with after multiple first foreground subdivision brightness adjustment
Average brightness difference value absolute value be less than the second threshold when, which is determined as the second foreground subdivision
Colour system.
For example, multiple first foreground subdivision is respectively the first foreground subdivision 1, the first foreground subdivision 2 and first
Foreground subdivision 3 calculates before the first foreground subdivision is respectively the first foreground subdivision 1, the first foreground subdivision 2 and first
The average brightness of scape subdivision 3, according to the difference and second threshold of the average brightness and the brightness of the second foreground subdivision
Relationship determines the colour system of the second foreground subdivision.
It should be understood that can also be according to the first foreground of the brightness minimum after the adjustment in multiple first foreground subdivision
The average value of the brightness after arbitrary several first foreground subdivisions adjustment in partial brightness, multiple first foreground subdivision
With the relationship of the difference and the second threshold of the brightness of the second foreground subdivision, the color of the second foreground subdivision is determined
System.
It should be understood that the foreground subdivision can be divided into multiple sub- foreground parts, foreground part is divided in this application
It is the first foreground subdivision and the second foreground subdivision only as an example, and non-limiting.
Optionally, when the brightness of the foreground subdivision after the adjustment is near the critical value of the brightness of a colour system,
The brightness of the foreground subdivision after the adjustment can be determined according to the foreground subdivision in the tone and saturation degree of the HSV space
The colour system of foreground subdivision near the critical value of brightness in a colour system.
Optionally, the colour system of the foreground part is determined according to the tone H of the foreground part and saturation degree S.
It should be understood that in actual scene, the H and S of different colours have the syntagmatic of specific rule.Therefore, Ke Yigen
The colour system of the foreground part is determined according to the tone H and saturation degree S of the foreground part.It is carried out by taking red as an example in this application detailed
Description.
For example, listing in table 5 in coloured colour system, red objects image is empty in rgb space and HSV under different illumination
Between parameter.The tone H and saturation degree S of red image have specific rule, i.e., V values value is different, but H is in [0.9,1]
Section, and correspondingly S is also in [0.9,1] section.In table 6, the foreground part of 6 target images is satisfied by the red colour system
The syntagmatic of H and S, it is thus determined that the foreground part of 6 target images in table 6 belongs to coloured colour system.
RGB the and HSV parameters of 6 red objects image of table
Optionally, the average value of the brightness of the background parts of the multiple images in image storage database is calculated, it is multiple
Image and the image that the image is under same capturing scenes;By the background parts of the target image where the foreground part
Brightness and the ratio of the average value of the brightness of the background parts of the multiple images in image storage database are determined as the foreground
Partial brightness correction coefficient.
Optionally, by the tone of the foreground part, saturation degree and brightness and the brightness input parameter mould of the background image
Type, and the label value for obtaining parameter model output determines the foreground part according to the label value of the output of the parameter model
Colour system.
It should be understood that the parameter model is used to indicate under the capturing scenes of the target image, the label value of multiple colour systems, with
The correspondence of the tone of foreground part, saturation degree and brightness and the brightness of background parts.
It should be understood that the foreground part brightness can be according to after the brightness correction coefficient adjustment the foreground part it is bright
The original brightness of degree or the foreground part not adjusted.
Optionally, according to multiple in the label value of each colour system setting and image storage database in multiple colour system
Tone, saturation degree and the brightness of foreground part in image and the brightness of the background parts in each image carry out algorithm instruction
Practice, determines the parameter model, multiple image and the image that the target image is under same capturing scenes.
In 230, according to the colour system of the foreground part, the brightness of the foreground part is adjusted.
Optionally, it is bright in the corresponding brightness set of colour system of the foreground part by the brightness adjustment of the foreground part
Degree.
Optionally, according to the colour system of the foreground part, the corresponding brightness set of the colour system of the foreground part is determined;According to this
Brightness set adjusts the brightness of the foreground part.
Optionally, which is a kind of colour system in dark colour system, coloured colour system and white light tone system, which corresponds to
Brightness set in element be a;The corresponding brightness collection of the coloured colour system is combined into the brightness model more than or equal to b and less than or equal to c
It encloses;The white light tone is that the element in corresponding brightness set is d,
Wherein, a, the b, the c and the d meet relational expression:
D≤1 0≤a < b≤c <
A, b, c and the d are constant.
It should be understood that according to the colour system of the foreground part, the brightness of the foreground part is adjusted it is not necessary to the foreground portion
The brightness divided is adjusted, but is mapped according to the brightness of the corresponding colour system of foreground part colour system corresponding with the foreground part
Set, it is determined whether adjust the brightness of the foreground part.If the brightness of the foreground part is in the corresponding color of the foreground part
In the brightness mapping set section of system, then do not have to be adjusted the brightness of the foreground part.
It should be understood that the brightness set may include an element, such as the corresponding brightness collection of dark colour system is combined into { a }, only
Including element a, white light tone is that corresponding brightness collection is combined into { d }, only includes element d, which can also include multiple members
Element, such as the corresponding brightness collection of coloured colour system are combined into { b≤x≤c }, which can be discrete, i.e. the element of the set is
More than or equal to b and less than or equal to the integer between c, which can also be continuous, i.e., the element of the set is more than or equal to b
And less than or equal to the real number between c.
Specifically, as Fig. 3, Fig. 3 show the correspondence area of the brightness set of dark colour system, coloured colour system and white light tone system
Between.For being judged as the foreground target image of dark colour system or a part for foreground target image, by its V value VHIt is mapped as one
Fixed smaller V values a, i.e. f (VH)=a;For be judged as coloured colour system foreground target image or foreground target image one
Part, if its V value VYLess than or greater than scheduled V value sets [b, c], it is mapped as closest therewith in the section [b, c]
Value, if V values VYBetween V value sets [b, c], then VYIt does not adjust.If for example, VY<=b, then f (VY)=b;If VY∈
[b, c], then f (VY)=VY;If VY>=c, then f (VY)=c;For being judged as the foreground target image or foreground mesh of white light tone system
A part for logo image, by its V value VWIt is mapped as a fixed larger V values d, i.e. f (VW)=d.
It should be understood that the selection of the parameter has a significant impact experimental result.In practice, the selection of parameter will consider
Following some factors:First, parameter has corresponded to three kinds of different colour systems respectively, and therefore, the selection of three kinds of parameters should meet three kinds
The corresponding V value sets of colour system.For example, the parameter a of first parameter, that is, front, it corresponds to dark colour system, therefore the value of a
Ying Ying meets:0=<a<=0.18 ± δ, wherein δ>=0,0.18+ δ<b*, b is second parameter, and * formulas are meant that parameter a
Cannot be identical with b, the two should there is some difference, this is because a and b has a physical significance, a corresponds to dark colour system, and b pairs
Answer coloured colour system.Second, the quality or quality that parameter is chosen, the judgement based on experience.Therefore, a certain number of experiments are carried out
It is necessary.The selection of third, parameter should combine with entire application system.For image retrieval or inquiry, in order to
Recall precision and the required space of characteristic storage are improved, it is common practice to do quantization to feature.Quantify being done to feature
In the case of, the selection of parameter should be accounted in conjunction with quantization step so that the characteristic value of identical colour system is after quantization as far as possible
In same quantized interval.
In the application, for coloured colour system, a brightness value section is devised for the colour system, when the brightness of the foreground part
When value is in predefined section, photo-irradiation treatment need not be done, reduces the calculating generated due to processing and storage cost;But
Larger tolerance set is provided, avoiding processing procedure from introducing excessive noise leads to serious distortion.
In this application, the brightness value of the colour system adjustment image based on image is total to one after the colour system by judging image
Same smaller set so that the color distortion of the different pictures of same target caused by illumination (such as pedestrian) is as small as possible,
The difference of target color values caused by significantly reduce different illumination, and then be conducive to the retrieval or identification of object.
In 240, according to the brightness after the adjustment of the foreground part, which is transformed into RGB skies from the HSV space
Between.According to treated the image, the target image is searched in storage device.
Optionally, each image in the storage device is handled all in accordance with the method in the application, if inquiry
Image in one storage device can be inquired directly in the database;If inquired in the non-storage device
Image, since each image in the storage device is all handled according to the method in the application, first to this
Image in the non-storage device is handled with the method in the application, and the non-storage is then inquired in the storage device and is set
Image in standby.Because every image in the storage device and the image of needs inquiry all according to the method in the application into
It has gone processing, the brightness of the target image is adjusted according to different colour systems, reduces the colour-difference of target object caused by illumination
It is different, improve the accuracy rate of searched targets object.
Therefore, in this application, image processing equipment is satisfied by the way that target image is transformed into tone from RGB rgb space
With degree brightness HSV space, according to the brightness of the background parts of the target image and the brightness of the foreground part of the target image,
Determine the colour system of the foreground part;According to the colour system of the foreground part, the brightness of the foreground part is adjusted;The foreground portion will be adjusted
The target image of brightness is divided to be transformed into the rgb space from the HSV space.By according to the brightness adjustments of the background parts before this
The brightness of scape part reduces the luminance difference of target object caused by different illumination, according to the foreground part after the adjustment
Brightness determines that the colour system of the foreground part improves the accuracy rate for the colour system for determining the foreground part, according to the color of the foreground part
System adjusts the brightness of the foreground part, and the target image for adjusting the foreground part brightness is transformed into this from the HSV space
Rgb space, reduces the difference of the target object color caused by the brightness of image difference under different illumination, and then is conducive to
The retrieval or identification of target object.
Fig. 4 is the schematic flow chart according to a kind of method 300 of processing image of another embodiment of the application.Such as Fig. 4
Shown, this method 300 includes the following contents.
In 310, target image is transformed into tone saturation degree brightness HSV space from RGB rgb space.
In 320, when the brightness of the target image belongs to the brightness range of the first colour system in multiple colour systems, and with this
When the absolute difference of the critical value of the brightness range of one colour system is less than first threshold, according to the target image in the HSV space
Tone and saturation degree, determine the colour system of the foreground part.
In 330, according to the colour system of the target image, the brightness of the target image is adjusted.
In 340, according to the brightness after the adjustment of the target image, which is transformed into this from the HSV space
Rgb space.
Therefore, in this application, image processing equipment is satisfied by the way that target image is transformed into tone from RGB rgb space
With degree brightness HSV space, and when the brightness of the target image belongs to the brightness range of the first colour system in multiple colour systems, and with
When the absolute difference of the critical value of the brightness range of first colour system is less than first threshold, according to the target image in the HSV
The tone and saturation degree in space, determine the colour system of the foreground part, improve the colour system that the target image is determined according to only brightness
Accuracy, adjust the brightness of the foreground part according to the colour system of the foreground part, and will adjust the foreground part brightness should
Target image is transformed into the rgb space from the HSV space, reduces the mesh caused by the brightness of image difference under different illumination
The difference of object color is marked, and then is conducive to the retrieval or identification of target object.
It should be understood that the above method 200 can be combined the colour system for judging the foreground part with this method 300, i.e., as above-mentioned side
Method 200 be adjusted after the brightness of foreground part when being in the critical value of first colour system, can be according to the foreground part
H and the syntagmatic of S determine the colour system of the foreground part, in order to avoid repeating, details are not described herein again.
Fig. 5 is the schematic flow chart according to a kind of method 400 of processing image of another embodiment of the application.Such as Fig. 5
Shown, this method 400 includes the following contents.
In 410, target image is transformed into tone saturation degree brightness HSV space, the target figure from RGB rgb space
As including first part and second part, the brightness of the first part and the brightness of the second part belong to the first colour system
The absolute difference of brightness range, the critical value of the brightness range of the brightness of the first part and first colour system be more than or
Equal to first threshold, the brightness of the second part and the absolute difference of the critical value of the brightness range of first colour system are small
In the first threshold.
In 420, the first colour system is determined as to the colour system of the first part;When the second part brightness with it is described
When the absolute difference of the brightness of first part is greater than or equal to second threshold, according to the second part in the HSV space
Tone and saturation degree, determine the colour system of the second part, or the brightness when the second part and the first part
When the absolute difference of brightness is greater than or equal to second threshold, in the tone of the HSV space and satisfied according to the second part
And degree, determine the colour system of the second part;Or when the second part the brightness and first part brightness difference
When absolute value is greater than or equal to second threshold, the corresponding colour system of the adjacent range of the brightness of the second part is determined as described
The colour system of second part;Or, when the absolute difference of the brightness of the brightness and second part of the second part is less than institute
When stating second threshold, first colour system is determined as to the colour system of the second part.
In 430, according to the colour system of the colour system of the first part and the second part, the first part and second are adjusted
The brightness divided.
In 440, according to the brightness after the adjustment of the target image, which is transformed into this from the HSV space
Rgb space.
Therefore, in this application, image processing equipment is satisfied by the way that target image is transformed into tone from RGB rgb space
With degree brightness HSV space, the first part and second are determined according to the first part of the target image and second part respectively
The colour system divided, adjusts the brightness of the first part and second part so that the face of the different pictures of target object caused by illumination
Aberration is different as small as possible, significantly reduces the difference of color of object caused by different illumination, and then is conducive to target object
Retrieval or identification.
Fig. 6 is the schematic block diagram according to the image processing equipment 500 of the application.As shown in fig. 6, described image processing is set
Standby 500 include:
Conversion module 510, for target image to be transformed into tone saturation degree brightness HSV space from RGB rgb space,
Wherein, which includes foreground part and background parts.
First processing module 520 is used for according to the brightness of the background parts and the brightness of the foreground part, before determining this
The colour system of scape part.
Module 530 is adjusted, for the colour system according to the foreground part, adjusts the brightness of the foreground part.
The conversion module 510 is additionally operable to:
According to the brightness after the adjustment of the foreground part, which is transformed into the rgb space from the HSV space.
Optionally, which is specifically used for:According to the brightness of the background parts, the foreground part is determined
Brightness correction coefficient;According to the brightness correction coefficient of the foreground part, the brightness of the foreground part is adjusted;According to the foreground portion
Brightness after the adjustment divided, determines the colour system of the foreground part.
Optionally, which is specifically used for:According to the section of the brightness of the background parts and background luminance
Range determines the interval range of the background luminance belonging to the background parts;Determine the area of the background luminance belonging to the background parts
Between the corresponding brightness correction coefficient of range be the foreground part brightness correction coefficient.
Optionally, which is specifically used for:Calculate the background of the multiple images in image storage database
The average value of partial brightness, multiple image and the image that the image is under same capturing scenes;According to the foreground part institute
The target image the background parts brightness and image storage database in multiple images background parts
The ratio of the average value of brightness is determined as the brightness correction coefficient of the foreground part.
Optionally, which is specifically used for:Compare the brightness of the adjustment of the foreground part and multiple colour systems
Brightness range, determine the colour system of the foreground part.
Optionally, which is specifically used for:The brightness after adjustment of the foreground part belongs to multiple colors
The brightness range of the first colour system in system, and it is less than first with the absolute difference of the critical value of the brightness range of first colour system
When threshold value, according to the foreground part in the tone and saturation degree of the HSV space, the colour system of the foreground part is determined.
Optionally, which is specifically used for:The foreground part is divided into multiple foreground subdivisions;Root
According to the brightness of the background parts, the brightness of each foreground subdivision in multiple foreground subdivision is adjusted;It is every according to this
Brightness after a foreground subdivision adjustment, determines the colour system of each foreground subdivision;The adjustment module 430 is specifically used for:Root
According to the colour system of each foreground subdivision, the brightness of each foreground subdivision is adjusted.
Optionally, multiple foreground subdivision includes the first foreground subdivision and the second foreground subdivision, first foreground
The brightness after brightness and the second foreground subdivision adjustment after subdivision adjustment belongs to the brightness range of the first colour system, this first
The absolute difference of the critical value of the brightness range of brightness and first colour system after the adjustment of foreground subdivision is greater than or equal to the
One threshold value, the absolute difference of brightness and the critical value of the brightness range of first colour system after the second foreground subdivision adjustment
Less than the first threshold;
The first processing module 520 is used to the first colour system being determined as the colour system of the first foreground subdivision;When this second
The absolute difference of the brightness after the adjustment of brightness and the first foreground subdivision after the adjustment of foreground subdivision is greater than or equal to the
When two threshold values, according to the second foreground subdivision in the tone and saturation degree of the HSV space, the second foreground subdivision is determined
Colour system;Or, the difference of the brightness and the brightness after the first foreground subdivision adjustment after the second foreground subdivision adjusts is exhausted
When being greater than or equal to second threshold to value, the adjacent corresponding colour system of range of the brightness of the second foreground subdivision adjustment is determined
For the colour system of the second foreground subdivision;Or, brightness after the second foreground subdivision adjusts and the second foreground subdivision
Brightness absolute difference be less than the second threshold when, which is determined as to the colour system of the second foreground subdivision.
Optionally, which is additionally operable to the tone of the foreground part, saturation degree and brightness and the back of the body
The brightness input parameter model of scape image, and obtain the label value of parameter model output, wherein the parameter model is used to indicate
Under the capturing scenes of the target image, the label value of multiple colour systems, the tone with foreground part, saturation degree and brightness and the back of the body
The correspondence of the brightness of scape part;According to the label value of the output of the parameter model, the colour system of the foreground part is determined.
Optionally, which further includes Second processing module 540, as shown in Figure 7.This by the foreground part
Tone, saturation degree and brightness and the background parts brightness input parameter model before, the Second processing module 540, use
According to the foreground in the multiple images in the label value of each colour system setting and image storage database in multiple colour system
Partial tone, saturation degree and brightness and the brightness of the background parts in each image carry out algorithm training, determine the ginseng
Exponential model, multiple image and the image that the target image is under same capturing scenes.
Optionally, which is used for the colour system according to the foreground part, determines the colour system of the foreground part
Corresponding brightness set;According to the brightness set, the brightness of the foreground part is adjusted.
Optionally, the adjustment module 530 be used for according to the colour system of the foreground subdivision to the brightness of the foreground subdivision into
Row adjustment, the colour system are a kind of colour system in dark colour system, coloured colour system and white light tone system, the corresponding brightness collection of the dark colour system
Element in conjunction is a;The corresponding brightness collection of the coloured colour system is combined into the brightness range more than or equal to b and less than or equal to c;This is white bright
Element in the corresponding brightness set of colour system is d,
Wherein, a, the b, the c and the d meet relational expression:
D≤1 0≤a < b≤c <
A, b, c and the d are constant.
Optionally, which can be also used for executing the above method 300 for 500.When the image processing equipment is used for
When executing the above method 300, which includes:
Conversion module 510, for target image to be transformed into tone saturation degree brightness HSV space from RGB rgb space.
First processing module 520, the brightness for belonging to the first colour system in multiple colour systems when the brightness of the target image
Range, and with the absolute difference of the critical value of the brightness range of first colour system be less than first threshold when, according to the target figure
As the tone and saturation degree in the HSV space, the colour system of the foreground part is determined.
Module 530 is adjusted, for the colour system according to the target image, adjusts the brightness of the target image.
The conversion module 510 is additionally operable to:
According to the brightness after the adjustment of the target image, which is transformed into the rgb space from the HSV space.
Optionally, which can be also used for executing the above method 300 for 500.When the image processing equipment is used for
When executing the above method 300, which includes:
Conversion module 510, for target image to be transformed into tone saturation degree brightness HSV space from RGB rgb space,
The target image includes first part and second part, and the brightness of the first part and the brightness of the second part belong to
The brightness range of one colour system, the brightness of the first part and the difference of the critical value of the brightness range of first colour system are absolute
Value is greater than or equal to first threshold, the difference of the brightness of the second part and the critical value of the brightness range of first colour system
Absolute value is less than the first threshold, and the first colour system is determined as to the colour system of the first part.
First processing module 520, the difference for brightness and the brightness of the first part when the second part are exhausted
To value be greater than or equal to second threshold when, according to the second part the HSV space tone and saturation degree, determine described in
The colour system of second part, or when the absolute difference of brightness and the brightness of the first part of the second part is more than or waits
When second threshold, the corresponding colour system of the adjacent range of the brightness of the second part is determined as to the color of the second part
System;Or, when the absolute difference of the brightness of the second part and the brightness of the second part is less than the second threshold,
First colour system is determined as to the colour system of the second part.
Adjust module 530, for the colour system according to the colour system and the second part of the first part, adjust separately this first
The brightness of part and second part.
The conversion module 510 is additionally operable to, according to the brightness after the adjustment of the target image, by the target image from the HSV
Spatial transformation is to the rgb space.
Fig. 8 shows the schematic block diagram of image processing equipment 600 provided by the present application, the image processing equipment 600 packet
It includes:
Memory 610, for storing program, which includes code;
Transceiver 620, for being communicated with other equipment;
Processor 630, for executing the program code in memory 610.
Optionally, when the code is performed, which may be implemented image procossing in method 200 or method 300
Equipment executes each operation, and transceiver 620 under the driving of processor 630 for executing specific signal transmitting and receiving.For sake of simplicity,
Details are not described herein.
It should be understood that in the embodiment of the present application, which can be central processing unit (Central
ProcessingUnit, CPU), which can also be other general processors, digital signal processor, special integrated
Circuit, ready-made programmable gate array either other programmable logic device, discrete gate or transistor logic, discrete hardware
Component etc..General processor can be microprocessor or the processor can also be any conventional processor etc..
The memory 610 may include read-only memory and random access memory, and to processor 630 provide instruction and
Data.The a part of of memory 610 can also include nonvolatile RAM.For example, memory 610 can also be deposited
Store up the information of device type.
Transceiver 620 can send and receive function for realizing signal.
Those of ordinary skill in the art may realize that lists described in conjunction with the examples disclosed in the embodiments of the present disclosure
Member and algorithm steps can be realized with the combination of electronic hardware or computer software and electronic hardware.These functions are actually
It is implemented in hardware or software, depends on the specific application and design constraint of technical solution.Professional technician
Each specific application can be used different methods to achieve the described function, but this realization is it is not considered that exceed
Scope of the present application.
It is apparent to those skilled in the art that for convenience and simplicity of description, the system of foregoing description,
The specific work process of device and unit, can refer to corresponding processes in the foregoing method embodiment, and details are not described herein.
In several embodiments provided herein, it should be understood that disclosed systems, devices and methods, it can be with
It realizes by another way.For example, the apparatus embodiments described above are merely exemplary, for example, the unit
It divides, only a kind of division of logic function, formula that in actual implementation, there may be another division manner, such as multiple units or component
It can be combined or can be integrated into another system, or some features can be ignored or not executed.Another point, it is shown or
The mutual coupling, direct-coupling or communication connection discussed can be the indirect coupling by some interfaces, device or unit
It closes or communicates to connect, can be electrical, machinery or other forms.
The unit illustrated as separating component may or may not be physically separated, aobvious as unit
The component shown may or may not be physical unit, you can be located at a place, or may be distributed over multiple
In network element.Some or all of unit therein can be selected according to the actual needs to realize the mesh of this embodiment scheme
's.
In addition, each functional unit in each embodiment of the application can be integrated in a processing unit, it can also
It is that each unit physically exists alone, it can also be during two or more units be integrated in one unit.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer read/write memory medium.Based on this understanding, the technical solution of the application is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be expressed in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be
People's computer, server or network equipment etc.) execute each embodiment the method for the application all or part of step.
And storage medium above-mentioned includes:USB flash disk, mobile hard disk, read-only memory (Read-Only Memory, ROM), arbitrary access are deposited
The various media that can store program code such as reservoir (Random Access Memory, RAM), magnetic disc or CD.
The above, the only specific implementation mode of the application, but the protection domain of the application is not limited thereto, it is any
Those familiar with the art can easily think of the change or the replacement in the technical scope that the application discloses, and should all contain
It covers within the protection domain of the application.Therefore, the protection domain of the application should be based on the protection scope of the described claims.
Claims (30)
1. a kind of method of processing image, which is characterized in that including:
Target image is transformed into tone saturation degree brightness HSV space from RGB rgb space, wherein the target image packet
Include foreground part and background parts;
According to the brightness of the background parts and the brightness of the foreground part, the colour system of the foreground part is determined;
According to the colour system of the foreground part, the brightness of the foreground part is adjusted;
According to the brightness after the adjustment of the foreground part, the target image is transformed into the RGB skies from the HSV space
Between.
2. according to the method described in claim 1, it is characterized in that, the brightness according to the background parts and it is described before
The brightness of scape part determines the colour system of the foreground part, including:
According to the brightness of the background parts, the brightness correction coefficient of the foreground part is determined;
According to the brightness correction coefficient of the foreground part, the brightness of the foreground part is adjusted;
According to the brightness after the adjustment of the foreground part, the colour system of the foreground part is determined.
3. according to the method described in claim 2, it is characterized in that, the brightness according to the background parts, determine described in
The brightness correction coefficient of foreground part, including:
According to the range of the brightness of the background parts and background luminance, the model of the background luminance belonging to the background parts is determined
It encloses;
Determine that the corresponding brightness correction coefficient of the range of the background luminance belonging to the background parts is the bright of the foreground part
Spend correction factor.
4. according to the method described in claim 2, it is characterized in that, the brightness according to the background parts, determine described in
The brightness correction coefficient of foreground part, including:
Calculate image storage database in multiple images background parts brightness average value, described multiple images with it is described
Target image is the image under same capturing scenes;
Number is stored according to the brightness of the background parts of the target image where the foreground part and described image
According to the average value of the brightness of the background parts of the multiple images in library, the brightness correction coefficient of the foreground part is determined.
5. method according to any one of claim 2 to 4, which is characterized in that the tune according to the foreground part
Brightness after whole determines the colour system of the foreground part, including:
Compare the brightness of the adjustment of the foreground part and the brightness set of multiple colour systems, determines the colour system of the foreground part.
6. according to the method described in claim 5, it is characterized in that, the brightness of the adjustment of the foreground part with it is more
The brightness range of a colour system determines the colour system of the foreground part, including:
The brightness after adjustment of the foreground part belongs to the brightness range of the first colour system in multiple colour systems, and with described
When the absolute difference of the critical value of the brightness range of one colour system is less than first threshold, according to the foreground part in the HSV
The tone and saturation degree in space, determine the colour system of the foreground part;Or
The brightness after adjustment of the foreground part belongs to the brightness range of the first colour system in multiple colour systems, and with described
It is when the absolute difference of the critical value of the brightness range of one colour system is greater than or equal to the first threshold, first colour system is true
It is set to the colour system of the foreground subdivision.
7. the method according to any one of claims 1 to 5, it is characterized in that, described according to the bright of the background parts
The brightness of degree and the foreground part, determines that the colour system of the foreground part includes:
The foreground part is divided into multiple foreground subdivisions;
According to the brightness of the background parts, the brightness of each foreground subdivision in the multiple foreground subdivision is adjusted
It is whole;
According to the brightness after each foreground subdivision adjustment, the colour system of each foreground subdivision is determined;
The colour system according to the foreground part adjusts the brightness of the foreground part, including:
According to the colour system of each foreground subdivision, the brightness of each foreground subdivision is adjusted.
8. the method according to the description of claim 7 is characterized in that the multiple foreground subdivision includes the first foreground subdivision
It is bright after the brightness and the second foreground subdivision adjustment after the first foreground subdivision adjustment with the second foreground subdivision
Degree belongs to the brightness range of the first colour system, the brightness model of brightness and first colour system after the first foreground subdivision adjustment
The absolute difference for the critical value enclosed is greater than or equal to second threshold, the brightness after the second foreground subdivision adjustment with it is described
The absolute difference of the critical value of the brightness range of first colour system is less than the second threshold;
The brightness according to after each foreground subdivision adjustment determines the colour system of each foreground subdivision, including:
First colour system is determined as to the colour system of the first foreground subdivision;
The difference of brightness and the brightness after the first foreground subdivision adjustment after the second foreground subdivision adjusts is exhausted
To value be greater than or equal to third threshold value when, according to the second foreground subdivision the HSV space tone and saturation degree, really
The colour system of the fixed second foreground subdivision;Or, brightness after the second foreground subdivision adjusts and first foreground
When the absolute difference of brightness after subdivision adjustment is greater than or equal to the third threshold value, by the second foreground subdivision tune
The corresponding colour system of the adjacent range of whole brightness is determined as the colour system of the second foreground subdivision;Or, working as second foreground
It, will when the absolute difference of brightness and the brightness of the second foreground subdivision after subdivision adjustment is less than the third threshold value
First colour system is determined as the colour system of the second foreground subdivision.
9. method according to claim 1 to 4, which is characterized in that according to the brightness of the background parts with
And the brightness of the foreground part, determine the colour system of the foreground part, including:
By the tone of the foreground part, saturation degree and brightness and the brightness input parameter model of the background image, and obtain
The label value of the parameter model output is taken,
Wherein, the parameter model is used to indicate under the capturing scenes of the target image, the label value of multiple colour systems, and preceding
The correspondence of the tone of scape part, saturation degree and brightness and the brightness of background parts;
According to the label value of the output of the parameter model, the colour system of the foreground part is determined.
10. according to the method described in claim 9, it is characterized in that, described by the tone of the foreground part, saturation degree and bright
Before degree and the brightness input parameter model of the background parts, the method further includes:
According in the multiple images in the label value of each colour system setting and described image storage database in the multiple colour system
Foreground part tone, saturation degree and brightness and the background parts in each image brightness carry out algorithm training,
Determine the parameter model, described multiple images and the image that the target image is under same capturing scenes.
11. method according to any one of claim 1 to 10, which is characterized in that described according to the foreground part
Colour system adjusts the brightness of the foreground part, including:
It is the brightness in the corresponding brightness set of colour system of the foreground part by the brightness adjustment of the foreground part.
12. according to the method for claim 11, which is characterized in that the brightness adjustment by the foreground part is described
The corresponding brightness set of colour system of foreground part, including:
According to the colour system of the foreground part, the corresponding brightness set of the colour system of the foreground part is determined;
According to the brightness set, the brightness of the foreground part is adjusted.
13. according to the method for claim 12, which is characterized in that the colour system is dark colour system, coloured colour system and Bai Liang
A kind of colour system in colour system, the element in the corresponding brightness set of the dark colour system is a;The corresponding brightness of the coloured colour system
Collection is combined into the brightness range more than or equal to b and less than or equal to c;The white light tone is that the element in corresponding brightness set is d,
Wherein, a, the b, the c and the d meet relational expression:
D≤1 0≤a < b≤c <
Described a, b, c and d are constant.
14. a kind of method of processing image, which is characterized in that including:
Target image is transformed into tone saturation degree brightness HSV space from RGB rgb space;
When the brightness of the target image belongs to the brightness range of the first colour system in multiple colour systems, and with first colour system
The absolute difference of the critical value of brightness range be less than first threshold when, according to the target image the HSV space color
Reconciliation saturation degree, determines the colour system of the target image;Or, when the brightness of the target image belongs to first in multiple colour systems
The brightness range of colour system, and it is more than or equal to described first with the absolute difference of the critical value of the brightness range of first colour system
When threshold value, first colour system is determined as to the colour system of the target image;
According to the colour system of the target image, the brightness of the target image is adjusted;After the adjustment of the target image
Described image is transformed into the rgb space by brightness from the HSV space.
15. a kind of method of processing image, which is characterized in that including:
Target image is transformed into tone saturation degree brightness HSV space from RGB rgb space, the target image includes first
Part and second part;
The brightness of the first part and the brightness of the second part belong to the brightness range of the first colour system, the first part
The absolute difference of critical value of brightness range of brightness and first colour system be greater than or equal to first threshold, described second
Partial brightness and the absolute difference of the critical value of the brightness range of first colour system are less than the first threshold, by first
Colour system is determined as the colour system of the first part;
When the absolute value of the difference of the brightness of the brightness and first part of the second part is greater than or equal to second threshold
When, according to the second part in the tone and saturation degree of the HSV space, determine the colour system of the second part;Or work as institute
When stating the absolute difference of the brightness of second part and the brightness of the first part and being greater than or equal to second threshold, by described the
The adjacent corresponding colour system of range of the brightness of two parts is determined as the colour system of the second part;Or, when the second part
When the absolute difference of brightness and the brightness of the second part is less than the second threshold, first colour system is determined as institute
State the colour system of second part;
According to the colour system of the first part and the second part, the brightness of the first part and second part is adjusted;
According to the brightness after the adjustment of target image, the target image is transformed into the rgb space from the HSV space.
16. a kind of equipment of processing image, which is characterized in that including:
Conversion module, for target image to be transformed into tone saturation degree brightness HSV space from RGB rgb space, wherein institute
It includes foreground part and background parts to state target image;
First processing module, for according to the brightness of the background parts and the brightness of the foreground part, determine it is described before
The colour system of scape part;
Module is adjusted, for the colour system according to the foreground part, adjusts the brightness of the foreground part;
The conversion module is used for:
According to the brightness after the adjustment of the foreground part, the target image is transformed into the RGB skies from the HSV space
Between.
17. equipment according to claim 16, which is characterized in that the first processing module is specifically used for:
According to the brightness of the background parts, the brightness correction coefficient of the foreground part is determined;
According to the brightness correction coefficient of the foreground part, the brightness of the foreground part is adjusted;
According to the brightness after the adjustment of the foreground part, the colour system of the foreground part is determined.
18. equipment according to claim 17, which is characterized in that the first processing module is specifically used for:
According to the interval range of the brightness of the background parts and background luminance, the background luminance belonging to the background parts is determined
Interval range;
Determine that the corresponding brightness correction coefficient of the interval range of the background luminance belonging to the background parts is the foreground part
Brightness correction coefficient.
19. equipment according to claim 17, which is characterized in that the first processing module is specifically used for:
Calculate image storage database in multiple images background parts brightness average value, described multiple images with it is described
Target image is the image under same capturing scenes;
Number is stored according to the brightness of the background parts of the target image where the foreground part and described image
It is determined as the brightness correction system of the foreground part according to the ratio of the average value of the brightness of the background parts of the multiple images in library
Number.
20. the equipment according to any one of claim 17 to 19, which is characterized in that the first processing module is also used
In:
The brightness range for comparing the brightness and multiple colour systems of the adjustment of the foreground part, determines the colour system of the foreground part.
21. equipment according to claim 20, which is characterized in that the first processing module is specifically used for:
The brightness after adjustment of the foreground part belongs to the brightness range of the first colour system in multiple colour systems, and with described
When the absolute difference of the critical value of the brightness range of one colour system is less than first threshold, according to the foreground part in the HSV
The tone and saturation degree in space, determine the colour system of the foreground part;Or
The brightness after adjustment of the foreground part belongs to the brightness range of the first colour system in multiple colour systems, and with described
It is when the absolute difference of the critical value of the brightness range of one colour system is greater than or equal to the first threshold, first colour system is true
It is set to the colour system of the foreground subdivision.
22. the equipment according to any one of claim 16 to 20, which is characterized in that the first processing module is specifically used
In:
The foreground part is divided into multiple foreground subdivisions;
According to the brightness of the background parts, the brightness of each foreground subdivision in the multiple foreground subdivision is adjusted
It is whole;
According to the brightness after each foreground subdivision adjustment, the colour system of each foreground subdivision is determined;
The adjustment module is specifically used for:
According to the colour system of each foreground subdivision, the brightness of each foreground subdivision is adjusted.
23. equipment according to claim 22, which is characterized in that the multiple foreground subdivision includes the first foreground sub-portion
Point and the second foreground subdivision, after the brightness and the second foreground subdivision adjustment after the first foreground subdivision adjustment
Brightness belongs to the brightness range of the first colour system, the brightness of brightness and first colour system after the first foreground subdivision adjustment
The absolute difference of the critical value of range is greater than or equal to second threshold, the brightness after the second foreground subdivision adjustment and institute
The absolute difference for stating the critical value of the brightness range of the first colour system is less than the second threshold;
The first processing module is specifically used for:
First colour system is determined as to the colour system of the first foreground subdivision;
The difference of brightness and the brightness after the first foreground subdivision adjustment after the second foreground subdivision adjusts is exhausted
To value be greater than or equal to third threshold value when, according to the second foreground subdivision the HSV space tone and saturation degree, really
The colour system of the fixed second foreground subdivision;Or, brightness after the second foreground subdivision adjusts and first foreground
When the absolute difference of brightness after subdivision adjustment is greater than or equal to the third threshold value, by the second foreground subdivision tune
The corresponding colour system of the adjacent range of whole brightness is determined as the colour system of the second foreground subdivision;Or, working as second foreground
It, will when the absolute difference of brightness and the brightness of the second foreground subdivision after subdivision adjustment is less than the third threshold value
First colour system is determined as the colour system of the second foreground subdivision.
24. the equipment according to any one of claim 16 to 20, which is characterized in that the first processing module is specifically used
In:
By the tone of the foreground part, saturation degree and brightness and the brightness input parameter model of the background image, and obtain
The label value of the parameter model output is taken,
Wherein, the parameter model is used to indicate under the capturing scenes of the target image, the label value of multiple colour systems, and preceding
The correspondence of the tone of scape part, saturation degree and brightness and the brightness of background parts;
According to the label value of the output of the parameter model, the colour system of the foreground part is determined.
25. equipment according to claim 24, which is characterized in that it is described by the tone of the foreground part, saturation degree and
Before the brightness input parameter model of brightness and the background parts, the equipment further includes:
Second processing module, for storing data according to the label value of each colour system setting and described image in the multiple colour system
Tone, saturation degree and the brightness of the foreground part in multiple images in library and the background parts in each image it is bright
Degree carries out algorithm training, determines that the parameter model, described multiple images are under same capturing scenes with the target image
Image.
26. the equipment according to any one of claim 16 to 25, which is characterized in that described according to the foreground part
Colour system adjusts the brightness of the foreground part, including:
It is the brightness in the corresponding brightness set of colour system of the foreground part by the brightness adjustment of the foreground part.
27. equipment according to claim 26, which is characterized in that the brightness adjustment by the foreground part is described
The corresponding brightness set of colour system of foreground part, including:
According to the colour system of the foreground part, the corresponding brightness set of the colour system of the foreground part is determined;
According to the brightness set, the brightness of the foreground part is adjusted.
28. equipment according to claim 27, which is characterized in that the colour system is dark colour system, coloured colour system and Bai Liang
A kind of colour system in colour system, the element in the corresponding brightness set of the dark colour system is a;The corresponding brightness of the coloured colour system
Collection is combined into the brightness range more than or equal to b and less than or equal to c;The white light tone is that the element in corresponding brightness set is d,
Wherein, a, the b, the c and the d meet relational expression:
D≤1 0≤a < b≤c <
Described a, b, c and d are constant.
29. a kind of equipment of processing image, which is characterized in that including:
Conversion module, for target image to be transformed into tone saturation degree brightness HSV space from RGB rgb space;
Processing module, the brightness range for belonging to the first colour system in multiple colour systems when the brightness of the target image, and with
When the absolute difference of the critical value of the brightness range of first colour system is less than first threshold, according to the target image in institute
The tone and saturation degree for stating HSV space, determine the colour system of the foreground part;Or, the brightness when the target image belongs to more
The brightness range of the first colour system in a colour system, and it is big with the absolute difference of the critical value of the brightness range of first colour system
When equal to the first threshold, first colour system is determined as to the colour system of the target image;
Module is adjusted, for the colour system according to the target image, adjusts the brightness of the target image;
The conversion module is used for:
According to the brightness after the adjustment of the target image, described image is transformed into the rgb space from the HSV space.
30. a kind of equipment of processing image, which is characterized in that including:
Conversion module, for target image to be transformed into tone saturation degree brightness HSV space, the mesh from RGB rgb space
Logo image includes first part and second part;
Processing module, the brightness model for belonging to the first colour system when the brightness of the first part and the brightness of the second part
It encloses, the absolute difference of the critical value of the brightness range of the brightness of the first part and first colour system is greater than or equal to the
The absolute difference of one threshold value, the brightness of the second part and the critical value of the brightness range of first colour system is less than described
First colour system is determined as the colour system of the first part by first threshold;
The processing module is used for:When the brightness of the second part and the absolute value of the difference of the brightness of the first part are big
When second threshold, according to the second part in the tone and saturation degree of the HSV space, described second is determined
The colour system divided;Or when the absolute difference of the brightness of the brightness and first part of the second part is greater than or equal to second
When threshold value, the corresponding colour system of the adjacent range of the brightness of the second part is determined as to the colour system of the second part;Or, working as
When the absolute difference of the brightness of the brightness of the second part and the second part is less than the second threshold, by described the
One colour system is determined as the colour system of the second part;
Module is adjusted, for the colour system according to the first part and the second part, adjusts the first part and second
Partial brightness;
The conversion module is used for according to the brightness after the adjustment of target image, and the target image is turned from the HSV space
Change to the rgb space.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710082941.8A CN108446705B (en) | 2017-02-16 | 2017-02-16 | Method and apparatus for image processing |
PCT/CN2018/071783 WO2018149253A1 (en) | 2017-02-16 | 2018-01-08 | Image processing method and device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710082941.8A CN108446705B (en) | 2017-02-16 | 2017-02-16 | Method and apparatus for image processing |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108446705A true CN108446705A (en) | 2018-08-24 |
CN108446705B CN108446705B (en) | 2021-03-23 |
Family
ID=63170502
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710082941.8A Active CN108446705B (en) | 2017-02-16 | 2017-02-16 | Method and apparatus for image processing |
Country Status (2)
Country | Link |
---|---|
CN (1) | CN108446705B (en) |
WO (1) | WO2018149253A1 (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109308687A (en) * | 2018-09-06 | 2019-02-05 | 百度在线网络技术(北京)有限公司 | Method and apparatus for adjusting brightness of image |
CN109509461A (en) * | 2018-12-19 | 2019-03-22 | 惠科股份有限公司 | The brightness adjusting method and device of display panel |
CN109871455A (en) * | 2019-01-28 | 2019-06-11 | 厦门理工学院 | Be carbonized bamboo chip color separation method and system |
CN110726725A (en) * | 2019-10-23 | 2020-01-24 | 许昌许继软件技术有限公司 | Transmission line hardware corrosion detection method and device |
CN110865856A (en) * | 2018-08-27 | 2020-03-06 | 华为技术有限公司 | Interface element color display method and device |
CN111882493A (en) * | 2020-06-22 | 2020-11-03 | 浙江大华技术股份有限公司 | Image color adjustment method, device, equipment and computer readable storage medium |
CN111966933A (en) * | 2020-07-10 | 2020-11-20 | 口碑(上海)信息技术有限公司 | Color data recommendation method and device |
CN113487700A (en) * | 2021-06-22 | 2021-10-08 | 维沃移动通信有限公司 | Image processing method and device and electronic equipment |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109853267B (en) * | 2018-12-29 | 2021-08-20 | 杭州智数创联科技有限公司 | Method for quickly manufacturing digital printing color card |
CN113223016A (en) * | 2021-05-13 | 2021-08-06 | 上海西虹桥导航技术有限公司 | Image segmentation method and device for plant seedlings, electronic equipment and medium |
CN114828337B (en) * | 2022-07-01 | 2022-09-27 | 杭州罗莱迪思科技股份有限公司 | Control method and application of outdoor LED dyeing lamp |
Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4007487A (en) * | 1975-09-25 | 1977-02-08 | The Association Of Motion Picture And Television Producers Inc. | Electronic composite photography with color control |
US5194008A (en) * | 1992-03-26 | 1993-03-16 | Spartanics, Ltd. | Subliminal image modulation projection and detection system and method |
CN1445984A (en) * | 2003-04-14 | 2003-10-01 | 浙江大学 | Method for fast picking up picture with any image as background in digital image process |
US20050157204A1 (en) * | 2004-01-16 | 2005-07-21 | Sony Computer Entertainment Inc. | Method and apparatus for optimizing capture device settings through depth information |
CN101166226A (en) * | 2006-10-17 | 2008-04-23 | 三星电子株式会社 | Image compensation in regions of low image contrast |
CN101304488A (en) * | 2008-06-20 | 2008-11-12 | 北京中星微电子有限公司 | Method and device for capturing image |
CN101998063A (en) * | 2009-08-20 | 2011-03-30 | 财团法人工业技术研究院 | Foreground image separation method |
CN102013006A (en) * | 2009-09-07 | 2011-04-13 | 泉州市铁通电子设备有限公司 | Method for automatically detecting and identifying face on the basis of backlight environment |
CN102075780A (en) * | 2011-02-25 | 2011-05-25 | 福建华映显示科技有限公司 | Stereoscopic image generating device and method |
CN102270427A (en) * | 2010-06-04 | 2011-12-07 | 英华达(上海)电子有限公司 | Method and apparatus for enhancing reading effect of electronic book and electronic terminal capable of reading electronic book |
CN102881260A (en) * | 2009-09-16 | 2013-01-16 | 致伸科技股份有限公司 | Image processing method and device |
CN103123725A (en) * | 2011-11-18 | 2013-05-29 | 鸿富锦精密工业(深圳)有限公司 | Image analyzing device and analyzing method |
CN103208126A (en) * | 2013-04-17 | 2013-07-17 | 同济大学 | Method for monitoring moving object in natural environment |
US20130216132A1 (en) * | 2012-02-21 | 2013-08-22 | Seiko Epson Corporation | Image processing apparatus, image processing method, and program |
CN104899881A (en) * | 2015-05-28 | 2015-09-09 | 湖南大学 | Shadow detection method for moving vehicle in video image |
CN105354554A (en) * | 2015-11-12 | 2016-02-24 | 西安电子科技大学 | Color and singular value feature-based face in-vivo detection method |
CN105488793A (en) * | 2015-11-26 | 2016-04-13 | 西安诺瓦电子科技有限公司 | Image display method and image processing method |
Family Cites Families (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20070036371A1 (en) * | 2003-09-08 | 2007-02-15 | Koninklijke Philips Electronics N.V. | Method and apparatus for indexing and searching graphic elements |
US20100322513A1 (en) * | 2009-06-19 | 2010-12-23 | Sharp Laboratories Of America, Inc. | Skin and sky color detection and enhancement system |
CN102096911B (en) * | 2011-01-31 | 2012-08-01 | 格科微电子(上海)有限公司 | Luminance raising method |
CN106327437B (en) * | 2016-08-10 | 2019-04-05 | 大连海事大学 | A kind of color documents images bearing calibration and system |
-
2017
- 2017-02-16 CN CN201710082941.8A patent/CN108446705B/en active Active
-
2018
- 2018-01-08 WO PCT/CN2018/071783 patent/WO2018149253A1/en active Application Filing
Patent Citations (17)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4007487A (en) * | 1975-09-25 | 1977-02-08 | The Association Of Motion Picture And Television Producers Inc. | Electronic composite photography with color control |
US5194008A (en) * | 1992-03-26 | 1993-03-16 | Spartanics, Ltd. | Subliminal image modulation projection and detection system and method |
CN1445984A (en) * | 2003-04-14 | 2003-10-01 | 浙江大学 | Method for fast picking up picture with any image as background in digital image process |
US20050157204A1 (en) * | 2004-01-16 | 2005-07-21 | Sony Computer Entertainment Inc. | Method and apparatus for optimizing capture device settings through depth information |
CN101166226A (en) * | 2006-10-17 | 2008-04-23 | 三星电子株式会社 | Image compensation in regions of low image contrast |
CN101304488A (en) * | 2008-06-20 | 2008-11-12 | 北京中星微电子有限公司 | Method and device for capturing image |
CN101998063A (en) * | 2009-08-20 | 2011-03-30 | 财团法人工业技术研究院 | Foreground image separation method |
CN102013006A (en) * | 2009-09-07 | 2011-04-13 | 泉州市铁通电子设备有限公司 | Method for automatically detecting and identifying face on the basis of backlight environment |
CN102881260A (en) * | 2009-09-16 | 2013-01-16 | 致伸科技股份有限公司 | Image processing method and device |
CN102270427A (en) * | 2010-06-04 | 2011-12-07 | 英华达(上海)电子有限公司 | Method and apparatus for enhancing reading effect of electronic book and electronic terminal capable of reading electronic book |
CN102075780A (en) * | 2011-02-25 | 2011-05-25 | 福建华映显示科技有限公司 | Stereoscopic image generating device and method |
CN103123725A (en) * | 2011-11-18 | 2013-05-29 | 鸿富锦精密工业(深圳)有限公司 | Image analyzing device and analyzing method |
US20130216132A1 (en) * | 2012-02-21 | 2013-08-22 | Seiko Epson Corporation | Image processing apparatus, image processing method, and program |
CN103208126A (en) * | 2013-04-17 | 2013-07-17 | 同济大学 | Method for monitoring moving object in natural environment |
CN104899881A (en) * | 2015-05-28 | 2015-09-09 | 湖南大学 | Shadow detection method for moving vehicle in video image |
CN105354554A (en) * | 2015-11-12 | 2016-02-24 | 西安电子科技大学 | Color and singular value feature-based face in-vivo detection method |
CN105488793A (en) * | 2015-11-26 | 2016-04-13 | 西安诺瓦电子科技有限公司 | Image display method and image processing method |
Non-Patent Citations (2)
Title |
---|
ZHU ZHENGYU等: "Saliency detection combining foreground and background features based on manifold ranking", 《JOURNAL OF COMPUTER APPLICATIONS》 * |
邢帅: "多源遥感影像配准与融合技术的研究", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110865856A (en) * | 2018-08-27 | 2020-03-06 | 华为技术有限公司 | Interface element color display method and device |
US11423590B2 (en) | 2018-08-27 | 2022-08-23 | Huawei Technologies Co., Ltd. | Interface element color display method and apparatus |
US11663754B2 (en) | 2018-08-27 | 2023-05-30 | Huawei Technologies Co., Ltd. | Interface element color display method and apparatus |
CN109308687A (en) * | 2018-09-06 | 2019-02-05 | 百度在线网络技术(北京)有限公司 | Method and apparatus for adjusting brightness of image |
CN109509461A (en) * | 2018-12-19 | 2019-03-22 | 惠科股份有限公司 | The brightness adjusting method and device of display panel |
CN109509461B (en) * | 2018-12-19 | 2020-11-06 | 惠科股份有限公司 | Brightness adjusting method and device of display panel |
CN109871455A (en) * | 2019-01-28 | 2019-06-11 | 厦门理工学院 | Be carbonized bamboo chip color separation method and system |
CN109871455B (en) * | 2019-01-28 | 2020-11-10 | 厦门理工学院 | Color separation method and system for carbonized bamboo chips |
CN110726725A (en) * | 2019-10-23 | 2020-01-24 | 许昌许继软件技术有限公司 | Transmission line hardware corrosion detection method and device |
CN111882493A (en) * | 2020-06-22 | 2020-11-03 | 浙江大华技术股份有限公司 | Image color adjustment method, device, equipment and computer readable storage medium |
CN111966933A (en) * | 2020-07-10 | 2020-11-20 | 口碑(上海)信息技术有限公司 | Color data recommendation method and device |
CN113487700A (en) * | 2021-06-22 | 2021-10-08 | 维沃移动通信有限公司 | Image processing method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
WO2018149253A1 (en) | 2018-08-23 |
CN108446705B (en) | 2021-03-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108446705A (en) | The method and apparatus of image procossing | |
CN105915816B (en) | Method and apparatus for determining the brightness of given scenario | |
US9852499B2 (en) | Automatic selection of optimum algorithms for high dynamic range image processing based on scene classification | |
JP5611457B2 (en) | Gradation and color gamut mapping method and apparatus | |
US9460521B2 (en) | Digital image analysis | |
US20070041636A1 (en) | Apparatus and method for image contrast enhancement using RGB value | |
ITVA20060079A1 (en) | PIXEL CHROMATIC CLASSIFICATION METHOD AND ADAPTIVE IMPROVEMENT METHOD OF A COLOR IMAGE | |
CN112752023B (en) | Image adjusting method and device, electronic equipment and storage medium | |
KR20070090224A (en) | Method of electronic color image saturation processing | |
US7885458B1 (en) | Illuminant estimation using gamut mapping and scene classification | |
WO2019210707A1 (en) | Image sharpness evaluation method, device and electronic device | |
CN111630854A (en) | System and method for image signal processor tuning | |
CN107862654A (en) | Image processing method, device, computer-readable recording medium and electronic equipment | |
WO2022120799A9 (en) | Image processing method and apparatus, electronic device, and storage medium | |
CN112016621B (en) | Training method of classification model, color classification method and electronic equipment | |
CN106791744A (en) | Projector's picture HDR processing system and its processing method | |
Bianco et al. | Computational color constancy | |
CN111615827A (en) | System and method for image signal processor tuning | |
CN101019131B (en) | System and method for effectively performing an image data transformation procedure | |
Zini et al. | Back to the future: a night photography rendering ISP without deep learning | |
CN115810021A (en) | Tone mapping method, equipment and system | |
CN115602136A (en) | Brightness adjusting method and device, electronic equipment and storage medium | |
CN105631812A (en) | Control method and control device for performing color enhancement on displayed image | |
CN110351542A (en) | A kind of color correcting method and device for video frame | |
US20120218280A1 (en) | Method, apparatus and system for modifying quality of an image |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |