CN104517272B - A kind of image enchancing method and device - Google Patents
A kind of image enchancing method and device Download PDFInfo
- Publication number
- CN104517272B CN104517272B CN201410852937.1A CN201410852937A CN104517272B CN 104517272 B CN104517272 B CN 104517272B CN 201410852937 A CN201410852937 A CN 201410852937A CN 104517272 B CN104517272 B CN 104517272B
- Authority
- CN
- China
- Prior art keywords
- msub
- mrow
- region
- image
- pixel value
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The present invention is applied to image processing field there is provided a kind of image enchancing method and device, and methods described includes：To currently processed image according to brightness zoning；It is that corresponding tone adjustment function is specified in each region according to the regional luminance；Pixel value is calculated in each region with the corresponding tone adjustment function respectively.The embodiment of the present invention according to brightness zoning, and for each region by specifying corresponding tone adjustment function to calculate the pixel value of each pixel after image enhaucament currently processed image, so as to realize efficiently quick image enhancement effects.
Description
Technical field
The invention belongs to image processing field, more particularly to a kind of image enchancing method and device.
Background technology
Because reasons such as equipment, illumination, video compress, causing the image frame of display often has contrast low, unclear
Clear the problems such as, the visual effect of picture is had a strong impact on, and then the bandwagon effect of video image product can be influenceed.In order to improve human eye
To the visual effect of this kind of image, improve the definition of image, be easy to follow-up other processing, it is necessary to such " fuzzy " or
The image of low contrast carries out enhancing processing.
Traditional picture superposition algorithm has two kinds, and gamma is adjusted and histogram equalization.Gamma regulation is using seat
The method of graticule regulation, the color range to original image is rearranged, and obtains the light and shade distribution for more meeting human eye custom.But gal
The regulation that horse is adjusted to image has of overall importance, it is impossible to which the part to image is adjusted, therefore uses after the method processing
Image often deviates from the custom of normal eye.Histogram equalization be the grey level histogram of original image from compare concentration certain
Individual gray scale interval becomes being uniformly distributed in the range of whole color ranges, i.e., carry out Nonlinear extension to image, redistribute image
Pixel value, makes the pixel quantity in the range of certain color range roughly the same.Histogram equalization is indiscriminate to the data of processing, often
Ambient noise can often be amplified, the contrast of signal, the natural contrast of warp image is reduced.Therefore, above-mentioned image enchancing method
Clearly satisfied image enhancement effects can not be obtained.
The content of the invention
The embodiment of the present invention provides a kind of image enchancing method, it is intended to improve image definition.
The embodiment of the present invention is achieved in that a kind of image enchancing method, and methods described includes：
To currently processed image according to brightness zoning；
It is that corresponding tone adjustment function is specified in each region according to the regional luminance；
Pixel value is calculated in each region with the corresponding tone adjustment function respectively.
The embodiment of the present invention also provides a kind of image intensifier device, it is characterised in that described device includes：
Luminance area division unit, for currently processed image according to brightness zoning；
Tone adjustment function designating unit, is that each region specifies corresponding tone to adjust according to the regional luminance
Save function；
Area pixel value computing unit, for being calculated respectively with the corresponding tone adjustment function in each region
Pixel value.
The embodiment of the present invention according to brightness zoning, and for each region to currently processed image by specifying corresponding
Tone adjustment function calculates the pixel value of each pixel after image enhaucament, so as to realize efficiently quick image enhancement effects.
Brief description of the drawings
Fig. 1 is the implementation process figure of image enchancing method provided in an embodiment of the present invention；
Fig. 2 be first embodiment of the invention provide each region respectively with corresponding tone adjustment function calculating pixel
The implementation process figure of value；
Fig. 3 is the structure chart for the image intensifier device that second embodiment of the invention is provided；
Fig. 4 is the structure chart for the image intensifier device that third embodiment of the invention is provided；
Fig. 5 is the structure chart for the image intensifier device that fourth embodiment of the invention is provided；
Fig. 6 is the structure chart for the three area pixel value computing units that fourth embodiment of the invention is provided.
Embodiment
In order to make the purpose , technical scheme and advantage of the present invention be clearer, it is right below in conjunction with drawings and Examples
The present invention is further elaborated.It should be appreciated that the specific embodiments described herein are merely illustrative of the present invention, and
It is not used in the restriction present invention.
The embodiment of the present invention according to brightness zoning, and for each region to currently processed image by specifying corresponding
Tone adjustment function calculates the pixel value of each pixel after image enhaucament, so as to realize efficiently quick image enhancement effects.
Fig. 1 shows the implementation process of image enchancing method provided in an embodiment of the present invention, and details are as follows：
In step S101, to currently processed image according to brightness zoning.
In embodiments of the present invention, image is strengthened, it is necessary to image based on luminance area for the ease of follow-up
Luminance area division is carried out, so as to carry out brightness regulation using different tone adjustment functions in different luminance areas.
As one embodiment of the present of invention, when carrying out luminance area division to image, N number of brightness region is divided an image into
Domain, can carry out region division, so as to be adjusted in N number of luminance area using N number of tone adjustment function based on brightness histogram.
In embodiments of the present invention, N values have been defined previously as a positive integer.
In one embodiment of the invention, when carrying out region division based on brightness histogram, then region division problem
Histogrammic GTG partition problem is translated into, luminance area division can be carried out to image using the method for cluster, so as to
Region division easily is carried out to image.
In the specific embodiment of the present invention, image is carried out to be implemented as when N number of luminance area is divided：
N number of luminance area is given, the gray average in each region is μn(n=1 ..., N), variance is σn(n=1 ..., N), picture
Global luminance mean value is μ0, variance is σ0, then optimization problem definition is the optimization problem of formula (2).
max{Sb/Sw}
s.t.
Wherein ωnIt is that the pixel in n-th of region accounts for the ratio of total pixel, SbCharacterize the weighting dispersion in each region, SwTable
Levy population variance degree.
In one embodiment of the invention, luminance area can also be divided using other clustering algorithms.
As one embodiment of the present of invention, when N values are smaller, formula (1) can be solved using full search, because N values compare
It is small, solved with full search also without very big amount of calculation, it is possible to obtain more accurate result.
As an alternative embodiment of the invention, when N values are larger, then commonly used using genetic algorithm, ant group algorithm etc.
Heuritic approach, because N values are than larger, when being solved with full search, it would be desirable to very big amount of calculation, so using inspiration
Formula algorithm carries out region division.
In a preferred embodiment of the invention, the domain of definition of full search is strictly limited in histogrammic trough
On, so as to reduce amount of calculation, so as to reduce amount of calculation.
As the preferred embodiment of the present invention, when image is carried out into luminance area division, only divide an image into
Clear zone, middle area and the region of dark space three, so that more convenient calculate.
In the preferred embodiment of one of the present invention, when only dividing an image into clear zone, middle area and dark space three
Region is implemented as:
Histogram H is calculated first, then histogram is filtered, filtered histogram wave trough position is tried to achieve, and is recycled
Formula (1) calculates optimal dividing, and wherein domain of definition is limited in the histogram H wave trough position tried to achieve.
As one embodiment of the present of invention, when being filtered to histogram H, [1/3,1/3,1/3] is used to histogram H
Carry out smothing filtering.Region division is carried out to image in this way, fast and accurately region division result can be obtained, be easy to
It is follow-up to calculate, and clear and definite dark space, middle area and three, clear zone region are divided an image into, it can be obtained in follow-up calculating
Efficiently quick enhancing effect.
In step s 102, it is that corresponding tone adjustment function is specified in each region.
In embodiments of the present invention, in order to which the tone to image is adjusted, suppress clear zone, lifting dark space, retain middle
The pixel value of image is adjusted, it is necessary to which different tone adjustment functions are respectively adopted in different luminance areas for area, so that
Need that different tone adjustment functions are respectively adopted according to different luminance areas.
As one embodiment of the present of invention, in order to which the tone to image is adjusted, suppresses clear zone, lifting dark space, protect
Stay middle area and the pixel value of image is adjusted, it is necessary to which different tone adjustment functions are respectively adopted in different luminance areas
Section, uses different γ values, so that in different brightness using the tone adjustment function described in (2) formula in different luminance areas
Region obtains different tone adjustment functions and tone is adjusted.
F (x)=x(1+x)×rX=(0,1) (2)
Wherein, x is to normalize to the pixel value between 0~1.γ is index system, and the different corresponding curves of γ values have
Different enhancing effect, so that tone scale map is different under different γ values.Low γ values are tended to lift dark space, high γ values
Tend to suppress clear zone.
In embodiments of the present invention, it is adjusted for the region of different brightness in picture using different γ values, so that
The tone of image can be adjusted as needed.Such as, for clear zone, then clear zone is suppressed as needed, for dark
Area, then as needed, can suitably be lifted to dark space.By the way that different luminance areas are adjusted using different γ values,
So as to obtain more preferably tone regulating effect.
As one embodiment of the present of invention, tone adjustment function can also adjust equation using gamma, can obtain and (2)
The similar enhancing effect of formula.
In one embodiment of the invention, when currently processed image is divided into N number of luminance area, come for formula (2)
Say, can be that initial value is N number of number that the difference between 0~1 is 1/N by γ values, so that N number of tone adjustment function is can obtain,
N number of luminance area is corresponded to respectively, present image is divided into after N number of luminance area, so as to be adopted in different luminance areas
Image calculating is carried out with different tone adjustment functions.
In embodiments of the present invention, N values are a pre-defined positive integer.
In a preferred embodiment of the invention, when picture is divided into clear zone, middle area and the region of dark space three
After, it can be 0.3,0.6 and 0.9 by γ difference values, the tone adjustment function of dark space, middle area and clear zone is corresponded to respectively, by
Tend to lift dark space in low value, and high r values are tended to suppress clear zone, so dark space, suppression will be lifted to image using this γ value
Clear zone processed and reservation middle area.
As one embodiment of the present of invention, tone adjustment function can also adjust equation using gamma.
In step s 103, pixel value is calculated with corresponding tone adjustment function respectively in each region.
In embodiments of the present invention, corresponding tone is being specified to adjust to currently processed image zoning and for each region
Save after function, so as to calculate pixel value with corresponding tone adjustment function respectively in each region.
In one embodiment of the invention, it is divided into when by currently processed image after N number of luminance area, according to (1)
Formula is correspondingly made available N number of tone adjustment function by changing γ values, so as in different luminance areas respectively with different
Tone adjustment function calculates enhanced pixel value.
In a preferred embodiment of the invention, when N values are defined previously as into 3, then currently processed image is drawn
It is divided into behind dark space, middle area and three, clear zone region, and point these three regions are respectively by the specified corresponding γ values of formula (1)
0.3rd, after 0.6 and 0.9 three tone adjustment functions, so as to respectively in these three luminance areas according to these three tones
Adjustment function calculates enhanced pixel value.
In another embodiment of the present invention, it would however also be possible to employ other tone adjustment functions in addition to (1) formula.
As one embodiment of the present of invention, after currently processed image is divided into N number of luminance area, recycle (1)
Formula is calculated according to different luminance areas using different γ values after the tone adjustment function for obtaining different luminance areas, gives I × J
A point P in picture spacei,j∈ (0,1), 0≤i≤I, 0≤j≤J and its neighborhoodSo as to be calculated using formula (3)
Enhanced pixel value.
WhereinThat is region division (An-1,An) in point Pi,jRatio in neighborhood.
In one embodiment of the invention, P during region divisioni,jFieldSelection is circular, so that algorithm
Can be optimal, it can obtain preferable picture enhancing effect.
As the preferred embodiment of the present invention, P during region divisioni,jNeighborhoodSelection is square, so that sharp
W can be quickly calculated with integration nomographyn。
In a preferred embodiment of the invention, the luminance area of currently processed image is divided into clear zone, in
Between after area and the area of dark space three, (1) formula of recycling obtains different brightness according to different luminance areas using different γ values calculating
After the tone adjustment function in region, and P during region divisioni,jNeighborhoodSelection is square, so as to utilize integrogram
Algorithm can quickly calculate Wn, recycle formula (3) to calculate enhanced pixel value.
In embodiments of the present invention, step S101 and step S102 can exchange order, in step S101 and step S102
The value to N is redefined for a positive integer before.
As the preferred embodiment of the present invention, N values are 3.
Fig. 2 shows being calculated respectively with corresponding tone adjustment function in each region for first embodiment of the invention offer
The implementation process of pixel value, details are as follows：
In step s 201, dark space integrogram and clear zone integrogram are calculated respectively.
In embodiments of the present invention, after dark space, middle area and three, clear zone region is divided an image into, and by area
Domain divides (An-1,An) in point Pi,jNeighborhood elects Square Neighborhood as,So as to quickly calculate W using integration nomographyn, to calculate
The pixel value of enhanced each pixel.Firstly the need of dark space integrogram and clear zone integrogram is calculated respectively, consequently facilitating subsequently
It is quick to calculate WnAnd calculate the pixel value of final enhanced each pixel.
In a preferred embodiment of the invention, when divide an image into dark space, middle area and three, clear zone region with
Afterwards, and by region division (An-1,An) in point Pi,jNeighborhood elects square field as, so as to quickly be counted using integration nomography
Calculate Wn, to calculate the pixel value of enhanced each pixel.Firstly the need of dark space integrogram and clear zone integrogram is calculated respectively, divide
Li Yong not formula (4) and formula (5) calculating dark space integrogram S and clear zone integrogram T.
In step S202, pixel value is calculated with corresponding tone adjustment function respectively in dark space, middle area and clear zone.
In embodiments of the present invention, after calculating dark space integrogram and clear zone integrogram, then calculate enhanced each
The pixel value of pixel, so as to obtain the final pixel value for carrying out each pixel after enhancing regulation.
In a preferred embodiment of the invention, after dark space integrogram and clear zone integrogram is calculated, then
Enhanced pixel value is calculated according to formula (3), wherein, WnIt can be calculated and obtained according to dark space integrogram S and clear zone integrogram T.
As the preferred embodiment of the present invention, after dark space integrogram and clear zone integrogram is calculated, then
Enhanced pixel value is calculated according to formula (3), so that obtain final result of calculation, i.e., the pixel of enhanced each pixel
Value.Wherein, WnIt can be calculated and obtained by formula (6) according to dark space integrogram S and clear zone integrogram T.
Wc=1-Wa-Wb
One of ordinary skill in the art will appreciate that：The step of realizing above method embodiment or part steps can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in computer read/write memory medium, and the program exists
During execution, the step of execution includes above method embodiment, and foregoing storage medium includes：ROM, RAM, magnetic disc or CD
Etc. it is various can be with the medium of store program codes.
The embodiment of the present invention can apply to image recognition, picture control, image and the image procossing scene such as show, preferably
Ground, the embodiment of the present invention is applied to picture control scene.
Fig. 3 shows the structure for the image intensifier device that second embodiment of the invention is provided, and Fig. 4 shows the present invention the 3rd
The structure for the image intensifier device that embodiment is provided, Fig. 5 shows the image intensifier device that fourth embodiment of the invention is provided
Structure, is described with reference to Fig. 3, Fig. 4 and Fig. 5, for convenience of description, illustrate only the portion related to the embodiment of the present invention
Point.
Luminance area division unit 100 is to currently processed image according to brightness zoning.
In second embodiment of the invention, for the ease of strengthening subsequently based on luminance area image, first
Luminance area division unit 100 needs to carry out luminance area division to image, so as to use different in different luminance areas
Tone adjustment function carry out brightness regulation.
As the third embodiment of the present invention, when N luminance areas division unit 110 carries out luminance area division to image,
N number of luminance area is divided an image into, region division can be carried out based on brightness histogram, so that in N number of luminance area using N number of
Tone adjustment function is adjusted.
In embodiments of the present invention, N values have been defined previously as a positive integer.
In one embodiment of this invention, luminance area division unit 100 is carrying out region division based on brightness histogram
When, then region division problem translates into histogrammic GTG partition problem, image can be carried out using the method for cluster bright
Region division is spent, so as to easily carry out region division to image.
In the third embodiment of the present invention, N luminance areas division unit 110 carries out N number of luminance area division to image
When be implemented as：N number of luminance area is given, the gray average in each region is μn(n=1 ..., N), variance is σn(n=
1 ..., N), the global luminance mean value of picture is μ0, variance is σ0, then optimization problem definition is the optimization problem of formula (1).
max{Sb/Sw}
s.t.
Wherein ωnIt is that the pixel in n-th of region accounts for the ratio of total pixel, SbCharacterize the weighting dispersion in each region, SwTable
Levy population variance degree.
In one embodiment of the invention, luminance area can also be divided using other clustering algorithms.
As one embodiment of the present of invention, when N values are smaller, formula (1) can be solved using full search, because N values compare
It is small, solved with full search also without very big amount of calculation, it is possible to obtain more accurate result.
As an alternative embodiment of the invention, when N values are larger, then commonly used using genetic algorithm, ant group algorithm etc.
Heuritic approach, because N values are than larger, when being solved with full search, it would be desirable to very big amount of calculation, so using inspiration
Formula algorithm carries out region division.
In a preferred embodiment of the invention, the domain of definition of full search is strictly limited in histogrammic trough
On, so as to reduce amount of calculation, so as to reduce amount of calculation.
As the fourth embodiment of the present invention, when image is carried out luminance area division by three luminance area division units 111,
Clear zone, middle area and the region of dark space three are only divided an image into, so that more convenient calculate.
In the preferred embodiment of one of the present invention, when three luminance area division units 111 are only divided an image into
Clear zone, middle area and dark space is trizonal is implemented as:
Histogram H is calculated first, then histogram is filtered, filtered histogram wave trough position is tried to achieve, and is recycled
Formula (1) calculates optimal dividing, and wherein domain of definition is limited in the histogram H wave trough position tried to achieve.
As one embodiment of the present of invention, when being filtered to histogram H, [1/3,1/3,1/3] is used to histogram H
Carry out smothing filtering.Region division is carried out to image in this way, fast and accurately region division result can be obtained, be easy to
It is follow-up to calculate, and clear and definite dark space, middle area and three, clear zone region are divided an image into, it can be obtained in follow-up calculating
Efficiently quick enhancing effect.
Tone adjustment function designating unit 200 is that corresponding tone adjustment function is specified in each region.
In the first embodiment of the invention, in order to which the tone to image is adjusted, suppress clear zone, lifting dark space, retain
The pixel value of image is adjusted, it is necessary to which different tone adjustment functions are respectively adopted in different luminance areas for middle area,
So as to need that different tone adjustment functions are respectively adopted according to different luminance areas, tone adjustment function designating unit 200 is
Different luminance areas specify corresponding tone adjustment function.
As one embodiment of the present of invention, in order to which the tone to image is adjusted, suppresses clear zone, lifting dark space, protect
Stay middle area and the pixel value of image is adjusted, it is necessary to which different tone adjustment functions are respectively adopted in different luminance areas
Section, tone adjustment function designating unit 200 is using the tone adjustment function described in (2) formula in different luminance areas using different
γ values, tone is adjusted so as to obtain different tone adjustment functions in different luminance areas.
F (x)=x(1+x)×rX=(0,1) (2)
Wherein, x is to normalize to the pixel value between 0~1.γ is index system, and the different corresponding curves of γ values have
Different enhancing effect, so that tone scale map is different under different γ values.Low γ values are tended to lift dark space, high γ values
Tend to suppress clear zone.
In embodiments of the present invention, tone adjustment function designating unit 200 is used for the region of different brightness in picture
Different γ values are adjusted, so as to which the tone of image is adjusted as needed.Such as, for clear zone, then according to need
Clear zone is suppressed, for dark space, then as needed, dark space can suitably be lifted.Tone adjustment function is specified single
Member 200 is by the way that different luminance areas are adjusted using different γ values, so as to obtain more preferably tone regulation effect
Really.
As one embodiment of the present of invention, tone adjustment function can also adjust equation using gamma, can obtain and (2)
The similar enhancing effect of formula.
In the third embodiment of the present invention, when N luminance areas division unit 110 currently processed image is divided into it is N number of
Luminance area, for formula (2), γ values can be that initial value is between 0~1 by N tone adjustment functions designating unit 210
Difference is 1/N N number of number, so as to can obtain N number of tone adjustment function, N number of luminance area is corresponded to respectively, present image is divided
After N number of luminance area, so as to carry out image calculating using different tone adjustment functions in different luminance areas.
In embodiments of the present invention, N values are a pre-defined positive integer.
In the fourth embodiment of the present invention, after picture to be divided into clear zone, middle area and the region of dark space three, three
γ difference values can be 0.3,0.6 and 0.9 by tone adjustment function designating unit 211, and dark space, middle area and clear zone are corresponded to respectively
Tone adjustment function, due to low value tend to lifted dark space, and high r values tend to suppress clear zone, so utilize this γ value general
To image lifting dark space, suppress clear zone and reservation middle area.
As one embodiment of the present of invention, tone adjustment function can also adjust equation using gamma.
Area pixel value computing unit 300 calculates pixel value with corresponding tone adjustment function respectively in each region.
In embodiments of the present invention, corresponding tone is being specified to adjust to currently processed image zoning and for each region
Save after function, so that area pixel value computing unit 300 can calculate picture with corresponding tone adjustment function respectively in each region
Element value.
In third embodiment of the invention, when N luminance areas division unit 110 currently processed image is divided into it is N number of bright
Spend after region, N number of tone regulation is correspondingly made available by changing γ values according to (1) formula N tone adjustment functions designating unit 210
Function, so that n-quadrant pixel value calculating unit 310 can be in different luminance areas respectively with different tone adjustment function meters
Calculate enhanced pixel value.
In the fourth embodiment of the present invention, when three area division units 111 currently processed image is divided into dark space, in
Between behind area and three, clear zone region, and be that correspondence is specified in these three regions by formula (1) by three color scheme adjustment function designating unit 211
γ values be respectively 0.3,0.6 and 0.9 three tone adjustment functions after so that three area pixel value computing units 311 can
To calculate enhanced pixel value according to these three tone adjustment functions in these three luminance areas respectively.
In another embodiment of the present invention, it would however also be possible to employ other tone adjustment functions in addition to (1) formula.
As one embodiment of the present of invention, when N luminance areas division unit 110 currently processed image is divided into it is N number of
After luminance area, N tone adjustment functions designating unit 210 recycles (1) formula to be counted according to different luminance areas using different γ values
Calculate after the tone adjustment function for obtaining different luminance areas, give the point P in I × J picture spacesi,j∈(0,1),0≤i
≤ I, 0≤j≤J and its neighborhoodSo as to calculate enhanced pixel value using formula (3).
WhereinThat is region division (An-1,An) in point Pi,jRatio in neighborhood.
In one embodiment of the invention, P during region divisioni,jFieldSelection is circular, so that algorithm performance
Most preferably, it can obtain preferable picture enhancing effect.
As the preferred embodiment of the present invention, P during region divisioni,jNeighborhoodSelection is square, so that
W can be quickly calculated using nomography is integratedn。
In a preferred embodiment of the invention, in three area division units 111 by the brightness of currently processed image
Region division be clear zone, middle area and the area of dark space three after, and by three color scheme adjustment function designating unit 211 be these three areas
Domain is after the specified corresponding γ values of formula (1) are respectively 0.3,0.6 and 0.9 three tone adjustment functions, and region division
When Pi,jNeighborhoodSelection is square, so that the utilization of three area pixel value computing units 311 integrates nomography and can quickly calculated
Wn。
Fig. 6 shows the structure for the three area pixel value computing units that fourth embodiment of the invention is provided, for the ease of saying
It is bright, it illustrate only the part related to the embodiment of the present invention.
Integrogram computing unit 3111 calculates dark space integrogram and clear zone integrogram respectively.
In embodiments of the present invention, after dark space, middle area and three, clear zone region is divided an image into, and by area
Domain divides (An-1,An) in point Pi,jNeighborhood elects Square Neighborhood as,So as to quickly calculate W using integration nomographyn, to calculate
The pixel value of enhanced each pixel.Integrogram computing unit 3111 is accumulated firstly the need of calculating dark space integrogram respectively and clear zone
Component, consequently facilitating follow-up quick calculating WnAnd calculate the pixel value of final enhanced each pixel.
In a preferred embodiment of the invention, when divide an image into dark space, middle area and three, clear zone region with
Afterwards, and by region division (An-1,An) in point Pi,jNeighborhood elects square field as, so as to quickly be counted using integration nomography
Calculate Wn, to calculate the pixel value of enhanced each pixel.It is long-pending firstly the need of dark space integrogram and clear zone integrogram is calculated respectively
Component computing unit 3111 is utilized respectively formula (4) and formula (5) calculates dark space integrogram S and clear zone integrogram T.
Pixel value calculating unit 3112 calculates pixel with corresponding tone adjustment function respectively in dark space, middle area and clear zone
Value.
In embodiments of the present invention, after calculating dark space integrogram and clear zone integrogram, pixel value calculating unit
3112 calculate the pixel value of enhanced each pixel again, so as to obtain the final pixel for carrying out each pixel after enhancing regulation
Value.
In fourth embodiment of the invention, after dark space integrogram and clear zone integrogram is calculated, calculated for pixel values
Unit 3112 calculates enhanced pixel value further according to formula (3), wherein, WnIt can be counted according to dark space integrogram S and clear zone integrogram T
Obtain.
In fourth embodiment of the invention, after dark space integrogram and clear zone integrogram is calculated, calculated for pixel values
Unit 3112 calculates enhanced pixel value further according to formula (3), so that obtain final result of calculation, i.e., enhanced each pixel
The pixel value of point.Wherein, WnIt can be calculated and obtained by formula (6) according to dark space integrogram S and clear zone integrogram T.
Wc=1-Wa-Wb
One of ordinary skill in the art will appreciate that realizing that all or part of step of above-described embodiment can be by hardware
To complete, the hardware of correlation can also be instructed to complete by program, described program can be stored in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only storage, disk or CD etc..
It should be noted that：The image intensifier device that above-described embodiment is provided is when strengthening image, only with above-mentioned
The division progress of each functional module is for example, in practical application, as needed can distribute above-mentioned functions by different
Functional module is completed, to complete all or part of function described above.In addition, the image enhaucament dress that above-described embodiment is provided
Put and belong to same design with image enchancing method embodiment, it implements process and refers to embodiment of the method, repeats no more here.
The embodiment of the present invention according to brightness zoning, and for each region to currently processed image by specifying corresponding
Tone adjustment function calculates the pixel value of each pixel after image enhaucament, so as to realize efficiently quick image enhancement effects.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
Any modifications, equivalent substitutions and improvements made within refreshing and principle etc., should be included in the scope of the protection.
Claims (18)
1. a kind of image enchancing method, it is characterised in that methods described includes：
To currently processed image according to brightness zoning, it is specially：
N number of luminance area is given, the gray average in each region is μn, the μnIn n can use any positive integer, variance is σn,
The σnIn n can use any positive integer, the global luminance mean value of picture is μ0, variance is σ0, then optimization problem definition be
The optimization problem of following formula：
max{Sb/Sw}
s.t.
<mrow>
<msub>
<mi>S</mi>
<mi>b</mi>
</msub>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mi>n</mi>
</munder>
<msub>
<mi>&omega;</mi>
<mi>n</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>&mu;</mi>
<mi>n</mi>
</msub>
<mo>-</mo>
<msub>
<mi>&mu;</mi>
<mn>0</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mrow>
<msub>
<mi>S</mi>
<mi>w</mi>
</msub>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mi>n</mi>
</munder>
<msub>
<mi>&omega;</mi>
<mi>n</mi>
</msub>
<msubsup>
<mi>&sigma;</mi>
<mi>n</mi>
<mn>2</mn>
</msubsup>
</mrow>
Wherein N is positive integer, ωnIt is that the pixel in n-th of region accounts for the ratio of total pixel, SbThe weighting for characterizing each region is discrete
Degree, SwCharacterize population variance degree；
It is that corresponding tone adjustment function is specified in each region according to the regional luminance；
Pixel value is calculated in each region with the corresponding tone adjustment function respectively.
2. image enchancing method as claimed in claim 1, it is characterised in that described to be divided to currently processed image according to brightness
Region is specially：Region division is carried out by the way of cluster based on brightness histogram.
3. image enchancing method as claimed in claim 1, it is characterised in that the N values are 3, then divide an image into clear zone,
Middle area and the region of dark space three.
4. image enchancing method as claimed in claim 1, it is characterised in that described to specify corresponding color for each region
Adjust adjustment function be specially：
It is each region by changing function f (x)=x according to the regional luminance(1+x)×rγ values to tone specify not
Same tone adjustment function, the x is any number in 0 to 1；
Wherein, x is to normalize to the pixel value between 0~1；γ is index system, and the different corresponding curves of γ values have difference
Enhancing effect.
5. the image enchancing method as described in claim 1 or 4, it is characterised in that described to use institute respectively in each region
Stating corresponding tone adjustment function calculating pixel value is specially：
A point P in given I × J picture spacesi,j∈ (0,1), 0≤i≤I, 0≤j≤J and its neighborhoodSo as to profit
Enhanced pixel value is calculated with following formula：
<mrow>
<msub>
<mover>
<mi>P</mi>
<mo>~</mo>
</mover>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mi>n</mi>
</munder>
<msub>
<mi>W</mi>
<mi>n</mi>
</msub>
<mo>&times;</mo>
<msub>
<mi>f</mi>
<mi>n</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
Wherein fn(x)=x(1+x)×r, i.e., described tone adjustment function,That is region division
(An-1,An) in point Pi,jRatio in neighborhood.
6. image enchancing method as claimed in claim 5, the calculating point Pi,jNeighborhoodTo be circular or square.
7. image enchancing method as claimed in claim 3, it is characterised in that it is described in each region respectively with described right
The tone adjustment function answered calculates pixel value：
The dark space integrogram and the clear zone integrogram are calculated respectively；
Pixel value is calculated in the dark space, the middle area and the clear zone with the corresponding tone adjustment function respectively；
Wherein, P during region divisioni,jNeighborhoodSelection is square.
8. image enchancing method as claimed in claim 7, it is characterised in that described in the dark space, the middle area and institute
State clear zone is specially respectively with the corresponding tone adjustment function calculating pixel value：
Calculate the dark space integrogram S and the clear zone integrogram T respectively using equation below：
<mrow>
<msub>
<mi>S</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>s</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>i</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</munderover>
<mi>&omega;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>s</mi>
<mo>,</mo>
<mi>t</mi>
</mrow>
</msub>
<mo>&Element;</mo>
<mi>a</mi>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<msub>
<mi>T</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>s</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>i</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</munderover>
<mi>&omega;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>s</mi>
<mo>,</mo>
<mi>t</mi>
</mrow>
</msub>
<mo>&Element;</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein, ω is the pixel value of pixel in image, and a represents the set of all pixels point in dark space, and c, which is represented in clear zone, to be owned
The set of pixel.
9. image enchancing method as claimed in claim 8, it is characterised in that described in the dark space, the middle area and institute
State clear zone is specially respectively with the corresponding tone adjustment function calculating pixel value：
According to formulaEnhanced pixel value is calculated, wherein, WnIt can be accumulated according to dark space integrogram S and clear zone
Component T is calculated by following formula and obtained：
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>W</mi>
<mi>a</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>S</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>S</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>3</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>3</mn>
</msub>
</mrow>
</msub>
<mo>-</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>S</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>2</mn>
</msub>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>S</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mo>(</mo>
<msub>
<mi>i</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
<mo>(</mo>
<msub>
<mi>j</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>W</mi>
<mi>b</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>T</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>T</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>3</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>3</mn>
</msub>
</mrow>
</msub>
<mo>-</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>T</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>2</mn>
</msub>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>T</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mo>(</mo>
<msub>
<mi>i</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
<mo>(</mo>
<msub>
<mi>j</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>W</mi>
<mi>c</mi>
</msub>
<mo>=</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>W</mi>
<mi>a</mi>
</msub>
<mo>-</mo>
<msub>
<mi>W</mi>
<mi>b</mi>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>.</mo>
</mrow>
10. a kind of image intensifier device, it is characterised in that described device includes：
Luminance area division unit, for currently processed image according to brightness zoning, the luminance area division unit
N luminance area division units are specifically included, for giving N number of luminance area, the gray average in each region is μn, the μnIn
N can use any positive integer, variance is σn, the σnIn n can use any positive integer, the global luminance mean value of picture is μ0, side
Difference is σ0, then optimization problem definition is the optimization problem of following formula：
max{Sb/Sw}
s.t.
<mrow>
<msub>
<mi>S</mi>
<mi>b</mi>
</msub>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mi>n</mi>
</munder>
<msub>
<mi>&omega;</mi>
<mi>n</mi>
</msub>
<msup>
<mrow>
<mo>(</mo>
<msub>
<mi>&mu;</mi>
<mi>n</mi>
</msub>
<mo>-</mo>
<msub>
<mi>&mu;</mi>
<mn>0</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
</mrow>
<mrow>
<msub>
<mi>S</mi>
<mi>w</mi>
</msub>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mi>n</mi>
</munder>
<msub>
<mi>&omega;</mi>
<mi>n</mi>
</msub>
<msubsup>
<mi>&sigma;</mi>
<mi>n</mi>
<mn>2</mn>
</msubsup>
</mrow>
Wherein N is positive integer, ωnIt is that the pixel in n-th of region accounts for the ratio of total pixel, SbThe weighting for characterizing each region is discrete
Degree, SwCharacterize population variance degree；
Tone adjustment function designating unit, is that corresponding tone regulation letter is specified in each region according to the regional luminance
Number；
Area pixel value computing unit, for calculating pixel with the corresponding tone adjustment function respectively in each region
Value.
11. image intensifier device as claimed in claim 10, it is characterised in that the luminance area division unit is to current place
Manage image is specially according to brightness zoning：Region division is carried out by the way of cluster based on brightness histogram.
12. image intensifier device as claimed in claim 10, it is characterised in that the luminance area division unit also includes three
Area division unit, is 3 for N values, then divides an image into clear zone, middle area and the region of dark space three.
13. image intensifier device as claimed in claim 10, it is characterised in that the tone adjustment function designating unit is every
The individual region specifies the corresponding tone adjustment function to be specially：
It is each region by changing function f (x)=x according to the regional luminance(1+x)×rγ values to tone specify not
Same tone adjustment function, the x is any number in 0 to 1；
Wherein, x is to normalize to the pixel value between 0~1；γ is index system, and the different corresponding curves of γ values have difference
Enhancing effect.
14. image intensifier device as claimed in claim 10, it is characterised in that the area pixel value computing unit is each
The region calculates pixel value with the corresponding tone adjustment function respectively：
A point P in given I × J picture spacesi,j∈ (0,1), 0≤i≤I, 0≤j≤J and its neighborhoodSo as to profit
Enhanced pixel value is calculated with following formula：
<mrow>
<msub>
<mover>
<mi>P</mi>
<mo>~</mo>
</mover>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<munder>
<mo>&Sigma;</mo>
<mi>n</mi>
</munder>
<msub>
<mi>W</mi>
<mi>n</mi>
</msub>
<mo>&times;</mo>
<msub>
<mi>f</mi>
<mi>n</mi>
</msub>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
Wherein fn(x)=x(1+x)×r, i.e., described tone adjustment function,That is region division
(An-1,An) in point Pi,jRatio in neighborhood.
15. image intensifier device as claimed in claim 14, the calculating point Pi,jNeighborhoodFor circular or side
Shape.
16. image intensifier device as claimed in claim 12, it is characterised in that the area pixel value computing unit is also wrapped
Include：
Integrogram computing unit, for calculating the dark space integrogram and the clear zone integrogram respectively；
Pixel value calculating unit, for being adjusted respectively with the corresponding tone in the dark space, the middle area and the clear zone
Save function and calculate pixel value；
Wherein, P during region divisioni,jNeighborhoodSelection is square.
17. image intensifier device as claimed in claim 16, it is characterised in that the pixel value calculating unit is described dark
Area, the middle area and the clear zone calculate pixel value with the corresponding tone adjustment function respectively：
Calculate the dark space integrogram S and the clear zone integrogram T respectively using equation below：
<mrow>
<msub>
<mi>S</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>s</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>i</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</munderover>
<mi>&omega;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>s</mi>
<mo>,</mo>
<mi>t</mi>
</mrow>
</msub>
<mo>&Element;</mo>
<mi>a</mi>
<mo>)</mo>
</mrow>
</mrow>
3
<mrow>
<msub>
<mi>T</mi>
<mrow>
<mi>i</mi>
<mo>,</mo>
<mi>j</mi>
</mrow>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>s</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>i</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<mi>t</mi>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>j</mi>
</munderover>
<mi>&omega;</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>P</mi>
<mrow>
<mi>s</mi>
<mo>,</mo>
<mi>t</mi>
</mrow>
</msub>
<mo>&Element;</mo>
<mi>c</mi>
<mo>)</mo>
</mrow>
</mrow>
Wherein, ω is the pixel value of pixel in image, and a represents the set of all pixels point in dark space, and c, which is represented in clear zone, to be owned
The set of pixel.
18. image intensifier device as claimed in claim 17, it is characterised in that the pixel value calculating unit is described dark
Area, the middle area and the clear zone calculate pixel value with the corresponding tone adjustment function respectively：
According to formulaEnhanced pixel value is calculated, wherein, WnIt can be accumulated according to dark space integrogram S and clear zone
Component T is calculated by following formula and obtained：
<mrow>
<mtable>
<mtr>
<mtd>
<mrow>
<msub>
<mi>W</mi>
<mi>a</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>S</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>S</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>3</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>3</mn>
</msub>
</mrow>
</msub>
<mo>-</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>S</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>2</mn>
</msub>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>S</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mo>(</mo>
<msub>
<mi>i</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
<mo>(</mo>
<msub>
<mi>j</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>W</mi>
<mi>b</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msub>
<mi>T</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>T</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>3</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>3</mn>
</msub>
</mrow>
</msub>
<mo>-</mo>
<mrow>
<mo>(</mo>
<msub>
<mi>T</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>2</mn>
</msub>
</mrow>
</msub>
<mo>+</mo>
<msub>
<mi>T</mi>
<mrow>
<msub>
<mi>i</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
<mrow>
<mo>(</mo>
<msub>
<mi>i</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>i</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
<mo>(</mo>
<msub>
<mi>j</mi>
<mn>2</mn>
</msub>
<mo>-</mo>
<msub>
<mi>j</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
</mfrac>
</mrow>
</mtd>
</mtr>
<mtr>
<mtd>
<mrow>
<msub>
<mi>W</mi>
<mi>c</mi>
</msub>
<mo>=</mo>
<mn>1</mn>
<mo>-</mo>
<msub>
<mi>W</mi>
<mi>a</mi>
</msub>
<mo>-</mo>
<msub>
<mi>W</mi>
<mi>b</mi>
</msub>
</mrow>
</mtd>
</mtr>
</mtable>
<mo>.</mo>
</mrow>
4
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410852937.1A CN104517272B (en) | 2014-12-31 | 2014-12-31 | A kind of image enchancing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410852937.1A CN104517272B (en) | 2014-12-31 | 2014-12-31 | A kind of image enchancing method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104517272A CN104517272A (en) | 2015-04-15 |
| CN104517272B true CN104517272B (en) | 2017-11-03 |
Family
ID=52792522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410852937.1A Active CN104517272B (en) | 2014-12-31 | 2014-12-31 | A kind of image enchancing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104517272B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104766338A (en) * | 2015-04-28 | 2015-07-08 | 中云智慧（北京）科技有限公司 | Method for detecting significance of complex X-ray pseudo-color image |
| CN105096267B (en) * | 2015-07-02 | 2018-06-22 | 广东欧珀移动通信有限公司 | A kind of method and apparatus that eye brightness is adjusted based on identification of taking pictures |
| CN104978710B (en) * | 2015-07-02 | 2018-07-10 | 广东欧珀移动通信有限公司 | A kind of method and apparatus that face brightness is adjusted based on identification of taking pictures |
| CN105895054A (en) * | 2016-05-17 | 2016-08-24 | 深圳天珑无线科技有限公司 | Adjustment method of output brightness, adjustment method of Gamma curve and display device |
| CN106875344B (en) | 2016-12-21 | 2019-09-17 | 浙江大华技术股份有限公司 | A kind of light filling processing method and processing device of video image |
| CN108230256A (en) * | 2017-11-09 | 2018-06-29 | 珠海市魅族科技有限公司 | Image processing method, device, computer installation and computer readable storage medium |
| CN108665428B (en) * | 2018-04-26 | 2022-11-11 | 青岛海信移动通信技术股份有限公司 | Image enhancement method, device, equipment and storage medium |
| CN112819838B (en) * | 2021-04-19 | 2021-07-06 | 浙江华创视讯科技有限公司 | Image enhancement method, electronic device, and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5963676A (en) * | 1997-02-07 | 1999-10-05 | Siemens Corporate Research, Inc. | Multiscale adaptive system for enhancement of an image in X-ray angiography |
| CN1996384A (en) * | 2006-12-25 | 2007-07-11 | 华中科技大学 | Infrared image multistage mean contrast enhancement method |
-
2014
- 2014-12-31 CN CN201410852937.1A patent/CN104517272B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US5963676A (en) * | 1997-02-07 | 1999-10-05 | Siemens Corporate Research, Inc. | Multiscale adaptive system for enhancement of an image in X-ray angiography |
| CN1996384A (en) * | 2006-12-25 | 2007-07-11 | 华中科技大学 | Infrared image multistage mean contrast enhancement method |
Non-Patent Citations (5)
| Title |
|---|
| Enhancement of Mammographic Features by Optimal Adaptive Neighborhood Image Processing;A P Dhawan等;《IEEE Trans.Medical Imagings》;19861231;第4卷(第1期);第8-14页 * |
| 基于线性拉伸的遥感图像处理;殷年;《光电子技术与信息》;19981231;第11卷(第5期);第29-33页 * |
| 小波分析在遥感图像增强中的应用及MATLAB实现;张瑾等;《半导体光电》;20051231;第3卷(第26期);第149-151页 * |
| 彩色图像色调增强技术研究;罗涛;《中国优秀硕士学位论文全文数据库 信息科技辑》;20090115(第01期);第33-34页 * |
| 遥感图像增强方法的研究及实现;汤晓春;《中国优秀硕士学位论文全文数据库 信息科技辑》;20100615(第06期);第31-33页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104517272A (en) | 2015-04-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104517272B (en) | A kind of image enchancing method and device | |
| Xiao et al. | Brightness and contrast controllable image enhancement based on histogram specification | |
| US8289412B2 (en) | Apparatus and methods for boosting dynamic range in digital images | |
| CN104537615B (en) | A kind of local Retinex Enhancement Methods based on HSV color spaces | |
| US8103120B2 (en) | Method and apparatus of local contrast enhancement | |
| CN104346776B (en) | Retinex-theory-based nonlinear image enhancement method and system | |
| CN109817170B (en) | Pixel compensation method and device and terminal equipment | |
| US9336578B2 (en) | Interactive tone mapping for high dynamic range video | |
| CN105895054A (en) | Adjustment method of output brightness, adjustment method of Gamma curve and display device | |
| CN105869577A (en) | Display device image processing method and system | |
| CN107993189B (en) | Image tone dynamic adjustment method and device based on local blocking | |
| CN109686342B (en) | Image processing method and device | |
| CN103810681B (en) | Low-power consumption contrast enhancing method | |
| CN104166967A (en) | Method for improving definition of video image | |
| US11232545B2 (en) | Systems and methods for image processing | |
| Lee et al. | High dynamic range image tone mapping based on asymmetric model of retinal adaptation | |
| CN105191277A (en) | Guided filter-based detail enhancement | |
| Khan et al. | Tone-mapping using perceptual-quantizer and image histogram | |
| CN109343692A (en) | Mobile device display electricity saving method based on image segmentation | |
| CN103702116A (en) | Wide dynamic compressing method and device for image | |
| Shin et al. | Rendering high dynamic range images by using integrated global and local processing | |
| WO2020107308A1 (en) | Low-light-level image rapid enhancement method and apparatus based on retinex | |
| CN104580826A (en) | Video signal processing method for improving image sharpness | |
| KR101287508B1 (en) | Apparatus and method for contrast enhancement using dominant brightness level and adaptive intensity transformation | |
| US11176866B2 (en) | Image processing method based on peripheral reduction of contrast |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |