CN107203982A - A kind of image processing method and device - Google Patents
A kind of image processing method and device Download PDFInfo
- Publication number
- CN107203982A CN107203982A CN201710493809.6A CN201710493809A CN107203982A CN 107203982 A CN107203982 A CN 107203982A CN 201710493809 A CN201710493809 A CN 201710493809A CN 107203982 A CN107203982 A CN 107203982A
- Authority
- CN
- China
- Prior art keywords
- gray
- standard deviation
- image
- setting
- pixel
- 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.)
- Pending
Links
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000012545 processing Methods 0.000 claims abstract description 81
- 230000002708 enhancing effect Effects 0.000 claims abstract description 60
- 238000000034 method Methods 0.000 claims abstract description 25
- 230000003044 adaptive effect Effects 0.000 claims description 16
- 238000005728 strengthening Methods 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 7
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000006870 function Effects 0.000 claims description 3
- 230000004069 differentiation Effects 0.000 abstract description 8
- 230000008859 change Effects 0.000 description 7
- 238000010606 normalization Methods 0.000 description 6
- 238000013461 design Methods 0.000 description 5
- 230000000694 effects Effects 0.000 description 5
- 238000004380 ashing Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 230000003321 amplification Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 2
- 230000007812 deficiency Effects 0.000 description 2
- 238000003199 nucleic acid amplification method Methods 0.000 description 2
- WFKWXMTUELFFGS-UHFFFAOYSA-N tungsten Chemical compound [W] WFKWXMTUELFFGS-UHFFFAOYSA-N 0.000 description 2
- 229910052721 tungsten Inorganic materials 0.000 description 2
- 239000010937 tungsten Substances 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
- 230000006399 behavior Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/40—Image enhancement or restoration by the use of histogram techniques
-
- G06T5/94—
-
- 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
-
- 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
- G06T2207/20172—Image enhancement details
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Facsimile Image Signal Circuits (AREA)
- Image Processing (AREA)
Abstract
The present invention proposes a kind of image processing method, and this method performs following operate to the pixel in pending image：Calculating is obtained in described image, centered on the pixel, the gray average and gray standard deviation of the image-region being sized；The gray average is judged whether in the range of the first threshold of setting, and judges the gray standard deviation whether in the range of the Second Threshold of setting；If the gray average is in the range of the first threshold of setting, and the gray standard deviation is in the range of the Second Threshold of setting, then according to the gray average and gray standard deviation, and enhancing processing is carried out to the gray value of the pixel.Using technical solution of the present invention, the gray average and gray standard deviation of image-region realize the enhancing processing that differentiation is carried out to different pixels point as the foundation that grey level enhancement is carried out to pixel using around pixel.
Description
Technical field
The present invention relates to digital image processing techniques field, more particularly to a kind of image processing method and device.
Background technology
Image enhaucament refers to the entirety or local characteristicses for purposefully emphasizing image, and original unsharp image is become into clear
It is clear or emphasize some features interested, so as to improve picture quality, rich image information content, strengthen image interpretation and identification is imitated
Really.
Histogram equalization is conventional algorithm for image enhancement.Histogram equalization is exactly to gray probability known to a width point
The image of cloth carries out conversion process, is allowed to develop into the image that there is a width uniform gray probability to be distributed.Histogram equalization
The overall intensity for realizing image is balanced, and the enhancing processing to image is realized on the whole.True epigraph different piece
Gamma characteristic is simultaneously differed, and the enhancing processing of required progress should also have otherness.Therefore, piece image is carried out overall
On image enhancement processing, it is clear that do not meet the gamma characteristic difference of image each several part.
Traditional algorithm for image enhancement based on local mean value and standard deviation can make up above-mentioned image to a certain extent and increase
The deficiency of strong algorithms.Traditional algorithm for image enhancement based on local mean value and standard deviation, can be according to the gray average of image
Enhanced pixel is needed with gray standard deviation automatic identification, and grey level enhancement processing is carried out to the pixel of identification.This method
The grey level enhancement processing of enhanced pixel the need for identification, is that will need the grey level enhancement identical times of enhanced pixel
Number, its essence is still to needing enhanced pixel to carry out unified enhancing processing, does not realize and different pixels are clicked through
The enhancing processing of row differentiation.
The content of the invention
Defect and deficiency based on above-mentioned prior art, the present invention propose a kind of image processing method and device, Neng Goushi
The enhancing that differentiation is now carried out to the different pixels point in a sub-picture is handled.
A kind of image processing method, including：
Obtain pending image；
To each pixel in described image, following operate is performed respectively：
Calculating is obtained in described image, centered on the pixel, the gray average for the image-region being sized
And gray standard deviation；
The gray average is judged whether in the range of the first threshold of setting, and whether judges the gray standard deviation
In the range of the Second Threshold of setting；
If the gray average is in the range of the first threshold of setting, and the gray standard deviation is the second of setting
In threshold range, then according to the gray average and gray standard deviation, enhancing processing is carried out to the gray value of the pixel.
Preferably, it is described according to the gray average and gray standard deviation, the gray value of the pixel is strengthened
Processing, including：
According to the gray average and gray standard deviation, calculating obtains adaptively strengthening coefficient；
According to the adaptive enhancing coefficient, enhancing processing is carried out to the gray value of the pixel.
Preferably, it is described to judge the gray average whether in the range of the first threshold of setting, and judge the ash
Standard deviation is spent whether in the range of the Second Threshold of setting, including：
The global gray average for obtaining described image, and global gray standard deviation are calculated respectively；
If the value of the gray average is not more than the value of the first multiple of the setting of the global gray average, judge
The gray average is in the range of the first threshold of setting；
If the value of the gray standard deviation is not less than the value of the second multiple of the setting of the global gray standard deviation, and
And the value of the triple of the setting of no more than described global gray standard deviation, then judge the gray standard deviation the of setting
In two threshold ranges；Wherein, second multiple is not more than the triple.
Preferably, the calculating is obtained in described image, centered on the pixel, the image-region being sized
Gray average and gray standard deviation, including：
Calculating is obtained in described image, centered on the pixel, the normalizing ashing for the image-region being sized
Spend histogram；
According to the Normalized Grey Level histogram, the gray average for obtaining described image region is calculated；
According to the gray average, and the Normalized Grey Level histogram, the gray scale for obtaining described image region is calculated
Standard deviation.
A kind of image processing apparatus, including：
Image acquisition unit, the pending image for obtaining；
Computing unit, is obtained in described image for calculating, centered on pixel, the image-region being sized
Gray average and gray standard deviation；
Judging unit, for judging the gray average whether in the range of the first threshold of setting, and judges described
Whether gray standard deviation is in the range of the Second Threshold of setting；
Processing unit, gray average is stated in the range of the first threshold of setting for working as, and the gray standard deviation exists
When in the range of the Second Threshold of setting, according to the gray average and gray standard deviation, the gray value of the pixel is carried out
Enhancing is handled.
Preferably, the processing unit, including：
Strengthen coefficient calculation unit, for according to the gray average and gray standard deviation, calculating adaptively to be strengthened
Coefficient；
Strengthen processing unit, for according to the adaptive enhancing coefficient, strengthening the gray value of the pixel
Processing.
Preferably, the judging unit judges the gray average whether in the range of the first threshold of setting, and sentences
When breaking the gray standard deviation whether in the range of the Second Threshold of setting, specifically for：
The global gray average for obtaining described image, and global gray standard deviation are calculated respectively；If the gray scale is equal
The value of value is not more than the value of the first multiple of the setting of the global gray average, then judges the gray average the of setting
In one threshold range；If the value of the gray standard deviation is not less than the second multiple of the setting of the global gray standard deviation
Value, and the value of the triple of the setting of no more than described global gray standard deviation, then judge that the gray standard deviation is being set
In the range of fixed Second Threshold；Wherein, second multiple is not more than the triple.
Preferably, the computing unit is calculated and obtained in described image, centered on the pixel, is sized
When the gray average and gray standard deviation of image-region, specifically for：
Calculating is obtained in described image, centered on the pixel, the normalizing ashing for the image-region being sized
Spend histogram；According to the Normalized Grey Level histogram, the gray average for obtaining described image region is calculated；According to the gray scale
Average, and the Normalized Grey Level histogram, calculate the gray standard deviation for obtaining described image region.
A kind of image processing apparatus, including：
Memory and processor；
Wherein, the memory is connected with the processor, for the number produced in storage program and program operation process
According to；
The processor, for by running the program stored in the memory, realizing following functions：
Obtain pending image；To each pixel in described image, following operate is performed respectively：Calculating obtains institute
State in image, centered on the pixel, the gray average and gray standard deviation of the image-region being sized；Judge institute
Gray average is stated whether in the range of the first threshold of setting, and judge the gray standard deviation whether setting the second threshold
In the range of value；If the gray average is in the range of the first threshold of setting, and the gray standard deviation is the of setting
In two threshold ranges, then according to the gray average and gray standard deviation, enhancing processing is carried out to the gray value of the pixel.
Preferably, the processor enters according to the gray average and gray standard deviation to the gray value of the pixel
During row enhancing processing, specifically for：
According to the gray average and gray standard deviation, calculating obtains adaptively strengthening coefficient；According to the adaptive increasing
Strong coefficient, enhancing processing is carried out to the gray value of the pixel.
Image processing method proposed by the present invention, to the pixel in pending image, performs following operate：Calculating is obtained
In described image, centered on the pixel, the gray average and gray standard deviation of the image-region being sized；Judge
Whether whether the gray average is in the range of the first threshold of setting, and judge the gray standard deviation the second of setting
In threshold range；If the gray average is in the range of the first threshold of setting, and the gray standard deviation is in setting
In the range of Second Threshold, then according to the gray average and gray standard deviation, the gray value of the pixel is carried out at enhancing
Reason.Using technical solution of the present invention, the gray average and gray standard deviation of image-region are as to pixel using around pixel
The foundation of grey level enhancement is carried out, the enhancing processing that differentiation is carried out to different pixels point is realized.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
The embodiment of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can also basis
The accompanying drawing of offer obtains other accompanying drawings.
Fig. 1 is a kind of schematic flow sheet of image processing method provided in an embodiment of the present invention；
Fig. 2 is the schematic flow sheet of another image processing method provided in an embodiment of the present invention；
Fig. 3 is the schematic flow sheet of another image processing method provided in an embodiment of the present invention；
Fig. 4 (a) is the original image of the tungsten filament image of amplification provided in an embodiment of the present invention；
Fig. 4 (b) is the image after the progress histogram equalization processing provided in an embodiment of the present invention to Fig. 4 (a)；
Fig. 4 (c) be it is provided in an embodiment of the present invention Fig. 4 (a) is handled using traditional local enhancement algorithm after figure
Picture；
Fig. 4 (d) is provided in an embodiment of the present invention Fig. 4 (a) to be located using adaptive local contrast enhancement algorithms
Image after reason；
Fig. 4 (e) is the traditional enhancing algorithm pair based on local mean value and standard deviation of utilization provided in an embodiment of the present invention
Fig. 4 (a) handled after image；
Fig. 4 (f) is the image processing method that is proposed of the utilization embodiment of the present invention provided in an embodiment of the present invention to Fig. 4
(a) image after enhancing processing is carried out；
Fig. 5 is a kind of structural representation of image processing apparatus provided in an embodiment of the present invention；
Fig. 6 is the structural representation of another image processing apparatus provided in an embodiment of the present invention；
Fig. 7 is the structural representation of another image processing apparatus provided in an embodiment of the present invention.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
Shown in Figure 1 the embodiment of the invention discloses a kind of image processing method, this method includes：
The pending image of S101, acquisition；
Specifically, technical scheme of the embodiment of the present invention is used to carry out image enhancement processing, therefore, acquisition to gray level image
Pending image is generally gray level image.The gray level image of image enhancement processing is carried out the need for being obtained by any approach, all
Pending image can be used as.It will be apparent that coloured image can also be obtained, gray-scale map is then colored image into
Picture, then it regard gray level image as pending image.
To each pixel in described image, following operate is performed respectively：
S102, calculating are obtained in described image, centered on the pixel, the gray scale for the image-region being sized
Average and gray standard deviation；
Specifically, assuming the coordinate of (x, y) for a certain pixel in pending image, S is madexyDuring expression is with (x, y)
The image-region that neighbor pixel in the range of being sized of the heart is constituted.
Then SxyGray averageFor：
Wherein, rs,tIt is in SxyThe gray scale of middle coordinate (s, t) place pixel, and p (rs,t) be and coordinate (s, t) place pixel
Corresponding normalization histogram component.
Accordingly, image-region SxyGray standard deviation be：
Wherein, rs,tIt is in SxyThe gray scale of middle coordinate (s, t) place pixel, and p (rs,t) be and coordinate (s, t) place pixel
Corresponding normalization histogram component,For image-region SxyGray average.
It should be noted that the size of the above-mentioned image-region being sized, sets according to actual scene.
S103, the gray average is judged whether in the range of the first threshold of setting, and judge the grey scale
Whether difference is in the range of the Second Threshold of setting；
Specifically, the gray average of image-region illustrates the brightness of image-region, and the gray standard deviation of image-region
Illustrate the contrast of image-region.The embodiment of the present invention decides whether to image according to the brightness and contrast of image-region
Pixel in region carries out grey level enhancement processing.
If image-region is dark, i.e., its gray average is less than the first threshold of setting, and image-region contrast exists
In the contrast range of setting, then the central pixel point to the image-region carries out grey level enhancement processing.
Using such scheme, realize and the difference of different pixels point in image is treated, it is achieved thereby that to different pixels
The differentiation processing of point.
It should be noted that above-mentioned first threshold scope, and Second Threshold scope, can be according to the spirit of actual use demand
Setting living, is realized to any brightness, and the central pixel point of the image-region in any contrast range carries out grey level enhancement
Processing.
If the gray average is in the range of the first threshold of setting, and the gray standard deviation is the second of setting
In threshold range, then perform step S104, according to the gray average and gray standard deviation, the gray value of the pixel is entered
Row enhancing is handled.
If specifically, the brightness of image-region is in the range of the first threshold of setting, and its contrast is in setting
In the range of Second Threshold, then it represents that image enhancement processing, and enhancement value should be carried out to the central pixel point of the image-region
Determined by the gray average and gray standard deviation of the image-region.That is, the gray average and gray standard deviation in different images region
Difference, then strengthen the degree difference of processing to the gray value of the central pixel point of the image-region, thus achieve to not
The enhancing processing of differentiation is carried out with pixel.
The image processing method that the embodiment of the present invention is proposed, to the pixel in pending image, performs following operate：Meter
Calculation is obtained in described image, centered on the pixel, the gray average and grey scale of the image-region being sized
Difference；The gray average is judged whether in the range of the first threshold of setting, and judges whether the gray standard deviation is setting
In the range of fixed Second Threshold；If the gray average is in the range of the first threshold of setting, and the gray standard deviation
In the range of the Second Threshold of setting, then according to the gray average and gray standard deviation, the gray value of the pixel is entered
Row enhancing is handled.Using technical solution of the present invention, using around pixel the gray average and gray standard deviation of image-region as
The foundation of grey level enhancement is carried out to pixel, the enhancing processing that differentiation is carried out to different pixels point is realized.
Optionally, in another embodiment of the present invention, it is shown in Figure 2, it is described according to the gray average and ash
Standard deviation is spent, enhancing processing is carried out to the gray value of the pixel, including：
S204, according to the gray average and gray standard deviation, calculating obtains adaptively strengthening coefficient；
Specifically, adaptively enhancing coefficient η calculation formula is：
Wherein, k is constant,Represent image-region SxyGray standard deviation,Represent image-region SxyGray scale
Average.
S205, according to the adaptive enhancing coefficient, enhancing processing is carried out to the gray value of the pixel.
Specifically, assuming image-region SxyCentral pixel point gray value be f (x, y), it is carried out after enhancing processing
Gray value be g (xy), then to above-mentioned pixel carry out enhancing processing can be formulated as：
Wherein,Represent image-region SxyGray average.
If image-regionGray average not in the range of the first threshold of setting, or image-region's
Gray standard deviation is not in the range of the Second Threshold of setting, then not to image-regionAbove-mentioned central pixel point strengthened
Handle, now g (x, y)=f (x, y).
It is understood that technical scheme of the embodiment of the present invention utilizes adaptive enhancing coefficient corresponding with image slices vegetarian refreshments
Grey level enhancement processing is carried out to the pixel of image.The size of adaptive enhancing coefficient is by including the image of above-mentioned image slices vegetarian refreshments
The gray average and gray standard deviation in region are determined, that is to say, that for different image slices vegetarian refreshments, due to its adjacent area
Gray average is different with gray standard deviation, and the adaptive enhancing coefficient for carrying out strengthening processing to it is different, thus achieves to not
The grey level enhancement processing of differentiation is carried out with image pixel point.
In addition, the gray average and gray standard deviation of image-region with reference to where image slices vegetarian refreshments are carried out at grey level enhancement
Reason, equivalent to both having carried out Edge contrast to image, and has carried out smoothing processing, enhancing effect is more preferable to image.
The step S101 in embodiment of the method shown in step S201 in the present embodiment~S203 difference corresponding diagrams 1~
S103, its particular content refers to the content in the embodiment of the method shown in corresponding diagram 1, and here is omitted.
Optionally, in another embodiment of the present invention, it is shown in Figure 3, it is described whether to judge the gray average
In the range of the first threshold of setting, and the gray standard deviation is judged whether in the range of the Second Threshold of setting, including：
S303, respectively calculating obtain the global gray average of described image, and global gray standard deviation；
Specifically, making r represent what the pixel gray value in above-mentioned image was constituted, on interval [0, L-1], represent discrete
The discrete random variable of gray value, p (ri) represent normalization histogram component corresponding to i-th of r value.
The then global gray average M of above-mentioned imageGFor：
The global gray standard deviation (variance) of above-mentioned imageFor：
If S304, the value of the gray average are not more than the value of the first multiple of the setting of the global gray average,
Then judge the gray average in the range of the first threshold of setting；
Specifically, the brightness of the gray average phenogram picture of image.The embodiment of the present invention is selected in pending image, gray scale
The image-region that average is not more than the value of the first multiple of global gray average setting carries out enhancing processing, that is, selects to wait to locate
Manage dark image-region in image and carry out image enhancement processing.
IfIt is darker area then to represent the region, is the area that enhancing processing is carried out the need for candidate
Domain, wherein k0For the normal number less than 1.0.
If the value of S305, the gray standard deviation is not less than the second multiple of the setting of the global gray standard deviation
Value, and the value of the triple of the setting of no more than described global gray standard deviation, then judge that the gray standard deviation is being set
In the range of fixed Second Threshold；Wherein, second multiple is not more than the triple.
Specifically, the contrast of the gray standard deviation phenogram picture of image.The embodiment of the present invention is selected in pending image,
Contrast setting range in image-region carry out enhancing processing, so as to reach enhancing contrast, make image apparent
Purpose.
IfThe pixel for then thinking pixel (x, y) place is enhancing candidate point, and because of image enhancement processes
The constant region domains that standard deviation is 0 may be strengthened, it is therefore desirable to pass throughk1＜ k2One is set to Local standard deviation
Relatively low limits value.
With reference to the introduction of above-mentioned image enhancement processing condition judgment, it can summarize and obtain, using technology of the embodiment of the present invention
Scheme to image carry out image enhancement processing algorithmic formula be：
Wherein, η is adaptive enhancing coefficient,K is normal number, MGIt is the overall situation ash of input picture
Spend average；DGIt is global gray standard deviation.F (x, y), g (x, y) are input picture and output image respectively at point (x, y) place
Gray value；It is the gray average in the neighborhood centered on (x, y)；It is gray standard deviation；k0,k1,k2It is setting ginseng
Number.
The step in the embodiment of the method shown in step S301, S302, S306 difference corresponding diagram 1 in the present embodiment
S101, S102, S104, its particular content refer to the content of the embodiment of the method shown in corresponding diagram 1, and here is omitted.
Optionally, in another embodiment of the present invention, it is described calculating obtain in described image, using the pixel as
Center, the gray average and gray standard deviation of the image-region being sized, including：
Calculating is obtained in described image, centered on the pixel, the normalizing ashing for the image-region being sized
Spend histogram；
Specifically, make r represent in above-mentioned image, and centered on above-mentioned pixel, the picture for the image-region being sized
What vegetarian refreshments gray value was constituted, on interval [0, L-1], represent the discrete random variable of discrete grey's value, p (ri) represent correspond to
The normalization histogram component of r i-th of value.
According to the Normalized Grey Level histogram, the gray average for obtaining described image region is calculated；
Specifically, assuming the coordinate that (x, y) is above-mentioned pixel, S is madexyExpression is sized model centered on (x, y)
The image-region that neighbor pixel in enclosing is constituted.
Then SxyGray averageFor：
Wherein, rs,tIt is in SxyThe gray scale of middle coordinate (s, t) place pixel, and p (rs,t) be and coordinate (s, t) place pixel
Corresponding normalization histogram component.
According to the gray average, and the Normalized Grey Level histogram, the gray scale for obtaining described image region is calculated
Standard deviation.
Accordingly, image-region SxyGray standard deviation be：
Wherein, rs,tIt is in SxyThe gray scale of middle coordinate (s, t) place pixel, and p (rst) be and coordinate (s, t) place pixel
Corresponding normalization histogram component,For image-region SxyGray average.
In order to protrude the treatment effect advantage of technical scheme of the embodiment of the present invention, below with to the image progress in Fig. 4 (a)
Exemplified by image enhancement processing, traditional algorithm for image enhancement is contrasted, illustrates that the treatment effect of technical scheme of the embodiment of the present invention is excellent
Gesture.
Fig. 4 (a) show the original image of the tungsten filament image of amplification, and some is thin for darker area wherein on the right side of the image
Section needs to carry out enhancing processing.When technical scheme of the embodiment of the present invention is embodied, pending picture is used as using 3 × 3 region
Image-region is sized where vegetarian refreshments.
Fig. 4 (b) is the design sketch after histogram equalization processing, it will be apparent from this figure that needing enhanced thin
Section part is strengthened really, but because it is the processing to entire image, the gray level of image is caused by excessive merging
Image seems overall partially bright.
Fig. 4 (c) is the design sketch of gained after traditional local enhancement algorithm process, the histogram equalization processing that compares image
For, the treatment effect of image is preferable, but enhancing coefficient k is that constant is non-adjustable so that other regions during enhancing designated area
Also it is enhanced, it is impossible to terms of localization approach.
Fig. 4 (d) is the design sketch obtained after being handled using adaptive local contrast enhancement algorithms.The algorithm, which is solved, to be put
The nonadjustable problem of big coefficient k, the value that it can be according to the dynamic regulation enhancing coefficient of change of local contrast, but the algorithm is still
It is to be handled entire image, and the algorithm only considered change of the change of local contrast without considering local mean value
Change the influence brought to image, other regions of image are equally enhanced processing as seen from the figure and effect is unsatisfactory.
Fig. 4 (e) is the design sketch obtained using traditional enhancing algorithm based on local mean value and standard deviation, can from figure
To find out, the algorithm is that the region for meeting condition is strengthened, and other regions do not change then, effectively enhance finger
Determine the image in region, but the simple operation of enhanced region also simply to gray value, the computing behaviour for not carrying out contrast
Make, and without adaptivity.
Fig. 4 (f) is the design sketch obtained by using after algorithm process of the embodiment of the present invention, for technology of the embodiment of the present invention
In scheme, the coefficient selection that the algorithmic formula of image enhancement processing is carried out to image is：K=2.5, k0=0.42, k1=
0.01,k2=0.40.Compared with other above-mentioned several algorithms, it is equal that the algorithm had both considered local gray level in the region for the condition that meets
It is worth the influence that the change of (brightness) comes to picture strip, it is contemplated that the shadow that the change of local gray level standard deviation (contrast) is brought
Ring, the two takes into account simultaneously, effectively raises the display effect in the region that image is dark and contrast is low, be satisfaction for other
The region of condition still keeps constant.
Contrast is visible, the image after image enhancement processing is carried out to image using the embodiment of the present invention, relative to using biography
System method carries out the image after image enhancement processing to image, becomes apparent from, visual effect is more preferable.
Shown in Figure 5 the embodiment of the invention also discloses a kind of image processing apparatus, the device includes：
Image acquisition unit 501, the pending image for obtaining；
Computing unit 502, is obtained in described image for calculating, centered on pixel, the image district being sized
The gray average and gray standard deviation in domain；
Judging unit 503, for judging the gray average whether in the range of the first threshold of setting, and judges institute
Gray standard deviation is stated whether in the range of the Second Threshold of setting；
Processing unit 504, gray average is stated in the range of the first threshold of setting for working as, and the gray standard deviation
When in the range of the Second Threshold of setting, according to the gray average and gray standard deviation, the gray value of the pixel is entered
Row enhancing is handled.
Specifically, the specific works content of the unit in the present embodiment, refers to the interior of corresponding embodiment of the method
Hold, here is omitted.
Optionally, in another embodiment of the present invention, it is shown in Figure 6, processing unit 504, including：
Strengthen coefficient calculation unit 5041, for according to the gray average and gray standard deviation, calculating to obtain adaptive
Strengthen coefficient；
Strengthen processing unit 5042, for according to the adaptive enhancing coefficient, being carried out to the gray value of the pixel
Enhancing is handled.
Specifically, the specific works content of the unit in the present embodiment, refers to the interior of corresponding embodiment of the method
Hold, here is omitted.
Optionally, in another embodiment of the present invention, whether judging unit 503 judges the gray average in setting
First threshold in the range of, and when judging that the gray standard deviation is whether in the range of the Second Threshold of setting, specifically for：
The global gray average for obtaining described image, and global gray standard deviation are calculated respectively；If the gray scale is equal
The value of value is not more than the value of the first multiple of the setting of the global gray average, then judges the gray average the of setting
In one threshold range；If the value of the gray standard deviation is not less than the second multiple of the setting of the global gray standard deviation
Value, and the value of the triple of the setting of no more than described global gray standard deviation, then judge that the gray standard deviation is being set
In the range of fixed Second Threshold；Wherein, second multiple is not more than the triple.
Specifically, the specific works content of the judging unit 503 in the present embodiment, refers to corresponding embodiment of the method
Content, here is omitted.
Optionally, in another embodiment of the present invention, computing unit 502 is calculated and obtained in described image, with described
Centered on pixel, when the gray average and gray standard deviation of the image-region being sized, specifically for：
Calculating is obtained in described image, centered on the pixel, the normalizing ashing for the image-region being sized
Spend histogram；According to the Normalized Grey Level histogram, the gray average for obtaining described image region is calculated；According to the gray scale
Average, and the Normalized Grey Level histogram, calculate the gray standard deviation for obtaining described image region.
Specifically, the specific works content of the computing unit 502 in the present embodiment, refers to corresponding embodiment of the method
Content, here is omitted.
Shown in Figure 7 the embodiment of the invention also discloses another image processing apparatus, the device includes：
Memory 701 and processor 702；
Wherein, memory 701 is connected with processor 702, for the data produced in storage program and program operation process；
Processor 702, for the program by being stored in run memory 701, realizes following functions：
Obtain pending image；To each pixel in described image, following operate is performed respectively：Calculating obtains institute
State in image, centered on the pixel, the gray average and gray standard deviation of the image-region being sized；Judge institute
Gray average is stated whether in the range of the first threshold of setting, and judge the gray standard deviation whether setting the second threshold
In the range of value；If the gray average is in the range of the first threshold of setting, and the gray standard deviation is the of setting
In two threshold ranges, then according to the gray average and gray standard deviation, enhancing processing is carried out to the gray value of the pixel.
Specifically, the specific works content of the various pieces in the present embodiment, refers to the interior of corresponding embodiment of the method
Hold, here is omitted.
Optionally, in another embodiment of the present invention, processor 702 is according to the gray average and grey scale
Difference, when enhancing processing is carried out to the gray value of the pixel, specifically for：
According to the gray average and gray standard deviation, calculating obtains adaptively strengthening coefficient；According to the adaptive increasing
Strong coefficient, enhancing processing is carried out to the gray value of the pixel.
Specifically, the specific works content of the processor 702 in the present embodiment, refers to the interior of corresponding embodiment of the method
Hold, here is omitted.
The foregoing description of the disclosed embodiments, enables professional and technical personnel in the field to realize or using the present invention.
A variety of modifications to these embodiments will be apparent for those skilled in the art, as defined herein
General Principle can be realized in other embodiments without departing from the spirit or scope of the present invention.Therefore, it is of the invention
The embodiments shown herein is not intended to be limited to, and is to fit to and principles disclosed herein and features of novelty phase one
The most wide scope caused.
Claims (10)
1. a kind of image processing method, it is characterised in that including：
Obtain pending image；
To each pixel in described image, following operate is performed respectively：
Calculating is obtained in described image, centered on the pixel, the gray average and ash of the image-region being sized
Spend standard deviation；
The gray average is judged whether in the range of the first threshold of setting, and judges whether the gray standard deviation is setting
In the range of fixed Second Threshold；
If the gray average is in the range of the first threshold of setting, and the gray standard deviation is in the Second Threshold of setting
In the range of, then according to the gray average and gray standard deviation, enhancing processing is carried out to the gray value of the pixel.
2. it is according to the method described in claim 1, it is characterised in that described according to the gray average and gray standard deviation, right
The gray value of the pixel carries out enhancing processing, including：
According to the gray average and gray standard deviation, calculating obtains adaptively strengthening coefficient；
According to the adaptive enhancing coefficient, enhancing processing is carried out to the gray value of the pixel.
3. according to the method described in claim 1, it is characterised in that described to judge the gray average whether the first of setting
In threshold range, and the gray standard deviation is judged whether in the range of the Second Threshold of setting, including：
The global gray average for obtaining described image, and global gray standard deviation are calculated respectively；
If the value of the gray average is not more than the value of the first multiple of the setting of the global gray average, judge described
Gray average is in the range of the first threshold of setting；
If the value of the gray standard deviation is not less than the value of the second multiple of the setting of the global gray standard deviation, and not
More than the value of the triple of the setting of the global gray standard deviation, then second threshold of the gray standard deviation in setting is judged
In the range of value；Wherein, second multiple is not more than the triple.
4. according to the method described in claim 1, it is characterised in that the calculating is obtained in described image, with the pixel
Centered on, the gray average and gray standard deviation of the image-region being sized, including：
Calculating is obtained in described image, centered on the pixel, and the Normalized Grey Level for the image-region being sized is straight
Fang Tu；
According to the Normalized Grey Level histogram, the gray average for obtaining described image region is calculated；
According to the gray average, and the Normalized Grey Level histogram, the grey scale for obtaining described image region is calculated
Difference.
5. a kind of image processing apparatus, it is characterised in that including：
Image acquisition unit, the pending image for obtaining；
Computing unit, is obtained in described image for calculating, centered on pixel, the gray scale for the image-region being sized
Average and gray standard deviation；
Judging unit, for judging the gray average whether in the range of the first threshold of setting, and judges the gray scale
Whether standard deviation is in the range of the Second Threshold of setting；
Processing unit, gray average is stated in the range of the first threshold of setting for working as, and the gray standard deviation is in setting
Second Threshold in the range of when, according to the gray average and gray standard deviation, the gray value of the pixel is strengthened
Processing.
6. device according to claim 5, it is characterised in that the processing unit, including：
Strengthen coefficient calculation unit, for according to the gray average and gray standard deviation, calculating to obtain adaptively strengthening coefficient；
Strengthen processing unit, for according to the adaptive enhancing coefficient, enhancing processing to be carried out to the gray value of the pixel.
7. device according to claim 5, it is characterised in that the judging unit judges whether the gray average is setting
It is specific to use in the range of fixed first threshold, and when judging that the gray standard deviation is whether in the range of the Second Threshold of setting
In：
The global gray average for obtaining described image, and global gray standard deviation are calculated respectively；If the gray average
Value is not more than the value of the first multiple of the setting of the global gray average, then judges first threshold of the gray average in setting
In the range of value；If the value of the gray standard deviation is not less than the value of the second multiple of the setting of the global gray standard deviation,
And the value of the triple of the setting of no more than described global gray standard deviation, then judge the gray standard deviation in setting
In the range of Second Threshold；Wherein, second multiple is not more than the triple.
8. device according to claim 5, it is characterised in that the computing unit is calculated and obtained in described image, with institute
Centered on stating pixel, when the gray average and gray standard deviation of the image-region being sized, specifically for：
Calculating is obtained in described image, centered on the pixel, and the Normalized Grey Level for the image-region being sized is straight
Fang Tu；According to the Normalized Grey Level histogram, the gray average for obtaining described image region is calculated；It is equal according to the gray scale
Value, and the Normalized Grey Level histogram, calculate the gray standard deviation for obtaining described image region.
9. a kind of image processing apparatus, it is characterised in that including：
Memory and processor；
Wherein, the memory is connected with the processor, for the data produced in storage program and program operation process；
The processor, for by running the program stored in the memory, realizing following functions：
Obtain pending image；To each pixel in described image, following operate is performed respectively：Calculating obtains the figure
As in, centered on the pixel, the gray average and gray standard deviation of the image-region being sized；Judge the ash
Spend average whether in the range of the first threshold of setting, and judge the gray standard deviation whether setting Second Threshold model
In enclosing；If the gray average is in the range of the first threshold of setting, and the gray standard deviation is in the second threshold of setting
In the range of value, then according to the gray average and gray standard deviation, enhancing processing is carried out to the gray value of the pixel.
10. device according to claim 9, it is characterised in that the processor is according to the gray average and gray scale
It is accurate poor, when carrying out enhancing to the gray value of the pixel and handling, specifically for：
According to the gray average and gray standard deviation, calculating obtains adaptively strengthening coefficient；According to the adaptive enhancing system
Number, enhancing processing is carried out to the gray value of the pixel.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710493809.6A CN107203982A (en) | 2017-06-26 | 2017-06-26 | A kind of image processing method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710493809.6A CN107203982A (en) | 2017-06-26 | 2017-06-26 | A kind of image processing method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107203982A true CN107203982A (en) | 2017-09-26 |
Family
ID=59907728
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710493809.6A Pending CN107203982A (en) | 2017-06-26 | 2017-06-26 | A kind of image processing method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107203982A (en) |
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230258A (en) * | 2017-11-15 | 2018-06-29 | 浙江工业大学 | A kind of license plate area Enhancement Method calculated based on horizontal neighbors standard deviation |
| CN108665428A (en) * | 2018-04-26 | 2018-10-16 | 青岛海信移动通信技术股份有限公司 | Image enchancing method, device, equipment and storage medium |
| CN109525776A (en) * | 2018-11-01 | 2019-03-26 | 浙江大华技术股份有限公司 | A kind of image-pickup method and device |
| WO2019085969A1 (en) * | 2017-11-02 | 2019-05-09 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for image processing |
| CN109949246A (en) * | 2019-03-26 | 2019-06-28 | 河南理工大学 | A method of processing image |
| CN110580693A (en) * | 2018-06-07 | 2019-12-17 | 湖南爱威医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN110772788A (en) * | 2019-10-24 | 2020-02-11 | 苏州佳世达光电有限公司 | Method for correcting aiming star of shooting game by display equipment |
| CN111444486A (en) * | 2019-12-31 | 2020-07-24 | 深圳贝特莱电子科技股份有限公司 | Startup self-adaptive fingerprint parameter initialization method based on android system |
| CN111451623A (en) * | 2020-05-26 | 2020-07-28 | 上海法信机电设备制造有限公司 | Plasma welding seam tracking device |
| CN111915497A (en) * | 2019-05-09 | 2020-11-10 | 杭州睿琪软件有限公司 | Image black and white enhancement method and device, electronic equipment and readable storage medium |
| CN114998159A (en) * | 2022-08-04 | 2022-09-02 | 邹城市天晖软件科技有限公司 | Design image self-adaptive enhancement method |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303765A (en) * | 2008-06-23 | 2008-11-12 | 四川虹微技术有限公司 | Method for reinforcing image contrast based on image mean-squared deviation |
| US8744208B2 (en) * | 2009-12-02 | 2014-06-03 | Jadavpur University | Image binarization based on grey membership parameter of pixels |
| CN104182967A (en) * | 2014-07-29 | 2014-12-03 | 小米科技有限责任公司 | Image processing method, device and terminal |
-
2017
- 2017-06-26 CN CN201710493809.6A patent/CN107203982A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101303765A (en) * | 2008-06-23 | 2008-11-12 | 四川虹微技术有限公司 | Method for reinforcing image contrast based on image mean-squared deviation |
| US8744208B2 (en) * | 2009-12-02 | 2014-06-03 | Jadavpur University | Image binarization based on grey membership parameter of pixels |
| CN104182967A (en) * | 2014-07-29 | 2014-12-03 | 小米科技有限责任公司 | Image processing method, device and terminal |
Non-Patent Citations (5)
| Title |
|---|
| DAH-CHUNG CHANG等: "Image Contrast Enhancement Based on a Histogram Transformation of Local Standard Deviation", 《IEEE TRANSACTIONS ON MEDICAL IMAGING》 * |
| M. A. YOUSUF等: "An Effective Image Contrast Enhancement Method Using Global Histogram Equalization", 《JOURNAL OF SCIENTIFIC RESEARCH》 * |
| M. SUNDARAM等: "Histogram Modified Local Contrast Enhancement for mammogram images", 《APPLIED SOFT COMPUTING》 * |
| YUNQI HU等: "Contrast Enhancement Based on Fuzzy Clustering", 《2014 4TH IEEE INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND TECHNOLOGY》 * |
| 李锦等: "一种结合直方图均衡化和MSRCR的图像增强新算法", 《西安电子科技大学学报（自然科学版）》 * |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019085969A1 (en) * | 2017-11-02 | 2019-05-09 | Zhejiang Dahua Technology Co., Ltd. | Systems and methods for image processing |
| US11232545B2 (en) | 2017-11-02 | 2022-01-25 | Zhejiang Dahlia Technology Co., Ltd. | Systems and methods for image processing |
| CN108230258A (en) * | 2017-11-15 | 2018-06-29 | 浙江工业大学 | A kind of license plate area Enhancement Method calculated based on horizontal neighbors standard deviation |
| CN108230258B (en) * | 2017-11-15 | 2021-06-04 | 浙江工业大学 | License plate region enhancement method based on horizontal neighborhood standard deviation calculation |
| CN108665428A (en) * | 2018-04-26 | 2018-10-16 | 青岛海信移动通信技术股份有限公司 | Image enchancing method, device, equipment and 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 |
| CN110580693B (en) * | 2018-06-07 | 2022-03-25 | 湖南爱威医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN110580693A (en) * | 2018-06-07 | 2019-12-17 | 湖南爱威医疗科技有限公司 | Image processing method, image processing device, computer equipment and storage medium |
| CN109525776B (en) * | 2018-11-01 | 2020-12-08 | 浙江大华技术股份有限公司 | Image acquisition method and device |
| CN109525776A (en) * | 2018-11-01 | 2019-03-26 | 浙江大华技术股份有限公司 | A kind of image-pickup method and device |
| CN109949246A (en) * | 2019-03-26 | 2019-06-28 | 河南理工大学 | A method of processing image |
| CN109949246B (en) * | 2019-03-26 | 2023-03-31 | 河南理工大学 | Method for processing image |
| CN111915497A (en) * | 2019-05-09 | 2020-11-10 | 杭州睿琪软件有限公司 | Image black and white enhancement method and device, electronic equipment and readable storage medium |
| CN111915497B (en) * | 2019-05-09 | 2023-11-03 | 杭州睿琪软件有限公司 | Image black-and-white enhancement method and device, electronic equipment and readable storage medium |
| CN110772788A (en) * | 2019-10-24 | 2020-02-11 | 苏州佳世达光电有限公司 | Method for correcting aiming star of shooting game by display equipment |
| CN110772788B (en) * | 2019-10-24 | 2023-08-18 | 苏州佳世达光电有限公司 | Method for correcting sight of shooting game by display equipment |
| CN111444486A (en) * | 2019-12-31 | 2020-07-24 | 深圳贝特莱电子科技股份有限公司 | Startup self-adaptive fingerprint parameter initialization method based on android system |
| CN111444486B (en) * | 2019-12-31 | 2022-03-22 | 深圳贝特莱电子科技股份有限公司 | Startup self-adaptive fingerprint parameter initialization method based on android system |
| CN111451623A (en) * | 2020-05-26 | 2020-07-28 | 上海法信机电设备制造有限公司 | Plasma welding seam tracking device |
| CN114998159A (en) * | 2022-08-04 | 2022-09-02 | 邹城市天晖软件科技有限公司 | Design image self-adaptive enhancement method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107203982A (en) | A kind of image processing method and device | |
| CN115311176B (en) | Night image enhancement method based on histogram equalization | |
| CN105096259B (en) | The depth value restoration methods and system of depth image | |
| CN113313657B (en) | Unsupervised learning method and system for low-illumination image enhancement | |
| CN108805829B (en) | Image data processing method, device, equipment and computer readable storage medium | |
| CN108509819A (en) | A kind of Quick Response Code binarization method even for uneven illumination | |
| CN107680056B (en) | Image processing method and device | |
| CN102147857A (en) | Image processing method for detecting similar round by using improved hough transformation | |
| CN101408973A (en) | Method of image processing and device thereof | |
| CN113706534B (en) | Injection molding product defect detection method based on multi-ray analysis | |
| CN103778599A (en) | Image processing method and system thereof | |
| CN110969046B (en) | Face recognition method, face recognition device and computer-readable storage medium | |
| CN103226824B (en) | Maintain the video Redirectional system of vision significance | |
| CN102855617A (en) | Method and system for processing adaptive images | |
| CN102096802A (en) | Face detection method and device | |
| CN111062331B (en) | Image mosaic detection method and device, electronic equipment and storage medium | |
| WO2021118463A1 (en) | Defect detection in image space | |
| CN108665428A (en) | Image enchancing method, device, equipment and storage medium | |
| CN112348763A (en) | Image enhancement method, device, electronic equipment and medium | |
| CN106096491A (en) | The automatic identifying method of the microaneurysm in color fundus image | |
| CN109101985A (en) | It is a kind of based on adaptive neighborhood test image mismatch point to elimination method | |
| CN111275642A (en) | Low-illumination image enhancement method based on significant foreground content | |
| CN103824250A (en) | GPU-based image tone mapping method | |
| CN107452008A (en) | Method for detecting image edge and device | |
| CN113393394B (en) | Low-illumination gray level image enhancement method and device based on gamma conversion and storage medium |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170926 |