CN107622471A - A kind of adaptive photographic quality bearing calibration - Google Patents
A kind of adaptive photographic quality bearing calibration Download PDFInfo
- Publication number
- CN107622471A CN107622471A CN201710782618.1A CN201710782618A CN107622471A CN 107622471 A CN107622471 A CN 107622471A CN 201710782618 A CN201710782618 A CN 201710782618A CN 107622471 A CN107622471 A CN 107622471A
- Authority
- CN
- China
- Prior art keywords
- quality
- photo
- low
- color
- photos
- 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
- 230000003044 adaptive effect Effects 0.000 title claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 15
- 238000013441 quality evaluation Methods 0.000 claims abstract description 10
- 238000012546 transfer Methods 0.000 claims abstract description 5
- 238000011156 evaluation Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 abstract description 35
- 239000011159 matrix material Substances 0.000 description 4
- 238000010586 diagram Methods 0.000 description 2
- 230000003760 hair shine Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000013508 migration Methods 0.000 description 1
- 230000005012 migration Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a kind of adaptive photographic quality bearing calibration, belong to digital image processing field.This method key step includes：Pending photo is divided into high-quality photos and the class of low quality photo two using image quality evaluation index；Color balance processing is carried out to high-quality photos；High-quality photos after being handled using color balance carry out color transfer processing as reference to low quality photo.The present invention adaptively can carry out colour correction processing to photochrome collection so that the photo after processing preserves color consistency, and this method does not need manual intervention arrange parameter, can apply to the fields such as batch photo automation colour correction.
Description
Technical field
The present invention relates to a kind of photographic quality bearing calibration, and in particular to a kind of adaptive photographic quality bearing calibration,
Belong to digital image processing field.
Background technology
With the popularization of the imaging devices such as digital camera, smart mobile phone with camera, people can easily shoot very much
Photo, when especially shooting photo in tourist attractions, it will usually very multiple pictures are shot in different angles, different focal lengths, by
In the influence of ambient lighting, the automatic arrange parameter of camera etc., these different photos shot in same place, often occur
The inconsistent phenomenon of color.
Many different image color correction methods existing at present, auto color regulation (Auto Color
Adjustment) technology is a kind of color correcting method being widely studied with application, but this kind of method is all respectively for single
Open photo and carry out colour correction processing, do not account for the relevance between multiple pictures color.The colour correction side manually participated in
Method is by photographer's extensive use, but this kind of method needs more professional knowledge, and workload is very big, is not suitable for batch and shines
Piece colour correction is handled.
Traditional image color correction does not account for the relevance between multiple pictures color either or needs artificial adjust
The color of every photo is saved to reach the purpose of color consistency, these reality that can all limit this kind of color correcting method should
With.
The content of the invention
In view of the deficiencies in the prior art, can be adaptive the invention provides a kind of adaptive photographic quality bearing calibration
Answer ground to carry out colour correction processing to image, each photo can be made to keep color consistency.
A kind of adaptive photographic quality bearing calibration provided by the invention, comprises the following steps：
Step 1：Using image quality evaluation index by pending photograph collection I={ I1,I2,I3,…,InBe divided into it is high-quality
Measure photograph collection IHigh={ IHigh(1),IHigh(2),IHigh(3),…,IHigh(s)And low quality photograph collection ILow={ ILow(1),ILow(2),
ILow(3),…,ILow(t)Two classes.
The step 1 includes：
A, the image quality evaluation values of each photo are calculated, are designated as IQA={ IQA1,IQA2,IQA3,…,IQAn, and obtain
Take the median Median of these evaluations of estimate；
B, it is high-quality photos by photograph tags of the image quality evaluation values more than or equal to Median, picture quality is commented
Photograph tags of the value less than Median are low quality photo.
Step 2：To high-quality photos IHigh={ IHigh(1),IHigh(2),IHigh(3),…,IHigh(s)Carry out at color balance
Reason, obtains the photo I after colour correctionCorrection={ ICorrection(1),ICorrection(2),ICorrection(3),…,
ICorrection(s)}。
Step 3：To low quality photo ILow={ ILow(1),ILow(2),ILow(3),…,ILow(t), first after colour correction
High-quality photos collection ICorrection={ ICorrection(1),ICorrection(2),ICorrection(3),…,ICorrection(s)In find with
The most photo of its match point, then by its color transfer to low quality photo, reach the purpose of colour correction；
The beneficial effects of the invention are as follows：Colour correction processing adaptively can be carried out to photochrome collection so that processing
Photo afterwards preserves color consistency, and this method does not need manual intervention arrange parameter, can apply to the automation of batch photo
The fields such as colour correction.
Brief description of the drawings
Fig. 1 is a kind of schematic diagram of adaptive photographic quality bearing calibration of the present invention.
Embodiment
In order that technical scheme and advantage become apparent from, it is right below in conjunction with the accompanying drawing in the embodiment of the present invention
Technical scheme completely clearly illustrate in inventive embodiments.
The method of the invention includes three steps：Pending photograph collection is divided into height using image quality evaluation index
Quality photographs collection and the class of low quality photograph collection two, high-quality photos are carried out with color balance processing, color is carried out to low quality photo
Color migration process.Fig. 1 gives the schematic diagram of the inventive method.
Step 1：Pending photograph collection is divided into high-quality photos collection using image quality evaluation index and low quality is shone
The class of piece collection two.
Input pending photograph collection I={ I1,I2,I3,…,In, calculate IiThe picture quality of (i ∈ [1,2,3 ..., n])
Evaluation of estimate IQAi, calculation formula is as follows：
IQAi=α Contrasti+β·Sharpnessi (1)
In formula (1), ContrastiRepresent photo IiContrast evaluation of estimate, SharpnessiRepresent photo IiAcutance comment
Value, α, β are corresponding weights, in this example, α=0.5, β=0.5.
ContrastiCalculation formula be：
In formula (2), YiRepresent photo IiY-component in YCbCr color spaces, YiIt is divided into p × q local window, window
Mouth Yi(a,b)In pixel value maximum be Yi(max,a,b), window Yi(a,b)In pixel value minimum value be Yi(min,a,b), δ is very little
Constant, avoid the occurrence of denominator be 0 situation.
SharpnessiCalculation formula be：
In formula (3), EiRepresent YiMarginal information, EiIt is divided into p × q local window, window Ei(a,b)In maximum
For Ei(max,a,b), window Ei(a,b)In minimum value be Ei(min,a,b), δ is the constant of very little, avoids the occurrence of the situation that denominator is 0.
After the image quality evaluation values for having calculated all photos, their median Median is obtained, picture quality is commented
Photograph tags of the value more than or equal to Median are high-quality photos IHigh={ IHigh(1),IHigh(2),IHigh(3),…,
IHigh(s), it is low quality photo I by photograph tags of the image quality evaluation values less than MedianLow={ ILow(1),ILow(2),
ILow(3),…,ILow(t), wherein s+t=n.
Step 2：To high-quality photos IHigh={ IHigh(1),IHigh(2),IHigh(3),…,IHigh(s)Carry out at color balance
Reason.
Specific method is：
A, the SIFT feature of each photo is extracted；
B, photo I is matchedHigh(i)And IHigh(j)Characteristic point between (wherein i, j ∈ [1,2 ..., s], i ≠ j), matching knot
Structure is stored in the matrix M that size is k × s × 31(i) in, k is the quantity that photo describes characteristic point in scene, and s shines for high quality
The quantity of piece, 3 represent to store the information of three color components respectively；
C, for matrix M1(i), in every a line, all nonzero values are found out, calculate their average value, and are substituted
Foregoing nonzero value, new matrix are designated as M2(i)；
D, for every photo IHigh(i), linear transformation T (i) is calculated, T (i) meets M2(i)=M1(i)·T(i)；
E, for every photo IHigh(i), calculate the image I after linear transformationTrans(i)=IHigh(i)·T(i)；
F, I is calculatedTrans(i)Histogram, with the histogram to IHigh(i)Histogram Matching processing is carried out, obtains color school
Photo I after justCorrection(i)。
Step 3：To low quality photo ILow={ ILow(1),ILow(2),ILow(3),…,ILow(t), first after colour correction
High-quality photos collection ICorrection={ ICorrection(1),ICorrection(2),ICorrection(3),…,ICorrection(s)In find with
The most photo of its match point, then by its color transfer to low quality photo, reach the purpose of colour correction；
The step 3 includes：
A, the SIFT feature of each photo is extracted；
B, photo I is matchedLow(j)And ICorrection(i)Spy between (wherein j ∈ [1,2 ..., t], i ∈ [1,2 ..., s])
Point is levied, is obtained and photo ILow(j)The most photo I of match pointCorrection(h(j)), corresponding match point is respectively stored in matrix
MjAnd Mh(j)In；
C, for photo ILow(j), linear transformation T (j) is calculated, T (j) meets Mh(j)=Mj·T(j)；
D, I is calculatedTrans(j)Histogram, with the histogram to ILow(j)Histogram Matching processing is carried out, obtains colour correction
Photo I afterwardsCorrection(j)。
Described above, only presently preferred embodiments of the present invention, protection scope of the present invention are not limited thereto, in the present invention
In the technical scope of exposure, equivalent substitution or change that technique according to the invention scheme and inventive concept are made, all Ying Ben
Within the protection domain of invention.
Claims (4)
1. a kind of adaptive photographic quality bearing calibration, it is characterised in that methods described includes：
Step 1), pending photo is divided into high-quality photos and the class of low quality photo two using image quality evaluation index；
Step 2), color balance processing is carried out to high-quality photos；
Step 3), the high-quality photos after being handled using color balance carry out color transfer processing as reference to low quality photo.
A kind of 2. adaptive photographic quality bearing calibration according to claim 1, it is characterised in that：Step 1) utilization pair
Total quality evaluation is carried out to image than the weighted sum of degree evaluation of estimate and acutance evaluation of estimate, and is classified as high quality graphic and low
The class of quality image two.
A kind of 3. adaptive photographic quality bearing calibration according to claim 1, it is characterised in that：Step 2) is to high-quality
Measure photo and carry out color balance processing.
A kind of 4. adaptive photographic quality bearing calibration according to claim 1, it is characterised in that：Step 3) is with color
High-quality photos after Balance Treatment are reference, and color transfer processing is carried out to low quality photo.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710782618.1A CN107622471A (en) | 2017-09-04 | 2017-09-04 | A kind of adaptive photographic quality bearing calibration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710782618.1A CN107622471A (en) | 2017-09-04 | 2017-09-04 | A kind of adaptive photographic quality bearing calibration |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107622471A true CN107622471A (en) | 2018-01-23 |
Family
ID=61089188
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710782618.1A Pending CN107622471A (en) | 2017-09-04 | 2017-09-04 | A kind of adaptive photographic quality bearing calibration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107622471A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107608643A (en) * | 2017-09-14 | 2018-01-19 | 四川长虹电器股份有限公司 | Multi dimensional analysis, identification and optimization method based on low quality photo |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007087147A (en) * | 2005-09-22 | 2007-04-05 | Seiko Epson Corp | Image retouching method, image retouching device, and image retouching program |
| US20080002905A1 (en) * | 2006-06-30 | 2008-01-03 | Brother Kogyo Kabushiki Kaisha | Image processing method |
| WO2014185714A1 (en) * | 2013-05-15 | 2014-11-20 | 세종대학교산학협력단 | Method for improving medical image quality and apparatus therefor |
-
2017
- 2017-09-04 CN CN201710782618.1A patent/CN107622471A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007087147A (en) * | 2005-09-22 | 2007-04-05 | Seiko Epson Corp | Image retouching method, image retouching device, and image retouching program |
| US20080002905A1 (en) * | 2006-06-30 | 2008-01-03 | Brother Kogyo Kabushiki Kaisha | Image processing method |
| WO2014185714A1 (en) * | 2013-05-15 | 2014-11-20 | 세종대학교산학협력단 | Method for improving medical image quality and apparatus therefor |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107608643A (en) * | 2017-09-14 | 2018-01-19 | 四川长虹电器股份有限公司 | Multi dimensional analysis, identification and optimization method based on low quality photo |
| CN107608643B (en) * | 2017-09-14 | 2020-04-28 | 四川长虹电器股份有限公司 | Multi-dimensional analysis, identification and optimization method based on low-quality photos |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109068056B (en) | An electronic device, a filter processing method for capturing an image, and a storage medium | |
| CN112565636B (en) | Image processing method, device, equipment and storage medium | |
| CN100515042C (en) | Multiple exposure image intensifying method | |
| CN104717432B (en) | Handle method, image processing equipment and the digital camera of one group of input picture | |
| WO2019233341A1 (en) | Image processing method and apparatus, computer readable storage medium, and computer device | |
| CN100591101C (en) | Method for automatically adjusting photographing parameters according to photographing operation habit of user | |
| CN106683147B (en) | A method for blurring the background of an image | |
| Safonov et al. | Adaptive image processing algorithms for printing | |
| CN1577396A (en) | A system and process for generating high dynamic range images from multiple exposures of a moving scene | |
| CN111292246A (en) | Image color correction method, storage medium, and endoscope | |
| US20150317510A1 (en) | Rating photos for tasks based on content and adjacent signals | |
| CN110335221A (en) | A multi-exposure image fusion method based on unsupervised learning | |
| CN108764371A (en) | Image processing method, device, computer-readable storage medium, and electronic device | |
| WO2021051304A1 (en) | Shutter speed adjustment and safe shutter calibration methods, portable device and unmanned aerial vehicle | |
| WO2023000878A1 (en) | Photographing method and apparatus, and controller, device and computer-readable storage medium | |
| CN110881103B (en) | Focusing control method and device, electronic equipment and computer readable storage medium | |
| WO2022206353A1 (en) | Image processing method, photographic apparatus, image processing apparatus and readable storage medium | |
| CN114331835A (en) | Panoramic image splicing method and device based on optimal mapping matrix | |
| CN111083348A (en) | Mobile terminal, photographing method thereof and computer storage medium | |
| CN107622471A (en) | A kind of adaptive photographic quality bearing calibration | |
| CN110246162A (en) | A kind of total focus light field image composing method and system | |
| CN108270914A (en) | A kind of Intelligent photographing method and device, intelligent terminal | |
| CN118570590B (en) | Simulation method, device, equipment and medium for image printing and photographing process | |
| CN111294502A (en) | Photographing method, device, equipment and storage medium with photographing function | |
| CN110533729B (en) | Intelligent terminal, pixel processing method and computer readable 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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180123 |