CN104112255A - Rain removing method and system for single image - Google Patents
Rain removing method and system for single image Download PDFInfo
- Publication number
- CN104112255A CN104112255A CN201410277377.1A CN201410277377A CN104112255A CN 104112255 A CN104112255 A CN 104112255A CN 201410277377 A CN201410277377 A CN 201410277377A CN 104112255 A CN104112255 A CN 104112255A
- Authority
- CN
- China
- Prior art keywords
- rain
- image
- color space
- component
- converted
- 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
Landscapes
- Color Image Communication Systems (AREA)
- Image Processing (AREA)
- Facsimile Image Signal Circuits (AREA)
Abstract
The invention relates to a rain removing method and system for a single image. The method comprises the following steps: converting an RGB color image into a YIQ color space; extracting a Y component expressing the image brightness in the YIQ color space; carrying out rain removing processing on the Y component; combining the Y component processed by rain removing with an I component and a Q component and converting the YIQ unit after combination into a CMYK color space so as to obtain a CMYK image after the rain removing process. With the method and system, the RGB image is converted into the YIQ color space; only the Y component is processed by rain removing and the Y component processed by rain removing is combined with I component and the Q component; and conversion is carried out to obtain an RGB image. Therefore, rain removing processing of the single color image is realized; the image color distortion is prevented; and the usage range of the rain removing algorithm of the single image is expanded. Moreover, the mode of the output image is converted into a CMYK mode and direct printing can be realized, thereby avoiding the phenomenon of distortion of the RGB image printed directly, saving the cost, and reducing the operation step.
Description
Technical field
The present invention relates to image processing field, particularly relate to a kind of single image and remove rain method and system.
Background technology
Rain has a great impact image imaging, can cause the fuzzy and information of image imaging to cover, and its direct result is that the sharpness of video image declines, and the digitized processing of video image is affected and hydraulic performance decline by this also can.The video image that polluted by raindrop is carried out to the further processing that repair process is conducive to image, comprise target detection, identification based on image, follow the trail of, cut apart and the raising of the technical feature such as monitoring.
Traditional rain algorithm that goes has a lot, as the video image based on methods such as degree of bias calculating, K mean cluster, Kalman filtering, dictionary learning and sparse coding, guiding filtering, interframe luminance differences removes rain algorithm.Wherein, single image goes rain algorithm kind a lot, carry out single image as the method by picture breakdown and remove rain, remove rain etc. by context aware, but, what traditional single image went to obtain after rain algorithm process is all gray level image, cannot process to ensure that image color is undistorted to coloured image, and output image cannot be printed.
Summary of the invention
Based on this, be necessary to remove for traditional single width the gray level image that is that rain method obtains, the problem that cannot process coloured image, provide a kind of single image to remove rain method and system, can realize coloured image is gone to rain processing, guarantee image color is undistorted, and output image can be printed.
A kind of single image goes rain method, comprises the following steps:
RGB image is converted to YIQ color space;
Extract the Y component of the presentation video brightness in described YIQ color space;
Described Y component is gone to rain processing;
To go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, obtain the CMYK image after rain.
Therein in an embodiment, describedly RGB image is converted to YIQ color space adopts matrix conversion.
Therein in an embodiment, describedly RGB image be converted to YIQ color space adopt the formula of matrix conversion to be:
Therein in an embodiment, describedly will go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, the step that obtains the CMYK image after rain comprises:
To go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to rgb color space;
Rgb color space is converted to cmyk color space, obtains the CMYK image after rain.
Therein in an embodiment, described in connection with after the YIQ formula that is converted to rgb color space be:
Described rgb color space is converted to cmyk color space, the computing formula that obtains the CMYK image after rain comprises:
C'=1-R/255
M'=1-G/255,
Y'=1-B/255
If min{C', M', Y'}=1, C'=0, M'=0, K=1, otherwise:
K=min{C',M',Y'},
A kind of single image goes rain system, comprising:
The first modular converter, for being converted to YIQ color space by RGB image;
Extraction module, for extracting the Y component of presentation video brightness of described YIQ color space;
Go rain module, for described Y component is gone to rain processing;
The second modular converter, for going Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, obtain the CMYK image after rain.
Therein in an embodiment, describedly RGB image is converted to YIQ color space adopts matrix conversion.
Therein in an embodiment, describedly RGB image be converted to YIQ color space adopt the formula of matrix conversion to be:
Therein in an embodiment, described the second modular converter is also for going Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to rgb color space; Rgb color space is converted to cmyk color space, obtains the CMYK image after rain.
Therein in an embodiment, described in connection with after the YIQ formula that is converted to rgb color space be:
Described rgb color space is converted to cmyk color space, the computing formula that obtains the CMYK image after rain comprises:
C'=1-R/255
M'=1-G/255,
Y'=1-B/255
If min{C', M', Y'}=1, C'=0, M'=0, K=1, otherwise:
K=min{C',M',Y'},
Above-mentioned single image removes rain method and system, by RGB image is converted to YIQ color space, then only Y component is gone to rain processing, to go rain Y component after treatment and I, Q component combination, be converted to RGB image, that has realized single width coloured image goes rain processing, guarantee image color is undistorted, improve the usable range that single image removes rain algorithm, and output image is converted to CMYK pattern, can directly prints, avoided direct printing RGB image to occur the phenomenon of distortion, cost-saving, reduce operation steps.
Brief description of the drawings
Fig. 1 is that in an embodiment, single image removes the process flow diagram of rain method;
Fig. 2 is the schematic diagram of raindrop impact;
Fig. 3 is that in an embodiment, single image removes the structured flowchart of rain system.
Embodiment
In order to make object of the present invention, technical scheme and advantage clearer, below in conjunction with drawings and Examples, the present invention is further elaborated.Should be appreciated that specific embodiment described herein, only in order to explain the present invention, is not intended to limit the present invention.
Fig. 1 is that in an embodiment, single image removes the process flow diagram of rain method.As shown in Figure 1, this RGB (Red-Green-Blue, R-G-B) color image processing method, comprises the following steps:
Step 102, is converted to YIQ color space by RGB image.
Concrete, YIQ is NTSC (National Television Standards Committee) standard television system.Y is to provide luminance signal, and I represents In-phase, and color is from orange to cyan, and Q represents Quadrature-phase, and color is from purple to yellow green.
Because the brightness of capped pixel is affected by raindrop not only, also can be subject to background influence.Consider that the camera exposure time is T, suppose that the time that raindrop during this period of time cover a certain pixel is τ, and τ is much smaller than camera exposure time T.The rain line brightness I of this pixel in time shutter T on image
brjointly determined by raindrop and background luminance, computing formula is suc as formula (1) and (2):
I
br=I
b+ΔI (2)
Wherein, E
rthe instantaneous raindrop brightness while having raindrop to cover, E
bit is the instantaneous background luminance while covering without raindrop.I
bbe the background luminance that does not have raindrop to cover in the T time, Δ I is the brightness variable quantity that affected by raindrop.The brightness of rain line higher than background luminance be mainly because raindrop in imaging because the light within the scope of Wide-angle has more been converged in the effects such as mirror-reflection, internal reflection, refraction, as shown in Figure 2, mirror-reflection
internal reflection
refraction
the brightness of rain line
because of ruddiness, green glow close with blue light frequency, the critical angle approximately equal of raindrop to three, and the variation of light intensity directly determines that the brightness of pixel changes, the mirror-reflection of adding three is the same, therefore raindrop cause brightness variation delta R, Δ G, the also approximately equal of Δ B of pixel, belong to the chromatic characteristic of raindrop.
In the present embodiment, this is converted to YIQ color space by RGB image and adopts matrix conversion.
Concrete, this is converted to YIQ color space by RGB image and adopts the formula of matrix conversion to be:
Known according to formula (2), its rgb value of the pixel not affected by raindrop remains unchanged, and the pixel intensity being affected by raindrop can change, and RGB converts to after YIQ, the brightness of Y represent pixel, i.e. and the gray-scale value of gray level image, I and Q are:
I=0.596(R
b+ΔR)-0.274(G
b+ΔG)-0.322(B
b+ΔB) (4)
Q=0.211(R
b+ΔR)-0.523(G
b+ΔG)+0.312(B
b+ΔB) (5)
In formula (4) and (5), R
b, G
b, B
brespectively the background luminance value that red, green, blue triple channel is not affected by raindrop, from the chromatic characteristic of raindrop, Δ R, Δ G, Δ B approximately equal:
I=0.596R
b-0.274G
b-0.322B
b (6)
Q=0.211R
b-0.523G
b+0.312B
b (7)
Therefore the value of I and Q passage is not subject to the impact that raindrop brightness changes, and only has Y passage influenced.
Step 104, extracts the Y component of the presentation video brightness in this YIQ color space.
Step 106, goes rain processing to this Y component.
Concrete, adopt single image to go rain algorithm to go rain processing to this Y component.Single image goes rain algorithm can comprise (the Fu Y H such as Yu-Hsiang Fu, Kang L W, Lin C W, et al.Single-frame-based rain removal via image decomposition.In:Proceeding of 2011IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) .Prague, Czech:IEEE Press, 2011:1453-1456.) and (the Kang L W such as Li-Wei Kang, Lin C W, Fu Y H.Automatic single-image-based rain streaks removal via image decomposition.Image Processing, IEEE Transactions on, 2012, 21 (4): 1742-1755.) proposed to carry out single image by the method for picture breakdown and removed rain, (the Huang D A such as De-An Huang, Kang L W, Yang M C, et al.Context-aware single image rain removal.In:Proceeding of 2012IEEE International Conference on Multimedia and Expo (ICME) .Melbourne, Australia:IEEEPress, 2012:164-169.) propose to remove rain by context aware, (the George J such as Jaina George, Bhavani S, Jaya J.Certain explorations on removal of rain streaks using morphological component analysis.International Journal of Engineering Research & Technology.2013,2 (2) .) propose to use the method for morphology constituent analysis to remove rain, (the Chen D Y such as Duan-Yu Chen, Chen C C, Kang L W.Visual depth guided image rain streaks removal via sparse coding.In:Proceeding of2012International Symposium on Intelligent Signal Processing and Communications Systems.New Taipei, Taiwan:IEEE, 2012:151-156.) remove rain by guiding filtering and sparse coding.
Step 108, will go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, obtain the CMYK image after rain.
Concrete, CMYK, also referred to as printing color pattern, is a kind of reflective color mode that relies on.Wherein, CMY is the initial of 3 kinds of printing-ink titles: cyan Cyan, magenta Magenta, yellow Yellow.K is derived from a kind of galley Key Plate that uses tusche.In theory, only need tri-kinds of ink of CMY enough, three are added together and just obtain black, but due to the restriction of technique, and result that CMY is added is actual is a kind of kermesinus.
In one embodiment, to go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, the step that obtains the CMYK image after rain comprises: will go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to rgb color space; Rgb color space is converted to cmyk color space, obtains the CMYK image after rain.
In one embodiment, should in connection with after YIQ be converted to rgb color space and adopt and ask for matrix
Inverse matrix change, obtain the RGB image after rain, its precision is high.
In one embodiment, should in connection with after the YIQ formula that is converted to rgb color space be:
Rgb color space is converted to cmyk color space, and the computing formula that obtains the CMYK image after rain comprises:
C'=1-R/255
M'=1-G/255 (9)
Y'=1-B/255
If min{C', M', Y'}=1, C'=0, M'=0, K=1, otherwise:
K=min{C',M',Y'},
Above-mentioned single image goes rain method, by RGB image is converted to YIQ color space, then only Y component is gone to rain processing, to go rain Y component after treatment and I, Q component combination, be converted to RGB image, that has realized single width coloured image goes rain processing, guarantee image color is undistorted, improve the usable range that single image removes rain algorithm, and output image is converted to CMYK pattern, can directly prints, avoided direct printing RGB image to occur the phenomenon of distortion, cost-saving, reduce operation steps.
Fig. 3 is that in an embodiment, single image removes the structured flowchart of rain system.As shown in Figure 3, this single image goes rain system, comprises the first modular converter 320, extraction module 340, removes rain module 360 and the second modular converter 380.Wherein:
The first modular converter 320 is for being converted to YIQ color space by RGB image.
In one embodiment, this is converted to YIQ color space by RGB image and adopts matrix conversion.
This is converted to YIQ color space by RGB image and adopts the formula of matrix conversion to be:
Extraction module 340 is for extracting the Y component of presentation video brightness of this YIQ color space.
Go rain module 360 for this Y component is gone to rain processing.
The second modular converter 380 is for going Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, obtain the CMYK image after rain.
The second modular converter 380 is also for going Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to rgb color space; Rgb color space is converted to cmyk color space, obtains the CMYK image after rain.
In one embodiment, should in connection with after YIQ be converted to rgb color space and adopt and ask for matrix
Inverse matrix change.
In one embodiment, should in connection with after the YIQ formula that is converted to rgb color space be:
Rgb color space is converted to cmyk color space, and the computing formula that obtains the CMYK image after rain comprises:
C'=1-R/255
M'=1-G/255(9)
Y'=1-B/255
If min{C', M', Y'}=1, C'=0, M'=0, K=1, otherwise:
K=min{C',M',Y'},
Above-mentioned single image goes rain system, by RGB image is converted to YIQ color space, then only Y component is gone to rain processing, to go rain Y component after treatment and I, Q component combination, be converted to RGB image, that has realized single width coloured image goes rain processing, guarantee image color is undistorted, improve the usable range that single image removes rain algorithm, and output image is converted to CMYK pattern, can directly prints, avoided direct printing RGB image to occur the phenomenon of distortion, cost-saving, reduce operation steps.
The above embodiment has only expressed several embodiment of the present invention, and it describes comparatively concrete and detailed, but can not therefore be interpreted as the restriction to the scope of the claims of the present invention.It should be pointed out that for the person of ordinary skill of the art, without departing from the inventive concept of the premise, can also make some distortion and improvement, these all belong to protection scope of the present invention.Therefore, the protection domain of patent of the present invention should be as the criterion with claims.
Claims (10)
1. single image goes a rain method, comprises the following steps:
RGB image is converted to YIQ color space;
Extract the Y component of the presentation video brightness in described YIQ color space;
Described Y component is gone to rain processing;
To go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, obtain the CMYK image after rain.
2. single image according to claim 1 goes rain method, it is characterized in that, described by RGB image be converted to YIQ color space adopt matrix conversion.
3. single image according to claim 2 goes rain method, it is characterized in that, describedly RGB image is converted to YIQ color space adopts the formula of matrix conversion to be:
4. single image according to claim 1 goes rain method, it is characterized in that, describedly will go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, the step that obtains the CMYK image after rain comprises:
To go Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to rgb color space;
Rgb color space is converted to cmyk color space, obtains the CMYK image after rain.
5. single image according to claim 1 goes rain method, it is characterized in that, described in connection with after the YIQ formula that is converted to rgb color space be:
Described rgb color space is converted to cmyk color space, the computing formula that obtains the CMYK image after rain comprises:
C'=1-R/255
M'=1-G/255,
Y'=1-B/255
If min{C', M', Y'}=1, C'=0, M'=0, K=1, otherwise:
K=min{C',M',Y'},
6. single image goes a rain system, it is characterized in that, comprising:
The first modular converter, for being converted to YIQ color space by RGB image;
Extraction module, for extracting the Y component of presentation video brightness of described YIQ color space;
Go rain module, for described Y component is gone to rain processing;
The second modular converter, for going Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to cmyk color space, obtain the CMYK image after rain.
7. single image according to claim 6 goes rain system, it is characterized in that, described by RGB image be converted to YIQ color space adopt matrix conversion.
8. single image according to claim 7 goes rain system, it is characterized in that, describedly RGB image is converted to YIQ color space adopts the formula of matrix conversion to be:
9. single image according to claim 6 goes rain system, it is characterized in that, described the second modular converter is also for going Y component after rain in conjunction with I and Q component, and in connection with after YIQ be converted to rgb color space; Rgb color space is converted to cmyk color space, obtains the CMYK image after rain.
10. single image according to claim 9 goes rain system, it is characterized in that, described in connection with after the YIQ formula that is converted to rgb color space be:
Described rgb color space is converted to cmyk color space, the computing formula that obtains the CMYK image after rain comprises:
C'=1-R/255
M'=1-G/255,
Y'=1-B/255
If min{C', M', Y'}=1, C'=0, M'=0, K=1, otherwise:
K=min{C',M',Y'},
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410277377.1A CN104112255A (en) | 2014-06-19 | 2014-06-19 | Rain removing method and system for single image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201410277377.1A CN104112255A (en) | 2014-06-19 | 2014-06-19 | Rain removing method and system for single image |
Publications (1)
Publication Number | Publication Date |
---|---|
CN104112255A true CN104112255A (en) | 2014-10-22 |
Family
ID=51709035
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201410277377.1A Pending CN104112255A (en) | 2014-06-19 | 2014-06-19 | Rain removing method and system for single image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN104112255A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104537622A (en) * | 2014-12-31 | 2015-04-22 | 中国科学院深圳先进技术研究院 | Method and system for removing raindrop influence in single image |
CN105184761A (en) * | 2015-08-28 | 2015-12-23 | 中国科学院深圳先进技术研究院 | Image rain removing method based on wavelet analysis and system |
CN106023112A (en) * | 2016-05-24 | 2016-10-12 | 中国科学院深圳先进技术研究院 | Image rain removing method and system based on wavelet analysis |
CN106204499A (en) * | 2016-07-26 | 2016-12-07 | 厦门大学 | Single image rain removing method based on convolutional neural networks |
CN106971377A (en) * | 2016-08-22 | 2017-07-21 | 上海海洋大学 | A kind of removing rain based on single image method decomposed based on sparse and low-rank matrix |
CN108900841A (en) * | 2018-07-10 | 2018-11-27 | 中国科学技术大学 | Method for video coding based on image rain removing algorithm |
CN109636738A (en) * | 2018-11-09 | 2019-04-16 | 温州医科大学 | The single image rain noise minimizing technology and device of double fidelity term canonical models based on wavelet transformation |
CN111399785A (en) * | 2018-12-27 | 2020-07-10 | 北大方正集团有限公司 | Color processing method, device, equipment and system of PDF (Portable document Format) file |
-
2014
- 2014-06-19 CN CN201410277377.1A patent/CN104112255A/en active Pending
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104537622A (en) * | 2014-12-31 | 2015-04-22 | 中国科学院深圳先进技术研究院 | Method and system for removing raindrop influence in single image |
CN105184761A (en) * | 2015-08-28 | 2015-12-23 | 中国科学院深圳先进技术研究院 | Image rain removing method based on wavelet analysis and system |
CN106023112A (en) * | 2016-05-24 | 2016-10-12 | 中国科学院深圳先进技术研究院 | Image rain removing method and system based on wavelet analysis |
CN106204499A (en) * | 2016-07-26 | 2016-12-07 | 厦门大学 | Single image rain removing method based on convolutional neural networks |
CN106204499B (en) * | 2016-07-26 | 2019-05-24 | 厦门大学 | Removing rain based on single image method based on convolutional neural networks |
CN106971377A (en) * | 2016-08-22 | 2017-07-21 | 上海海洋大学 | A kind of removing rain based on single image method decomposed based on sparse and low-rank matrix |
CN108900841A (en) * | 2018-07-10 | 2018-11-27 | 中国科学技术大学 | Method for video coding based on image rain removing algorithm |
CN109636738A (en) * | 2018-11-09 | 2019-04-16 | 温州医科大学 | The single image rain noise minimizing technology and device of double fidelity term canonical models based on wavelet transformation |
CN109636738B (en) * | 2018-11-09 | 2019-10-01 | 温州医科大学 | The single image rain noise minimizing technology and device of double fidelity term canonical models based on wavelet transformation |
CN111399785A (en) * | 2018-12-27 | 2020-07-10 | 北大方正集团有限公司 | Color processing method, device, equipment and system of PDF (Portable document Format) file |
CN111399785B (en) * | 2018-12-27 | 2021-08-27 | 北大方正集团有限公司 | Color processing method, device, equipment and system of PDF (Portable document Format) file |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN104112255A (en) | Rain removing method and system for single image | |
CN104112259A (en) | Rain removing method and system for single image | |
CN103327220B (en) | With green channel for the denoising method guided on low-light (level) Bayer image | |
CN101930596A (en) | Color constancy method in two steps under a kind of complex illumination | |
CN104618700B (en) | Enhanced display method for color high dynamic range image | |
US8565531B2 (en) | Edge detection for mixed raster content (MRC) images for improved compression and image quality | |
CN105205792A (en) | Underwater image enhancement method based on brightness and chrominance separation | |
CN103065334A (en) | Color cast detection and correction method and device based on HSV (Hue, Saturation, Value) color space | |
Lee et al. | Color image enhancement using histogram equalization method without changing hue and saturation | |
CN101212693A (en) | White balancing method and image adjusting device | |
CN102129682B (en) | A kind of prospect background region partitioning method, system | |
CN107895357A (en) | A kind of real-time water surface thick fog scene image Enhancement Method based on FPGA | |
CN109166135B (en) | Blue screen keying method based on HSV color space and chroma key | |
CN106340025A (en) | Background replacement visual communication method based on chromatic adaptation transformation | |
CN108960259A (en) | A kind of license plate preprocess method based on HSV | |
CN109658367A (en) | Image interfusion method based on Color transfer | |
CN103747222A (en) | Method and apparatus for suppressing color artifact of image | |
CN111612705B (en) | Background image eliminating method for enhancing OCR performance | |
KR102158633B1 (en) | A method for extraction of a registered seal impression from a document | |
CN104112254A (en) | Method and system for processing RGB color image | |
CN104112258A (en) | Method and system for realizing RGB color image processing | |
CN111611940A (en) | Rapid video face recognition method based on big data processing | |
Kim et al. | Automatic detection and correction of purple fringing using the gradient information and desaturation | |
CN105741248A (en) | Method for removing hazed and degraded part in image | |
CN101222572B (en) | White balance processing equipment |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20141022 |
|
RJ01 | Rejection of invention patent application after publication |