CN105976336A - Fuzzy repair method of video image - Google Patents
Fuzzy repair method of video image Download PDFInfo
- Publication number
- CN105976336A CN105976336A CN201610305079.8A CN201610305079A CN105976336A CN 105976336 A CN105976336 A CN 105976336A CN 201610305079 A CN201610305079 A CN 201610305079A CN 105976336 A CN105976336 A CN 105976336A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- threshold
- white space
- blank
- 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
- 238000000034 method Methods 0.000 title claims abstract description 26
- 230000008439 repair process Effects 0.000 title abstract description 15
- 239000013589 supplement Substances 0.000 claims description 3
- 230000008034 disappearance Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 230000002411 adverse Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000003384 imaging method Methods 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
- G06T5/77—Retouching; Inpainting; Scratch removal
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Image Processing (AREA)
Abstract
The invention discloses a fuzzy repair method of a video image. The method comprises the following steps that S1) a frame image with a local fuzzy part is obtained; S2) the local fuzzy part is segmented from the frame image to obtain an image to be repaired; S3) the image to be repaired is converted into a pixel coordinate, a blank area is formed corresponding to the segmented local fuzzy part in the pixel coordinate, and part beyond the blank area serves as a reference area; S4) a first threshold is preset; and S5) a blank pixel point in the edge in the blank area is selected, reference pixel points are obtained from the reference area according to the first threshold, and the average value of the reference points serves as the pixel value of the blank pixel point. The fuzzy repair method of the video image is high in the automatic degree and objectivity and low in dependence on human.
Description
Technical field
The present invention relates to technical field of video image processing, particularly relate to a kind of video image and obscure restorative procedure.
Background technology
Along with the development of electronic imaging technology, various video image demonstration equipments in the life of people without
Hole does not enters.Video image demonstration equipment is used for demonstration video or image, and the essence of video is image
Dynamic play, so, video image demonstration in, image be basis be also core.
One of source of image is to be shot actual scene by picture pick-up device.In shooting process, by
In the movement of picture pick-up device or the movement of actual scene easily according to becoming image blurring, even Cheng work has shot
The image become also easily occurs fuzzy due to a variety of causes in processing procedure, so, image blurring part
Reparation is problem very important in image processing techniques.
Summary of the invention
The technical problem existed based on background technology, the present invention proposes a kind of video image and obscures restorative procedure.
A kind of video image that the present invention proposes obscures restorative procedure, comprises the following steps:
S1, obtain with the picture image of On Local Fuzzy；
S2, On Local Fuzzy part is split away from picture image, it is thus achieved that image to be repaired；
S3, image to be repaired is converted to pixel coordinate, the corresponding On Local Fuzzy split away in pixel coordinate
Part formed white space, white space using outer portion as reference zone, each pixel picture in white space
Element value is empty set；
S4, preset first threshold value；
S5, select in white space a blank pixel point on edge, according to first threshold from reference area
Territory obtains selects nearest multiple pixels as reference image vegetarian refreshments apart from this blank pixel, and calculates multiple reference
The average of pixel is as the pixel value of blank pixel point；
S6, repeat above step, the blank pixel point in boundary line, edge in white space is carried out pixel value
Fill, then update white space and reference zone；
S7, repetition step S5 and S6, until obtaining the final pixel coordinate that white space reparation completes；
S8, final pixel coordinate is converted into portrait as reparation after picture image.
Preferably, step S9 is also included: the picture image after repairing enters with the image to be repaired in step S2
Row contrast, determines that image supplements part, and part supplementary to image is sharpened process.
Preferably, in step S4, first threshold is number threshold value；In step S5, reference image vegetarian refreshments is reference
First threshold the pixel that this blank pixel point of region distance is nearest.
Preferably, in step S4, first threshold is more than 1 and less than 10.
Preferably, first threshold is equal to 3 or 5.
Preferably, in step S4, first threshold is distance threshold；In step S5, reference image vegetarian refreshments is reference
This blank pixel point distance of region distance is less than the pixel of first threshold.
Preferably, also step S4 is included particularly as follows: calculate each blank pixel point on white space boundary line respectively
The distance of nearest pixel comparing in distance reference region, using the maximum range value that obtains as first
Threshold value.
The present invention propose a kind of video image obscure restorative procedure, by by On Local Fuzzy part from picture figure
Split away in Xiang, fuzzy repairing is converted to image disappearance and repairs.So, it is to avoid image repair process
In dependence to blurred portions, it is to avoid the mistake of blurred portions is for the adverse effect of image repair.
In the present invention, image to be repaired is converted to pixel coordinate so that image pixel value etc. more have as changing,
The most also image repair is converted to the filling of blank pixel point so that image repair work more has as changing,
Reduce image repair difficulty.
In the present invention, by the average calculating reference image vegetarian refreshments, blank pixel point is carried out pixel value filling.Phase
For fuzzy region, the pixel value of reference image vegetarian refreshments is more accurate, and it is as the reference specimen of repair,
Be conducive to improving the precision of image repair.
Additionally, a kind of video image that the present invention provides obscures restorative procedure, automaticity is high, manually depends on
Relying low, objectivity is strong.
Accompanying drawing explanation
Fig. 1 is that a kind of video image that the present invention proposes obscures restorative procedure flow chart.
Detailed description of the invention
Embodiment 1
With reference to Fig. 1, a kind of video image that the present invention proposes obscures restorative procedure, comprises the following steps.
S1, obtain with the picture image of On Local Fuzzy as image process target.
S2, On Local Fuzzy part is split away from picture image, it is thus achieved that image to be repaired.On Local Fuzzy
After part is split away, image correspondence blurred portions to be repaired is blank, so by fuzzy reparation in this step
Be converted to disappearance repair.
S3, image to be repaired is converted to pixel coordinate, the corresponding On Local Fuzzy split away in pixel coordinate
Part formed white space, white space using outer portion as reference zone, each pixel picture in white space
Element value is empty set.Convert the image into pixel coordinate so that image pixel value etc. more have as changing, and are conducive to
The precision of subsequent treatment and efficiency.
S4, preset first threshold value.First threshold is number threshold value, specifically can be more than 1 and less than 10.
S5, select in white space a blank pixel point on edge, choose reference zone apart from this sky
White pixel selects nearest first threshold pixel as reference image vegetarian refreshments, and calculates multiple reference image vegetarian refreshments
Average is as the pixel value of blank pixel point.In present embodiment, first threshold is equal to 3 or 5, i.e. reference
The quantity of pixel is 3 or 5.
S6, repeat above step, the blank pixel point in boundary line, edge in white space is carried out pixel value
Fill, then update white space and reference zone.
In present embodiment, formulate boundary line, edge by ecto-entad, then by step S5 to edge
Each blank spot in boundary line is sequentially filled.It should be noted that in present embodiment, filling edge circle
During blank spot on line, do not use the data of the pixel calculating acquisition in same boundary line, edge, i.e. reference
Pixel does not select the point in boundary line, edge, to improve image repair precision.
S7, repetition step S5 and S6, until obtaining the final pixel coordinate that white space reparation completes.
S8, final pixel coordinate is converted into portrait as reparation after picture image.
S9, will repair after picture image contrast with the image to be repaired in step S2, determine that image is mended
Fill part, and part supplementary to image is sharpened process.
In present embodiment, by mean value computation, the lack part of image to be repaired is filled with, so,
It is relatively big that image supplements obscure portions degree, by Edge contrast, can improve image outline definition.
Embodiment 2
The present embodiment is step S4 and step S5 with the difference of embodiment 1.
In the present embodiment, in step S4, first threshold is distance threshold, and step S4 is particularly as follows: count respectively
Calculate the distance of nearest pixel in each blank pixel point distance reference region on white space boundary line and compare
Relatively, using the maximum range value of acquisition as first threshold.
Step S5, particularly as follows: select in white space a blank pixel point on edge, chooses reference area
The distance pixel less than first threshold is selected as reference image vegetarian refreshments apart from this blank pixel in territory, and calculates multiple
The average of reference image vegetarian refreshments is as the pixel value of blank pixel point.
Integrating step S4 can ensure in the present embodiment, for any blank pixel point, at least can obtain a ginseng
Examine pixel, thus ensure that each blank pixel point can complete to repair.
The above, the only present invention preferably detailed description of the invention, but protection scope of the present invention not office
Being limited to this, any those familiar with the art is in the technical scope that the invention discloses, according to this
The technical scheme of invention and inventive concept thereof in addition equivalent or change, all should contain the protection in the present invention
Within the scope of.
Claims (7)
1. a video image obscures restorative procedure, it is characterised in that comprise the following steps:
S1, obtain with the picture image of On Local Fuzzy；
S2, On Local Fuzzy part is split away from picture image, it is thus achieved that image to be repaired；
S3, image to be repaired is converted to pixel coordinate, the corresponding On Local Fuzzy split away in pixel coordinate
Part formed white space, white space using outer portion as reference zone, each pixel picture in white space
Element value is empty set；
S4, preset first threshold value；
S5, select in white space a blank pixel point on edge, according to first threshold from reference area
Territory obtains selects nearest multiple pixels as reference image vegetarian refreshments apart from this blank pixel, and calculates multiple reference
The average of pixel is as the pixel value of blank pixel point；
S6, repeat above step, the blank pixel point in boundary line, edge in white space is carried out pixel value
Fill, then update white space and reference zone；
S7, repetition step S5 and S6, until obtaining the final pixel coordinate that white space reparation completes；
S8, final pixel coordinate is converted into portrait as reparation after picture image.
2. video image as claimed in claim 1 obscures restorative procedure, it is characterised in that also include step
S9: the picture image after repairing contrasts with the image to be repaired in step S2, determines that image supplements portion
Point, and partly it is sharpened process to image is supplementary.
3. video image as claimed in claim 1 obscures restorative procedure, it is characterised in that in step S4
First threshold is number threshold value；In step S5, reference image vegetarian refreshments is reference zone apart from this blank pixel point
Near first threshold pixel.
4. video image as claimed in claim 3 obscures restorative procedure, it is characterised in that in step S4,
First threshold is more than 1 and less than 10.
5. video image as claimed in claim 4 obscures restorative procedure, it is characterised in that first threshold etc.
In 3 or 5.
6. video image as claimed in claim 1 obscures restorative procedure, it is characterised in that in step S4
First threshold is distance threshold；In step S5, reference image vegetarian refreshments be reference zone apart from this blank pixel point away from
From the pixel less than first threshold.
7. video image as claimed in claim 6 obscures restorative procedure, it is characterised in that also include step
S4 is particularly as follows: calculate on white space boundary line in each blank pixel point distance reference region pixel recently respectively
Point distance and compare, using obtain maximum range value as first threshold.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610305079.8A CN105976336A (en) | 2016-05-06 | 2016-05-06 | Fuzzy repair method of video image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610305079.8A CN105976336A (en) | 2016-05-06 | 2016-05-06 | Fuzzy repair method of video image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105976336A true CN105976336A (en) | 2016-09-28 |
Family
ID=56992897
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610305079.8A Pending CN105976336A (en) | 2016-05-06 | 2016-05-06 | Fuzzy repair method of video image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105976336A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730457A (en) * | 2017-08-28 | 2018-02-23 | 广东数相智能科技有限公司 | A kind of image completion method, apparatus, electronic equipment and storage medium |
| CN107833196A (en) * | 2017-12-19 | 2018-03-23 | 蒙城县望槐信息科技有限责任公司 | A kind of image deflects point circle restorative procedure |
| CN108022224A (en) * | 2017-12-19 | 2018-05-11 | 蒙城县望槐信息科技有限责任公司 | A kind of image repair system |
| CN108596862A (en) * | 2018-05-29 | 2018-09-28 | 深圳点扬科技有限公司 | Processing method for excluding infrared thermal imagery panorama sketch interference source |
| WO2020107836A1 (en) * | 2018-11-30 | 2020-06-04 | 平安科技（深圳）有限公司 | Word2vec-based incomplete user persona completion method and related device |
| CN112083864A (en) * | 2020-09-18 | 2020-12-15 | 深圳铂睿智恒科技有限公司 | Method, device and equipment for processing object to be deleted |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101321241A (en) * | 2008-07-04 | 2008-12-10 | 浙江大学 | Interactive video moving object elimination method |
| CN101459843A (en) * | 2008-12-31 | 2009-06-17 | 浙江师范大学 | Method for precisely extracting broken content region in video sequence |
| CN104361565A (en) * | 2014-12-05 | 2015-02-18 | 华东理工大学 | Method for automatically detecting and repairing content of scrawled digital images |
-
2016
- 2016-05-06 CN CN201610305079.8A patent/CN105976336A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101321241A (en) * | 2008-07-04 | 2008-12-10 | 浙江大学 | Interactive video moving object elimination method |
| CN101459843A (en) * | 2008-12-31 | 2009-06-17 | 浙江师范大学 | Method for precisely extracting broken content region in video sequence |
| CN104361565A (en) * | 2014-12-05 | 2015-02-18 | 华东理工大学 | Method for automatically detecting and repairing content of scrawled digital images |
Non-Patent Citations (2)
| Title |
|---|
| 周春霞: "新颖的图像修复算法研究", 《中国优秀硕士学位论文全文数据库信息科技辑》 * |
| 王伟: "基于单幅图像的模糊去除及质量评价研究", 《中国博士学位论文全文数据库信息科技辑》 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107730457A (en) * | 2017-08-28 | 2018-02-23 | 广东数相智能科技有限公司 | A kind of image completion method, apparatus, electronic equipment and storage medium |
| CN107730457B (en) * | 2017-08-28 | 2020-02-14 | 广东数相智能科技有限公司 | Image completion method and device, electronic equipment and storage medium |
| CN107833196A (en) * | 2017-12-19 | 2018-03-23 | 蒙城县望槐信息科技有限责任公司 | A kind of image deflects point circle restorative procedure |
| CN108022224A (en) * | 2017-12-19 | 2018-05-11 | 蒙城县望槐信息科技有限责任公司 | A kind of image repair system |
| CN108596862A (en) * | 2018-05-29 | 2018-09-28 | 深圳点扬科技有限公司 | Processing method for excluding infrared thermal imagery panorama sketch interference source |
| WO2020107836A1 (en) * | 2018-11-30 | 2020-06-04 | 平安科技（深圳）有限公司 | Word2vec-based incomplete user persona completion method and related device |
| CN112083864A (en) * | 2020-09-18 | 2020-12-15 | 深圳铂睿智恒科技有限公司 | Method, device and equipment for processing object to be deleted |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105976336A (en) | Fuzzy repair method of video image | |
| CN109859278A (en) | The scaling method and calibration system joined outside in-vehicle camera system camera | |
| CN108648221A (en) | A kind of depth map cavity restorative procedure based on mixed filtering | |
| CN106707674A (en) | Automatic focusing method of projection equipment and the projection equipment | |
| CN104809698A (en) | Kinect depth image inpainting method based on improved trilateral filtering | |
| WO2007052191A2 (en) | Filling in depth results | |
| CN111080776B (en) | Human body action three-dimensional data acquisition and reproduction processing method and system | |
| CN105469386B (en) | A kind of method and device of determining stereoscopic camera height and pitch angle | |
| KR20150081837A (en) | Real time dynamic non planar projection apparatus and method | |
| CN111179195B (en) | Depth image cavity filling method and device, electronic equipment and storage medium thereof | |
| CN109474814A (en) | Two-dimensional calibration method, projector and the calibration system of projector | |
| CN104111038A (en) | Method for using phase fusion algorithm to repair phase error caused by saturation | |
| CN107680039B (en) | Point cloud splicing method and system based on white light scanner | |
| CN108022223A (en) | A kind of tone mapping method based on the processing fusion of logarithmic mapping function piecemeal | |
| CN106570907A (en) | Camera calibrating method and device | |
| CN106815832B (en) | A kind of steel mesh automatic image registration method and system of surface mounting technology | |
| CN106600549A (en) | Method and device for correcting fisheye image | |
| CN110738731A (en) | 3D reconstruction method and system for binocular vision | |
| CN110763306A (en) | Monocular vision-based liquid level measurement system and method | |
| CN103778607B (en) | A kind of method for correcting image | |
| CN104574312A (en) | Method and device of calculating center of circle for target image | |
| CN109493426B (en) | Monocular imaging-based three-dimensional reconstruction method and system for blast furnace charge level | |
| CN116934871B (en) | Multi-objective system calibration method, system and storage medium based on calibration object | |
| CN112132771B (en) | Multi-focus image fusion method based on light field imaging | |
| CN109587463A (en) | Calibration method, projector and the calibration system of projector |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | 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 |
Application publication date: 20160928 |
|
| RJ01 | Rejection of invention patent application after publication |