CN1728181A - Automatic method for recovering blurred digital image caused by movement - Google Patents
Automatic method for recovering blurred digital image caused by movement Download PDFInfo
- Publication number
- CN1728181A CN1728181A CN 200510016521 CN200510016521A CN1728181A CN 1728181 A CN1728181 A CN 1728181A CN 200510016521 CN200510016521 CN 200510016521 CN 200510016521 A CN200510016521 A CN 200510016521A CN 1728181 A CN1728181 A CN 1728181A
- Authority
- CN
- China
- Prior art keywords
- pixel
- image
- image file
- anglec
- rotation
- 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
Images
Landscapes
- Image Processing (AREA)
Abstract
A kind of automatic method for recovering blurred digital image caused by movement that belongs to the Computer Applied Technology field comprises the following steps: to read in image file; Image file is carried out view picture scanning; Determine to have in the image file pixel of prominent feature by the analysis image file; To carrying out horizontal stroke, longitudinal scanning around the pixel that has prominent feature in the image file; Determine the zone of pixel gray-scale value gradual change on every side, and gray-scale value gradation zone around the pixel is compared; Calculate these pixel anglec of rotation and displacement; Image is carried out the Pixel-level weighted mean to add up; By the weighted mean accumulation result pixel is rotated and moves, produce the image after restoring.The present invention adopts Computer Automatic Recognition to publish picture as the moving direction and the pixel count of pixel on the file, and moving direction according to pixels and mobile pixel count carry out moving of image pixel automatically, thereby realizes the automatic recovery of image file, and restored method is easy, quick.
Description
Technical field
The invention belongs to the Computer Applied Technology field, relate to a kind of image processing method, specifically a kind of automatic method for recovering blurred digital image caused by movement.
Technical background
Digital camera and old-fashioned film cameras all exist the phenomenon of photographic fog.Because current digital camera is just replacing old-fashioned film cameras, so the recovery technique of digital photograph just progressively is subject to people's attention.
Blooming for digital photograph, now the method that generally adopts is the observation by human eye logarithmic code photo, roughly determine the moving direction and the mobile pixel count of pixel on the digital photograph, mobile repeatedly pixel about on the direction that moves is till the people thinks that its sharpness is best.
Summary of the invention
The present invention has adopted the computing machine automatic recovering method, promptly utilize Computer Automatic Recognition to publish picture as the moving direction and the mobile pixel of pixel on the file, automatically moving direction according to pixels and mobile pixel count carry out moving of image pixel, thereby realize the recovery of image file, purpose provides a kind of automatic method for recovering blurred digital image caused by movement.
The task preprogramming of wanting carries out image to restore according to computing machine, and program deposited in this computer program memory.
Bian Zhi program comprises the following steps: in advance
Read in image file;
Analysis image;
Find the pixel that has prominent feature in the image most;
Determine the zone of pixel gray-scale value gradual change on every side;
Determine the side-play amount of each pixel according to the zone of gray-scale value gradual change around (10～30) individual pixel;
In (10～30) individual pixel-shift amount, find out identical (5～15) pixel of offset value;
In the gradation zone at identical (5～15) the pixel place of offset value, determine the anglec of rotation;
According to the anglec of rotation and side-play amount, by weighted-average method image is carried out the Pixel-level weighted mean and add up;
Pixel is rotated and moves by the weighted mean accumulation result according to Pixel-level, produce the image after restoring.
Carrying out automatic method for recovering blurred digital image caused by movement under the programmed instruction of computing machine in pre-depositing memory comprises the following steps:
The device that is used to read in image file reads in image file;
The device that is used for scan document image carries out view picture scanning to image file;
The device that is used for the analysis image file determines that by the analysis image file image file has (10～30) individual pixel of prominent feature;
The device that is used for scan document image image file is had prominent feature (10～30) individual pixel around carry out horizontal stroke, longitudinal scanning;
The device that is used for the analysis image file is determined the zone of pixel gray-scale value gradual change on every side, and gray-scale value gradation zone around the pixel is compared;
The device that is used for the calculating pixel anglec of rotation and side-play amount calculates these pixel anglec of rotation and side-play amounts;
The device that is used for computing carries out the Pixel-level weighted mean according to the anglec of rotation of pixel and side-play amount to image and adds up;
The device that is used for mobile pixel is rotated pixel and move by the weighted mean accumulation result according to pixel, produces the image after restoring.
Beneficial effect of the present invention: the present invention adopts Computer Automatic Recognition to publish picture as the moving direction and the pixel count of pixel on the file, automatically moving direction according to pixels and mobile pixel count carry out moving of image pixel, thereby realize the automatic recovery of image file, restored method is easy, quick.
Description of drawings
Fig. 1 is a program flow diagram of the present invention.It also is the specification digest accompanying drawing.
Fig. 2 is an embodiment of the invention program flow diagram.
Embodiment
The blooming that the present invention is directed to digital photograph adopts the computing machine restored method, wants the task preprogramming of carries out image recovery according to computing machine, and program is deposited in this computer program memory.This computing machine is selected the computing machine of internal memory more than or equal to 128M for use.
Bian Zhi program comprises the following steps: in advance
Read in digital photograph;
Analyze digital photograph;
Find in the digital photograph ten brighter points and ten darker points as pixel;
In the logarithmic code photo ten brighter pixels and ten darker pixels around carry out horizontal stroke, longitudinal scanning;
Determine the zone of these 20 pixels gray-scale value gradual change on every side;
Determine the side-play amount of each pixel according to the zone of gray-scale value gradual change around these 20 pixels;
In the side-play amount of these 20 pixels, find out 5 identical pixels of offset value;
In the gradation zone at 5 identical pixel places of offset value, determine the anglec of rotation;
According to the anglec of rotation and side-play amount, by weighted-average method image is carried out the Pixel-level weighted mean and add up;
Pixel is rotated and moves by the weighted mean accumulation result according to Pixel-level, produce the image after restoring.
Reading image data step source program is as follows in the program:
Void CBmpDlg::OnReadbmpButton () //TODO:Add your control notification handler code here int nSize; CDC*pDC=GetDC (); CFileDialog dlg (TRUE, " bmp ", " * .bmp "); If (dlg.DoModal ()==FALSE) AfxMessageBox (" read BMP bitmap file failure "); CFile file; If (file.Open (dlg.GetFileName (), CFile::modeRead)) { BITMAPFILEHEADER bmfh; UINT number=file.Read (﹠amp; Amp; Bmfh, sizeof (BITMAPFILEHEADER));=sizeof (BITMAPFILEHEADER)) AfxMessageBox (" read BMP bitmap file size and lose＜!--SIPO＜DP n=" 3 "〉--〉＜dp n=" d3 "/lose ");=0x4d42) AfxMessageBox (" bitmap that reads is not the BMP bitmap "); NSize=bmfh.bfOffBits-sizeof (BITMAPFILEHEADER); M_lpBMIH=(LPBITMAPINFOHEADER) new BYTE[nSize]; File.Read (m_lpBMIH, nSize); If ((m_lpBMIH-＞biBitCount)!=0x08) AfxMessageBox (" not supporting colored BMP bitmap "); M_lpImage=new BYTE[m_lpBMIH-＞biSizeImage]; File.Read (m_pImage, m_lpBMIH-＞biSizeImage); DrawImage (); Void CBmpDlg::Histogram (BYTE*Array, int Width, int Height, int OffLeft, int OffTop) //nImgWidth=768; //nImgHeight=576; Int i=0; For (i=0; I＜256; I++) HistogramArray[i]=0; For (i=OffTop; I＜(OffTop+Height); I++) { for (int j=OffLeft; J＜(OffLeft+Width); J++) HistogramArray[Array[i*nImgWidth+j]] ++;
Display image data step source program is as follows in the program:
void CBmpDlg：：DrawImage() { CDC*pDC＝GetDC()； pDC-＞SetStretchBltMode(COLORONCOLOR)； ：：StretchDIBits(pDC-＞GetSafeHdc()， 0， 0， m_lpBMIH-＞biWidth， m_lpBMIH-＞biHeight， 0， <!-- SIPO <DP n="4"> --> <dp n="d4"/> 0， m_lpBMIH-＞biWidth， m_lpBMIH-＞biHeight， m_lpImage， (LPBITMAPINFO)m_lpBMIH， DIB_RGB_COLORS， SRCCOPY)； ReleaseDC(pDC)； }
Carrying out motion blur digital photograph automatic recovering method under the programmed instruction of computing machine in pre-depositing memory comprises the following steps:
The device that is used to read in image file reads in digital photograph:
The device logarithmic code photo that is used for scan document image carries out view picture scanning;
The device that is used for the analysis image file is determined ten brighter points of digital photograph and ten darker points as pixel by analyzing digital photograph;
Be used for ten brighter points of device logarithmic code photo of scan document image and ten darker points around carry out horizontal stroke, longitudinal scanning;
The device that is used for the calculating pixel anglec of rotation and side-play amount calculates these pixel anglec of rotation and side-play amounts;
The device that is used for computing carries out the Pixel-level weighted mean according to the anglec of rotation of pixel and side-play amount to image and adds up;
The device that is used for mobile pixel is rotated pixel and move by the weighted mean accumulation result according to pixel, produces the image after restoring.
Claims (2)
1. automatic method for recovering blurred digital image caused by movement is characterized in that adopting the following step:
The device that is used to read in image file reads in image file;
The device that is used for scan document image carries out view picture scanning to image file;
The device that is used for the analysis image file determines that by the analysis image file image file has (10～30) individual pixel of prominent feature;
The device that is used for scan document image image file is had prominent feature (10～30) individual pixel around carry out horizontal stroke, longitudinal scanning;
The device that is used for the analysis image file is determined the zone of pixel gray-scale value gradual change on every side, and gray-scale value gradation zone around the pixel is compared;
The device that is used for the calculating pixel anglec of rotation and side-play amount calculates these pixel anglec of rotation and side-play amounts;
The device that is used for computing carries out the Pixel-level weighted mean according to the anglec of rotation of pixel and side-play amount to image and adds up;
The device that is used for mobile pixel is rotated pixel and move by the weighted mean accumulation result according to pixel, produces the image after restoring.
2. according to the described automatic method for recovering blurred digital image caused by movement of claim 1, it is characterized in that adopting the following step:
The device that is used to read in image file reads in digital photograph:
The device logarithmic code photo that is used for scan document image carries out view picture scanning;
The device that is used for the analysis image file is determined ten brighter points of digital photograph and ten darker points as pixel by analyzing digital photograph;
Be used for ten brighter points of device logarithmic code photo of scan document image and ten darker points around carry out horizontal stroke, longitudinal scanning;
The device that is used for the calculating pixel anglec of rotation and side-play amount calculates these pixel anglec of rotation and side-play amounts;
The device that is used for computing carries out the Pixel-level weighted mean according to the anglec of rotation of pixel and side-play amount to image and adds up;
The device that is used for mobile pixel is rotated pixel and move by the weighted mean accumulation result according to pixel, produces the image after restoring.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200510016521 CN1728181A (en) | 2005-01-13 | 2005-01-13 | Automatic method for recovering blurred digital image caused by movement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN 200510016521 CN1728181A (en) | 2005-01-13 | 2005-01-13 | Automatic method for recovering blurred digital image caused by movement |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN1728181A true CN1728181A (en) | 2006-02-01 |
Family
ID=35927435
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN 200510016521 Pending CN1728181A (en) | 2005-01-13 | 2005-01-13 | Automatic method for recovering blurred digital image caused by movement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN1728181A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101241592B (en) * | 2007-02-07 | 2010-05-19 | 南京理工大学 | High frame frequency infrared image sequence movement target real time restoration method |
| CN101359398B (en) * | 2008-06-16 | 2011-04-13 | 北京航空航天大学 | Blind restoration method for moving blurred image |
| CN101742050B (en) * | 2009-12-03 | 2011-09-07 | 浙江大学 | Method for restoring TDICCD image aiming at motion fuzzy core space shift variant |
| CN102201112A (en) * | 2010-03-25 | 2011-09-28 | 联咏科技股份有限公司 | Method for scalely removing motion blur of single image |
| CN102542530A (en) * | 2010-12-07 | 2012-07-04 | 沈阳理工大学 | Motion-blurred image defining device |
| US8509559B2 (en) | 2010-03-16 | 2013-08-13 | Novatek Microelectronics Corp. | Hierarchical motion deblurring method for single image |
-
2005
- 2005-01-13 CN CN 200510016521 patent/CN1728181A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101241592B (en) * | 2007-02-07 | 2010-05-19 | 南京理工大学 | High frame frequency infrared image sequence movement target real time restoration method |
| CN101359398B (en) * | 2008-06-16 | 2011-04-13 | 北京航空航天大学 | Blind restoration method for moving blurred image |
| CN101742050B (en) * | 2009-12-03 | 2011-09-07 | 浙江大学 | Method for restoring TDICCD image aiming at motion fuzzy core space shift variant |
| US8509559B2 (en) | 2010-03-16 | 2013-08-13 | Novatek Microelectronics Corp. | Hierarchical motion deblurring method for single image |
| CN102201112A (en) * | 2010-03-25 | 2011-09-28 | 联咏科技股份有限公司 | Method for scalely removing motion blur of single image |
| CN102201112B (en) * | 2010-03-25 | 2013-05-22 | 联咏科技股份有限公司 | Method for scalely removing motion blur of single image |
| CN102542530A (en) * | 2010-12-07 | 2012-07-04 | 沈阳理工大学 | Motion-blurred image defining device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113052210B (en) | Rapid low-light target detection method based on convolutional neural network | |
| CN1728181A (en) | Automatic method for recovering blurred digital image caused by movement | |
| CN1568479A (en) | Method and apparatus for discriminating between different regions of an image | |
| CN1799079A (en) | Method and system for evaluating moving image quality of displays | |
| CN1577396A (en) | A system and process for generating high dynamic range images from multiple exposures of a moving scene | |
| CN1925545A (en) | Image processor | |
| EP1392047A3 (en) | Digital document processing for image enhancement | |
| CN1272747C (en) | Method and device for tracking moving object in image | |
| CN113781468B (en) | Tongue image segmentation method based on lightweight convolutional neural network | |
| CN1815489A (en) | Intelligent image counting method | |
| CN1452386A (en) | Camera unit | |
| CN1272631C (en) | Moving image detecting method | |
| CN112288726B (en) | Method for detecting foreign matters on belt surface of underground belt conveyor | |
| CN114581432A (en) | Tongue appearance tongue image segmentation method based on deep learning | |
| CN113327206A (en) | Image fuzzy processing method of intelligent power transmission line inspection system based on artificial intelligence | |
| CN115578291A (en) | Image brightness correction method, storage medium and electronic device | |
| CN112686804B (en) | Image super-resolution reconstruction method and device for mine low-light environment | |
| WO2022002002A1 (en) | Image processing method, image processing apparatus, electronic device, and storage medium | |
| CN1635363A (en) | Digital image analysis method for yarn appearance quality | |
| CN1595957A (en) | Method for determining automatic detection threshold of bad pixel of medical image | |
| CN1878245A (en) | Method for correcting digital image exposure | |
| Ye et al. | A survey on learning-based low-light image and video enhancement | |
| CN111383247A (en) | Method for enhancing image tracking stability of pyramid LK optical flow algorithm | |
| CN112233032B (en) | Method for eliminating ghost image of high dynamic range image | |
| CN110276738B (en) | ROI replacement processing method of BMP image |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| AD01 | Patent right deemed abandoned | ||
| C20 | Patent right or utility model deemed to be abandoned or is abandoned |