CN103500439B - Drawing method is beaten based on image processing techniques - Google Patents
Drawing method is beaten based on image processing techniques Download PDFInfo
- Publication number
- CN103500439B CN103500439B CN201310395645.5A CN201310395645A CN103500439B CN 103500439 B CN103500439 B CN 103500439B CN 201310395645 A CN201310395645 A CN 201310395645A CN 103500439 B CN103500439 B CN 103500439B
- Authority
- CN
- China
- Prior art keywords
- image
- matrix
- pixel
- minor matrix
- minor
- 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.)
- Expired - Fee Related
Links
- 238000000034 method Methods 0.000 title claims abstract description 53
- 239000000284 extract Substances 0.000 claims abstract description 20
- 230000006835 compression Effects 0.000 claims abstract description 19
- 238000007906 compression Methods 0.000 claims abstract description 19
- 239000011159 matrix material Substances 0.000 claims description 55
- 230000011218 segmentation Effects 0.000 claims description 9
- 238000001914 filtration Methods 0.000 claims description 4
- 238000004458 analytical method Methods 0.000 abstract description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000004575 stone Substances 0.000 description 2
- 239000006002 Pepper Substances 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006378 damage Effects 0.000 description 1
- 238000005034 decoration Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000003708 edge detection Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
Abstract
The invention discloses and a kind ofly beat drawing method based on image processing techniques, specifically implement according to following steps, step 1, carries out pre-service to original image; Step 2, carries out contours extract to through the pretreated image of step 1; Step 3, compresses the image after step 2 contours extract; Step 4, gets on drawing board by device for dotting by the compression figure obtained through step 3, namely completes to play picture to original image.By integrating multiple image processing techniques, to the collection of picture, process and analysis, the image after process is printed on drawing board by device for dotting; The method can extract the profile of image effectively, and portrays compared to manpower, substantially reduces the time, improves efficiency, has liberated manpower, realizes the collection to image information, process and analyzing, and solves existingly manually to beat the inefficient problem of drawing method.
Description
Technical field
The invention belongs to image procossing and automatic control technology field, relate to and a kind ofly beat drawing method based on image processing techniques.
Background technology
It is one of the traditional culture of Chinese Typical Representative that slabstone is portrayed, and stone inscription line drawing is exactly typical representative, from Han dynasty, engenders on the record of events inscribed on a tablet, lintel, the stone base of column etc.But along with the development of society, the continuous progress of science and technology, the appearance of global First printer from 1885, printed matter starts worldwide to spread to various aspects rapidly.Although printed matter occupies major part in decoration, but flagstone picture still occupies one seat at ornament as a kind of artwork, and along with the raising of living standard and spiritual level, the mankind more and more like the ornament with artistry, under normal circumstances, artificial flagstone picture needs manpower, so not only consuming time but also effort, work efficiency is low, is unfavorable for liberating manpower.
Summary of the invention
The object of this invention is to provide and a kind ofly beat drawing method based on image processing techniques, existingly manually beat the inefficient problem of drawing method to solve.
The technical solution used in the present invention is, beats drawing method based on image processing techniques, specifically implements according to following steps,
Step 1, carries out pre-service to original image;
Step 2, carries out contours extract to through the pretreated image of step 1;
Step 3, compresses the image after step 2 contours extract;
Step 4, gets on drawing board by device for dotting by the compression figure obtained through step 3, namely completes to play picture to original image.
Feature of the present invention is also,
The concrete grammar of step 1 is first carry out gray processing process to original image, obtain gray level image; Again filtering process is carried out to gray level image median filter; Finally histogram equalization process is carried out to filtered image, namely complete the pre-service of original image.
The concrete grammar of step 2 is calculate the gradient map through the pretreated image of step 1; The distance function image of compute gradient figure again; Then calculate external constraint and the internal constraint of distance function image, obtain constraints graph picture; Again to constraint Image Reconstruction gradient map; Finally by watershed algorithm, by the gradient map segmentation after reconstruct, obtain black white binarization figure, namely complete the contours extract to pretreated image.
In step 3, the concrete grammar of compression of images is,
3.1) length of the binary image obtained through step 2 and wide size is established to be respectively m and n, long and wide size compression ratio is respectively m1 and n1, p is the length of side of the drawing board will playing picture, the unit of p is millimeter, according to m1=[m/ (p/2)]+1 and n1=[n/ (p/2)]+1, namely calculate long and wide size compression ratio;
3.2) set the size of compression minor matrix as z × z, if m1>n1, then z is m1; If m1<n1, then z is n1; By the calculating of m/z and n/z, obtain remainder e and f respectively, then this binary image is dismissed respectively e capable and f row, obtain image after cutting;
3.3) s and t is calculated respectively, then by step 3.2 by s=(m-e)/z and t=(n-f)/z) Iamge Segmentation Cheng Kuanwei s after the cutting that obtains, the long matrix for t, this entry of a matrix element is divided into the minor matrix of z × z again;
3.4) if in minor matrix pixel value be 0 sum of all pixels be greater than the sum of all pixels that pixel value is 1, then this minor matrix is set to 0, if in minor matrix pixel value be 0 sum of all pixels be less than the sum of all pixels that pixel value is 1, then this minor matrix is set to 1, the new matrix finally formed is compressed image.
The concrete grammar playing picture in step 4 is, line by line scan to the compressed image after processing through step 3, if the pixel value of minor matrix is 1, then this minor matrix position place is not got ready; If the pixel value of minor matrix is 0, then at this minor matrix position place, got ready on drawing board by device for dotting, until all minor matrixs scan and get ready complete, what namely complete original image plays picture.
The invention has the beneficial effects as follows, integrate multiple image processing techniques, by the collection to picture, process and analysis, the image after process is up to by device for dotting on drawing board; The method can extract the profile of image effectively, and portrays compared to manpower, substantially reduces the time, improves efficiency, has liberated manpower, realizes the collection to image information, process and analyzing, and solves existingly manually to beat the inefficient problem of drawing method.
Embodiment
Below in conjunction with embodiment, the present invention is described in detail.
The invention provides and a kind ofly beat drawing method based on image processing techniques, specifically implement according to following steps,
Step 1, carries out pre-service to original image
First carry out gray processing process to original image and obtain gray level image, original image comprises colour picture and string diagram, and the image after usual gray processing contains a large amount of salt-pepper noises, and noise is less; So carry out filtering process to the gray level image median filter of 3 × 3 templates again; In order to strengthen the feature of destination object, finally histogram equalization process being carried out to filtered image, namely completing the pre-service of original image.
To original image pre-service, because image unavoidably can by destruction to a certain degree and various noise pollution in transmission and storing process, cause picture to lose essence or deviate from the demand of people, the impact thus just needing a series of pretreatment operation to carry out removal of images to be subject to.
From experiment, be mapped between [0,1] by the brightness value in image between [0.2,0.8], the image after histogram equalization can obtain good effect; Due to the difference of intensity of illumination, cause the feature of picture internal object object not obvious, be unfavorable for carrying out contours extract to image, in order to the profile of destination object can be extracted more like clockwork, therefore need to carry out normalization process to picture, improve the feature caused due to reasons such as illumination not obvious.
Step 2, carries out contours extract to through the pretreated image of step 1
Calculate the gradient map through the pretreated image of step 1; The distance function image of compute gradient figure again; Then calculate external constraint and the internal constraint of distance function image, obtain constraints graph picture; Again to constraint Image Reconstruction gradient map; Finally by watershed algorithm, by the gradient map segmentation after reconstruct, obtain black white binarization figure, namely complete the contours extract to pretreated image.
The object of carrying out contours extract is exactly with minimum pixel description object, therefore contours extract is carried out to image and just seem extremely important, image outline extracts its essence and carries out rim detection to image exactly, conventional edge detection operator comprises Roberts operator, Sobel operator, Prewitt operator, Canny operator etc., usually very responsive to noise when utilizing these operators to calculate, and easily lose marginal information, so the present invention's selection is watershed algorithm.
Step 3, compresses the image after step 2 contours extract
3.1) establish the length of the binary image obtained through step 2 and wide size to be respectively m pixel and n pixel, long and wide size compression ratio is respectively m1 and n1, and p is the length of side of the drawing board will playing picture, and the unit of p is millimeter; According to m1=[m/ (p/2)]+1 and n1=[n/ (p/2)]+1, namely calculate long and wide size compression ratio;
3.2) set the size of compression minor matrix as z × z, if m1>n1, then z is m1; If m1<n1, then z is n1; By the calculating of m/z and n/z, obtain remainder e and f respectively, then this binary image is dismissed respectively the capable pixel of e and f row pixel, obtain image after cutting;
In order to not produce distortion after making compression of images and the size of compressed images is no more than the relative size of playing picture machine drawing board, so the size of subdivision matrix chooses the length and width of number larger in m1 and n1 as subdivision matrix,
3.3) s and t is calculated respectively by s=(m-e)/z and t=(n-f)/z, then by step 3.2) Iamge Segmentation Cheng Kuanwei s pixel after the cutting that obtains, the long matrix for t pixel, this entry of a matrix element is divided into the minor matrix of z × z again;
In order to the Iamge Segmentation that will print be become the matrix of integral multiple, therefore need to fight each other watermark image length and widely to adjust, remainder e and f is calculated by m/z and n/z, e and f is respectively the number of lines of pixels and pixel columns that will dismiss and print image array, because e and f is less than z, therefore can not the overall content of effect diagram picture.
3.4) if in minor matrix pixel value be 0 sum of all pixels be greater than the sum of all pixels that pixel value is 1, then this minor matrix is set to 0, if in minor matrix pixel value be 0 sum of all pixels be less than the sum of all pixels that pixel value is 1, then this minor matrix is set to 1, the new matrix finally formed is compressed image.
Step 4, by device for dotting, gets on drawing board by the compression figure obtained through step 3, namely completes to play picture to original image.
The concrete grammar playing picture is,
Line by line scan to the compressed image after processing through step 3, if the pixel value of minor matrix is 1, then this minor matrix position place is not got ready; If the pixel value of minor matrix is 0, then at this minor matrix position place, got ready on drawing board by device for dotting, until all minor matrixs scan and get ready complete, what namely complete original image plays picture.
Embodiment
Step 1, the colour picture being first of a size of 420 pixel × 406 pixels to carries out gray processing process and obtains its gray level image; Again filtering process is carried out to the gray level image median filter of 3 × 3 templates; Finally histogram equalization process is carried out to filtered image, namely complete the pre-service of original image.
Step 2, calculates the gradient map through the pretreated image of step 1; Again to constraint Image Reconstruction gradient map; Finally by watershed algorithm, by the gradient map segmentation after reconstruct, obtain black white binarization figure, namely complete the contours extract to pretreated image.
Step 3, compresses the image after step 2 contours extract
3.1) length and the wide size of the binary image obtained through step 2 are respectively 420 pixels and 406 pixels, and the length of side of drawing board is 350mm, then long compression factor is be 3 with wide size compression ratio;
3.2) set the size of compression minor matrix as z × z, then z=3, e=0, f=1, then this binary image is dismissed 1 row, obtain image after cutting;
3.3) Iamge Segmentation Cheng Kuanwei 140 pixels after cutting, length is the matrix of 135 pixels, and this entry of a matrix element is divided into the minor matrix of 3*3 again;
3.4) if in minor matrix pixel value be 0 sum of all pixels be greater than the sum of all pixels that pixel value is 1, then this minor matrix is set to 0, if in minor matrix pixel value be 0 sum of all pixels be less than the sum of all pixels that pixel value is 1, then this minor matrix is set to 1, the new matrix finally formed is compressed image.
Step 4, line by line scan to the compressed image after processing through step 3, if the pixel value of minor matrix is 1, then this minor matrix position place is not got ready; If the pixel value of minor matrix is 0, then at this minor matrix position place, got ready on drawing board by device for dotting, until all minor matrixs scan and get ready complete, what namely complete original image plays picture.
Beat drawing method based on image processing techniques, integrate multiple image processing techniques, by the collection to picture, process and analysis, the image after process is printed by device for dotting on drawing board; The method can extract the profile of image effectively, and portrays compared to manpower, substantially reduces the time, improves efficiency, has liberated manpower, realizes the collection to image information, process and analyzing, and solves existingly manually to beat the inefficient problem of drawing method.
Claims (2)
1. beat drawing method based on image processing techniques, it is characterized in that, specifically implement according to following steps,
Step 1, carries out pre-service to original image;
Step 2, carries out contours extract to through the pretreated image of step 1;
Step 3, compresses the image after step 2 contours extract;
Step 4, gets on drawing board by device for dotting by the compression figure obtained through step 3, namely completes to play picture to original image;
The concrete grammar of described step 1 is,
First gray processing process is carried out to original image, obtain gray level image; Again filtering process is carried out to gray level image median filter; Finally histogram equalization process is carried out to filtered image, namely complete the pre-service of original image;
The concrete grammar of described step 2 is,
Calculate the gradient map through the pretreated image of step 1; The distance function image of compute gradient figure again; Then calculate external constraint and the internal constraint of distance function image, obtain constraints graph picture; Again to constraint Image Reconstruction gradient map; Finally by watershed algorithm, by the gradient map segmentation after reconstruct, obtain black white binarization figure, namely complete the contours extract to pretreated image;
In described step 3, the concrete grammar of compression of images is,
3.1) length of the binary image obtained through step 2 and wide size is established to be respectively m pixel and n pixel, long and wide size compression ratio is respectively m1 and n1, p is the length of side of the drawing board will playing picture, the unit of p is millimeter, according to m1=[m/ (p/2)]+1 and n1=[n/ (p/2)]+1, namely calculate long and wide size compression ratio;
3.2) set the size of compression minor matrix as z × z, if m1>n1, then z is m1; If m1<n1, then z is n1; By the calculating of m/z and n/z, obtain remainder e and f respectively, then this binary image is dismissed respectively the capable pixel of e and f row pixel, obtain image after cutting;
3.3) s and t is calculated respectively by s=(m-e)/z and t=(n-f)/z, then by step 3.2) Iamge Segmentation Cheng Kuanwei s pixel after the cutting that obtains, the long matrix for t pixel, this entry of a matrix element is divided into the minor matrix of z × z again;
3.4) if in minor matrix pixel value be 0 sum of all pixels be greater than the sum of all pixels that pixel value is 1, then this minor matrix is set to 0, if in minor matrix pixel value be 0 sum of all pixels be less than the sum of all pixels that pixel value is 1, then this minor matrix is set to 1, the new matrix finally formed is compressed image.
2. as claimed in claim 1 beat drawing method based on image processing techniques, it is characterized in that, the concrete grammar playing picture in described step 4 is,
Line by line scan to the compressed image after processing through step 3, if the pixel value of minor matrix is 1, then this minor matrix position place is not got ready; If the pixel value of minor matrix is 0, then at this minor matrix position place, got ready on drawing board by device for dotting, until all minor matrixs scan and get ready complete, what namely complete original image plays picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310395645.5A CN103500439B (en) | 2013-09-03 | 2013-09-03 | Drawing method is beaten based on image processing techniques |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310395645.5A CN103500439B (en) | 2013-09-03 | 2013-09-03 | Drawing method is beaten based on image processing techniques |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103500439A CN103500439A (en) | 2014-01-08 |
| CN103500439B true CN103500439B (en) | 2016-04-20 |
Family
ID=49865642
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310395645.5A Expired - Fee Related CN103500439B (en) | 2013-09-03 | 2013-09-03 | Drawing method is beaten based on image processing techniques |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103500439B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105491120A (en) * | 2015-12-01 | 2016-04-13 | 小米科技有限责任公司 | Method and device for picture transfer |
| CN105718945B (en) * | 2016-01-20 | 2020-07-31 | 江苏大学 | Apple picking robot night image recognition method based on watershed and neural network |
| CN109175718B (en) * | 2018-11-01 | 2020-08-04 | 重庆大学产业技术研究院 | Picture laser engraving method based on halftone technology |
| CN112634309B (en) * | 2020-11-30 | 2023-08-15 | 上海联影医疗科技股份有限公司 | Image processing method, device, electronic equipment and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1707502A (en) * | 2004-06-10 | 2005-12-14 | 佳能株式会社 | Image processing apparatus and control method therefor, |
| CN101600039A (en) * | 2008-06-05 | 2009-12-09 | 佳世达科技股份有限公司 | The method of half tone image conversion method, Method of printing and generation halftone shield |
| CN102332162A (en) * | 2011-09-19 | 2012-01-25 | 西安百利信息科技有限公司 | Method for automatic recognition and stage compression of medical image regions of interest based on artificial neural network |
-
2013
- 2013-09-03 CN CN201310395645.5A patent/CN103500439B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1707502A (en) * | 2004-06-10 | 2005-12-14 | 佳能株式会社 | Image processing apparatus and control method therefor, |
| CN101600039A (en) * | 2008-06-05 | 2009-12-09 | 佳世达科技股份有限公司 | The method of half tone image conversion method, Method of printing and generation halftone shield |
| CN102332162A (en) * | 2011-09-19 | 2012-01-25 | 西安百利信息科技有限公司 | Method for automatic recognition and stage compression of medical image regions of interest based on artificial neural network |
Non-Patent Citations (1)
| Title |
|---|
| 基于形态学梯度重建的分水岭算法改进研究;陈林林 等;《中国印刷与包装研究》;20130805;第5卷(第4期);第114-115页第2节 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103500439A (en) | 2014-01-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109522788B (en) | City range extraction method and device based on random forest classification algorithm and electronic equipment | |
| CN102158653B (en) | Device and method for acquiring digital image with high dynamic range in real time | |
| CN105424709A (en) | Fruit surface defect detection method based on image marking | |
| CN103002225B (en) | Multiple exposure high dynamic range image capture | |
| CN103927741B (en) | SAR image synthesis method for enhancing target characteristics | |
| CN103500439B (en) | Drawing method is beaten based on image processing techniques | |
| CN104021207B (en) | A kind of food information providing method based on image | |
| CN105989322B (en) | A kind of multi-index amalgamation landslide detection method based on high-resolution remote sensing image | |
| CN102163284A (en) | Chinese environment-oriented complex scene text positioning method | |
| CN101546426B (en) | Weak luminescence image processing method based on regional augmentation and regional extraction | |
| CN109242888A (en) | A kind of infrared and visible light image fusion method of combination saliency and non-down sampling contourlet transform | |
| US20110148897A1 (en) | Apparatus and methods for processing images | |
| CN101493939A (en) | Method for detecting cooked image based on small wave domain homomorphic filtering | |
| CN109859231A (en) | A kind of leaf area index extraction threshold segmentation method based on optical imagery | |
| CN103226829A (en) | Image edge detection method based on edge enhancement operator | |
| CN106815583A (en) | A kind of vehicle at night license plate locating method being combined based on MSER and SWT | |
| CN106778640B (en) | The generation method of vegetation cover model under a kind of three-dimensional visualization environment | |
| CN106228157A (en) | Coloured image word paragraph segmentation based on image recognition technology and recognition methods | |
| CN107264570A (en) | steel rail light band distribution detecting device and method | |
| CN102999890A (en) | Method for dynamically calibrating image light intensity on basis of environmental factors | |
| CN113052923B (en) | Tone mapping method, tone mapping apparatus, electronic device, and storage medium | |
| CN110176020A (en) | A kind of bird's nest impurity method for sorting merging 2D and 3D rendering | |
| Zhen et al. | Single Image Defogging Algorithm based on Dark Channel Priority. | |
| CN101718674B (en) | Method for measuring shape parameters of particles of particulate materials | |
| CN107239761A (en) | Fruit tree branch pulling effect evaluation method based on skeleton Corner Detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant | ||
| CB03 | Change of inventor or designer information |
Inventor after: Lao Yandong Inventor before: Xu Hongwei Inventor before: Chen Linlin Inventor before: Bai Xuejuan |
|
| CB03 | Change of inventor or designer information | ||
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20171009 Address after: 311200 11 households of 46 families in Zhangshu village, Mount Huangshan village, Xiaoshan District, Hangzhou, Zhejiang Patentee after: Lao Yandong Address before: 710048 Shaanxi city of Xi'an Province Jinhua Road No. 5 Patentee before: Xi'an University of Technology |
|
| TR01 | Transfer of patent right | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20171013 Address after: 310051 Building 1, building 599, 7 Waterfront Road, Changhe Road, Changhe street, Hangzhou, Zhejiang, Binjiang District Patentee after: Hangzhou enjoy Tour Technology Co., Ltd. Address before: 311200 11 households of 46 families in Zhangshu village, Mount Huangshan village, Xiaoshan District, Hangzhou, Zhejiang Patentee before: Lao Yandong |
|
| CF01 | Termination of patent right due to non-payment of annual fee | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20160420 Termination date: 20190903 |