CN104732556A - Image edge detection method based on dyeing matrix algorithm - Google Patents
Image edge detection method based on dyeing matrix algorithm Download PDFInfo
- Publication number
- CN104732556A CN104732556A CN201510173503.3A CN201510173503A CN104732556A CN 104732556 A CN104732556 A CN 104732556A CN 201510173503 A CN201510173503 A CN 201510173503A CN 104732556 A CN104732556 A CN 104732556A
- Authority
- CN
- China
- Prior art keywords
- matrix
- image edge
- dyeing
- picture
- detecting image
- 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
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an image edge detection method based on the dyeing matrix algorithm. The method includes the steps of generating an adjacent matrix B[p][p] from a matrix A[m][n], with p = m*n; reading a grey value of each pixel from the matrix A[m][n], and applying the grey values to diagonals of the adjacent matrix B[p][p], and initializing the adjacent matrix B[p][p]; weighting an edge between every two pixels; solving an average of all edge weights, and determining a threshold; performing edge dyeing according to a color set; finding boundary points, and performing point dyeing. Compared with the prior art, the method is higher in image edge detection precision and anti-noise capacity, better in application conditions and hardware cost, better in matching with application conditions of residential community access control systems and widely applicable to community automobile access control systems.
Description
Technical field
The present invention relates to a kind of method for detecting image edge, be specifically related to a kind of method for detecting image edge based on dyeing matrix algorithms.
Background technology
Technique of image edge detection is mainly used in the middle of monitoring and gate inhibition's facility, carries out the control of road traffic or the monitoring of automobile door control.This technology has higher researching value in the application of gate control system, on the one hand because, the propelling day by day of China's Development of China's Urbanization, urban population speedup is obvious, the requirement of town dweller to residence increases to some extent, and add that the entirety of modern resident's quality improves, the need awareness of resident to public safety strengthens gradually, more and more higher to the attention rate of gate inhibition community, make more and more scholar put into correlative study.On the other hand, developer is in order to cater to public demand, often some gate inhibition communities of Money making are as attraction, thus can corresponding increase gate control system, safety-protection system, monitor and control facility demand, this brings more business opportunities and opportunity to gate control system manufacturer, and many Gate-ban Monitoring Systems with New function emerge in an endless stream.
In addition, technique of image edge detection is the important component part of safety-protection system, it is equally one of core technology of safety-protection system (residential quarter car entry system schematic diagram as shown in Figure 1) with camera Sampling techniques, digital-to-analog conversion technology, interfacing, there is deep Research foundation, in nineteen sixty-five so far nearly 50 years, there are many Chinese scholars to study it, and obtain a lot of achievement in different field.The kind of edge detection algorithm is more, can be divided into traditional algorithm and emerging algorithm.Traditional algorithm has: Roberts operator, Sobel operator, Prewitt operator, LOG operator, laplacian operator and Canny operator etc.Traditional algorithm mostly realizes based on mathematical operation, or noiseproof feature is poor, or the precision of rim detection is not high.The research of emerging edge detection algorithm often intersects to some extent with Other subjects, have in engineering: based on edge detection method, the edge detection method based on fuzzy theory, the dividing method etc. based on neural network of wavelet analysis and wavelet packet, have in the field such as machine vision and artificial intelligence: based on the edge detection method, self-organizing clustering method, genetic algorithm etc. of mathematical morphology.
Because residential quarter car entry system needs image processing process relatively fast, accurately, reliability is high, be easy to store, although above-mentioned many technique of image edge detection are in corresponding field all extensive application, it all also exists weak point in precision, anti-noise ability, application conditions and hardware cost etc.Therefore, be necessary that taking out a kind of new technique of image edge detection solves these problems.
Summary of the invention
In order to solve the problems of the technologies described above, the invention provides a kind of method for detecting image edge based on dyeing matrix algorithms all in these at precision, anti-noise ability, application conditions and hardware cost with advantage.
In order to achieve the above object, technical scheme of the present invention is as follows:
Based on the method for detecting image edge of dyeing matrix algorithms, it adopts MyEclpise 7.0 instrument and Java language, and the method comprises the following steps:
1) picture is changed into the form of A [m] [n] matrix;
2) A [m] [n] matrix is generated adjacency matrix B [p] [p], wherein p=m*n;
3) from A [m] [n] matrix, read the gray-scale value of each pixel respectively, insert the diagonal positions of adjacency matrix B [p] [p] respectively, and initialization process is carried out to adjacency matrix B [p] [p];
4) weights are composed to the limit of adjacent point-to-point transmission;
5) mean value of all limits weights is asked and definite threshold;
6) Edge Coloring is carried out according to look set;
7) find out frontier point and carry out Vertex Coloring.
The present invention is according to graph theory viewpoint, by arranging matrix and utilizing its cornerwise form to carry out the calculating of limit tax weights and threshold, thus opposite side and point dye, achieve the detection to image border, the method is had by force structural, data structure and building process simple, the features such as institutional framework is clear, can effectively be applied in the middle of the car entry system of residential quarter, thus this method is improved compared to prior art for the precision of Image Edge-Detection and anti-noise ability, simultaneously only by means of MyEclpise 7.0 instrument and Java language and attainable this method, application conditions and hardware cost are compared prior art also there is its advantage, and mate better with the application conditions of residential quarter gate control system, can be widely used in the middle of the car entry system of community.
On the basis of technique scheme, the present invention can also do following improvement:
As preferred scheme, the above-mentioned the 1st) before step, also need to carry out gray proces to picture: open a pictures, and obtain the wide of picture and height, wide is w, height is h, generate one-dimension array pixels [w*h] according to wide with height, deposit often some pixel value, gradation conversion is carried out to picture, obtain gray-scale value, and leave in one-dimension array.
Adopt above-mentioned preferred scheme, the gray-scale value of picture can be obtained more efficiently and accurately.
As preferred scheme, in above-mentioned adjacency matrix B [p] [p], there is being set to " 1 " of neighbouring relations, being set to "-1 " without neighbouring relations.
Adopt above-mentioned preferred scheme, the judgement precision to adjacency matrix can be improved.
As preferred scheme, also utilize gradient convolution operator to ask gradient magnitude to often some pixel value, and be set to total, the 5th) judge whether total is greater than 80 after step, be that " 2 " are replaced former weights, otherwise " 1 " is replaced former weights, carry out staining procedure subsequently.
Adopt above-mentioned preferred scheme, the precision of dyeing can be improved.
As preferred scheme, the above-mentioned the 7th) after step, also determine whether frontier point one by one with behavior unit, subsequently grayvalue transition pixel value is produced picture according to array of pixels.
Adopt above-mentioned preferred scheme, the judgement precision to frontier point can be improved, thus improve the conversion accuracy of picture.
Accompanying drawing explanation
Fig. 1 is residential quarter car entry system schematic diagram.
Fig. 2 is the implementing procedure figure of the method for detecting image edge based on dyeing matrix algorithms of the present invention.
Embodiment
The preferred embodiment of the present invention is described in detail below in conjunction with accompanying drawing.
In order to reach object of the present invention, as shown in Figure 2, in the some of them embodiment of the method for detecting image edge based on dyeing matrix algorithms of the present invention, it adopts MyEclpise7.0 instrument and Java language, and the method comprises the following steps:
S1: form picture being changed into A [m] [n] matrix;
S2: A [m] [n] matrix is generated adjacency matrix B [p] [p] (Matrix [p*p] namely in Fig. 2), wherein p=m*n;
S3: the gray-scale value reading each pixel from A [m] [n] matrix respectively, inserts the diagonal positions of adjacency matrix B [p] [p] respectively, and carries out initialization process to adjacency matrix B [p] [p];
S4: compose weights to the limit of adjacent point-to-point transmission;
S5: ask the mean value of all limits weights and definite threshold;
S6: carry out Edge Coloring according to look set;
S7: find out frontier point and carry out Vertex Coloring.
This method is according to graph theory viewpoint, by arranging matrix and utilizing its cornerwise form to carry out the calculating of limit tax weights and threshold, thus opposite side and point dye, achieve the detection to image border, the method is had by force structural, data structure and building process simple, the features such as institutional framework is clear, can effectively be applied in the middle of the car entry system of residential quarter, thus this method is improved compared to prior art for the precision of Image Edge-Detection and anti-noise ability, simultaneously only by means of MyEclpise 7.0 instrument and Java language and attainable this method, application conditions and hardware cost are compared prior art also there is its advantage, and mate better with the application conditions of residential quarter gate control system, can be widely used in the middle of the car entry system of community.
Dyeing matrix algorithms usability of program fragments involved in this method is as follows:
In order to optimize implementation result of the present invention further, as shown in Figure 2, in other embodiments of the method for detecting image edge based on dyeing matrix algorithms of the present invention, on the basis of the above, before above-mentioned S1 step, also need to carry out gray proces to picture, i.e. step S11-12: open a pictures, and obtain the wide of picture and height, wide is w, height is h, generate one-dimension array pixels [w*h] according to wide with height, deposit often some pixel value, gradation conversion is carried out to picture, obtain gray-scale value, and leave in one-dimension array.Adopt the scheme of this embodiment, the gray-scale value of picture can be obtained more efficiently and accurately.
In order to optimize implementation result of the present invention further, as shown in Figure 2, in other embodiments of the method for detecting image edge based on dyeing matrix algorithms of the present invention, on the basis of the above, in above-mentioned adjacency matrix B [p] [p], there is being set to " 1 " of neighbouring relations, being set to "-1 " without neighbouring relations.Adopt the scheme of this embodiment, the judgement precision to adjacency matrix can be improved.
In order to optimize implementation result of the present invention further, as shown in Figure 2, in other embodiments of the method for detecting image edge based on dyeing matrix algorithms of the present invention, on the basis of the above, also comprise step S61-63: utilize gradient convolution operator to ask gradient magnitude to often some pixel value, and be set to total, the 5th) judge whether total is greater than 80 after step, be that " 2 " are replaced former weights, otherwise " 1 " is replaced former weights, carry out staining procedure subsequently.Adopt the scheme of this embodiment, the precision of dyeing can be improved.
In order to optimize implementation result of the present invention further, as shown in Figure 2, in other embodiments of the method for detecting image edge based on dyeing matrix algorithms of the present invention, on the basis of the above, after above-mentioned S7 step, also comprise step S8-S9: determine whether frontier point one by one with behavior unit, subsequently grayvalue transition pixel value and according to array of pixels production picture.Adopt the scheme of this embodiment, the judgement precision to frontier point can be improved, thus improve the conversion accuracy of picture.
Above-described is only the preferred embodiment of the present invention, it should be pointed out that for the person of ordinary skill of the art, and without departing from the concept of the premise of the invention, can also make some distortion and improvement, these all belong to protection scope of the present invention.
Claims (5)
1. based on the method for detecting image edge of dyeing matrix algorithms, it is characterized in that, adopt MyEclpise 7.0 instrument and Java language, said method comprising the steps of:
1) picture is changed into the form of A [m] [n] matrix;
2) described A [m] [n] matrix is generated adjacency matrix B [p] [p], wherein p=m*n;
3) from described A [m] [n] matrix, read the gray-scale value of each pixel respectively, insert the diagonal positions of described adjacency matrix B [p] [p] respectively, and initialization process is carried out to described adjacency matrix B [p] [p];
4) weights are composed to the limit of adjacent point-to-point transmission;
5) mean value of all limits weights is asked and definite threshold;
6) Edge Coloring is carried out according to look set;
7) find out frontier point and carry out Vertex Coloring.
2. the method for detecting image edge based on dyeing matrix algorithms according to claim 1, it is characterized in that, the described 1st) before step, also need to carry out gray proces to picture: open a pictures, and obtain the wide of picture and height, wide is w, and height is h, widely generates one-dimension array pixels [w*h] with height according to described, deposit often some pixel value, gradation conversion is carried out to described picture, obtains gray-scale value, and leave in described one-dimension array.
3. the method for detecting image edge based on dyeing matrix algorithms according to claim 1, is characterized in that, in described adjacency matrix B [p] [p], having being set to " 1 " of neighbouring relations, being set to "-1 " without neighbouring relations.
4. the method for detecting image edge based on dyeing matrix algorithms according to claim 1 or 3, it is characterized in that, gradient convolution operator is utilized to ask gradient magnitude to often some pixel value, and be set to total, the described 5th) judge whether total is greater than 80 after step, be that " 2 " are replaced former weights, otherwise " 1 " is replaced former weights, carry out staining procedure subsequently.
5. the method for detecting image edge based on dyeing matrix algorithms according to claim 1, it is characterized in that, described 7th) after step, also frontier point is determined whether one by one with behavior unit, subsequently grayvalue transition pixel value and according to array of pixels production picture.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510173503.3A CN104732556A (en) | 2015-04-13 | 2015-04-13 | Image edge detection method based on dyeing matrix algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510173503.3A CN104732556A (en) | 2015-04-13 | 2015-04-13 | Image edge detection method based on dyeing matrix algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104732556A true CN104732556A (en) | 2015-06-24 |
Family
ID=53456424
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510173503.3A Pending CN104732556A (en) | 2015-04-13 | 2015-04-13 | Image edge detection method based on dyeing matrix algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104732556A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019041590A1 (en) * | 2017-08-31 | 2019-03-07 | 中国科学院微电子研究所 | Edge detection method using arbitrary angle |
| CN111161303A (en) * | 2019-12-30 | 2020-05-15 | 上海眼控科技股份有限公司 | Marking method, marking device, computer equipment and storage medium |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040037451A1 (en) * | 2002-08-22 | 2004-02-26 | Kim Tae Jung | Image processing method for automatic image registration and correction |
| CN102708556A (en) * | 2012-05-10 | 2012-10-03 | 武汉大学 | Single image super resolution method on basis of maintenance of reversed image |
-
2015
- 2015-04-13 CN CN201510173503.3A patent/CN104732556A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20040037451A1 (en) * | 2002-08-22 | 2004-02-26 | Kim Tae Jung | Image processing method for automatic image registration and correction |
| CN102708556A (en) * | 2012-05-10 | 2012-10-03 | 武汉大学 | Single image super resolution method on basis of maintenance of reversed image |
Non-Patent Citations (2)
| Title |
|---|
| 刘建龙: ""基于图论的图像分割算法研究"", 《中国优秀博硕士学位论文全文数据库 (硕士) 信息科技辑》 * |
| 陈志鹏: ""图的可区别染色算法研究"", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2019041590A1 (en) * | 2017-08-31 | 2019-03-07 | 中国科学院微电子研究所 | Edge detection method using arbitrary angle |
| CN111161303A (en) * | 2019-12-30 | 2020-05-15 | 上海眼控科技股份有限公司 | Marking method, marking device, computer equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103258332B (en) | A kind of detection method of the moving target of resisting illumination variation | |
| CN104156693B (en) | A kind of action identification method based on the fusion of multi-modal sequence | |
| CN109918971B (en) | Method and device for detecting number of people in monitoring video | |
| CN103208123A (en) | Image segmentation method and system | |
| CN110111361A (en) | A kind of moving target detecting method based on multi-threshold self-optimizing background modeling | |
| CN103489012B (en) | Crowd density detecting method and system based on support vector machine | |
| CN110245550A (en) | A kind of face noise data collection CNN training method based on overall cosine distribution | |
| CN105335949A (en) | Video image rain removal method and system | |
| CN116485785B (en) | Surface defect detection method for solar cell | |
| CN104732555A (en) | Image edge detection method based on Sobel operator | |
| CN103106796A (en) | Vehicle detection method and device of intelligent traffic surveillance and control system | |
| CN103268498A (en) | Method for area-of-interest blurred image semantic comprehension | |
| CN1564600A (en) | Detection method of moving object under dynamic scene | |
| CN104732556A (en) | Image edge detection method based on dyeing matrix algorithm | |
| CN105205834A (en) | Target detection and extraction method based on Gaussian mixture and shade detection model | |
| CN111476727A (en) | Video motion enhancement method for face changing video detection | |
| CN105809092A (en) | Population target detection method and device thereof | |
| CN107871315B (en) | Video image motion detection method and device | |
| CN107358635B (en) | Color morphological image processing method based on fuzzy similarity | |
| CN108009480A (en) | A kind of image human body behavioral value method of feature based identification | |
| CN111310772B (en) | Point line characteristic selection method and system for binocular vision SLAM | |
| CN108320299A (en) | A kind of target tracking algorism based on motor behavior analysis | |
| CN104732554A (en) | Image edge detection method based on Roberts operator | |
| CN109255794A (en) | A kind of full convolution edge feature detection method of standard component depth | |
| CN104867114B (en) | Blind minimizing technology is permeated at a kind of ancient books scan image back side based on condition random field |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20150624 |