CN106326901B - Water stain image-recognizing method and TEDS system based on marginal point self-similarity - Google Patents
Water stain image-recognizing method and TEDS system based on marginal point self-similarity Download PDFInfo
- Publication number
- CN106326901B CN106326901B CN201610752438.4A CN201610752438A CN106326901B CN 106326901 B CN106326901 B CN 106326901B CN 201610752438 A CN201610752438 A CN 201610752438A CN 106326901 B CN106326901 B CN 106326901B
- Authority
- CN
- China
- Prior art keywords
- marginal point
- point
- self
- similarity
- marginal
- 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.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/50—Extraction of image or video features by performing operations within image blocks; by using histograms, e.g. histogram of oriented gradients [HoG]; by summing image-intensity values; Projection analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Image Analysis (AREA)
Abstract
The present invention proposes the water stain image recognition based on marginal point self-similarity, obtains the marginal point of image to be detected, to each marginal point distribution reference direction and its feature vector is calculated, to feature vector normalized;The part of each marginal point and whole self-similarity value on edge line are calculated, using its weighted array as the final self-similarity value of the marginal point;The edge point set that self-similarity is high on each of the edges line is obtained, is screened in the set according to scheduled mode and marks the low broken edge point of self-similarity;Count the directional spreding histogram of broken edge point, determine the principal direction of each broken edge point, default downwardly direction threshold range rejects principal direction not in the broken edge point of direction threshold range, and the broken edge point by principal direction in direction threshold range is labeled as water stain image.The present invention also proposes the TEDS system using the water stain image recognition, effectively identifies water stain in EMU, reduction False Rate.
Description
Technical field
The present invention relates to computer pictures to detect identification field, particularly relates to a kind of based on the water stain of marginal point self-similarity
The EMU operation troubles Motion Image Detection system of image-recognizing method and the application identification.
Background technique
Water stain image is usually a kind of interference image in field of image recognition, the influence to the identification of specified features compared with
Small, therefore, there is no be specifically directed to water stain knowledge method for distinguishing at present.
EMU fault detection is transformed into the analysis to vehicle image from the artificial detection at scene, is run using EMU
Fault dynamic images detection system (TEDS) monitors EMU driving conditions in real time, i.e. TEDS installs in-orbit side and rail bottom
To the position real-time image acquisition to be detected of the EMU of walking.TEDS failure automatic identifying method mainly utilizes comparison in difference
Method, unfaulty conditions when a kind of mode of comparison in difference method is the not running that will be stored in the realtime graphic of acquisition and image library
EMU standard picture carry out characteristics of image comparison;Another way is will to deposit in the realtime graphic of acquisition and image library
The history image of the EMU of the recent unfaulty conditions of storage carries out the comparison of characteristics of image, by feature difference in two ways
Apparent place, which marks, is.
Reference picture Precision criterion in above-mentioned standard image comparison method can be realized accurately sentencing for present image difference
It is fixed, however influenced by factors water stain etc. on overhaul of train-set maintenance, natural aging, vehicle, this method is easily normal by car body
Variation is mistaken for failure, improves False Rate;It can be effectively reduced car body normal variation bring failure in history image comparison method
Erroneous judgement problem, however since history image is collection in worksite on the spot, it is influenced by Along Railway complex environment, reference picture is inadequate
Accurately, also there is apparent failure erroneous judgement.
If the influence of water stain factor on EMU locomotive can be overcome in standard picture comparison method, failure mistake can be reduced
Sentence, improves the accuracy rate of fault detection.
Summary of the invention
The present invention proposes a kind of water stain image-recognizing method based on marginal point self-similarity, can will be water stain on motor-car
Image-recognizing method comes out, and solves the problems, such as that failure is judged by accident high in standard picture comparison method in the prior art.
The technical scheme of the present invention is realized as follows:
A kind of water stain image-recognizing method based on marginal point self-similarity, comprising the following steps:
Step 1: inputting image to be detected in a computer, and the institute of the image is obtained using canny edge detection algorithm
There is marginal point;
Step 2: classifying to all marginal points, and similar marginal point belongs to an initial edge of an image outline
Line obtains all initial edge lines of image to be detected, distributes a reference direction to each marginal point, and extract each
The feature vector of marginal point, and each feature vector is normalized;
Step 3: each side on every initial edge line is calculated according to the feature vector after each marginal point normalized
The local self-similarity value of edge point and whole self-similarity value, and by the weighting of local self-similarity value and whole self-similarity value
Combine the self-similarity value final as the marginal point;
Step 4: one high threshold of setting obtains the side that the self-similarity value on every initial edge line is higher than high threshold
The set of edge point rejects the marginal point that self-similarity value on every initial edge line is lower than high threshold;
Step 5: calculating the self-similarity value of each marginal point and its closest marginal point in above-mentioned set, sets one
Low threshold obtains the marginal point that self-similarity value all in set is higher than Low threshold, and the side of Low threshold will be lower than in the set
Edge point is labeled as forming the broken edge point of irregular image;
Step 6: classify to the marginal point for being higher than Low threshold in step 5, same class marginal point forms an image outline
Calibration edge line, set a length threshold to all calibration edge line, obtain the calibration edge for being less than the length threshold
Point on the calibration edge line is labeled as forming the broken edge point of irregular image by line;
Step 7: the directional spreding histogram of the broken edge point in statistic procedure five and step 6 determines each not
The principal direction of regular marginal point presets a downwardly direction threshold range, rejects all principal directions not in direction threshold range
Broken edge point of the principal direction in the threshold range of direction is labeled as water stain image by interior broken edge point.
Preferably, in the water stain image-recognizing method based on marginal point self-similarity, root in the step 3
The final self-similarity of the marginal point on every initial edge line is calculated according to the feature vector after each marginal point normalized
The mode of value are as follows: setting PnAnd PmFor any two marginal point on edge line, feature vector is respectivelyWithThen
Any two marginal point P on edge linenAnd PmSimilarity are as follows:Here vector
The calculation of inner product is that the multiplication of vector corresponding element is added again, obtains two marginal point PnAnd PmSimilarity;
Marginal point PnLocal self-similarity value are as follows: take marginal point PnOn the edge line at place it is adjacent with the marginal point and
Four marginal point P positioned at its two sidesn-1、Pn-2、Pn+1、Pn+2, then marginal point PnLocal self-similarity value are as follows:
Marginal point PnWhole self-similarity value are as follows: it is assumed that sharing n marginal point, then marginal point P on the edge linenIt is whole
Body self-similarity value are as follows:
The weight of local self-similarity and whole self-similarity is set as Wloc,Wglo, and Wloc+Wglo=1, Wloc,Wglo∈
[0,1] combines local self-similarity value and whole self-similarity value, then marginal point PnFinal self-similarity value are as follows:
Self_Sim(Pn)=Wloc·Self_Sim(Pn)_local+Wglo·Self_Sim(Pn)_global;
Feature vector after normalizedRange between 0 to 1, then self-similarity value indicates phase between 0 to 1
Like degree, it is complete similar state when being 1 that self-similarity value, which is complete dissimilar state when being 0,.
Preferably, it in the water stain image-recognizing method based on marginal point self-similarity, is given in the step 2
Each marginal point distributes the mode of a reference direction are as follows:
For any one marginal point, the local neighborhood centered on current edge point is constructed, all pictures in the neighborhood are calculated
The gradient value of vegetarian refreshments and direction, gradient value and direction using all pixels point in the statistics with histogram neighborhood, the interior packet of histogram
Containing 9 histogram columns for dividing equally the direction scope of 0~180 degree, 180~360 degree are divided equally and are merged on 9 histogram columns;
The weighting coefficient for calculating the two neighboring direction of each marginal point pair calculates each further according to weighting coefficient and gradient value
Contribution weight is added to each histogram of the histogram where the marginal point by the contribution weight in the two neighboring direction of marginal point pair
On column, histogram peak direction is the reference direction of the marginal point.
Preferably, in the water stain image-recognizing method based on marginal point self-similarity, appoint in the step 2
The extracting mode of the feature vector of one marginal point are as follows:
Any edge point is set as P0, the reference direction of the marginal point is θ, and reference axis is rotated to reference direction;It is revolving
It is taken respectively along four orientation apart from marginal point P in coordinate system after turning0The point P of predetermined location of pixels1、P2、P3、P4, construction
With P0、P1、P2、P3、P4Centered on 5 local neighborhoods, the gradient value for calculating each pixel and each pixel are to adjacent two
The contribution weight in a direction;The directional spreding histogram for counting 5 local neighborhoods obtains 5 histogram hist (1), hist
(2),hist(3),hist(4),hist(5);The feature vector of the marginal point are as follows: FeatureVector=[hist (1) hist
(2)hist(3)hist(4)hist(5)];Finally the feature vector of each marginal point is normalized.
Preferably, in the water stain image-recognizing method based on marginal point self-similarity, each broken edge
The method of determination of the principal direction of point are as follows:
For any one broken edge point Pt, the reference direction of the marginal point is θ, and reference axis is rotated to benchmark side
To construction is with current edge point PtCentered on local neighborhood, calculate the direction of all pixels point in the neighborhood;Constructing one will
The direction scope of 0~180 degree is divided into the column diagram of 18 histogram columns, and 180~360 degree are uniformly distributed and are merged into 18 histograms
On column, the pixel number in 18 histogram columns in each histogram column direction scope is counted;The column diagram peak finally counted
It is worth the principal direction that direction is current edge point.
The invention has the benefit that first considering every initial edge line in the present invention, calculating every according to feature vector
The self-similarity of marginal point on edge line obtains the biggish edge point set of self similarity, rejects the small marginal point of self-similarity;
Recalculate the self-similarity of each marginal point according to scheduled mode in the biggish all edge point sets of self-similarity again,
It is obtained from the edge point set that similarity is higher than Low threshold, increases the continuity of marginal point;To being higher than Low threshold in set
Marginal point reclassifies, and obtains calibration edge line;It is low lower than being lower than in the point of length threshold and set that edge line length will be corrected
The point of threshold value is labeled as broken edge point;According to the water stain characteristic having, water stain line orientations substantially downwardly, to never advise
Water stain image is then identified in image.It applies the method on EMU operation troubles Motion Image Detection system, it can be effective
It identifies the water stain image on vehicle, reduces EMU failure False Rate, improve the inspection of EMU operation troubles Motion Image Detection system
The accuracy of survey.
Detailed description of the invention
To describe the technical solutions in the embodiments of the present invention more clearly, make required in being described below to embodiment
Attached drawing is briefly described, it should be apparent that, drawings in the following description are only some embodiments of the invention, for
For those of ordinary skill in the art, without any creative labor, other can also be obtained according to embodiment
Attached drawing.
Fig. 1 is the image at a certain position of the existing EMU of acquisition;
Fig. 2 is the water stain image identified in Fig. 1.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Embodiment: it is a kind of apply in EMU operation troubles Motion Image Detection system (TEDS system) based on edge
The water stain image-recognizing method of point self-similarity, comprising the following steps:
Step 1: inputting EMU image to be detected in a computer, as shown in Figure 1, being calculated using canny edge detection
Method obtains all marginal points of the image;Detailed process is as follows:
1, on computers by EMU image procossing be gray level image;
2, Gaussian Blur is carried out to reduce the interference of picture noise to gray level image;
3, the gradient value of each pixel and direction in the image after calculating noise reduction;
4, non-maxima suppression is carried out to the gradient value of each pixel, tentatively obtains image border point set;
5, edge connection is carried out using dual threshold method, rejects false edge, completion emargintion obtains more
Accurate edge point set.
Step 2: classifying to all marginal points, and similar marginal point belongs to an initial edge of an image outline
Line obtains all initial edge lines of image to be detected, distributes a reference direction to each marginal point, and extract every
The feature vector of a marginal point, and the feature vector of each marginal point is normalized;
Each marginal point distributes the mode of a reference direction are as follows:
1, for any one marginal point, the 8*8 neighborhood centered on current edge point is constructed, all pictures in the neighborhood are calculated
The gradient value of vegetarian refreshments and direction, gradient value and direction using all pixels point in the statistics with histogram neighborhood, the interior packet of histogram
Containing 9 histogram columns for dividing equally the direction scope of 0~180 degree, 20 degree of each histogram column, 180~360 degree are divided equally and are merged 9
On a histogram column;
2, the weighting coefficient for calculating each two neighboring direction of marginal point pair calculates every further according to weighting coefficient and gradient value
It is straight to be added to each of histogram where the marginal point by the contribution weight in a two neighboring direction of marginal point pair for contribution weight
On square column, histogram peak direction is the reference direction of the marginal point.
The extracting mode of the feature vector of each marginal point are as follows:
1, any edge point is set as P0, the reference direction of the marginal point is θ, and reference axis is rotated to reference direction, is sat
Mark is transformed toIt is taken respectively along four orientation apart from marginal point in coordinate system after rotation
P0The point P of predetermined location of pixels1、P2、P3、P4, construct with P0、P1、P2、P3、P4Centered on 5 8*8 neighborhoods, calculate each
Gradient value m (x ', y ')=sqrt (dx ' * dx '+dy ' * dy ') of pixel, calculates each pixel to two neighboring direction
Contribute weight w1=m (x ', y ') * do, w2=m (x ', y ') * (1-do);
2, the directional spreding histogram for counting 5 8*8 neighborhoods, obtains 5 histogram hist (1), hist (2), hist
(3),hist(4),hist(5);The feature vector of the marginal point are as follows: FeatureVector=[hist (1) hist (2) hist
(3)hist(4)hist(5)];Finally the feature vector of each marginal point is normalized.
Step 3: each side on every initial edge line is calculated according to the feature vector after each marginal point normalized
The local self-similarity value of edge point and whole self-similarity value, and by the weighting of local self-similarity value and whole self-similarity value
Combine the self-similarity value final as marginal point;
The calculation of the final self-similarity value of marginal point on every initial edge line are as follows: setting PnAnd PmFor side
Any two marginal point on edge line, feature vector are respectivelyWithThen
Any two marginal point P on edge linenAnd PmSimilarity are as follows:Here to
The calculation of amount inner product is that the multiplication of vector corresponding element is added again, obtains two marginal point PnAnd PmSimilarity;
Marginal point PnLocal self-similarity value are as follows: take marginal point PnOn the edge line at place it is adjacent with the marginal point and
Four marginal point P positioned at its two sidesn-1、Pn-2、Pn+1、Pn+2, then marginal point PnLocal self-similarity value are as follows:
Marginal point PnWhole self-similarity value are as follows: it is assumed that sharing n marginal point, then marginal point P on the edge linenIt is whole
Body self-similarity value are as follows:
The weight of local self-similarity and whole self-similarity is set as Wloc,Wglo, choose Wloc=0.8, Wglo=0.2,
Wloc,Wglo∈ [0,1] combines local self-similarity value and whole self-similarity value, then marginal point PnFinal self-similarity
Value are as follows:
Self_Sim(Pn)=Wloc·Self_Sim(Pn)_local+Wglo·Self_Sim(Pn)_global;
Feature vector after normalizedRange between 0 to 1, then self-similarity value indicates phase between 0 to 1
Like degree, it is complete similar state when being 1 that self-similarity value, which is complete dissimilar state when being 0,.
Step 4: being set as 0.7 for high threshold, obtains the edge that the self-similarity value on every initial edge line is higher than 0.7
The set of point rejects the marginal point that self-similarity value on every initial edge line is lower than high threshold.
Step 5: calculating the self-similarity of any two marginal point in the set of step 4, Low threshold be set as 0.2,
The marginal point that self-similarity value all in set is higher than 0.2 is obtained, the marginal point that 0.2 is lower than in the set is labeled as being formed
The broken edge point of irregular image.
Step 6: classify to the marginal point for being higher than Low threshold in step 5, same class marginal point forms an image outline
Calibration edge line, set length threshold 10 to all calibration edge line, obtain calibration edge of the edge line length less than 10
Point on the calibration edge line is labeled as forming the broken edge point of irregular image by line.
Step 7: the directional spreding histogram of the broken edge point in statistic procedure five and step 6, determines each not
The principal direction of regular marginal point presets 70~110 degree of downwardly direction threshold range, rejects all principal directions not 70~110
Broken edge point of the principal direction in 70~110 degree is labeled as water stain image, the principal direction by the broken edge point in degree
Broken edge point it is as shown in Figure 2;
The method of determination of the principal direction of each broken edge point are as follows: for any one broken edge point Pt, the edge
The reference direction of point is θ, and reference axis is rotated to reference direction, is constructed with current edge point PtCentered on 8*8 neighborhood, calculate
The direction of all pixels point in the neighborhood;The direction scope of 0~180 degree is divided into the cylindricality of 18 histogram columns by building one
Figure, 180~360 degree are uniformly distributed and are merged on 18 histogram columns, and each histogram column is 10 degree, count every in 18 histogram columns
Pixel number in a histogram column direction scope;The peak value direction of the column diagram finally counted is current edge point
Principal direction.
Step 8: the reference picture of the EMU to be detected in image library is extracted, using standard picture method in EMU
Image to be detected and reference picture are compared in operation troubles Motion Image Detection system, by what is identified in step 7
Water stain image is defaulted as external disturbing factor, is not the malfunction of EMU, does not mark in EMU fault detection, reduces
Failure erroneous judgement, the accuracy of the fault detection figure improved.
The neighborhood of above-mentioned appearance selects as the case may be, is also chosen as other neighborhoods such as 8*16.It is above-mentioned high threshold, low
Threshold value, length threshold and direction threshold range can be chosen according to the type of actually detected image.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Within mind and principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (6)
1. a kind of water stain image-recognizing method based on marginal point self-similarity, which comprises the following steps:
Step 1: inputting image to be detected in a computer, and all sides of the image are obtained using canny edge detection algorithm
Edge point;
Step 2: classifying to all marginal points, and similar marginal point belongs to an initial edge line of an image outline, obtains
All initial edge lines of image to be detected are taken, distribute a reference direction to each marginal point, and extract each edge
The feature vector of point, and each feature vector is normalized;
Step 3: each marginal point on every initial edge line is calculated according to the feature vector after each marginal point normalized
Local self-similarity value and whole self-similarity value, and by the weighted array of local self-similarity value and whole self-similarity value
The self-similarity value final as the marginal point;
Step 4: one high threshold of setting obtains the marginal point that the self-similarity value on every initial edge line is higher than high threshold
Set, reject every initial edge line on self-similarity value be lower than high threshold marginal point;
Step 5: calculating the self-similarity value of each marginal point and its closest marginal point in above-mentioned set, sets a low threshold
Value obtains the marginal point that self-similarity value all in set is higher than Low threshold, and the marginal point of Low threshold will be lower than in the set
Labeled as the broken edge point for forming irregular image;
Step 6: classify to the marginal point for being higher than Low threshold in step 5, same class marginal point forms the school of an image outline
Positive edge line sets a length threshold to all calibration edge lines, obtains the calibration edge line for being less than the length threshold, will
Point on the calibration edge line is labeled as forming the broken edge point of irregular image;
Step 7: the directional spreding histogram of the broken edge point in statistic procedure five and step 6 determines each irregular
The principal direction of marginal point presets a downwardly direction threshold range, rejects all principal directions not in the threshold range of direction
Broken edge point of the principal direction in the threshold range of direction is labeled as water stain image by broken edge point.
2. the water stain image-recognizing method according to claim 1 based on marginal point self-similarity, which is characterized in that described
The marginal point calculated on every initial edge line in step 3 according to the feature vector after each marginal point normalized is final
Self-similarity value mode are as follows: setting PnAnd PmFor any two marginal point on edge line, feature vector is respectivelyWithThen
Any two marginal point P on edge linenAnd PmSimilarity are as follows:Here inner product of vectors
Calculation be vector corresponding element multiplication be added again, obtain two marginal point PnAnd PmSimilarity;
Marginal point PnLocal self-similarity value are as follows: take marginal point PnIt is adjacent with the marginal point and be located on the edge line at place
Four marginal point P of its two sidesn-1、Pn-2、Pn+1、Pn+2, then marginal point PnLocal self-similarity value are as follows:
Marginal point PnWhole self-similarity value are as follows: it is assumed that sharing n marginal point, then marginal point P on the edge linenIt is whole from
Similarity are as follows:
The weight of local self-similarity and whole self-similarity is set as Wloc,Wglo, and Wloc+Wglo=1, Wloc,Wglo∈[0,
1], combine local self-similarity value and whole self-similarity value, then marginal point PnFinal self-similarity value are as follows:
Self_Sim(Pn)=Wloc·Self_Sim(Pn)_local+Wglo·Self_Sim(Pn)_global;
Feature vector after normalizedRange between 0 to 1, then self-similarity value indicates similar journey between 0 to 1
Degree, self-similarity value are complete dissimilar state when being 0, are complete similar states when being 1.
3. the water stain image-recognizing method according to claim 1 based on marginal point self-similarity, which is characterized in that described
The mode of a reference direction is distributed in step 2 to each marginal point are as follows:
For any one marginal point, the local neighborhood centered on current edge point is constructed, all pixels point in the neighborhood is calculated
Gradient value and direction, gradient value and direction using all pixels point in the statistics with histogram neighborhood, comprising by 0 in histogram
9 histogram columns that the direction scope of~180 degree is divided equally, 180~360 degree are divided equally and are merged on 9 histogram columns;
The weighting coefficient for calculating the two neighboring direction of each marginal point pair calculates each edge further according to weighting coefficient and gradient value
Contribution weight is added to each histogram column of the histogram where the marginal point to the contribution weight in two neighboring direction by point
On, histogram peak direction is the reference direction of the marginal point.
4. the water stain image-recognizing method according to claim 1 based on marginal point self-similarity, which is characterized in that described
The extracting mode of the feature vector of any of step 2 marginal point are as follows:
Any edge point is set as P0, the reference direction of the marginal point is θ, and reference axis is rotated to reference direction;After rotation
It is taken respectively along four orientation apart from marginal point P in coordinate system0The point P of predetermined location of pixels1、P2、P3、P4, construct with P0、
P1、P2、P3、P4Centered on 5 local neighborhoods, the gradient value for calculating each pixel and each pixel are to two neighboring side
To contribution weight;The directional spreding histogram for counting 5 local neighborhoods, obtain 5 histogram hist (1), hist (2),
hist(3),hist(4),hist(5);The feature vector of the marginal point are as follows: FeatureVector=[hist (1) hist (2)
hist(3)hist(4)hist(5)];Finally the feature vector of each marginal point is normalized.
5. the water stain image-recognizing method according to claim 1 based on marginal point self-similarity, which is characterized in that each
The method of determination of the principal direction of broken edge point are as follows:
For any one broken edge point Pt, the reference direction of the marginal point is θ, and reference axis is rotated to reference direction, construction
With current edge point PtCentered on local neighborhood, calculate the direction of all pixels point in the neighborhood;One is constructed by 0~180
The direction scope of degree is divided into the column diagram of 18 histogram columns, and 180~360 degree are uniformly distributed and are merged on 18 histogram columns,
Count the pixel number in 18 histogram columns in each histogram column direction scope;Where the column diagram peak value finally counted
Direction is the principal direction of current edge point.
6. a kind of EMU operation troubles Motion Image Detection system, which is characterized in that including appointing described in claim 1 to 5
One water stain image-recognizing method based on marginal point self-similarity, the water stain normal shape for being defaulted as EMU that will identify that
State is not marked in EMU fault detection.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610752438.4A CN106326901B (en) | 2016-08-30 | 2016-08-30 | Water stain image-recognizing method and TEDS system based on marginal point self-similarity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610752438.4A CN106326901B (en) | 2016-08-30 | 2016-08-30 | Water stain image-recognizing method and TEDS system based on marginal point self-similarity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106326901A CN106326901A (en) | 2017-01-11 |
CN106326901B true CN106326901B (en) | 2019-06-14 |
Family
ID=57789936
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610752438.4A Active CN106326901B (en) | 2016-08-30 | 2016-08-30 | Water stain image-recognizing method and TEDS system based on marginal point self-similarity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106326901B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109063764A (en) * | 2018-07-26 | 2018-12-21 | 福建和盛高科技产业有限公司 | A kind of judgment method of disconnecting switch closing operation in place based on machine vision |
US11023770B2 (en) | 2019-09-23 | 2021-06-01 | Hong Kong Applied Science And Technology Research Institute Co., Ltd. | Systems and methods for obtaining templates for tessellated images |
CN110827220B (en) * | 2019-11-01 | 2023-05-30 | 杭州当虹科技股份有限公司 | Anti-aliasing method based on image edge analysis |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1107179A2 (en) * | 1999-11-29 | 2001-06-13 | Eastman Kodak Company | Method for detecting sky in images |
CN101789005A (en) * | 2010-01-22 | 2010-07-28 | 深圳创维数字技术股份有限公司 | Image searching method based on region of interest (ROI) |
CN102589808A (en) * | 2012-01-16 | 2012-07-18 | 苏州临点三维科技有限公司 | Large-scale tunnel seepage point measuring method |
CN105551035A (en) * | 2015-12-09 | 2016-05-04 | 深圳市华和瑞智科技有限公司 | Stereoscopic vision matching method based on weak edge and texture classification |
CN105844278A (en) * | 2016-04-15 | 2016-08-10 | 浙江理工大学 | Multi-feature fused fabric scanning pattern recognition method |
-
2016
- 2016-08-30 CN CN201610752438.4A patent/CN106326901B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1107179A2 (en) * | 1999-11-29 | 2001-06-13 | Eastman Kodak Company | Method for detecting sky in images |
CN101789005A (en) * | 2010-01-22 | 2010-07-28 | 深圳创维数字技术股份有限公司 | Image searching method based on region of interest (ROI) |
CN102589808A (en) * | 2012-01-16 | 2012-07-18 | 苏州临点三维科技有限公司 | Large-scale tunnel seepage point measuring method |
CN105551035A (en) * | 2015-12-09 | 2016-05-04 | 深圳市华和瑞智科技有限公司 | Stereoscopic vision matching method based on weak edge and texture classification |
CN105844278A (en) * | 2016-04-15 | 2016-08-10 | 浙江理工大学 | Multi-feature fused fabric scanning pattern recognition method |
Non-Patent Citations (1)
Title |
---|
《图像的局部自相似性用于边缘检测的方法研究》;张正炳 等;;《华中理工大学学报》;19961031;第24卷(第10期);第53-55页 |
Also Published As
Publication number | Publication date |
---|---|
CN106326901A (en) | 2017-01-11 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US11580647B1 (en) | Global and local binary pattern image crack segmentation method based on robot vision | |
CN109087510B (en) | Traffic monitoring method and device | |
CN110348297B (en) | Detection method, system, terminal and storage medium for identifying stereo garage | |
CN106682586A (en) | Method for real-time lane line detection based on vision under complex lighting conditions | |
CN112084869B (en) | Compact quadrilateral representation-based building target detection method | |
CN115018828A (en) | Defect detection method for electronic component | |
CN106897681B (en) | Remote sensing image contrast analysis method and system | |
CN106326901B (en) | Water stain image-recognizing method and TEDS system based on marginal point self-similarity | |
CN106778633B (en) | Pedestrian identification method based on region segmentation | |
CN105205486A (en) | Vehicle logo recognition method and device | |
CN104809433A (en) | Zebra stripe detection method based on maximum stable region and random sampling | |
CN112036385B (en) | Library position correction method and device, electronic equipment and readable storage medium | |
CN102867188A (en) | Method for detecting seat state in meeting place based on cascade structure | |
CN113781482B (en) | Method and system for detecting crack defects of mechanical parts in complex environment | |
Maček et al. | A lane detection vision module for driver assistance | |
CN107273802A (en) | A kind of detection method and device of railroad train brake shoe drill ring failure | |
CN103985106B (en) | Apparatus and method for carrying out multiframe fusion to very noisy image | |
CN114820625A (en) | Automobile top block defect detection method | |
CN116109986A (en) | Vehicle track extraction method based on laser radar and video technology complementation | |
CN107977608B (en) | Method for extracting road area of highway video image | |
Ying et al. | An illumination-robust approach for feature-based road detection | |
CN116596428B (en) | Rural logistics intelligent distribution system based on unmanned aerial vehicle | |
CN109784229B (en) | Composite identification method for ground building data fusion | |
CN106384358B (en) | The recognition methods of irregular image based on marginal point self-similarity | |
CN106327499B (en) | The identification of greasy dirt image based on marginal point self-similarity and TEDS systems |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |