CN107220946A - A kind of real-time eliminating method of bad lumpiness image on rock transportation band - Google Patents
A kind of real-time eliminating method of bad lumpiness image on rock transportation band Download PDFInfo
- Publication number
- CN107220946A CN107220946A CN201710353593.3A CN201710353593A CN107220946A CN 107220946 A CN107220946 A CN 107220946A CN 201710353593 A CN201710353593 A CN 201710353593A CN 107220946 A CN107220946 A CN 107220946A
- Authority
- CN
- China
- Prior art keywords
- image
- mrow
- mtd
- msub
- threshold value
- 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.)
- Granted
Links
- 239000011435 rock Substances 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000001914 filtration Methods 0.000 claims abstract description 59
- 238000013467 fragmentation Methods 0.000 claims abstract description 39
- 238000006062 fragmentation reaction Methods 0.000 claims abstract description 39
- ZPUCINDJVBIVPJ-LJISPDSOSA-N cocaine Chemical compound O([C@H]1C[C@@H]2CC[C@@H](N2C)[C@H]1C(=O)OC)C(=O)C1=CC=CC=C1 ZPUCINDJVBIVPJ-LJISPDSOSA-N 0.000 claims abstract description 30
- 230000033001 locomotion Effects 0.000 claims description 15
- 239000004575 stone Substances 0.000 claims description 8
- 238000009499 grossing Methods 0.000 claims description 5
- 230000010354 integration Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 abstract description 8
- 238000004458 analytical method Methods 0.000 description 12
- 238000004519 manufacturing process Methods 0.000 description 6
- 239000002245 particle Substances 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000012935 Averaging Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004880 explosion Methods 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 239000011707 mineral Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 238000013441 quality evaluation Methods 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 1
- 238000000205 computational method Methods 0.000 description 1
- 230000008878 coupling Effects 0.000 description 1
- 238000010168 coupling process Methods 0.000 description 1
- 238000005859 coupling reaction Methods 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005188 flotation Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000010298 pulverizing process Methods 0.000 description 1
- 238000004080 punching Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/0008—Industrial image inspection checking presence/absence
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Processing (AREA)
Abstract
The invention belongs to technical field of image processing, a kind of real-time eliminating method of bad lumpiness image on rock transportation band is disclosed, including：Obtain a width RGB lumpiness images；Calculate average gray value and relative variance that the gray level image after correspondence reduces carries out the gray level image after smothing filtering；The first normal average gray threshold value is set, a part of bad rock fragmentation image is rejected；The first normal relative variance threshold value is set, a part of bad rock fragmentation image is rejected；The second normal average gray threshold value and the second normal relative variance threshold value are set, a part of bad rock fragmentation image is rejected；Corresponding gradient image is obtained, gradient average value and gradient relative variance is calculated；Average gradient threshold value and gradient relative variance threshold value are set, a part of bad rock fragmentation image is rejected；Next width lumpiness image is obtained, and is repeated the above steps, the bad rock fragmentation image on conveyer belt can be rapidly and accurately detected.
Description
Technical field
The invention belongs in technical field of image processing, more particularly to a kind of rock transportation band bad lumpiness image it is real-time
Elimination method, it is adaptable to on-line checking and the analysis of rock fragmentation image are moved on conveyer belt.
Background technology
In quarrying and mineral engineering, the measurement to the Size Distribution of rock fragmentation is very important.Building stones are exactly certainly
The mixture of right sillar and the sillar of explosion and Mechanical Crushing, is mainly used for building, highway, railway and dam etc..In order to sentence
The quality of disconnected building stones, the size and dimension parameter progress estimation to building stones particle is necessary.The Size Distribution of building stones is not still
For assessing a data of product quality, but also it is the important information for adjusting disintegrating machine or explosion production, for example：In quarrying
In production, adjust crushing gap and aperture of punching etc. is adjusted in mineral engineering.Disintegrating machine is generally set to production
Building stones in some relative narrower size range strictly specified, such as from 16mm to 30mm.One of usual disintegrating machine operation
Leading indicator is exactly average-size.In automatic pulverizing control system, include the building stones size that is averaged from what real-time system was beamed back
Feedback signal, just shows the actual development of shattering process on streamline.In actual applications, broken come out from disintegrating machine
Grain is transmitted on a conveyer belt, and a CCD (charge coupled device, charge coupling device) is placed above it
Camera is shot downwards, and then the particle in the image of acquisition is measured with image procossing, segmentation and analysis.
Prior art is mainly carried out with image procossing and analysis and computer vision technique to Complex Rock lumpiness image
At a high speed with high-precision processing and analysis, the automatic monitoring and control level in production line to improve mining and ore dressing is established
Fixed new application foundation.Rock fragmentation image is many subject images the most complicated, because the color of Rock fragmentation, granularity chi
The characteristics such as very little, shape, roughness, three-dimensional structure make image procossing, analysis and description much be difficult to other granularity subject images,
So it is significant to carry out pattern-recognition, graphical analysis and machine vision in this respect.Problem is：Image change is too big
Image segmentation is frequently caused very much to produce mistake, so as to cause measurement and the analysis result of mistake, in order to overcome this problem, to place
The image of reason should be selective, as far as possible before image procossing, remove the image of those poor qualities, for example：Without rock
Lumpiness image, rainwater conveyer belt it is reflective according to blank, by motion jitter according into blurred picture etc..
The content of the invention
In view of the above-mentioned problems, it is an object of the invention to provide bad rock fragmentation image on a kind of real-time eliminating conveyer belt
Method, can rapidly and accurately detect the bad rock fragmentation image on conveyer belt, with solve picture quality evaluation and pick
Except the problem of, so as to serve the monitoring and control on the industrial flow production line on mine and stone pit.
To reach above-mentioned purpose, the present invention, which is adopted the following technical scheme that, to be achieved.
A kind of real-time eliminating method of bad lumpiness image on rock transportation band, methods described comprises the following steps：
Step 1, the width lumpiness image that rock is moved on conveyer belt is obtained, the width lumpiness image is RGB image；
Step 2, the RGB image is converted into corresponding gray level image, and to the gray level image according to presetting
Scale factor reduced, obtain a width reduce after gray level image；
Step 3, the gray level image after being reduced to a width carries out smothing filtering, obtains the gray-scale map after smothing filtering
Picture；
Step 4, the average gray value and relative variance of the gray level image after the smothing filtering are calculated；
Step 5, the first normal average gray threshold value is set, if the average gray value of the gray level image after the smothing filtering
Less than or equal to the described first normal average gray threshold value, then transported on the corresponding conveyer belt of gray level image after the smothing filtering
The width lumpiness image of dynamic rock is bad rock fragmentation image, and the bad rock fragmentation image is rejected；
If the average gray value of the gray level image after the smothing filtering is more than the described first normal average gray threshold value,
Continue executing with step 6；
Step 6, the first normal relative variance threshold value is set, if the relative variance of the gray level image after the smothing filtering is small
In or equal to the first normal relative variance threshold value, then moved on the corresponding conveyer belt of gray level image after the smothing filtering
The width lumpiness image of rock is bad rock fragmentation image, and the bad rock fragmentation image is rejected；
If the relative variance of the gray level image after the smothing filtering is more than the described first normal relative variance threshold value, after
It is continuous to perform step 7；
Step 7, the second normal average gray threshold value of setting and the second normal relative variance threshold value, if after the smothing filtering
The average gray value of gray level image be less than or equal to the described second normal average gray threshold value, and after the smothing filtering
The relative variance of gray level image is less than or equal to the described second normal relative variance threshold value, then the gray-scale map after the smothing filtering
As the width lumpiness image that rock is moved on corresponding conveyer belt is bad rock fragmentation image, by the bad rock fragmentation image
Rejected；Otherwise, step 8 is continued executing with；
Step 8, according to the gray level image after the smothing filtering, corresponding gradient image is obtained, the gradient map is calculated
The gradient average value and gradient relative variance of picture；
Step 9, setting average gradient threshold value and gradient relative variance threshold value, if the gradient average value of the gradient image is small
In or equal to the Grads threshold, and the gradient relative variance of the gradient image is less than or equal to the gradient contra
Poor threshold value, then width lumpiness image that rock is moved on the corresponding conveyer belt of the gradient image is bad rock fragmentation image, will
The bad rock fragmentation image is rejected；
Step 10, next width lumpiness image that rock is moved on conveyer belt is obtained, and is repeated in performing step 2 to step
9, so as to move the bad lumpiness image of rock on real-time eliminating conveyer belt.
The purpose of the present invention is to carry out the quality evaluation of dynamic image, can quickly remove the rock fragmentation figure of bad quality
Picture, so as to ensure the quality that the image of the next step processing to be carried out and segmentation analysis has had.If without this process, bad matter
The image of amount can cause difficult and analytical error to follow-up image procossing, so that the accurate testing result of real-time online can not be obtained
To guarantee.The need for this method is in order to adapt to processing in real time, several steps are divided to carry out the quality analysis of image, step and step
Between avoid the calculating of repetition, analysis and computational methods are in the hope of as easy and effective as possible, it is to avoid with complicated calculating and
Analysis.It is highly suitable for the application of Rock fragmentation production scene, is also easy to expand to other similar online particle detections,
Such as：Wooden flakes on dynamic flotation bubble, conveyer belt, the quality analysis and inspection of the image such as the grain and fruit of motion
Survey.
Brief description of the drawings
In order to illustrate more clearly about the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
There is the accompanying drawing used required in technology description to be briefly described, it should be apparent that, drawings in the following description are only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, can be with
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the stream of the real-time eliminating method of bad lumpiness image on a kind of rock transportation band provided in an embodiment of the present invention
Journey schematic diagram.
Embodiment
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Site preparation is described, it is clear that described embodiment is only a part of embodiment of the invention, rather than whole embodiments.It is based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under the premise of creative work is not made
Embodiment, belongs to the scope of protection of the invention.
The embodiment of the present invention provides a kind of real-time eliminating method of bad lumpiness image on rock transportation band, as shown in figure 1,
Methods described comprises the following steps：
Step 1, the width lumpiness image that rock is moved on conveyer belt is obtained, the width lumpiness image is RGB image.
In general, the lumpiness image of rock is moved on conveyer belt in order to obtain in real time for a long time, needed above conveyer belt
Set up the lumpiness image that a common CCD camera obtains the rock moved on conveyer belt, the inequality shone in order to avoid ambient light
And it is unstable, avenged etc. also for dustproof and rainproof, it is necessary to set up one above and side-closed lighting box, install in case uniform
Light source (lamp) and CCD camera, in order to clearly capture motion (general motion speed is 2-3 meter per seconds) lumpiness image, CCD phases
Machine should can set capture parameter, the shutter and aperture both often said, the image of acquisition can be transmitted by the image plate of connection
Successive image processing is carried out to computer.
Step 2, the RGB image is converted into corresponding gray level image, and to the gray level image according to presetting
Scale factor reduced, obtain a width reduce after gray level image.
Step 2 is specifically included：
Because rock fragmentation is not colored obvious, in order to reduce amount of calculation, the RGB image is converted into corresponding gray-scale map
Picture：
F (x, y)Ash=(f (x, y)R+ f (x, y)G+ f (x, y)B)/3
Wherein, f (x, y)R, f (x, y)G, f (x, y)BRespectively represent RGB image in be located at (x, y) place pixel it is red, green,
Blue pixel value, f (x, y)AshIt is located at the gray value of the pixel at (x, y) place in expression gray level image；X ∈ (1 ..., 2 × M), y ∈
(1 ..., 2 × N), 2 × M is total number of pixels that gray level image width is tieed up, and 2 × N is individual for total pixel of gray level image height dimension
Number；
In order to eliminate stain and bright spot noise and further reduce the workload of subsequent treatment, gray level image is contracted
It is small；Scale factor set in advance is 1/4, then the gray level image is reduced according to the scale factor, every four phases
Adjacent pixel take average gray as the gray level image after diminution corresponding position gray value so that the gray scale after reducing
Image is M in total number of pixels that width is tieed up, and is N in total number of pixels of height dimension.
Step 3, the gray level image after being reduced to a width carries out smothing filtering, obtains the gray-scale map after smothing filtering
Picture.
If smooth algorithm (such as neighborhood averaging or Gaussian smoothing method) routinely is to the gray-scale map after diminution
It is smooth as carrying out, faint edge smoothing may be fallen, so, fractional order integration smoothing method is taken to remove the diminution
The noise in gray level image afterwards, but in order to not only keep the smooth of image but also the border between lumpiness can be kept not to be lost, to passing
The filter template of system is improved：
Smothing filtering, used 5 × 5 are carried out to the gray level image after the diminution using fractional order integration smoothing method
The filter coefficient h of template is：
Then the gray level image after smothing filtering is in (x1, y1) place gray value F (x1, y1) be：F(x1, y1)=(f (x1, y1)*
H) left side two of the gray level image behind/8, and smothing filtering is arranged, the right two is arranged, the gray scale of the row of top two and following two rows pixel
The gray value being worth with the gray level image after diminution in corresponding position is identical；
It should be noted that the gray level image after smothing filtering is in (x1, y1) place gray value F (x1, y1) be：F(x1, y1)
=(f (x1, y1) * h)/8, the filtering operation represented by the formula refers to, obtains the gray level image after smothing filtering with (x1, y1) place
Pixel centered on 25 pixels so that this 25 pixels and filter coefficient distinguish convolution, so as to obtain (x1, y1) place
Gray value F (x1, y1)。
Wherein, f (x1, y1) represent reduce after gray level image in (x1, y1) place gray value, and x1∈ (0 ..., M),
y1∈ (0 ..., N).
Step 4, the average gray value and relative variance of the gray level image after the smothing filtering are calculated.
Step 4 is specifically included：
Calculate the average gray value y and relative variance S of the gray level image after the smothing filteringPhase：
SPhase=(s/v) × 100
Wherein, F (x1, y1) represent the gray level image after smothing filtering in (x1, y1) place gray value, x1∈ (0 ..., M),
y1Gray level image after ∈ (0 ..., N), smothing filtering is M in total number of pixels that width is tieed up, in total pixel of height dimension
Number is N, and S represents the variance of the gray level image after smothing filtering.
Step 5, the first normal average gray threshold value is set, if the average gray value of the gray level image after the smothing filtering
Less than or equal to the described first normal average gray threshold value, then transported on the corresponding conveyer belt of gray level image after the smothing filtering
The width lumpiness image of dynamic rock is bad rock fragmentation image, and the bad rock fragmentation image is rejected；
If the average gray value of the gray level image after the smothing filtering is more than the described first normal average gray threshold value,
Continue executing with step 6.
Typically, since being influenceed by illumination and movement velocity, the lumpiness picture quality of motion rock can be low, and works as
When lumpiness image averaging gray value is very low, it is a piece of (such as that the rock fragmentation in image can obscure a piece of or dark gray even black：Nothing
Lumpiness image), it is impossible to follow-up image procossing and segmentation are carried out, so in order to avoid choosing this image, it is necessary to according to scene
Situation (rock colourity, size etc.) sets the first normal average gray threshold value.
Setting the first normal average gray threshold value is specially：The artificial width qualitative picture for choosing motion rock, is somebody's turn to do
The average gray value of qualitative picture, set the qualitative picture average gray value 30% as the first normal average gray threshold
Value.
Step 6, the first normal relative variance threshold value is set, if the relative variance of the gray level image after the smothing filtering is small
In or equal to the first normal relative variance threshold value, then moved on the corresponding conveyer belt of gray level image after the smothing filtering
The width lumpiness image of rock is bad rock fragmentation image, and the bad rock fragmentation image is rejected；
If the relative variance of the gray level image after the smothing filtering is more than the described first normal relative variance threshold value, after
It is continuous to perform step 7.
Although the image of a part of bad quality can be rejected in steps of 5, although the image average gray value being selected
It is higher, but yet some images are low-quality images, for example：The image obscured as caused by movement velocity, or by unexpected
Whiteboard images etc. caused by strong light, the variance of these images all can be very low, therefore can be judged with the variance of image in image
Whether lumpiness is had：If variance yields is high, it was demonstrated that gradation of image difference is big, that is, lumpiness is more.
Problem is：Under different illumination conditions, the flat gray average of different images is had, and now, same lumpiness
Number and size also result in the variance differed greatly.It is difficult to the problem of unification judges in order to avoid this, the technical program is drawn
The quality of image is judged with relative error.
In step 6, the first normal relative variance threshold value of setting is specially：The artificial width high-quality figure for choosing motion rock
Picture, obtains the relative variance of the qualitative picture, set the qualitative picture relative variance 40% as the first normal contra
Poor threshold value.
Step 7, the second normal average gray threshold value of setting and the second normal relative variance threshold value, if after the smothing filtering
The average gray value of gray level image be less than or equal to the described second normal average gray threshold value, and after the smothing filtering
The relative variance of gray level image is less than or equal to the described second normal relative variance threshold value, then the gray-scale map after the smothing filtering
As the width lumpiness image that rock is moved on corresponding conveyer belt is bad rock fragmentation image, by the bad rock fragmentation image
Rejected；Otherwise, step 8 is continued executing with.
Further, step 5 and step 6 are the quality that image is judged with single index, but some situations need knot
Two kinds of parameters are closed to judge that ability is reliable.
In step 7, the second normal average gray threshold value of setting and the second normal relative variance threshold value are specially：
The artificial width qualitative picture for choosing motion rock, obtains the average gray value and relative variance of the qualitative picture,
Set the qualitative picture average gray value 45% as the second normal average gray threshold value, set the relative of the qualitative picture
The 60% of variance is used as the second normal relative variance threshold value.
Step 8, according to the gray level image after the smothing filtering, corresponding gradient image is obtained, the gradient map is calculated
The gradient average value and gradient relative variance of picture.
It should be noted that by the rejecting of above-mentioned steps 5, step 6 and step 7,70%-80% or so bad quality
Image can be screened, and the image of the remaining bad quality of 20%-30% can be picked by the criterion in step 8 and step 9
Remove.
Step 8 is specifically included：
First differential is carried out to the gray level image after the smothing filtering and obtains corresponding gradient image；Calculate the gradient
The gradient average value V of image1With gradient relative variance S1 phase：
S1 phase=(s1/v1)×100
Wherein, G (x2, y2) represent gradient image in (x2, y2) place Grad, x2∈ (0 ..., M), y2∈ (0 ...,
N), gradient image is M in total number of pixels that width is tieed up, and is N, S in total number of pixels of height dimension1Represent the side of gradient image
Difference.
Step 9, setting average gradient threshold value and gradient relative variance threshold value, if the gradient average value of the gradient image is small
In or equal to the Grads threshold, and the gradient relative variance of the gradient image is less than or equal to the gradient contra
Poor threshold value, then width lumpiness image that rock is moved on the corresponding conveyer belt of the gradient image is bad rock fragmentation image, will
The bad rock fragmentation image is rejected.
In step 9, setting average gradient threshold value and gradient relative variance threshold value are specially：
The artificial width qualitative picture for choosing motion rock, obtains the average gradient of the corresponding gradient image of the qualitative picture
Threshold value and gradient relative variance threshold value, 50% conduct for setting the average gradient threshold value of the corresponding gradient image of the qualitative picture are flat
Equal Grads threshold, set the corresponding gradient image of the qualitative picture gradient relative variance threshold value 60% as gradient contra
Poor threshold value.
Step 10, next width lumpiness image that rock is moved on conveyer belt is obtained, and is repeated in performing step 2 to step
9, so as to move the bad lumpiness image of rock on real-time eliminating conveyer belt.
Final remaining lumpiness image is the preferable image of quality, as long as follow-up Processing Algorithm is suitable for the class of image
Not, big error would not be produced to follow-up processing, so as to carry out follow-up image segmentation and analysis.
One of ordinary skill in the art will appreciate that：Realizing all or part of step of above method embodiment can pass through
Programmed instruction related hardware is completed, and foregoing program can be stored in computer read/write memory medium, and the program exists
During execution, the step of execution includes above method embodiment；And foregoing storage medium includes：ROM, RAM, magnetic disc or CD
Etc. it is various can be with the medium of store program codes.
The foregoing is only a specific embodiment of the invention, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention should be based on the protection scope of the described claims.
Claims (9)
1. a kind of real-time eliminating method of bad lumpiness image on rock transportation band, it is characterised in that methods described includes as follows
Step：
Step 1, the width lumpiness image that rock is moved on conveyer belt is obtained, the width lumpiness image is RGB image；
Step 2, the RGB image is converted into corresponding gray level image, and to the gray level image according to ratio set in advance
The example factor is reduced, and obtains the gray level image after a width reduces；
Step 3, the gray level image after being reduced to a width carries out smothing filtering, obtains the gray level image after smothing filtering；
Step 4, the average gray value and relative variance of the gray level image after the smothing filtering are calculated；
Step 5, the first normal average gray threshold value is set, if the average gray value of the gray level image after the smothing filtering is less than
Or equal to the described first normal average gray threshold value, then move rock on the corresponding conveyer belt of gray level image after the smothing filtering
The width lumpiness image of stone is bad rock fragmentation image, and the bad rock fragmentation image is rejected；
If the average gray value of the gray level image after the smothing filtering is more than the described first normal average gray threshold value, continue
Perform step 6；
Step 6, set the first normal relative variance threshold value, if the relative variance of the gray level image after the smothing filtering be less than or
Person is equal to the described first normal relative variance threshold value, then moves rock on the corresponding conveyer belt of gray level image after the smothing filtering
The width lumpiness image be bad rock fragmentation image, the bad rock fragmentation image is rejected；
If the relative variance of the gray level image after the smothing filtering is more than the described first normal relative variance threshold value, continue to hold
Row step 7；
Step 7, the second normal average gray threshold value of setting and the second normal relative variance threshold value, if the ash after the smothing filtering
The average gray value for spending image is less than or equal to the described second normal average gray threshold value, and the gray scale after the smothing filtering
The relative variance of image is less than or equal to the described second normal relative variance threshold value, then the gray level image pair after the smothing filtering
The width lumpiness image that rock is moved on the conveyer belt answered is bad rock fragmentation image, and the bad rock fragmentation image is carried out
Reject；Otherwise, step 8 is continued executing with；
Step 8, according to the gray level image after the smothing filtering, corresponding gradient image is obtained, the gradient image is calculated
Gradient average value and gradient relative variance；
Step 9, setting average gradient threshold value and gradient relative variance threshold value, if the gradient average value of the gradient image be less than or
Person is equal to the Grads threshold, and the gradient relative variance of the gradient image is less than or equal to the gradient relative variance threshold
Value, then width lumpiness image that rock is moved on the corresponding conveyer belt of the gradient image is bad rock fragmentation image, by this not
Good rock fragmentation image is rejected；
Step 10, next width lumpiness image that rock is moved on conveyer belt is obtained, and is repeated in performing step 2 to step 9, from
And the bad lumpiness image of rock is moved on real-time eliminating conveyer belt.
2. the real-time eliminating method of bad lumpiness image on a kind of rock transportation band according to claim 1, its feature exists
In step 2 is specifically included：
The RGB image is converted into corresponding gray level image：
f(x,y)Ash=(f (x, y)R+f(x,y)G+f(x,y)B)/3
Wherein, f (x, y)R、f(x,y)G、f(x,y)BIt is located at the red, green, blue picture of the pixel at (x, y) place in expression RGB image respectively
Element value, f (x, y)AshIt is located at the gray value of the pixel at (x, y) place in expression gray level image；X ∈ (1 ..., 2 × M), y ∈
(1 ..., 2 × N), 2 × M is total number of pixels that gray level image width is tieed up, and 2 × N is individual for total pixel of gray level image height dimension
Number；
Scale factor set in advance is 1/4, then the gray level image is reduced according to the scale factor, every four phases
Adjacent pixel take average gray as the gray level image after diminution corresponding position gray value so that the gray scale after reducing
Image is M in total number of pixels that width is tieed up, and is N in total number of pixels of height dimension.
3. the real-time eliminating method of bad lumpiness image on a kind of rock transportation band according to claim 1, its feature exists
In step 3 is specifically included：
Smothing filtering, used 5 × 5 template are carried out to the gray level image after the diminution using fractional order integration smoothing method
Filter coefficient be：
<mrow>
<mi>h</mi>
<mo>=</mo>
<mfenced open = "[" close = "]">
<mtable>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mn>0.09375</mn>
</mtd>
<mtd>
<mn>0.125</mn>
</mtd>
<mtd>
<mn>0.09375</mn>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0.09375</mn>
</mtd>
<mtd>
<mn>0.3125</mn>
</mtd>
<mtd>
<mn>0.5</mn>
</mtd>
<mtd>
<mn>0.3125</mn>
</mtd>
<mtd>
<mn>0.09375</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0.125</mn>
</mtd>
<mtd>
<mn>0.5</mn>
</mtd>
<mtd>
<mn>2</mn>
</mtd>
<mtd>
<mn>0.5</mn>
</mtd>
<mtd>
<mn>0.125</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0.09375</mn>
</mtd>
<mtd>
<mn>0.3125</mn>
</mtd>
<mtd>
<mn>0.5</mn>
</mtd>
<mtd>
<mn>0.3125</mn>
</mtd>
<mtd>
<mn>0.09375</mn>
</mtd>
</mtr>
<mtr>
<mtd>
<mn>0</mn>
</mtd>
<mtd>
<mrow>
<mo>-</mo>
<mn>0.09375</mn>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>-</mo>
<mn>0.125</mn>
</mrow>
</mtd>
<mtd>
<mrow>
<mo>-</mo>
<mn>0.09375</mn>
</mrow>
</mtd>
<mtd>
<mn>0</mn>
</mtd>
</mtr>
</mtable>
</mfenced>
</mrow>
Then the gray level image after smothing filtering is in (x1,y1) place gray value F (x1,y1) be：F(x1, y1) and=(f (x1,y1)*h)/
The left side two of gray level image behind 8, and smothing filtering is arranged, the right two is arranged, the gray value of the row of top two and following two rows pixel
Gray value with the gray level image after diminution in corresponding position is identical；
Wherein, f (x1,y1) represent reduce after gray level image in (x1,y1) place gray value, and x1∈ (0 ..., M), y1∈
(0,...,N)。
4. the real-time eliminating method of bad lumpiness image on a kind of rock transportation band according to claim 1, its feature exists
In step 4 is specifically included：
Calculate the average gray value V and relative variance S of the gray level image after the smothing filteringPhase：
<mrow>
<mi>V</mi>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>y</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mi>F</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>/</mo>
<mi>M</mi>
<mo>&times;</mo>
<mi>N</mi>
</mrow>
<mrow>
<mi>S</mi>
<mo>=</mo>
<msqrt>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>y</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<mi>F</mi>
<mo>(</mo>
<mrow>
<msub>
<mi>x</mi>
<mn>1</mn>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mn>1</mn>
</msub>
</mrow>
<mo>)</mo>
<mo>-</mo>
<mi>V</mi>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>/</mo>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mo>&times;</mo>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</msqrt>
</mrow>
SPhase=(S/V)×100
Wherein, F (x1,y1) represent the gray level image after smothing filtering in (x1,y1) place gray value, x1∈ (0 ..., M), y1∈
Gray level image after (0 ..., N), smothing filtering is M in total number of pixels that width is tieed up, and is in total number of pixels of height dimension
N, S represent the variance of the gray level image after smothing filtering.
5. the real-time eliminating method of bad lumpiness image on a kind of rock transportation band according to claim 1, its feature exists
In in step 5, the first normal average gray threshold value of setting is specially：The artificial width qualitative picture for choosing motion rock, is obtained
The average gray value of the qualitative picture, set the qualitative picture average gray value 30% as the first normal average gray threshold
Value.
6. the real-time eliminating method of bad lumpiness image on a kind of rock transportation band according to claim 1, its feature exists
In in step 6, the first normal relative variance threshold value of setting is specially：The artificial width qualitative picture for choosing motion rock, is obtained
The relative variance of the qualitative picture, set the qualitative picture relative variance 40% as the first normal relative variance threshold value.
7. the real-time eliminating method of bad lumpiness image on a kind of rock transportation band according to claim 1, its feature exists
In in step 7, the second normal average gray threshold value of setting and the second normal relative variance threshold value are specially：
The artificial width qualitative picture for choosing motion rock, obtains the average gray value and relative variance of the qualitative picture, sets
The 45% of the average gray value of the qualitative picture sets the relative variance of the qualitative picture as the second normal average gray threshold value
60% be used as the second normal relative variance threshold value.
8. the real-time eliminating method of bad lumpiness image on a kind of rock transportation band according to claim 1, its feature exists
In step 8 is specifically included：
First differential is carried out to the gray level image after the smothing filtering and obtains corresponding gradient image；Calculate the gradient image
Gradient average value V1With gradient relative variance S1 phase：
<mrow>
<msub>
<mi>V</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>y</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<mi>G</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mn>2</mn>
</msub>
<mo>)</mo>
</mrow>
<mo>/</mo>
<mi>M</mi>
<mo>&times;</mo>
<mi>N</mi>
</mrow>
<mrow>
<msub>
<mi>S</mi>
<mn>1</mn>
</msub>
<mo>=</mo>
<msqrt>
<mrow>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>M</mi>
</munderover>
<munderover>
<mo>&Sigma;</mo>
<mrow>
<msub>
<mi>y</mi>
<mn>2</mn>
</msub>
<mo>=</mo>
<mn>1</mn>
</mrow>
<mi>N</mi>
</munderover>
<msup>
<mrow>
<mo>(</mo>
<mi>G</mi>
<mo>(</mo>
<mrow>
<msub>
<mi>x</mi>
<mn>2</mn>
</msub>
<mo>,</mo>
<msub>
<mi>y</mi>
<mn>2</mn>
</msub>
</mrow>
<mo>)</mo>
<mo>-</mo>
<msub>
<mi>V</mi>
<mn>1</mn>
</msub>
<mo>)</mo>
</mrow>
<mn>2</mn>
</msup>
<mo>/</mo>
<mrow>
<mo>(</mo>
<mi>M</mi>
<mo>&times;</mo>
<mi>N</mi>
<mo>-</mo>
<mn>1</mn>
<mo>)</mo>
</mrow>
</mrow>
</msqrt>
</mrow>
S1 phase=(S1/V1)×100
Wherein, G (x2,y2) represent gradient image in (x2,y2) place Grad, x2∈ (0 ..., M), y2∈ (0 ..., N), ladder
Degree image is M in total number of pixels that width is tieed up, and is N, S in total number of pixels of height dimension1Represent the variance of gradient image.
9. the real-time eliminating method of bad lumpiness image on a kind of rock transportation band according to claim 1, its feature exists
In in step 9, setting average gradient threshold value and gradient relative variance threshold value are specially：
The artificial width qualitative picture for choosing motion rock, obtains the average gradient threshold value of the corresponding gradient image of the qualitative picture
With gradient relative variance threshold value, set the 50% of the average gradient threshold value of the corresponding gradient image of the qualitative picture and be used as average ladder
Spend threshold value, set the corresponding gradient image of the qualitative picture gradient relative variance threshold value 60% as gradient relative variance threshold
Value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710353593.3A CN107220946B (en) | 2017-05-18 | 2017-05-18 | Real-time removing method for bad block degree images on rock conveyer belt |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710353593.3A CN107220946B (en) | 2017-05-18 | 2017-05-18 | Real-time removing method for bad block degree images on rock conveyer belt |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107220946A true CN107220946A (en) | 2017-09-29 |
| CN107220946B CN107220946B (en) | 2020-06-23 |
Family
ID=59944259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710353593.3A Expired - Fee Related CN107220946B (en) | 2017-05-18 | 2017-05-18 | Real-time removing method for bad block degree images on rock conveyer belt |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107220946B (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241867A (en) * | 2018-08-16 | 2019-01-18 | 清能艾科（深圳）能源技术有限公司 | Using the method and device of intelligent algorithm identification digital cores image |
| CN110689550A (en) * | 2019-10-12 | 2020-01-14 | 嘉应学院 | Efficient and automatic screening system and method for lumbar vertebra sagittal plane CT (computed tomography) images |
| WO2023279556A1 (en) * | 2021-07-09 | 2023-01-12 | 福建南方路面机械股份有限公司 | Aggregate particle size sampling and monitoring method |
| CN116687442A (en) * | 2023-08-08 | 2023-09-05 | 汕头市超声仪器研究所股份有限公司 | Fetal face imaging method based on three-dimensional volume data |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101567044A (en) * | 2009-05-22 | 2009-10-28 | 北京大学 | Method for detecting quality of human face image |
| CN102567996A (en) * | 2012-01-05 | 2012-07-11 | 中国地质大学（武汉） | Remote sensing satellite image quality evaluation method |
| CN104881878A (en) * | 2015-06-12 | 2015-09-02 | 武汉大学 | Image quality evaluation method based on multi-scale gradient difference entropies |
-
2017
- 2017-05-18 CN CN201710353593.3A patent/CN107220946B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101567044A (en) * | 2009-05-22 | 2009-10-28 | 北京大学 | Method for detecting quality of human face image |
| CN102567996A (en) * | 2012-01-05 | 2012-07-11 | 中国地质大学（武汉） | Remote sensing satellite image quality evaluation method |
| CN104881878A (en) * | 2015-06-12 | 2015-09-02 | 武汉大学 | Image quality evaluation method based on multi-scale gradient difference entropies |
Non-Patent Citations (2)
| Title |
|---|
| 王卫星: "岩石颗粒计算机视觉系统", 《有色金属(矿山部分)》 * |
| 王志明: "无参考图像质量评价综述", 《自动化学报 》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241867A (en) * | 2018-08-16 | 2019-01-18 | 清能艾科（深圳）能源技术有限公司 | Using the method and device of intelligent algorithm identification digital cores image |
| CN110689550A (en) * | 2019-10-12 | 2020-01-14 | 嘉应学院 | Efficient and automatic screening system and method for lumbar vertebra sagittal plane CT (computed tomography) images |
| CN110689550B (en) * | 2019-10-12 | 2022-06-21 | 嘉应学院 | High-efficiency automatic screening system and method for CT (computed tomography) images of sagittal plane of lumbar vertebra |
| WO2023279556A1 (en) * | 2021-07-09 | 2023-01-12 | 福建南方路面机械股份有限公司 | Aggregate particle size sampling and monitoring method |
| CN116687442A (en) * | 2023-08-08 | 2023-09-05 | 汕头市超声仪器研究所股份有限公司 | Fetal face imaging method based on three-dimensional volume data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107220946B (en) | 2020-06-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103051872B (en) | Based on the belt deflection detection method of Edge extraction | |
| CN107220946A (en) | A kind of real-time eliminating method of bad lumpiness image on rock transportation band | |
| Schmugge et al. | Detection of cracks in nuclear power plant using spatial-temporal grouping of local patches | |
| CN107314957B (en) | Method for measuring rock block size distribution | |
| CN102495069B (en) | Method for detecting defects of chain belts of zipper on basis of digital image processing | |
| CN102175700B (en) | Method for detecting welding seam segmentation and defects of digital X-ray images | |
| CN110363781B (en) | Molten pool contour detection method based on deep neural network | |
| CN102636490A (en) | Method for detecting surface defects of dustproof cover of bearing based on machine vision | |
| Guo et al. | A method of blasted rock image segmentation based on improved watershed algorithm | |
| US9846929B2 (en) | Fast density estimation method for defect inspection application | |
| CN104537651B (en) | Proportion detecting method and system for cracks in road surface image | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN109685760A (en) | A kind of SLM powder bed powder laying image convex closure depression defect detection method based on MATLAB | |
| CN105738294A (en) | Automatic spikelike fruit detection device and method based on monocular multi-view imaging | |
| CN108280838A (en) | A kind of intermediate plate tooth form defect inspection method based on edge detection | |
| CN116188459B (en) | Line laser rapid identification method and system for belt tearing detection | |
| CN107274403A (en) | A kind of evaluation method of flotation surface quality | |
| CN104568956A (en) | Machine vision based detection method for strip steel surface defects | |
| CN109544513A (en) | A kind of steel pipe end surface defect extraction knowledge method for distinguishing | |
| Hashmi et al. | Computer-vision based visual inspection and crack detection of railroad tracks | |
| Koh et al. | Improving particle size measurement using multi-flash imaging | |
| CN117078584A (en) | Roadway damage detection and safety rating method based on multi-region attention mechanism | |
| Ji et al. | Bucket teeth detection based on faster region convolutional neural network | |
| CN113361532B (en) | Image recognition method, system, storage medium, device, terminal and application | |
| CN110533698B (en) | Foundation pit construction pile detection control method based on visual detection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| 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: 20200623 |