CN107220946B - Real-time removing method for bad block degree images on rock conveyer belt - Google Patents
Real-time removing method for bad block degree images on rock conveyer belt Download PDFInfo
- Publication number
- CN107220946B CN107220946B CN201710353593.3A CN201710353593A CN107220946B CN 107220946 B CN107220946 B CN 107220946B CN 201710353593 A CN201710353593 A CN 201710353593A CN 107220946 B CN107220946 B CN 107220946B
- Authority
- CN
- China
- Prior art keywords
- image
- gray
- gradient
- rock
- average
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
- 239000011435 rock Substances 0.000 title claims abstract description 79
- 238000000034 method Methods 0.000 title claims abstract description 26
- 238000001914 filtration Methods 0.000 claims abstract description 35
- 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 13
- 230000002411 adverse Effects 0.000 claims description 12
- 238000009499 grossing Methods 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims description 2
- 238000012545 processing Methods 0.000 abstract description 14
- 238000004458 analytical method Methods 0.000 description 8
- 238000004519 manufacturing process Methods 0.000 description 6
- 239000002245 particle Substances 0.000 description 5
- 238000005286 illumination Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 3
- 238000005065 mining Methods 0.000 description 3
- 239000004575 stone Substances 0.000 description 3
- 238000005422 blasting Methods 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 238000010191 image analysis Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 229910052500 inorganic mineral Inorganic materials 0.000 description 2
- 239000000463 material Substances 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
- 230000011218 segmentation Effects 0.000 description 2
- 238000003860 storage Methods 0.000 description 2
- 238000006467 substitution reaction Methods 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 239000000428 dust Substances 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
- 238000005516 engineering process Methods 0.000 description 1
- 238000005188 flotation Methods 0.000 description 1
- 239000012634 fragment Substances 0.000 description 1
- 238000003706 image smoothing Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003909 pattern recognition Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 238000000926 separation method Methods 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Images
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 the technical field of image processing, and discloses a method for removing bad block images on a rock conveyer belt in real time, which comprises the following steps: acquiring an RGB block image; calculating the average gray value and the relative variance of the gray image subjected to smooth filtering corresponding to the reduced gray image; setting a first normal average gray threshold value, and removing a part of bad rock block degree images; setting a first normal relative variance threshold value, and removing a part of bad rock block degree images; setting a second normal average gray threshold and a second normal relative variance threshold, and removing a part of bad rock block degree images; obtaining a corresponding gradient image, and calculating a gradient average value and a gradient relative variance; setting an average gradient threshold value and a gradient relative variance threshold value, and removing a part of bad rock block degree images; and acquiring the next block image, and repeating the steps to quickly and accurately detect the bad rock block image on the conveyor belt.
Description
Technical Field
The invention belongs to the technical field of image processing, and particularly relates to a real-time removing method of bad block degree images on a rock conveyer belt, which is suitable for online detection and analysis of moving rock block degree images on the conveyer belt.
Background
In quarrying and mining engineering, the measurement of the size distribution of rock mass is very important. The rock material is a mixture of natural rock blocks and rock blocks obtained by blasting and mechanical crushing, and is mainly used for buildings, roads, railways, dams and the like. In order to judge the quality of stone, it is necessary to estimate the size and shape parameters of stone particles. The size distribution of rock is not only a data used to evaluate the quality of the product, but also important information for adjusting the crusher or blasting production, such as: in quarrying production, the clearance of a crusher is adjusted, and the hole diameter of a punched hole is adjusted in mining engineering. Crushers are generally set to produce rock material in a relatively narrow size range, such as from 16mm to 30mm, which is strictly specified. Typically one of the main indicators of crusher operation is average size. In an automatic crushing control system, a feedback signal including the average stone size, sent back from the real-time system, shows the actual progress of the crushing process on the production line. In practical applications, the crushed particles from the crusher are transported on a conveyor belt, a CCD (charge coupled device) camera is placed above the conveyor belt to take a downward image, and the particles in the acquired image are measured by image processing, segmentation and analysis.
In the prior art, image processing and analysis and computer vision technology are mainly used for processing and analyzing complex rock block images at high speed and high precision, and a new application foundation is laid for improving the automatic monitoring and control level on a production line of mining and mineral separation. The rock block image is the most complex multi-object image, and because the characteristics of the rock block such as color, granularity size, shape, roughness, three-dimensional structure and the like make the image processing, analysis and description more difficult for other granularity object images, the rock block image is significant in the aspects of pattern recognition, image analysis and machine vision. The problems are that: to overcome the problem of image segmentation errors resulting from too frequent image changes, which may lead to erroneous measurement and analysis results, the processed images should be selective, trying to remove those of poor quality before image processing, for example: a rock-free block image, a white board formed by reflecting light of a rainwater conveyer belt, a blurred image formed by motion shake and the like.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method for removing an image of a block size of a bad rock on a conveyor belt in real time, which can quickly and accurately detect the image of the block size of the bad rock on the conveyor belt to solve the problems of image quality evaluation and removal, and thus can serve for monitoring and control in an industrial flow production line in mines and quarries.
In order to achieve the purpose, the invention is realized by adopting the following technical scheme.
A real-time removing method for bad block images on a rock conveyer belt comprises the following steps:
step 1, acquiring a lumpy image of a moving rock on a conveyor belt, wherein the lumpy image is an RGB image;
step 2, converting the RGB image into a corresponding gray image, and reducing the gray image according to a preset scale factor to obtain a reduced gray image;
step 3, performing smooth filtering on the reduced gray level image to obtain a smooth filtered gray level image;
step 4, calculating the average gray value and the relative variance of the gray image after smooth filtering;
step 5, setting a first normal average gray threshold, if the average gray value of the gray image after smooth filtering is smaller than or equal to the first normal average gray threshold, taking the block degree image of the moving rocks on the conveyer belt corresponding to the gray image after smooth filtering as a bad rock block degree image, and removing the bad rock block degree image;
if the average gray value of the gray image after smooth filtering is larger than the first normal average gray threshold value, continuing to execute the step 6;
step 6, setting a first normal relative variance threshold, if the relative variance of the smooth filtered gray level image is less than or equal to the first normal relative variance threshold, taking the block degree image of the moving rocks on the conveyer belt corresponding to the smooth filtered gray level image as an undesirable rock block degree image, and removing the undesirable rock block degree image;
if the relative variance of the gray-scale image after smooth filtering is larger than the first normal relative variance threshold, continuing to execute step 7;
step 7, setting a second normal average gray threshold and a second normal relative variance threshold, if the average gray value of the gray image after smooth filtering is smaller than or equal to the second normal average gray threshold and the relative variance of the gray image after smooth filtering is smaller than or equal to the second normal relative variance threshold, the block image of the moving rocks on the conveyer belt corresponding to the gray image after smooth filtering is an adverse rock block image, and removing the adverse rock block image; otherwise, continuing to execute the step 8;
step 8, obtaining a corresponding gradient image according to the smooth filtered gray level image, and calculating a gradient average value and a gradient relative variance of the gradient image;
step 9, setting an average gradient threshold value and a relative gradient variance threshold value, if the average gradient value of the gradient image is less than or equal to the gradient threshold value and the relative gradient variance of the gradient image is less than or equal to the relative gradient variance threshold value, determining that the block image of the moving rocks on the conveyer belt corresponding to the gradient image is an adverse rock block image, and removing the adverse rock block image;
and step 10, acquiring the next block degree image of the moving rock on the conveyor belt, and sequentially and repeatedly executing the step 2 to the step 9, thereby eliminating the bad block degree image of the moving rock on the conveyor belt in real time.
The invention aims to evaluate the quality of a dynamic image, and can quickly remove a rock block image with poor quality, thereby ensuring that the image to be processed and segmented and analyzed in the next step has good quality. Without this process, the poor quality images cause difficulties and analysis errors in subsequent image processing, so that real-time online accurate detection results cannot be guaranteed. The method is divided into a plurality of steps to analyze the quality of the image so as to meet the requirement of real-time processing, repeated calculation is avoided among the steps, the analysis and calculation method is simple and effective as far as possible, and the complex calculation and analysis are avoided. The method is very suitable for the application of a mineral rock block size production field, and can be easily expanded to other similar online particle detection methods, such as: dynamic flotation bubbles, wood fragments on a conveyor belt, moving grain particles, fruits and other images are analyzed and detected.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flow chart of a method for removing bad block degree images on a rock conveyer belt in real time according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
The embodiment of the invention provides a method for removing bad block degree images on a rock conveyer belt in real time, which comprises the following steps of:
step 1, acquiring a lumpy image of a moving rock on a conveyor belt, wherein the lumpy image is an RGB image.
Generally, in order to obtain the block images of the rocks moving on the conveyor belt in real time for a long time, a common CCD camera needs to be erected above the conveyor belt to obtain the block images of the rocks moving on the conveyor belt, in order to avoid the unevenness and instability of external illumination and also to prevent dust, rain, snow and the like, an illumination box with a closed upper surface and side surfaces needs to be erected, a uniform light source (lamp) and a CCD camera are installed in the illumination box, and in order to clearly capture the moving (the general moving speed is 2-3 m/s) block images, the CCD camera should be capable of setting parameters, namely a shutter and an aperture, and the obtained images can be transmitted to a computer through a connected image plate to perform subsequent image processing.
And 2, converting the RGB image into a corresponding gray image, and reducing the gray image according to a preset scale factor to obtain a reduced gray image.
The step 2 specifically comprises the following steps:
since rock block color is not obvious, to reduce the amount of computation, the RGB image is converted into a corresponding grayscale image:
f(x，y)ash of＝(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 representing red, green and blue pixel values of a pixel located at (x, y) in an RGB image, f (x, y)Ash ofRepresenting a location at (x, y) in a grayscale imageX ∈ (1,.., 2 × M), y ∈ (1,.., 2 × N), 2 × M being the total number of pixels in the width dimension of the grayscale image, 2 × N being the total number of pixels in the height dimension of the grayscale image;
in order to eliminate the noise of the black spots and the bright spots and further reduce the workload of subsequent processing, the gray level image is reduced; and when the preset scale factor is 1/4, the gray scale image is reduced according to the scale factor, the gray scale average value of every four adjacent pixels is taken as the gray scale value of the reduced gray scale image at the corresponding position, and the total number of pixels of the reduced gray scale image in the width dimension is M and the total number of pixels of the reduced gray scale image in the height dimension is N.
And 3, performing smooth filtering on the reduced gray level image to obtain a smooth filtered gray level image.
If the reduced gray-scale image is smoothed according to a conventional image smoothing algorithm (such as a neighborhood averaging method or a gaussian smoothing method), a weak boundary may be smoothed, so that a fractional order integral smoothing method is adopted to remove noise in the reduced gray-scale image, but in order to keep the image smooth and keep the boundary between the block sizes from being lost, a traditional filter template is improved:
and performing smooth filtering on the reduced gray level image by adopting a fractional order integral smoothing method, wherein the filter coefficient h of the used 5 × 5 template is as follows:
the smooth filtered gray scale image is at (x)1，y1) Gray value of F (x)1，y1) Comprises the following steps: f (x)1，y1)＝(f(x1，y1) H)/8, and the gray values of the pixels in the left two columns, the right two columns, the upper two rows and the lower two rows of the gray image after smooth filtering are the same as the gray values of the pixels in the corresponding positions of the reduced gray image;
the gray-scale image after smooth filtering is (x)1，y1) Gray value of F (x)1，y1) Comprises the following steps: f (x)1，y1)＝(f(x1，y1) H)/8, the filtering operation expressed by the formula is to obtain a smooth filtered gray scale image with (x)1，y1) 25 pixels centered on the pixel of (a), so that the 25 pixels are respectively convolved with the filter coefficients, thereby obtaining (x)1，y1) Gray value of F (x)1，y1)。
Wherein, f (x)1，y1) Indicating the gray scale image after reduction is in (x)1，y1) At a gray value of x1∈(0，...，M)，y1∈(0，...，N)。
And 4, calculating the average gray value and the relative variance of the gray image after smooth filtering.
The step 4 specifically comprises the following steps:
calculating the average gray value y and the relative variance S of the gray image after smooth filteringPhase (C)：
SPhase (C)＝(s/v)×100
Wherein, F (x)1，y1) Represents the smooth filtered gray scale image in (x)1，y1) Gray value of (x)1∈(0，...，M)，y1∈ (0...., N), the total number of pixels of the smooth-filtered gray-scale image in the width dimension is M, the total number of pixels in the height dimension is N, and S represents the variance of the smooth-filtered gray-scale image.
Step 5, setting a first normal average gray threshold, if the average gray value of the gray image after smooth filtering is smaller than or equal to the first normal average gray threshold, taking the block degree image of the moving rocks on the conveyer belt corresponding to the gray image after smooth filtering as a bad rock block degree image, and removing the bad rock block degree image;
and if the average gray value of the gray image after smooth filtering is larger than the first normal average gray threshold value, continuing to execute the step 6.
Generally, the quality of a block image of a moving rock is low due to the influence of illumination and a moving speed, and when the average gray value of the block image is low, the block of the rock in the image is blurred or dark gray or even black (for example, no block image), and subsequent image processing and segmentation cannot be performed.
The setting of the first normal average grayscale threshold specifically includes: artificially selecting a high-quality image of the moving rock to obtain the average gray value of the high-quality image, and setting 30% of the average gray value of the high-quality image as a first normal average gray threshold value.
Step 6, setting a first normal relative variance threshold, if the relative variance of the smooth filtered gray level image is less than or equal to the first normal relative variance threshold, taking the block degree image of the moving rocks on the conveyer belt corresponding to the smooth filtered gray level image as an undesirable rock block degree image, and removing the undesirable rock block degree image;
and if the relative variance of the gray-scale image after smooth filtering is larger than the first normal relative variance threshold, continuing to execute the step 7.
Although a part of the poor quality images can be rejected in step 5, the selected images have a higher average gray value, but some of the images are low quality images, for example: the variance of the image is low, so that the variance of the image can be used to determine whether there is a block degree in the image: if the variance value is high, the image gray scale difference is proved to be large, namely the image gray scale difference is proved to be large.
The problems are that: under different lighting conditions, there are different average gray levels of the image, and the same number and size of the blocks also result in a large variance. In order to avoid the problem of difficult unified judgment, the technical scheme quotes relative errors to judge the quality of the image.
In step 6, setting a first normal relative variance threshold specifically includes: manually selecting a high-quality image of the moving rock to obtain the relative variance of the high-quality image, and setting 40% of the relative variance of the high-quality image as a first normal relative variance threshold value.
Step 7, setting a second normal average gray threshold and a second normal relative variance threshold, if the average gray value of the gray image after smooth filtering is smaller than or equal to the second normal average gray threshold and the relative variance of the gray image after smooth filtering is smaller than or equal to the second normal relative variance threshold, the block image of the moving rocks on the conveyer belt corresponding to the gray image after smooth filtering is an adverse rock block image, and removing the adverse rock block image; otherwise, step 8 is continued.
Further, step 5 and step 6 both use a single index to judge the image quality, but there are cases where two parameters need to be combined for judgment to be reliable.
In step 7, setting a second normal average gray level threshold and a second normal relative variance threshold specifically includes:
artificially selecting a high-quality image of the moving rock to obtain an average gray value and a relative variance of the high-quality image, setting 45% of the average gray value of the high-quality image as a second normal average gray threshold value, and setting 60% of the relative variance of the high-quality image as a second normal relative variance threshold value.
And 8, obtaining a corresponding gradient image according to the smooth filtered gray level image, and calculating a gradient average value and a gradient relative variance of the gradient image.
It should be noted that, by the above elimination in step 5, step 6 and step 7, about 70% -80% of the poor quality images are screened, and the remaining 20% -30% of the poor quality images can be eliminated by the criteria in step 8 and step 9.
The step 8 specifically comprises:
performing first order differentiation on the smooth filtered gray level image to obtain a corresponding gradient image; calculating a gradient mean V of the gradient image1Sum gradient relative variance S1 phase：
S1 phase＝(s1/v1)×100
Wherein, G (x)2，y2) Represents a gradient image in (x)2，y2) A gradient value of x2∈(0，...，M)，y2∈ (0,.. ang., N), the total number of pixels of the gradient image in the width dimension being M and the total number of pixels in the height dimension being N, S1Representing the variance of the gradient image.
And 9, setting an average gradient threshold value and a relative gradient variance threshold value, if the average gradient value of the gradient image is less than or equal to the gradient threshold value and the relative gradient variance of the gradient image is less than or equal to the relative gradient variance threshold value, determining that the block image of the moving rocks on the conveyer belt corresponding to the gradient image is an adverse rock block image, and removing the adverse rock block image.
In step 9, setting the average gradient threshold and the gradient relative variance threshold specifically includes:
artificially selecting a high-quality image of the moving rock to obtain an average gradient threshold and a relative gradient variance threshold of a gradient image corresponding to the high-quality image, setting 50% of the average gradient threshold of the gradient image corresponding to the high-quality image as the average gradient threshold, and setting 60% of the relative gradient variance threshold of the gradient image corresponding to the high-quality image as the relative gradient variance threshold.
And step 10, acquiring the next block degree image of the moving rock on the conveyor belt, and sequentially and repeatedly executing the step 2 to the step 9, thereby eliminating the bad block degree image of the moving rock on the conveyor belt in real time.
The final remaining blockiness image is an image with better quality, and as long as the subsequent processing algorithm is suitable for the type of the image, large errors cannot be generated in the subsequent processing, so that the subsequent image segmentation and analysis can be performed.
Those of ordinary skill in the art will understand that: all or part of the steps for realizing the method embodiments can be completed by hardware related to program instructions, the program can be stored in a computer readable storage medium, and the program executes the steps comprising the method embodiments when executed; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.
The above description is only for the specific embodiments of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and all the changes or substitutions should be covered within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the appended claims.
Claims (7)
1. A real-time removing method for bad block images on a rock conveyer belt is characterized by comprising the following steps:
step 1, acquiring a lumpy image of a moving rock on a conveyor belt, wherein the lumpy image is an RGB image;
step 2, converting the RGB image into a corresponding gray image, and reducing the gray image according to a preset scale factor to obtain a reduced gray image;
step 3, performing smooth filtering on the reduced gray level image to obtain a smooth filtered gray level image;
step 4, calculating the average gray value V and the relative variance S of the gray image after smooth filtrationPhase (C)：
SPhase (C)＝(S/V)×100
Wherein, F (x)1,y1) Represents the smooth filtered gray scale image in (x)1,y1) Gray value of (x)1∈(0,...,M)，y1∈ (0,.. multidot.n), the total number of pixels of the smooth-filtered gray-scale image in the width dimension is M, the total number of pixels in the height dimension is N, S represents the variance of the smooth-filtered gray-scale image, and V represents the average gray-scale value of the smooth-filtered gray-scale image;
step 5, setting a first normal average gray threshold, if the average gray value of the gray image after smooth filtering is smaller than or equal to the first normal average gray threshold, taking the block degree image of the moving rocks on the conveyer belt corresponding to the gray image after smooth filtering as a bad rock block degree image, and removing the bad rock block degree image;
if the average gray value of the gray image after smooth filtering is larger than the first normal average gray threshold value, continuing to execute the step 6;
step 6, setting a first normal relative variance threshold, if the relative variance of the smooth filtered gray level image is less than or equal to the first normal relative variance threshold, taking the block degree image of the moving rocks on the conveyer belt corresponding to the smooth filtered gray level image as an undesirable rock block degree image, and removing the undesirable rock block degree image;
if the relative variance of the gray-scale image after smooth filtering is larger than the first normal relative variance threshold, continuing to execute step 7;
step 7, setting a second normal average gray threshold and a second normal relative variance threshold, if the average gray value of the gray image after smooth filtering is smaller than or equal to the second normal average gray threshold and the relative variance of the gray image after smooth filtering is smaller than or equal to the second normal relative variance threshold, the block image of the moving rocks on the conveyer belt corresponding to the gray image after smooth filtering is an adverse rock block image, and removing the adverse rock block image; otherwise, continuing to execute the step 8;
step 8, obtaining a corresponding gradient image according to the smooth filtered gray level image, and calculating a gradient average value and a gradient relative variance of the gradient image;
performing first order differentiation on the smooth filtered gray level image to obtain a corresponding gradient image; calculating a gradient mean V of the gradient image1Sum gradient relative variance S1 phase：
S1 phase＝(S1/V1)×100
Wherein, G (x)2,y2) Represents a gradient image in (x)2,y2) A gradient value of x2∈(0,...,M)，y2∈ (0,.. ang., N), the total number of pixels of the gradient image in the width dimension being M and the total number of pixels in the height dimension being N, S1Representing the variance, V, of the gradient image1A gradient mean value representing a gradient image;
step 9, setting an average gradient threshold value and a relative gradient variance threshold value, if the average gradient value of the gradient image is less than or equal to the average gradient threshold value and the relative gradient variance of the gradient image is less than or equal to the relative gradient variance threshold value, the block image of the moving rocks on the conveyer belt corresponding to the gradient image is an adverse rock block image, and removing the adverse rock block image;
and step 10, acquiring the next block degree image of the moving rock on the conveyor belt, and sequentially and repeatedly executing the step 2 to the step 9, thereby eliminating the bad block degree image of the moving rock on the conveyor belt in real time.
2. The method for removing the bad block degree images on the rock conveyer belt in real time according to claim 1, wherein the step 2 specifically comprises the following steps:
converting the RGB image into a corresponding grayscale image:
f(x,y)ash of＝(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 representing red, green and blue pixel values of a pixel located at (x, y) in an RGB image, f (x, y)Ash ofX ∈ (1,.., 2 × M), y ∈ (1,.., 2 × N), 2 × M being the total number of pixels in the width dimension of the grayscale image, 2 × N being the total number of pixels in the height dimension of the grayscale image;
and when the preset scale factor is 1/4, the gray scale image is reduced according to the scale factor, the gray scale average value of every four adjacent pixels is taken as the gray scale value of the reduced gray scale image at the corresponding position, and the total number of pixels of the reduced gray scale image in the width dimension is M and the total number of pixels of the reduced gray scale image in the height dimension is N.
3. The method for removing the bad block degree images on the rock conveyer belt in real time according to claim 1, wherein the step 3 specifically comprises the following steps:
and performing smooth filtering on the reduced gray level image by adopting a fractional order integral smoothing method, wherein the filter coefficient of the used 5 × 5 template is as follows:
the smooth filtered gray scale image is at (x)1,y1) Gray value of F (x)1,y1) Comprises the following steps: f (x)1,y1)＝(f(x1,y1) H)/8, and the gray values of the pixels in the left two columns, the right two columns, the upper two rows and the lower two rows of the gray image after smooth filtering are the same as the gray values of the pixels in the corresponding positions of the reduced gray image;
wherein, f (x)1,y1) Indicating the gray scale image after reduction is in (x)1,y1) At a gray value of x1∈(0,...,M)，y1∈ (0.. multidot.N), wherein the total number of pixels in the width dimension of the smooth-filtered gray-scale image is M, the total number of pixels in the height dimension is N, and h is the filter coefficient of the used 5 × 5 template.
4. The method for removing the bad block images on the rock conveyer belt in real time according to claim 1, wherein in the step 5, the setting of the first normal average gray threshold specifically comprises: artificially selecting a high-quality image of the moving rock to obtain the average gray value of the high-quality image, and setting 30% of the average gray value of the high-quality image as a first normal average gray threshold value.
5. The method for removing the bad block degree images on the rock conveyer belt in real time according to claim 1, wherein in the step 6, the setting of the first normal relative variance threshold specifically comprises: manually selecting a high-quality image of the moving rock to obtain the relative variance of the high-quality image, and setting 40% of the relative variance of the high-quality image as a first normal relative variance threshold value.
6. The method for removing the bad block images on the rock conveyer belt in real time according to claim 1, wherein in the step 7, the setting of the second normal average gray threshold and the second normal relative variance threshold specifically comprises:
artificially selecting a high-quality image of the moving rock to obtain an average gray value and a relative variance of the high-quality image, setting 45% of the average gray value of the high-quality image as a second normal average gray threshold value, and setting 60% of the relative variance of the high-quality image as a second normal relative variance threshold value.
7. The method for removing the bad block images on the rock conveyer belt in real time according to claim 1, wherein in the step 9, the setting of the average gradient threshold and the gradient relative variance threshold specifically comprises:
artificially selecting a high-quality image of the moving rock to obtain an average gradient threshold and a relative gradient variance threshold of a gradient image corresponding to the high-quality image, setting 50% of the average gradient threshold of the gradient image corresponding to the high-quality image as the average gradient threshold, and setting 60% of the relative gradient variance threshold of the gradient image corresponding to the high-quality image as the relative gradient variance threshold.
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 CN107220946A (en) | 2017-09-29 |
| CN107220946B true 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) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109241867B (en) * | 2018-08-16 | 2022-03-15 | 清能艾科（深圳）能源技术有限公司 | Method and device for recognizing digital rock core image by adopting artificial intelligence algorithm |
| 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 |
| CN113674201B (en) * | 2021-07-09 | 2024-07-26 | 福建南方路面机械股份有限公司 | Aggregate particle size sampling 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 |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101567044B (en) * | 2009-05-22 | 2012-08-22 | 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 |
| CN104881878B (en) * | 2015-06-12 | 2017-07-28 | 武汉大学 | A kind of image quality evaluating method based on multi-scale gradient difference entropy |
-
2017
- 2017-05-18 CN CN201710353593.3A patent/CN107220946B/en not_active Expired - Fee Related
Non-Patent Citations (1)
| Title |
|---|
| GMVP: gradient magnitude and variance pooling-based image quality assessment in sensor networks;Zhong Zhang et al.;《EURASIP Journal on Wireless Communications and Networking》;20160112;第1-6页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN107220946A (en) | 2017-09-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110286126B (en) | Wafer surface defect regional detection method based on visual image | |
| CN107220946B (en) | Real-time removing method for bad block degree images on rock conveyer belt | |
| Wang et al. | Research on crack detection algorithm of the concrete bridge based on image processing | |
| CN115239704B (en) | Accurate detection and repair method for wood surface defects | |
| CN110286124B (en) | Machine vision-based refractory brick measuring system | |
| CN111383209B (en) | Unsupervised flaw detection method based on full convolution self-encoder network | |
| Schmugge et al. | Detection of cracks in nuclear power plant using spatial-temporal grouping of local patches | |
| CN109598715B (en) | Material granularity online detection method based on machine vision | |
| CN107314957B (en) | Method for measuring rock block size distribution | |
| CN113646801B (en) | Defect detection method, device and computer readable storage medium for defect image | |
| CN115345885A (en) | Method for detecting appearance quality of metal fitness equipment | |
| CN115375686B (en) | Glass edge flaw detection method based on image processing | |
| CN109215009B (en) | Continuous casting billet surface image defect detection method based on deep convolution neural network | |
| CN102608016A (en) | Method for measuring average size of complicated particles based on Canny boundary detection | |
| CN110189297B (en) | Magnetic material appearance defect detection method based on gray level co-occurrence matrix | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN103824304A (en) | Method for performing fault diagnosis on ores on conveying belt during conveying process | |
| CN107784646B (en) | Adaptive detection method for road aggregate | |
| CN114332026A (en) | Visual detection method and device for scratch defects on surface of nameplate | |
| CN108280838A (en) | A kind of intermediate plate tooth form defect inspection method based on edge detection | |
| CN104568956A (en) | Machine vision based detection method for strip steel surface defects | |
| CN115272336A (en) | Metal part defect accurate detection method based on gradient vector | |
| CN115597494B (en) | Precision detection method and system for prefabricated part preformed hole based on point cloud | |
| CN116485719A (en) | Self-adaptive canny method for crack detection | |
| Lu et al. | Fusion-based color and depth image segmentation method for rocks on conveyor belt |
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 |