CN110197478A - A kind of detection method and system of cigarette case inside casing paper joint - Google Patents
A kind of detection method and system of cigarette case inside casing paper joint Download PDFInfo
- Publication number
- CN110197478A CN110197478A CN201910406510.1A CN201910406510A CN110197478A CN 110197478 A CN110197478 A CN 110197478A CN 201910406510 A CN201910406510 A CN 201910406510A CN 110197478 A CN110197478 A CN 110197478A
- Authority
- CN
- China
- Prior art keywords
- image
- pixel
- gray
- inside casing
- paper
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 235000019504 cigarettes Nutrition 0.000 title claims abstract description 51
- 238000001514 detection method Methods 0.000 title claims abstract description 40
- 238000001914 filtration Methods 0.000 claims abstract description 36
- 238000006243 chemical reaction Methods 0.000 claims abstract description 32
- 230000007704 transition Effects 0.000 claims abstract description 22
- 238000000034 method Methods 0.000 claims abstract description 13
- 238000007781 pre-processing Methods 0.000 claims abstract description 11
- 238000012856 packing Methods 0.000 claims abstract description 8
- 230000002159 abnormal effect Effects 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 16
- 230000002146 bilateral effect Effects 0.000 claims description 7
- 238000004519 manufacturing process Methods 0.000 description 9
- 230000000694 effects Effects 0.000 description 6
- 238000012423 maintenance Methods 0.000 description 6
- 238000007689 inspection Methods 0.000 description 3
- 241000208125 Nicotiana Species 0.000 description 2
- 235000002637 Nicotiana tabacum Nutrition 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 239000000428 dust Substances 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000004806 packaging method and process Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 239000005022 packaging material Substances 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000003860 storage 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
- G06T5/70—Denoising; Smoothing
-
- 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
-
- 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
- G06T2207/10016—Video; Image sequence
-
- 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
- G06T2207/30124—Fabrics; Textile; Paper
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 Analysis (AREA)
Abstract
The present invention provides the detection method and system of a kind of cigarette case inside casing paper joint, this method comprises: obtaining the paper tape image of the inner box paper obbbin on cigarette case packing machine in real time, and image preprocessing is carried out according to the paper tape image, described image pretreatment includes: image format conversion and image filtering；Pretreated paper tape image progress grayvalue transition is obtained into corresponding gray level image；The difference map in strength of two temporally adjacent images is obtained after the gray level image is carried out difference operation frame by frame, it handles difference map in strength progress threshold values to obtain binary map, and judge whether the paper tape image is inside casing paper joint image according to the binary map, if it is, being judged to detecting inside casing paper joint.The present invention can improve the Stability and veracity of inner box paper tool joint monitor.
Description
Technical field
The present invention relates to the detection method of cigarette case production equipment technology more particularly to a kind of cigarette case inside casing paper joint and
System.
Background technique
Inner box paper primarily serves the effect of support cigarette case box cover as one of cigarette packaging material.In the life of hard case cigarette packet
During production, there are inside casing paper joints for random site in inner box paper obbbin, it is necessary to accurately detect and reject, in order not to allow it to flow into
Next procedure accurately must be detected and be rejected to it, prevent product quality defect, and the country is mainly passed using color at present
Sensor carries out detection inside casing paper joint, but since color sensor has detection faces small, low, solid vulnerable to foreign matter interference, accuracy rate
The phenomenon that determining the disadvantages of setup parameter adaptability is low, maintenance difficulties are big, leading to the missing inspection of inside casing connector, erroneous detection happens occasionally.Inside casing
Paper joint accurately cannot be detected and be rejected, and directly influence the packaging quality of parcel, once coming into the market will cause seriously
Mass defect.Therefore, the Stability and veracity for how improving inner box paper tool joint monitor, has great importance.
Summary of the invention
The present invention provides the detection method and system of a kind of cigarette case inside casing paper joint, solves existing inner box paper detection using face
Colour sensor detection has that accuracy rate is low, big vulnerable to the interference of easy object and maintenance difficulties, can improve inner box paper tool joint monitor
Stability and veracity, improve cigarette case production efficiency.
In order to achieve the above object, the present invention the following technical schemes are provided:
A kind of detection method of cigarette case inside casing paper joint, comprising:
The paper tape image of the inner box paper obbbin on cigarette case packing machine is obtained in real time, and image is carried out according to the paper tape image
Pretreatment, described image pretreatment includes: image format conversion and image filtering；
Pretreated paper tape image progress grayvalue transition is obtained into corresponding gray level image；
The difference map in strength of temporally adjacent two image is obtained after the gray level image is carried out difference operation frame by frame；
It handles differential chart progress threshold values to obtain binary map, and the paper tape image is judged according to the binary map
It whether is inside casing paper joint image, if it is, being judged to detecting inside casing paper joint.
It is preferably, described that image preprocessing is carried out according to the paper tape image, comprising:
The picture format of the paper tape image is judged, it, will be described if described image format is not rgb format
Paper tape image carries out RGB conversion；
The paper tape image is filtered, the filtering processing uses mean filter, gaussian filtering or bilateral filter
Wave will obtain the image of low picture noise after processing.
It is preferably, described that pretreated paper tape image progress grayvalue transition is obtained into corresponding gray level image, comprising:
Grayvalue transition is carried out to the image of the low picture noise obtained after filtering processing, and passes through gradation conversion formula
Gray=(R+G+B)/3 obtains the gray value of each pixel, and then according to the gray value of each pixel to low picture noise
Image carry out being converted to a gray level image corresponding with paper tape image.
Preferably, described to obtain temporally adjacent two image after gray level image progress frame by frame difference operation
Difference map in strength, comprising:
The present frame of the gray level image and previous frame are subjected to gray scale difference value operation, the difference operation process are as follows:
It is obtained often with the gray value that the gray value of each pixel of present frame subtracts the identical 2-d spatial coordinate corresponding pixel points of previous frame
The gray scale difference value of one pixel, and the difference map in strength of two temporally adjacent images is obtained according to the gray scale difference value.
It is preferably, described that differential chart progress threshold values operation is obtained into binary map, comprising:
Each pixel of the difference map in strength is rewritten again, when the gray scale difference value of pixel is greater than setting
When binaryzation threshold values, rewriting the pixel gray value is 255, and using the point as abnormal point, is set when the gray scale difference value is less than
When fixed binaryzation threshold values, the gray value for rewriting the pixel is 0, after having rewritten the pixel of the difference map in strength, is obtained
To a binary map.
It is preferably, described and judge whether the paper tape image is inside casing paper joint image according to the binary map, comprising:
Abnormal point in the binary map is counted to obtain abnormal point number N, abnormal point, that is, grey scale pixel value is 255
Pixel, also referred to as bright spot is judged to detecting inner box paper if the N value is greater than setting abnormal point numerical threshold values
Connector.
The present invention also provides a kind of detection systems of cigarette case inside casing paper joint, comprising:
Acquisition unit, for obtaining the paper tape image of the inner box paper obbbin on cigarette case packing machine in real time；
Image pre-processing unit, for carrying out image preprocessing according to the paper tape image, described image pretreatment includes:
Image format conversion and image filtering；
Gradation conversion unit, for pretreated paper tape image progress grayvalue transition to be obtained corresponding grayscale image
Picture；
Difference operation unit frame by frame carries out gray scale difference for the gray level image to be carried out temporally adjacent two gray level images
It is worth operation, obtains the corresponding difference map in strength of present frame gray image；
Recognition unit, for handling difference map in strength progress threshold values to obtain binary map, and according to the two-value
Figure judges whether the paper tape image is inside casing paper joint image, if it is, being judged to detecting inside casing paper joint.
Preferably, described image pretreatment unit includes:
Image format conversion unit judges for the picture format to the paper tape image, if described image lattice
Formula is not rgb format, then the paper tape image is carried out RGB conversion；
Image filtering unit, for being filtered to the paper tape image, it is described filtering processing using mean filter,
Gaussian filtering or bilateral filtering obtain the image of corresponding low picture noise.
Preferably, the gradation conversion unit includes:
RGB grayvalue transition unit carries out grayvalue transition for the image to the low picture noise after filtering processing, and
The gray value of each pixel is obtained by gradation conversion formula Gray=(R+G+B)/3, and then according to the ash of each pixel
Angle value carries out the image of low picture noise to be converted to a gray level image corresponding with paper tape image.
Preferably, the difference operation unit frame by frame includes:
Gray scale difference value arithmetic element carries out gray scale difference value operation with previous frame for the present frame to the gray level image,
The difference operation process are as follows: it is empty that the gray value of each pixel of the present frame of the gray level image subtracts the identical two dimension of previous frame
Between the gray values of coordinate corresponding pixel points obtain the gray scale difference value of each pixel, and time phase is obtained according to the gray scale difference value
The difference map in strength of two adjacent images.
Preferably, the recognition unit includes:
Threshold values processing unit, for the difference map in strength to be carried out threshold values operation, to the difference map in strength
Each pixel is rewritten again, when the gray scale difference value of pixel is greater than the binaryzation threshold values of setting, rewrites the pixel
Gray value is 255, and rewrites the picture when the gray scale difference value is less than the binaryzation threshold values of setting using the point as abnormal point
The gray value of vegetarian refreshments is 0, after having rewritten the pixel of the difference map in strength, obtains a binary map；
Connector judging unit obtains abnormal point number N, abnormal point for being counted the abnormal point in the binary map
I.e. grey scale pixel value is that 255 pixel, also referred to as bright spot are sentenced if the N value is greater than setting abnormal point numerical threshold values
It is set to and detects inside casing paper joint.
The present invention provides the detection method and system of a kind of cigarette case inside casing paper joint, by shooting to cigarette case inner box paper
Paper tape image is obtained, and is handled to obtain gray level image according to paper tape image, and then be compared judgement according to gray level image
Whether inside casing paper joint is detected.It solves the detection of existing inner box paper to detect using color sensor, that there are accuracys rate is low, vulnerable to easy
Object interference and the big problem of maintenance difficulties, can improve the Stability and veracity of inner box paper tool joint monitor, improve cigarette case production effect
Rate.
Detailed description of the invention
In order to illustrate more clearly of specific embodiments of the present invention, attached drawing needed in the embodiment will be made below
Simply introduce.
Fig. 1 is a kind of detection method schematic diagram of cigarette case inside casing paper joint provided by the invention；
Fig. 2 is the procedure chart of the image detection of inside casing paper joint provided in an embodiment of the present invention；
Fig. 3 is the detection method flow chart of cigarette case inside casing paper joint provided in an embodiment of the present invention.
Specific embodiment
The scheme of embodiment in order to enable those skilled in the art to better understand the present invention with reference to the accompanying drawing and is implemented
Mode is described in further detail the embodiment of the present invention.
For in current cigarette case production process frequently with FOCKE350 packing machine, in Hard Roll parcel packaging, cigarette case inside casing
Paper is one of raw and auxiliary material, but since inner box paper random site can contain junction portion, must accurately be detected simultaneously in production
It rejects, although FOCKE350 is furnished with corresponding detection device at present, due to the unstability of former detection device, leads to missing inspection, misses
The phenomenon that inspection, happens occasionally.The present invention provides the detection method and system of a kind of cigarette case inside casing paper joint, by cigarette case inside casing
Paper is shot to obtain paper tape image, and is handled to obtain gray level image according to paper tape image, so according to gray level image into
Whether row multilevel iudge detects inside casing paper joint.It solves existing inner box paper detection to detect using color sensor, it is accurate to exist
Low, big vulnerable to the interference of the easy object and maintenance difficulties problem of rate, can improve the Stability and veracity of inner box paper tool joint monitor, improve
Cigarette case production efficiency.
As shown in Figure 1, a kind of detection method of cigarette case inside casing paper joint, comprising:
S1: the paper tape image of the inner box paper obbbin on cigarette case packing machine is obtained in real time, and is carried out according to the paper tape image
Image preprocessing, described image pretreatment includes: image format conversion and image filtering.
S2: pretreated paper tape image progress grayvalue transition is obtained into corresponding gray level image.
S3: the gray scale difference value of temporally adjacent two image is obtained after the gray level image is carried out difference operation frame by frame
Figure.
S4: it handles differential chart progress threshold values to obtain binary map, and the paper tape is judged according to the binary map
Whether image is inside casing paper joint image, if it is, being judged to detecting inside casing paper joint.
Specifically, for the detection of cigarette case inside casing paper joint, industrial camera can be used and continuously taken pictures to inner box paper, into
And obtain paper tape image.The call back function and driver in development kit provided by camera producer obtains paper tape image
Image data.Industrial personal computer obtains paper tape image by the image data in acquisition industrial camera, and according to paper tape image by default
Program pre-processed.Since the image after acquisition has picture noise (digitized process generation), need to be filtered place
Reason, obtains the image more close with actual conditions, then carry out respective algorithms processing just can guarantee the accuracy of recognition result with
Stability.Filtered image, eliminates picture noise, in order to improve the efficiency of image recognition, can by the image of acquisition into
The conversion of row gray value, obtains a gray level image after conversion, obtain a time phase after gray level image is carried out difference operation frame by frame
The difference map in strength of two adjacent images carries out threshold values to difference map in strength and handles to obtain binary map, and then according to binary map
On abnormal point number to determine whether detect inside casing paper joint, this method belongs to servo-actuated sensitivity setting, has very strong
Anti-interference (dust, intensity of illumination variation, pipe tobacco splashing, hardware aging etc.) ability.
It is further, described that image preprocessing is carried out according to the paper tape image, comprising:
S11: judging the picture format of the paper tape image, will if described image format is not rgb format
The paper tape image carries out RGB conversion.
S12: being filtered the paper tape image, it is described filtering processing can be used mean filter, gaussian filtering or
Bilateral filtering.
In practical applications, image is often stored as RAW format, is obtaining paper by industrial camera in order to more preferably use image
After band image, first to picture format into judgement, if picture format is not rgb format, simultaneously the image copy of RAW format first
Storage, then carries out color conversion, converts paper tape image to the image of rgb format.It is carried out at image filtering after image conversion
Reason, existing filtering algorithm include: mean filter, Gauss filter stream and bilateral filtering etc., and each algorithm all has the advantages that respective.Root
According to the actual needs that cigarette case produces, optional gaussian filtering is filtered, and does convolution with image and normal distribution, which can make
Linear smoothing filtering, fidelity are preferable.
It is further, described that pretreated paper tape image progress grayvalue transition is obtained into corresponding gray level image, comprising:
S21: grayvalue transition is carried out to pretreated image, in order to which the component for balancing RGB triple channel is having the same
Weight, the gradation conversion formula used is Gray=(R+G+B)/3；It is obtained after carrying out the operation to each pixel of described image
One gray level image corresponding with paper tape image.
Further, the gray scale of temporally adjacent two image is obtained after the gray level image being carried out difference operation frame by frame
Differential chart, comprising:
S31: present frame and previous frame to the gray level image carry out gray scale difference value operation, the difference operation process
Are as follows: it is obtained with the gray value that the gray value of each pixel of present frame subtracts the identical 2-d spatial coordinate corresponding pixel points of previous frame
The gray scale difference value of each pixel, and the difference map in strength of two temporally adjacent images is obtained according to the gray scale difference value.
Further, differential chart progress threshold values is handled to obtain binary map, and according to binary map judgement
Whether paper tape image is inside casing paper joint image, if it is, being judged to detecting inside casing paper joint, comprising:
S41: rewriting each pixel of the difference map in strength again, sets when the gray scale difference value of pixel is greater than
When fixed binaryzation threshold values, rewriting the pixel gray value is 255, and using the point as abnormal point, when the gray scale difference value is small
When the binaryzation threshold values of setting, the gray value for rewriting the pixel is 0, when the pixel for having rewritten the difference map in strength
Afterwards, a binary map is obtained.
S42: the abnormal point in the binary map is counted to obtain abnormal point number N, abnormal point, that is, grey scale pixel value
It is judged to detecting interior if the N value is greater than setting abnormal point numerical threshold values for 255 pixel, also referred to as bright spot
Frame paper joint.
In one embodiment, as shown in Fig. 2, carrying out grayvalue transition to each pixel of the RGB image of paper tape image,
And gray level image is obtained according to grayvalue transition formula GRAY=(R+G+B)/3, and then by the gray level image of present frame with it is previous
The corresponding pixel of the gray level image of frame carries out gray scale difference operation, obtains difference map in strength, carries out thresholding to difference map in strength
Obtain binary map.From Fig. 2, if connector image binaryzation threshold values is 35, abnormal point numerical threshold values is 6, and it is 8 that N value, which can be obtained, due to
8 are greater than 6, then can determine whether to detect inside casing paper joint.
Specifically, as shown in figure 3, reading paper tape image and converting rgb format for image, image is filtered to go
Except interference, grayvalue transition is carried out to pretreated low noise image and obtains gray level image figure, copies the grayscale image of present frame
As the previous frame gray level image as operation next time, subtract each other to obtain the ash of temporally adjacent two images with present frame and previous frame
Differential chart is spent, threshold values is carried out to differential chart and handles to obtain binary map, the abnormal point number N of binary map is counted, if abnormal point
Number N is greater than the abnormal point numerical threshold values of setting, then is judged as and detects inside casing paper joint, and then sends inner box paper joint information to cigarette
The host of box package machine.If abnormal point number is less than the second abnormal point numerical threshold values of setting, repeat the above steps.
It should be noted that when reading first frame inner box paper paper tape image, without the corresponding gray scale of previous frame image
Image needs to judge whether previous frame gray level image is sky, then without judgement when being empty.In practical applications, camera is continuous
Paper tape image is acquired, obtain the gray level image of successive frame, the acquisition time between these frames is different, but adjacent
Time difference very little between two frames, if acquisition frame rate is 50, then the time difference between two frames is then 20ms, if at this
Occur interfering (dust, intensity of illumination variation, pipe tobacco splashing, hardware aging etc.) in period, this interference is usually slow
The process of variation will not produce bigger effect differential chart within this of short duration time；If on the contrary, when this is shorter
It is interior connector occur, it will to make the pixel point value of the corresponding joints position of differential chart that larger change occur, go out in no connector
When existing, for differential chart pixel point value close to 0, the core of this detection method is exactly to be changed according to this in a short time larger
Become to carry out judging whether connector occur.
As it can be seen that the present invention provides a kind of detection method of cigarette case inside casing paper joint, by shooting to cigarette case inner box paper
Paper tape image is obtained, and is handled to obtain gray level image according to paper tape image, and then be compared judgement according to gray level image
Whether inside casing paper joint is detected.It solves the detection of existing inner box paper to detect using color sensor, that there are accuracys rate is low, vulnerable to easy
Object interference and the big problem of maintenance difficulties, can improve the Stability and veracity of inner box paper tool joint monitor, improve cigarette case production effect
Rate.
Correspondingly, the present invention also provides a kind of detection systems of cigarette case inside casing paper joint, comprising: acquisition unit, for real
When obtain cigarette case packing machine on inner box paper obbbin paper tape image.Image pre-processing unit, for according to the paper tape image
Image preprocessing is carried out, described image pretreatment includes: image format conversion and image filtering.Gradation conversion unit, being used for will
Pretreated paper tape image carries out grayvalue transition and obtains corresponding gray level image.Difference operation unit frame by frame is used for institute
It states gray level image and carries out temporally adjacent two gray level images progress gray scale difference value operation, obtain the corresponding ash of present frame gray image
Spend differential chart.Recognition unit, for handling difference map in strength progress threshold values to obtain binary map, and according to the two-value
Figure judges whether the paper tape image is inside casing paper joint image, if it is, being judged to detecting inside casing paper joint.
Described image pretreatment unit includes: image format conversion unit, for the picture format to the paper tape image
Judged, if described image format is not rgb format, the paper tape image is subjected to RGB conversion.Image filtering list
Member, for being filtered to the paper tape image, mean filter, gaussian filtering or bilateral filter is can be used in the filtering processing
Wave obtains the image of corresponding low picture noise.
The gradation conversion unit includes: RGB grayvalue transition unit, for the low picture noise after filtering processing
Image carries out grayvalue transition, and the component weight having the same in order to balance RGB triple channel passes through gradation conversion formula Gray
=(R+G+B)/3 obtains the gray value of each pixel, and then according to the gray value of each pixel to the figure of low picture noise
As carrying out being converted to a gray level image corresponding with paper tape image.
The difference operation unit frame by frame includes: gray scale difference value arithmetic element, for the present frame to the gray level image
Gray scale difference value operation, the difference operation process are as follows: to each pixel of the present frame of the gray level image are carried out with previous frame
The gray value that the gray value of point subtracts the identical 2-d spatial coordinate corresponding pixel points of previous frame obtains the gray scale difference of each pixel
Value, and the difference map in strength of two temporally adjacent images is obtained according to the gray scale difference value.
The recognition unit includes: threshold values processing unit, right for the difference map in strength to be carried out threshold values operation
Each pixel of the difference map in strength is rewritten again, when the gray scale difference value of pixel is greater than the binaryzation threshold values of setting
When, rewriting the pixel gray value is 255, and using the point as abnormal point, when the gray scale difference value is less than the binaryzation of setting
When threshold values, the gray value for rewriting the pixel is 0, after having rewritten the pixel of the difference map in strength, obtains a two-value
Figure.Connector judging unit obtains abnormal point number N, abnormal point, that is, picture for being counted the abnormal point in the binary map
The pixel that plain gray value is 255, also referred to as bright spot are determined as if the N value is greater than setting abnormal point numerical threshold values
Detect inside casing paper joint.
As it can be seen that the present invention provides a kind of detection system of cigarette case inside casing paper joint, by shooting to cigarette case inner box paper
Paper tape image is obtained, and is handled to obtain gray level image according to paper tape image, and then be compared judgement according to gray level image
Whether inside casing paper joint is detected.It solves the detection of existing inner box paper to detect using color sensor, that there are accuracys rate is low, vulnerable to easy
Object interference and the big problem of maintenance difficulties, can improve the Stability and veracity of inner box paper tool joint monitor, improve cigarette case production effect
Rate.
Structure, feature and effect of the invention, the above institute is described in detail according to diagrammatically shown embodiment above
Only presently preferred embodiments of the present invention is stated, but the present invention does not limit the scope of implementation as shown in the drawings, it is all according to structure of the invention
Think made change or equivalent example modified to equivalent change, when not going beyond the spirit of the description and the drawings,
It should all be within the scope of the present invention.
Claims (11)
1. a kind of detection method of cigarette case inside casing paper joint characterized by comprising
The paper tape image of the inner box paper obbbin on cigarette case packing machine is obtained in real time, and image is carried out according to the paper tape image and is located in advance
Reason, described image pretreatment includes: image format conversion and image filtering；
Pretreated paper tape image progress grayvalue transition is obtained into corresponding gray level image；
The difference map in strength of temporally adjacent two image is obtained after the gray level image is carried out difference operation frame by frame；
It handles differential chart progress threshold values to obtain binary map, and whether the paper tape image is judged according to the binary map
For inside casing paper joint image, if it is, being judged to detecting inside casing paper joint.
2. the detection method of cigarette case inside casing paper joint according to claim 1, which is characterized in that described according to the paper tape
Image carries out image preprocessing, comprising:
The picture format of the paper tape image is judged, if described image format is not rgb format, by the paper tape
Image carries out RGB conversion；
The paper tape image is filtered, the filtering processing uses mean filter, gaussian filtering or bilateral filtering, place
The image of low picture noise will be obtained after reason.
3. the detection method of cigarette case inside casing paper joint according to claim 2, which is characterized in that it is described will be pretreated
Paper tape image carries out grayvalue transition and obtains corresponding gray level image, comprising:
Grayvalue transition is carried out to the image of the low picture noise obtained after filtering processing, and passes through gradation conversion formula Gray=
(R+G+B)/3 the gray value of each pixel is obtained, and then according to the gray value of each pixel to the image of low picture noise
It carries out being converted to a gray level image corresponding with paper tape image.
4. the detection method of cigarette case inside casing paper joint according to claim 3, which is characterized in that described by the grayscale image
As obtaining the difference map in strength of temporally adjacent two image after carrying out difference operation frame by frame, comprising:
The present frame of the gray level image and previous frame are subjected to gray scale difference value operation, the difference operation process are as follows: with working as
The gray value that the gray value of each pixel of previous frame subtracts the identical 2-d spatial coordinate corresponding pixel points of previous frame obtains each picture
The gray scale difference value of vegetarian refreshments, and the difference map in strength of two temporally adjacent images is obtained according to the gray scale difference value.
5. the detection method of cigarette case inside casing paper joint according to claim 4, which is characterized in that described by the differential chart
It carries out threshold values operation and obtains binary map, comprising:
Each pixel of the difference map in strength is rewritten again, when the gray scale difference value of pixel is greater than the two-value of setting
When changing threshold values, rewriting the pixel gray value is 255, and using the point as abnormal point, when the gray scale difference value is less than setting
When binaryzation threshold values, the gray value for rewriting the pixel is 0, after having rewritten the pixel of the difference map in strength, obtains one
Open binary map.
6. the detection method of cigarette case inside casing paper joint according to claim 5, which is characterized in that described and according to described two
Value figure judges whether the paper tape image is inside casing paper joint image, comprising:
Abnormal point in the binary map is counted to obtain abnormal point number N, the picture that abnormal point, that is, grey scale pixel value is 255
Vegetarian refreshments, also referred to as bright spot are judged to detecting inside casing paper joint if the N value is greater than setting abnormal point numerical threshold values.
7. a kind of detection system of cigarette case inside casing paper joint characterized by comprising
Acquisition unit, for obtaining the paper tape image of the inner box paper obbbin on cigarette case packing machine in real time；
Image pre-processing unit, for carrying out image preprocessing according to the paper tape image, described image pretreatment includes: image
Format conversion and image filtering；
Gradation conversion unit, for pretreated paper tape image progress grayvalue transition to be obtained corresponding gray level image；
Difference operation unit frame by frame carries out gray scale difference value fortune for the gray level image to be carried out temporally adjacent two gray level images
It calculates, obtains the corresponding difference map in strength of present frame gray image；
Recognition unit for handling difference map in strength progress threshold values to obtain binary map, and is sentenced according to the binary map
Whether the paper tape image that breaks is inside casing paper joint image, if it is, being judged to detecting inside casing paper joint.
8. the detection system of cigarette case inside casing paper joint according to claim 7, which is characterized in that described image pretreatment is single
Member includes:
Image format conversion unit judges for the picture format to the paper tape image, if described image format is not
It is rgb format, then the paper tape image is subjected to RGB conversion；
Image filtering unit, for being filtered to the paper tape image, the filtering processing uses mean filter, Gauss
Filtering or bilateral filtering, obtain the image of corresponding low picture noise.
9. the detection system of cigarette case inside casing paper joint according to claim 8, which is characterized in that the gradation conversion unit
Include:
RGB grayvalue transition unit carries out grayvalue transition for the image to the low picture noise after filtering processing, and passes through
Gradation conversion formula Gray=(R+G+B)/3 obtains the gray value of each pixel, and then according to the gray value of each pixel
The image of low picture noise is carried out to be converted to a gray level image corresponding with paper tape image.
10. the detection system of cigarette case inside casing paper joint according to claim 9, which is characterized in that the fortune of difference frame by frame
Calculating unit includes:
Gray scale difference value arithmetic element carries out gray scale difference value operation with previous frame for the present frame to the gray level image, described
Difference operation process are as follows: the gray value of each pixel of the present frame of the gray level image subtracts the identical two-dimensional space of previous frame and sits
The gray value of mark corresponding pixel points obtains the gray scale difference value of each pixel, and is obtained according to the gray scale difference value temporally adjacent
The difference map in strength of two images.
11. the detection system of cigarette case inside casing paper joint according to claim 7, which is characterized in that the recognition unit packet
It includes:
Threshold values processing unit, for the difference map in strength to be carried out threshold values operation, to each of the difference map in strength
Pixel is rewritten again, when the gray scale difference value of pixel is greater than the binaryzation threshold values of setting, rewrites the pixel gray level
Value is 255, and rewrites the pixel when the gray scale difference value is less than the binaryzation threshold values of setting using the point as abnormal point
Gray value be 0, after having rewritten the pixel of the difference map in strength, obtain a binary map；
Connector judging unit obtains abnormal point number N, abnormal point, that is, picture for being counted the abnormal point in the binary map
The pixel that plain gray value is 255, also referred to as bright spot are determined as if the N value is greater than setting abnormal point numerical threshold values
Detect inside casing paper joint.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910406510.1A CN110197478A (en) | 2019-05-16 | 2019-05-16 | A kind of detection method and system of cigarette case inside casing paper joint |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910406510.1A CN110197478A (en) | 2019-05-16 | 2019-05-16 | A kind of detection method and system of cigarette case inside casing paper joint |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110197478A true CN110197478A (en) | 2019-09-03 |
Family
ID=67752776
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910406510.1A Pending CN110197478A (en) | 2019-05-16 | 2019-05-16 | A kind of detection method and system of cigarette case inside casing paper joint |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110197478A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003244469A (en) * | 2002-02-19 | 2003-08-29 | Nisca Corp | Image deciding apparatus, image reader, image deciding method, program and storage medium stored with program |
| CN102519984A (en) * | 2011-11-16 | 2012-06-27 | 湖南大学 | Anti-vibration machine vision detection method of foreign matters in liquid medicine |
| CN103910078A (en) * | 2014-04-15 | 2014-07-09 | 中国电子科技集团公司第四十一研究所 | Device for detecting integrity of aluminized paper and lining paper of cigarette packets |
| CN206679321U (en) * | 2017-03-20 | 2017-11-28 | 河南中烟工业有限责任公司 | A kind of cigarette case aluminum foil paper joint detector |
| CN108520260A (en) * | 2018-04-11 | 2018-09-11 | 中南大学 | The recognition methods of visible foreign matters in bottled oral solution |
-
2019
- 2019-05-16 CN CN201910406510.1A patent/CN110197478A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2003244469A (en) * | 2002-02-19 | 2003-08-29 | Nisca Corp | Image deciding apparatus, image reader, image deciding method, program and storage medium stored with program |
| CN102519984A (en) * | 2011-11-16 | 2012-06-27 | 湖南大学 | Anti-vibration machine vision detection method of foreign matters in liquid medicine |
| CN103910078A (en) * | 2014-04-15 | 2014-07-09 | 中国电子科技集团公司第四十一研究所 | Device for detecting integrity of aluminized paper and lining paper of cigarette packets |
| CN206679321U (en) * | 2017-03-20 | 2017-11-28 | 河南中烟工业有限责任公司 | A kind of cigarette case aluminum foil paper joint detector |
| CN108520260A (en) * | 2018-04-11 | 2018-09-11 | 中南大学 | The recognition methods of visible foreign matters in bottled oral solution |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109870461B (en) | Electronic components quality detection system | |
| CN109507192B (en) | Magnetic core surface defect detection method based on machine vision | |
| KR102203112B1 (en) | Defect detection and classification based on attributes determined from a standard reference image | |
| US4958307A (en) | Roll mark inspection apparatus | |
| CN106920219A (en) | Article defect detection method, image processing system and computer readable recording medium | |
| CN106548111B (en) | A kind of two dimensional code open defect detection method and device | |
| CN109752392B (en) | PCB defect type detection system and method | |
| CN115641332B (en) | Method, device, medium and equipment for detecting product edge appearance defects | |
| CN114359246B (en) | Conveyor belt detection method, device, system, electronic device and medium | |
| JP2020128877A (en) | Linear object abnormality detection device and abnormality detection method | |
| CN116503388B (en) | Defect detection method, device and storage medium | |
| CN111539927B (en) | Detection method of automobile plastic assembly fastening buckle missing detection device | |
| CN113155839A (en) | Steel plate outer surface defect online detection method based on machine vision | |
| CN106093051A (en) | Paper roll tangent plane burr detection method based on machine vision and device | |
| CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
| KR20220095468A (en) | Steel quality inspection system based on xai and large scale deep learning hpc system | |
| Ferreira et al. | Character recognition for automatic draught survey | |
| CN110197478A (en) | A kind of detection method and system of cigarette case inside casing paper joint | |
| CN110501339B (en) | Cloth cover positioning method in complex environment | |
| CN110153036A (en) | A kind of cigarette case inside casing paper slice detecting device | |
| CN110186929A (en) | A kind of real-time product defect localization method | |
| CN109949292A (en) | A kind of detection method and device of steel strip surface defect | |
| CN113311060B (en) | Elevator cladding belt defect online detection and marking device and system | |
| CN109448012A (en) | A kind of method for detecting image edge and device | |
| CN114882009A (en) | Fatigue crack tip automatic detection method and system capable of adapting to various surface states |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190903 |