CN1653975A - On line foreign matter distinguishing method for article inspection based on unit gradation uniformity - Google Patents
On line foreign matter distinguishing method for article inspection based on unit gradation uniformity Download PDFInfo
- Publication number
- CN1653975A CN1653975A CN 200510020135 CN200510020135A CN1653975A CN 1653975 A CN1653975 A CN 1653975A CN 200510020135 CN200510020135 CN 200510020135 CN 200510020135 A CN200510020135 A CN 200510020135A CN 1653975 A CN1653975 A CN 1653975A
- Authority
- CN
- China
- Prior art keywords
- foreign matter
- unit
- article
- image
- gray
- 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
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Spectrometry And Color Measurement (AREA)
Abstract
The on-line foreign matter detecting process based on unit grey homogeneity includes the following steps: 1) image taking; 2) image transmission: 3) foreign matter distinguishing and processing; 4) distinguishing signal transmission; and 5) eliminating foreign matter. During the process, LED is used as light source to raise image brightness and stability, images are taken from both the upper side and the lower side of the detected matter, and the detected matter is distinguished from two sides for raised distinction rate. In the foreign matter distinguishing and processing, the integral unit gray homogeneity is utilized in judging the unit attribute to distinguish the foreign matter with color similar to that of the detected matter. The present invention has raised distinguishing rate between tobacco or other detected matter and foreign matter.
Description
Technical field:
The present invention relates to the method in the online detection of a kind of article the foreign matter close with thing color to be checked discerned, the foreign matter that is mainly used in article such as tobacco detects.
Background technology:
At present, the conventional foreign matter recognition methods of using in article on-line detecting systems such as tobacco is based on the colourity statistic law of pixel, its basic principle is to utilize tobacco and the foreign matter difference on color, pixel belongs to tobacco or foreign matter in the judging unit, and then whether includes foreign matter in the judging unit.Its course of work has following basic step: 1, chroma space: transform to Ohta or HIS space by rgb space; 2, computational discrimination threshold value: the scope (as R, G, B etc.) of the color parameter of statistics tobacco leaf and various foreign matters in chrominance space, the upper and lower bound that obtains differentiating; 3, the pixel attribute is differentiated: according to the threshold value that obtains, the pixel of differentiating in the testing image belongs to tobacco leaf or foreign matter; 4, cell attribute is differentiated: the ratio that belongs to tobacco leaf according to pixel in the unit determines whether this unit comprises foreign matter.
Said method has recognition effect preferably for the bigger foreign matter of color and tobacco leaf difference, but powerless for the color foreign matter similar to tobacco leaf.In the step (3) of said method, be that to differentiate this point be to belong to tobacco or foreign matter for colorimetric parameter (as R, G, B etc.) according to pixel.In the actual conditions, some foreign matter has in a big way overlapping with tobacco in color controls, therefore only differentiate according to color of pixel, is easy to occur erroneous judgement.This also is the place that this method haves much room for improvement.
Summary of the invention:
In order to improve the correct decision rate of article such as tobacco and foreign matter, especially improve the discrimination of the color foreign matter close with thing to be checked, to develop the more excellent foreign body eliminating system of performance, the invention provides a kind of recognition methods based on the whole uniformity of chromaticity of judgement unit.It at first supposes all Normal Distribution of each statistic, whole unit gray scale to standard article and background image is added up, thereby obtain the inhomogeneity discrimination threshold in unit, and judge whether including foreign matter in the to-be-measured cell, make easier being identified of the colourity foreign matter similar, thereby improved the correct recognition rata of article such as tobacco and foreign matter to article to be measured.In order to realize the foregoing invention purpose, technical scheme of the present invention is:
The present invention has comprised the basic step of prior art:
(1) image capture:
(2) image transmission:
(3) foreign matter identification is handled:
(4) identification signal transmission:
(5) reject foreign matter.
Improvement of the present invention is:
In step (3), at first be colour information according to image, utilize based on whether including foreign matter in the pixel colourity diagnostic method recognition unit; If run into color and the approaching unit of article to be measured, can't use based on the method for pixel colourity and judge then come whether to include in the judgement unit foreign matter according to whole unit gradation uniformity method.Why to utilize earlier and discern based on pixel colourity diagnostic method, be owing to need the ASSOCIATE STATISTICS amount of computing unit gradation uniformity according to whole unit gradation uniformity method, operand is a bit larger tham in the background technology method based on pixel colourity, and the color unit proportion similar to the standard article neither be very big generally speaking, in order to shorten recognition time under the prerequisite that improves recognition effect as far as possible, this method need cooperate based on the method for pixel color degree to be used.Running into the color unit similar, can't the judgement unit attribute time, just using according to whole unit gradation uniformity method and use based on the method for pixel colourity to the standard article.
Based on the method that judgement unit overall intensity uniformity is come the attribute of judgement unit, be to be that unit adds up differentiation with the unit.The basic principle of this method is as follows:
Suppose with g (m, n) expression unit intensity profile, then available respectively following two formulas of the gray average A of this unit and gray variance D are represented:
Another that use always in the statistics represents that inhomogeneity parameter is single order center square D
1Its form is:
For increasing the reliability of threshold value, again the statistic of a plurality of unit is added up, obtain A, D, D respectively
1Average, variance and single order center square.
Suppose all Normal Distribution of each statistic, thereby obtain the distribution of each statistic.Carry out the unit uniformity when differentiating, when the parameter of to-be-measured cell in scope, then judge it is standard article such as tobacco leaf, otherwise, be considered as foreign matter.
Therefore this method comprises following concrete steps:
1. image preliminary treatment: at first the coloured image with the standard article is transformed to gray level image; Carrying out smothing filtering then, adopt medium filtering to eliminate noise, specifically is use a sliding window on the gray level image of gained, the gray scale of each pixel in the window is sorted by size, with the former gray scale of its intermediate value replacement window center pixel;
2. with the gray level image division unit of standard article, calculate the gray-scale statistical amount of each unit: the gray average of individual unit, variance, single order center square in the basis of calculation article gray level image;
3. computational discrimination threshold value: gray average, variance and the single order center square average and the variance separately of adding up all said units, according to the normal distribution principle, calculate the upper and lower bound of gray average, variance, single order center square, thereby obtain the discrimination threshold of reference material article unit gradation uniformity;
4. identification is handled: with the to-be-measured cell image gray processing, and calculate gray average, variance and the single order center square of this unit, and compare with discrimination threshold, judge whether include foreign matter in the unit to be identified, the standard that is considered as article in scope, on the contrary then be foreign matter.
Further, the present invention also in step (1), uses light emitting diode to replace common fluorescent tube as light source, because lifetime of LED is long, stabilized intensity, the color and the brightness that obtain image are also just more stable.With two CCD line array video cameras the upper and lower surface of determinand is taken pictures simultaneously, respectively two width of cloth images that obtain are discerned, reduced like this owing to block the erroneous judgement of generation.
The invention has the beneficial effects as follows: some foreign matter colourities are similar to article to be measured, and a large amount of coincidences zone is arranged in the color space, only use in the background technology based on the recognition methods of pixel colourity, and discrimination is very low, and higher False Rate is arranged; By method of the present invention, adopt the overall intensity uniformity of unit to differentiate, make the color foreign matter similar obtain effective recognition, thereby improved the correct recognition rata of article such as tobacco and foreign matter to article to be measured.Method operand among the present invention is little, realizes easily, and is real-time, is highly suitable for the online detection of article such as tobacco.
Description of drawings:
Fig. 1 is the image of standard tobacco leaf;
Fig. 2 is a foreign matter---the image of Calusena lansium band;
Fig. 3 is the image that contains the Calusena lansium band;
A and B are to use the unit uniformity to differentiate the recognition effect contrast of front and back among Fig. 4.
Fig. 5 is the flow chart based on the online foreign matter method of identification of unit gradation uniformity.
Fig. 6 is the detection system structural representation based on the online foreign matter method of identification of unit gradation uniformity.
Specific embodiment:
Below with the example that is identified as of tobacco, in conjunction with the accompanying drawings, a specific embodiment of the present invention is described.
The image of standard tobacco leaf as shown in Figure 1, if be mixed with the more approaching foreign matter of color in the tobacco leaf such as Calusena lansium is with foreign matter---the image of Calusena lansium band is then obviously different, and as shown in Figure 2, they can be differentiated according to whole unit gradation uniformity method.
In conjunction with Fig. 5 and Fig. 6, being implemented as follows of this method:
1, image capture: on production line, when tobacco leaf stream is transferred into the conveyer belt rear end, produce high velocity air with starting drive, tobacco leaf stream is coupled in the air-flow and with high speed (about 5m/s) impelling, flow when unsettled at tobacco leaf, (5000 lines/s) absorb the tobacco in the certain limit and the coloured image of foreign matter mixture simultaneously from upper and lower surface, use light emitting diode as light source to adopt two high-speed CCD line array video cameras.
2, image transmission: the position signalling of taking the photograph view data and tobacco leaf stream is reached in the middle of the calculator memory with image pick-up card.
3, foreign matter identification is handled:
At first discern,, adopt method of the present invention if run into color and the approaching unit of article to be measured with the method based on pixel colourity in the background technology:
(1) to the standard tobacco leaf coloured image gray processing among Fig. 1, makes it to become the gray-scale map image pattern, and eliminate smooth noise with medium filtering.
(2), and calculate A, D, the D of each unit gradation with image division unit
1
(3) add up all unit A, D, D
1Average and variance, according to the normal distribution principle, calculate A, D, D
1Upper and lower bound.
(4),, and calculate A, D, the D of this unit as Fig. 3 with the to-be-measured cell gray processing
1
(5) with A, D, the D of to-be-measured cell
1Compare with threshold value, in threshold range, be considered as tobacco leaf, otherwise then be foreign matter.From the A of Fig. 4 and B, can compare and use the recognition effect contrast of unit uniformity before and after differentiating.
4, identification signal transmission: after tobacco and foreign matter discerned, the signal of expression foreign matter position is transferred to the ECU of system.In two width of cloth images that same unit obtains, there is foreign matter for two video cameras, thinks that then there is foreign matter in this unit as long as there is a width of cloth to be judged as.
5, reject foreign matter: ECU is controlled corresponding air nozzle with foreign body eliminating according to received foreign matter position signalling.
Claims (2)
1, the online foreign matter method of identification based on unit gradation uniformity during article detect may further comprise the steps:
(1) image capture: on production line, with the article to be measured in the CCD line array video camera picked-up certain limit and the image of foreign matter mixture;
(2) image transmission: the position signalling of taking the photograph view data and article flow is reached in the middle of the calculator memory with image pick-up card;
(3) foreign matter identification is handled: at first according to the colour information of image, utilize based on whether including foreign matter in the pixel colourity diagnostic method recognition unit; If run into color and the approaching unit of article to be measured, can't use based on the method for pixel colourity and judge then come whether to include in the judgement unit foreign matter according to whole unit gradation uniformity method;
(4) identification signal transmission: after article and foreign matter discerned, the signal of expression foreign matter position is transferred to ECU;
(5) reject foreign matter: ECU is controlled corresponding air nozzle with foreign body eliminating according to the foreign matter position signalling that is received;
Its characteristics are:
The foreign matter identification of step (3) has been adopted the method for coming the attribute of judgement unit based on judgement unit overall intensity uniformity in handling, and this method has following steps:
1. image preliminary treatment: at first the coloured image with the standard article is transformed to gray level image; Carrying out smothing filtering then, adopt medium filtering to eliminate noise, specifically is use a sliding window on the gray level image of gained, and the gray scale of each pixel in the window is sorted by size, and replaces the former gray scale of window center pixel with Mesophyticum;
2. with the gray level image division unit of standard article, calculate the gray-scale statistical amount of each unit: the gray average of individual unit, variance, single order center square in the basis of calculation article gray level image;
3. computational discrimination threshold value: gray average, variance and the single order center square average and the variance separately of adding up all said units, according to the normal distribution principle, calculate the upper and lower bound of gray average, variance, single order center square, thereby obtain the discrimination threshold of reference material article unit gradation uniformity;
4. identification is handled: with the to-be-measured cell image gray processing, and calculate gray average, variance and the single order center square of this unit, and compare with discrimination threshold, judge whether include foreign matter in the unit to be identified, the standard that is considered as article in threshold range, on the contrary then be foreign matter.
2, online foreign matter method of identification according to claim 1 is characterized in that: use light emitting diode as light source in step (1), and all make a video recording in the determinand top and bottom, simultaneously the two sides of determinand is discerned.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2005100201355A CN1293835C (en) | 2005-01-06 | 2005-01-06 | On line foreign matter distinguishing method for article inspection based on unit gradation uniformity |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CNB2005100201355A CN1293835C (en) | 2005-01-06 | 2005-01-06 | On line foreign matter distinguishing method for article inspection based on unit gradation uniformity |
Publications (2)
Publication Number | Publication Date |
---|---|
CN1653975A true CN1653975A (en) | 2005-08-17 |
CN1293835C CN1293835C (en) | 2007-01-10 |
Family
ID=34894262
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CNB2005100201355A Expired - Fee Related CN1293835C (en) | 2005-01-06 | 2005-01-06 | On line foreign matter distinguishing method for article inspection based on unit gradation uniformity |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN1293835C (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102042812A (en) * | 2010-09-15 | 2011-05-04 | 苏州凌创电子系统有限公司 | Visual machine detection method |
CN102297867A (en) * | 2011-07-20 | 2011-12-28 | 上海元一电子有限公司 | Detection system for assembly quality of wiring harness |
CN105445282A (en) * | 2014-08-22 | 2016-03-30 | 苏州惠生电子科技有限公司 | Method and apparatus for identifying dust outside counting chamber as well as automatic urinary sediment analysis system |
CN106447655A (en) * | 2016-09-20 | 2017-02-22 | 上海极清慧视科技有限公司 | Method for detecting the abnormal colors and the slight recession on the surface of a smooth object |
CN107330882A (en) * | 2017-06-30 | 2017-11-07 | 航天新长征大道科技有限公司 | Foreign matter online test method after a kind of cut based on machine vision |
CN110031461A (en) * | 2019-02-14 | 2019-07-19 | 江苏恒力化纤股份有限公司 | A kind of polyester filament dye uniformity test method |
CN115096943A (en) * | 2022-06-21 | 2022-09-23 | 郑州磨料磨具磨削研究所有限公司 | Nondestructive testing device and testing method for uniformity of fluid grinding tool |
CN115553491A (en) * | 2022-11-11 | 2023-01-03 | 湖北中烟工业有限责任公司 | Window cigarette missing detection method and device and electronic equipment |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1158021C (en) * | 2002-06-04 | 2004-07-21 | 重庆大学 | Method for recognizing impurities in in-line detection of tobacco |
-
2005
- 2005-01-06 CN CNB2005100201355A patent/CN1293835C/en not_active Expired - Fee Related
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102042812A (en) * | 2010-09-15 | 2011-05-04 | 苏州凌创电子系统有限公司 | Visual machine detection method |
CN102297867A (en) * | 2011-07-20 | 2011-12-28 | 上海元一电子有限公司 | Detection system for assembly quality of wiring harness |
CN105445282A (en) * | 2014-08-22 | 2016-03-30 | 苏州惠生电子科技有限公司 | Method and apparatus for identifying dust outside counting chamber as well as automatic urinary sediment analysis system |
CN106447655A (en) * | 2016-09-20 | 2017-02-22 | 上海极清慧视科技有限公司 | Method for detecting the abnormal colors and the slight recession on the surface of a smooth object |
CN107330882A (en) * | 2017-06-30 | 2017-11-07 | 航天新长征大道科技有限公司 | Foreign matter online test method after a kind of cut based on machine vision |
CN107330882B (en) * | 2017-06-30 | 2019-11-05 | 航天新长征大道科技有限公司 | Foreign matter online test method after a kind of tobacco shreds based on machine vision |
CN110031461A (en) * | 2019-02-14 | 2019-07-19 | 江苏恒力化纤股份有限公司 | A kind of polyester filament dye uniformity test method |
CN110031461B (en) * | 2019-02-14 | 2022-03-18 | 江苏恒力化纤股份有限公司 | Polyester filament yarn dyeing uniformity test method |
CN115096943A (en) * | 2022-06-21 | 2022-09-23 | 郑州磨料磨具磨削研究所有限公司 | Nondestructive testing device and testing method for uniformity of fluid grinding tool |
CN115096943B (en) * | 2022-06-21 | 2024-04-26 | 郑州磨料磨具磨削研究所有限公司 | Nondestructive testing device and testing method for uniformity of fluid grinding tool |
CN115553491A (en) * | 2022-11-11 | 2023-01-03 | 湖北中烟工业有限责任公司 | Window cigarette missing detection method and device and electronic equipment |
CN115553491B (en) * | 2022-11-11 | 2023-11-24 | 湖北中烟工业有限责任公司 | Window cigarette white leakage detection method and device and electronic equipment |
Also Published As
Publication number | Publication date |
---|---|
CN1293835C (en) | 2007-01-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN1293835C (en) | On line foreign matter distinguishing method for article inspection based on unit gradation uniformity | |
CN102043950B (en) | Vehicle outline recognition method based on canny operator and marginal point statistic | |
CN101030256A (en) | Method and apparatus for cutting vehicle image | |
CN102231236B (en) | Method and device for counting vehicles | |
CN104732235B (en) | A kind of vehicle checking method for eliminating the reflective interference of road at night time | |
CN102043959B (en) | License plate character segmentation method | |
CN109299674B (en) | Tunnel illegal lane change detection method based on car lamp | |
CN104769652B (en) | Method and system for detecting traffic lights | |
CN1920896A (en) | Real-time image monitoring and genuine-fake identification system for vehicle with automatic color regulating and light filling license plate | |
CN100341313C (en) | Method of determining color composition of an image | |
CN101030259A (en) | SVM classifier, method and apparatus for discriminating vehicle image therewith | |
CN103808723A (en) | Exhaust gas blackness automatic detection device for diesel vehicles | |
CN103927548B (en) | Novel vehicle collision avoiding brake behavior detection method | |
CN101063662A (en) | Method for detecting empty bottle bottom defect and device for detecting empty bottle bottom defect based on DSP | |
CN105046218A (en) | Multi-feature traffic video smoke detection method based on serial parallel processing | |
CN1293836C (en) | Lines feature on-line identifying method for detecting foreign matter in food | |
CN1272631C (en) | Moving image detecting method | |
CN112233111A (en) | Tunnel gap detection method based on digital image processing | |
CN102610104B (en) | Onboard front vehicle detection method | |
CN108229447B (en) | High beam light detection method based on video stream | |
CN106127124A (en) | The automatic testing method of the abnormal image signal in region, taxi front row | |
WO2006028571B1 (en) | Method for visual inspection of printed matter on moving lids | |
CN103175839A (en) | Processing method and system for detection of offset plate surface | |
CN1525155A (en) | Printed paper inspecting method and apparatus | |
CN106128112B (en) | Night bayonet vehicle identifies grasp shoot method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
C17 | Cessation of patent right | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20070110 Termination date: 20100208 |