CN105957061A - Methods for making threshold graph and detecting picture for rotary crown cover - Google Patents
Methods for making threshold graph and detecting picture for rotary crown cover Download PDFInfo
- Publication number
- CN105957061A CN105957061A CN201610254917.3A CN201610254917A CN105957061A CN 105957061 A CN105957061 A CN 105957061A CN 201610254917 A CN201610254917 A CN 201610254917A CN 105957061 A CN105957061 A CN 105957061A
- Authority
- CN
- China
- Prior art keywords
- threshold
- pixel
- region
- threshold value
- thresholds
- 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
Classifications
-
- 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
- G06T2207/10004—Still image; Photographic 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
- G06T2207/10—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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30144—Printing quality
Abstract
The invention discloses methods for making a threshold graph and detecting a picture for a rotary crown cover. The methods comprise a threshold graph making method and a picture detecting method. The methods automatically segment regions, automatically compute the range of the threshold pixel by pixel, an automatically generate a threshold limiting value graph according to acquired pictures and in view of transformation errors and printing errors. The methods compute a defective region according to the threshold graph in online detection. The detection process has simple computation, short computing time, full-region detection, and popularization and application value.
Description
Technical field
The present invention relates to a kind of image processing method, particularly relate to a kind of threshold figure for revolving official hats and canopies make and
Figure chip detection method.
Background technology
Rotation official hats and canopies typically uses multi-color chromaticity printing, there is error due to printing machinery, and capping chromatography is always deposited
Offset at some.Additionally, due to after there is punching press position error, and capping punching press be a curved surface, because of
A little distortion inaccuracy can be there is in this capping top view.
Most producers are generally directed to standard sample, use artificial detection region and the effective range of setting, so
The most suitably reduce detection region and manual setting detection threshold value detects.The method exists commissioning staff's element
Matter requires the problems such as high, color region boundary threshold is left in the basket when detecting.
Summary of the invention
The purpose of the present invention is that a kind of threshold figure system for revolving official hats and canopies that provides to solve the problems referred to above
Make and figure chip detection method.
The present invention is achieved through the following technical solutions above-mentioned purpose:
The present invention includes threshold figure manufacture method and figure chip detection method,
Described threshold figure manufacture method comprises the following steps:
(A) each pixel in picture is gathered；
(B) each Color Channel of selected pixel and neighbor is carried out top cap calculating, currently put every
The max-thresholds of individual Color Channel；
(C) each Color Channel of selected pixel and neighbor is carried out end cap calculating, currently put every
The minimum threshold of individual Color Channel；
(D) threshold tolerance that sets according to user, automatically whole capping is carried out region segmentation, by adjacent threshold
Value difference is less than one region of classification of tolerance；
(E) max-thresholds of all pixels in same region is set as each pixel max-thresholds in this region
Maximum plus upper limit tolerance；
(F) minimum threshold of all pixels in same region is set as each pixel minimum threshold in this region
Minima deduct lower limit tolerance；
(G) according to the bound threshold value of each pixel, each Color Channel generates two threshold figures, upper limit threshold
Value figure and lower threshold figure.In figure, the value of each pixel is the threshold value that step (A) is calculated to (F)
(H) take a collection of standard drawing and repeat step (A) to (G)；
(I) by all bound threshold figures merge, rule be the upper limit of each pixel be the current picture of each standard drawing
The maximum of element threshold value.The lower limit of each pixel is the minima of each standard drawing current pixel threshold value；
Described figure chip detection method comprises the following steps:
A () calculates the maximum of passage upper threshold figure and channel sample figure, obtain max-thresholds figure；
B () deducts passage upper threshold figure with max-thresholds figure, obtain upper limit those suspected defects figure；
C () calculates the minima of passage bottom threshold figure and channel sample figure, obtain minimum threshold figure；
D () deducts minimum threshold figure with passage bottom threshold figure and obtains lower limit those suspected defects figure；
E () bound those suspected defects figure has pixel value not to be 0, then this point is those suspected defects point；
If f () adjacent those suspected defects point has exceeded area, size or the number allowed, it is determined that be scarce
Trapping spot；
G each passage in picture is repeated step (a) to step (f) by ().
The beneficial effects of the present invention is:
The present invention is that a kind of threshold figure for revolving official hats and canopies makes and figure chip detection method, compared with prior art,
The present invention, according to the picture gathered, on the basis of considering distortion inaccuracy, printing error etc., carries out region automatically
Split, automatically calculate threshold range pixel-by-pixel, automatically generate threshold limit figure.During on-line checking, according to threshold
Value limit value figure calculates defect area.This detection process possesses that calculating is simple, the detection short, region-wide of calculating time
Etc. feature, there is the value of popularization and application.
Accompanying drawing explanation
Fig. 1 is the threshold figure Making programme figure of the present invention；
Fig. 2 is the figure chip detection method flow chart of the present invention.
Detailed description of the invention
The invention will be further described below in conjunction with the accompanying drawings:
The present invention includes threshold figure manufacture method and figure chip detection method,
As shown in Figure 1: described threshold figure manufacture method comprises the following steps:
(A) each pixel in picture is gathered；
(B) each Color Channel of selected pixel and neighbor is carried out top cap calculating, currently put every
The max-thresholds of individual Color Channel；
(C) each Color Channel of selected pixel and neighbor is carried out end cap calculating, currently put every
The minimum threshold of individual Color Channel；
(D) threshold tolerance that sets according to user, automatically whole capping is carried out region segmentation, by adjacent threshold
Value difference is less than one region of classification of tolerance；
(E) max-thresholds of all pixels in same region is set as each pixel max-thresholds in this region
Maximum plus upper limit tolerance；
(F) minimum threshold of all pixels in same region is set as each pixel minimum threshold in this region
Minima deduct lower limit tolerance；
(G) according to the bound threshold value of each pixel, each Color Channel generates two threshold figures, upper limit threshold
Value figure and lower threshold figure.In figure, the value of each pixel is the threshold value that step (A) is calculated to (F)
(H) take a collection of standard drawing and repeat step (A) to (G)；
(I) by all bound threshold figures merge, rule be the upper limit of each pixel be the current picture of each standard drawing
The maximum of element threshold value.The lower limit of each pixel is the minima of each standard drawing current pixel threshold value；
As shown in Figure 2: described figure chip detection method comprises the following steps:
A () calculates the maximum of passage upper threshold figure and channel sample figure, obtain max-thresholds figure；
B () deducts passage upper threshold figure with max-thresholds figure, obtain upper limit those suspected defects figure；
C () calculates the minima of passage bottom threshold figure and channel sample figure, obtain minimum threshold figure；
D () deducts minimum threshold figure with passage bottom threshold figure and obtains lower limit those suspected defects figure；
E () bound those suspected defects figure has pixel value not to be 0, then this point is those suspected defects point；
If f () adjacent those suspected defects point has exceeded area, size or the number allowed, it is determined that be scarce
Trapping spot；
G each passage in picture is repeated step (a) to step (f) by ().
The ultimate principle of the present invention and principal character and advantages of the present invention have more than been shown and described.The industry
Skilled person will appreciate that, the present invention is not restricted to the described embodiments, in above-described embodiment and description
The principle that the present invention is simply described described, without departing from the spirit and scope of the present invention, the present invention
Also having various changes and modifications, these changes and improvements both fall within scope of the claimed invention.This
The claimed scope of invention is defined by appending claims and equivalent thereof.
Claims (1)
1. one kind makes and figure chip detection method for revolving the threshold figure of official hats and canopies, it is characterised in that: include threshold value
Figure manufacture method and figure chip detection method,
Described threshold figure manufacture method comprises the following steps:
(A) each pixel in picture is gathered；
(B) each Color Channel of selected pixel and neighbor is carried out top cap calculating, currently put every
The max-thresholds of individual Color Channel；
(C) each Color Channel of selected pixel and neighbor is carried out end cap calculating, currently put every
The minimum threshold of individual Color Channel；
(D) threshold tolerance that sets according to user, automatically whole capping is carried out region segmentation, by adjacent threshold
Value difference is less than one region of classification of tolerance；
(E) max-thresholds of all pixels in same region is set as each pixel max-thresholds in this region
Maximum plus upper limit tolerance；
(F) minimum threshold of all pixels in same region is set as each pixel minimum threshold in this region
Minima deduct lower limit tolerance；
(G) according to the bound threshold value of each pixel, each Color Channel generates two threshold figures, upper limit threshold
Value figure and lower threshold figure.In figure, the value of each pixel is the threshold value that step (A) is calculated to (F)
(H) take a collection of standard drawing and repeat step (A) to (G)；
(I) by all bound threshold figures merge, rule be the upper limit of each pixel be the current picture of each standard drawing
The maximum of element threshold value.The lower limit of each pixel is the minima of each standard drawing current pixel threshold value；
Described figure chip detection method comprises the following steps:
A () calculates the maximum of passage upper threshold figure and channel sample figure, obtain max-thresholds figure；
B () deducts passage upper threshold figure with max-thresholds figure, obtain upper limit those suspected defects figure；
C () calculates the minima of passage bottom threshold figure and channel sample figure, obtain minimum threshold figure；
D () deducts minimum threshold figure with passage bottom threshold figure and obtains lower limit those suspected defects figure；
E () bound those suspected defects figure has pixel value not to be 0, then this point is those suspected defects point；
If f () adjacent those suspected defects point has exceeded area, size or the number allowed, it is determined that be scarce
Trapping spot；
G each passage in picture is repeated step (a) to step (f) by ().
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610254917.3A CN105957061A (en) | 2016-04-22 | 2016-04-22 | Methods for making threshold graph and detecting picture for rotary crown cover |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610254917.3A CN105957061A (en) | 2016-04-22 | 2016-04-22 | Methods for making threshold graph and detecting picture for rotary crown cover |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105957061A true CN105957061A (en) | 2016-09-21 |
Family
ID=56915670
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610254917.3A Pending CN105957061A (en) | 2016-04-22 | 2016-04-22 | Methods for making threshold graph and detecting picture for rotary crown cover |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105957061A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022017080A1 (en) * | 2020-07-23 | 2022-01-27 | 长鑫存储技术有限公司 | Photomask defect detection method and system |
| CN114937041A (en) * | 2022-07-25 | 2022-08-23 | 聊城市博源节能科技有限公司 | Method and system for detecting defects of copper bush of oil way of automobile engine |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070273927A1 (en) * | 2006-05-25 | 2007-11-29 | Fuji Xerox Co., Ltd. | Image processing apparatus, image forming apparatus, and image processing method |
| CN102682514A (en) * | 2012-05-17 | 2012-09-19 | 广州广电运通金融电子股份有限公司 | Paper identification method and relative device |
| CN102968616A (en) * | 2012-10-25 | 2013-03-13 | 中国电子科技集团公司第四十一研究所 | Light yellow tobacco shred identification and deepening method in cigarette loose-end detection process |
| CN103824304A (en) * | 2014-03-18 | 2014-05-28 | 中国矿业大学(北京) | Method for performing fault diagnosis on ores on conveying belt during conveying process |
| CN104318543A (en) * | 2014-01-27 | 2015-01-28 | 郑州大学 | Board metering method and device based on image processing method |
| CN104899863A (en) * | 2015-04-02 | 2015-09-09 | 厦门博视源机器视觉技术有限公司 | Mold protector and implementation method thereof |
| US20160055383A1 (en) * | 2014-08-20 | 2016-02-25 | Denso Corporation | Lane boundary lane recognition device and computer-readable storage medium storing program for recognizing lane boundary lines on roadway |
| CN105466950A (en) * | 2016-01-14 | 2016-04-06 | 上海孚兴电子科技有限公司 | Bamboo dice online detection method and system based on vision |
-
2016
- 2016-04-22 CN CN201610254917.3A patent/CN105957061A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20070273927A1 (en) * | 2006-05-25 | 2007-11-29 | Fuji Xerox Co., Ltd. | Image processing apparatus, image forming apparatus, and image processing method |
| CN102682514A (en) * | 2012-05-17 | 2012-09-19 | 广州广电运通金融电子股份有限公司 | Paper identification method and relative device |
| CN102968616A (en) * | 2012-10-25 | 2013-03-13 | 中国电子科技集团公司第四十一研究所 | Light yellow tobacco shred identification and deepening method in cigarette loose-end detection process |
| CN104318543A (en) * | 2014-01-27 | 2015-01-28 | 郑州大学 | Board metering method and device based on image processing method |
| CN103824304A (en) * | 2014-03-18 | 2014-05-28 | 中国矿业大学(北京) | Method for performing fault diagnosis on ores on conveying belt during conveying process |
| US20160055383A1 (en) * | 2014-08-20 | 2016-02-25 | Denso Corporation | Lane boundary lane recognition device and computer-readable storage medium storing program for recognizing lane boundary lines on roadway |
| CN104899863A (en) * | 2015-04-02 | 2015-09-09 | 厦门博视源机器视觉技术有限公司 | Mold protector and implementation method thereof |
| CN105466950A (en) * | 2016-01-14 | 2016-04-06 | 上海孚兴电子科技有限公司 | Bamboo dice online detection method and system based on vision |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022017080A1 (en) * | 2020-07-23 | 2022-01-27 | 长鑫存储技术有限公司 | Photomask defect detection method and system |
| CN114937041A (en) * | 2022-07-25 | 2022-08-23 | 聊城市博源节能科技有限公司 | Method and system for detecting defects of copper bush of oil way of automobile engine |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108921176B (en) | Pointer instrument positioning and identifying method based on machine vision | |
| CN108764229B (en) | Water gauge image automatic identification method based on computer vision technology | |
| CN110163219B (en) | Target detection method based on image edge recognition | |
| CN109426814B (en) | Method, system and equipment for positioning and identifying specific plate of invoice picture | |
| CN106097368B (en) | A kind of recognition methods in veneer crack | |
| CN107590447A (en) | A kind of caption recognition methods and device | |
| CN105139391B (en) | A kind of haze weather traffic image edge detection method | |
| CN105139386A (en) | Image processing method for quickly and automatically detecting soldered dot unsatisfied products of electric connectors | |
| CN104835242B (en) | A kind of banknote image processing method | |
| EP4071665A1 (en) | Character segmentation method and apparatus, and computer-readable storage medium | |
| CN104751097A (en) | Vehicle identification code detection processing method and device | |
| CN111275697A (en) | Battery silk-screen quality detection method based on ORB feature matching and LK optical flow method | |
| CN104851085A (en) | Method and system automatically obtaining detection zone in image | |
| CN104598907B (en) | Lteral data extracting method in a kind of image based on stroke width figure | |
| CN108960237A (en) | A kind of pointer type fuel level indicator Recognition of Reading method | |
| CN110930427A (en) | Image segmentation method, device and storage medium based on semantic contour information | |
| CN111122590A (en) | Ceramic surface defect detection device and detection method | |
| CN110032946A (en) | A kind of aluminium based on machine vision/aluminium blister package tablet identification and localization method | |
| CN106127124A (en) | The automatic testing method of the abnormal image signal in region, taxi front row | |
| CN103793923A (en) | Method and device for acquiring moving object in image | |
| CN105957061A (en) | Methods for making threshold graph and detecting picture for rotary crown cover | |
| CN110569774B (en) | Automatic line graph image digitalization method based on image processing and pattern recognition | |
| CN108492306A (en) | A kind of X-type Angular Point Extracting Method based on image outline | |
| CN104966283A (en) | Imaging layered registering method | |
| CN111768455A (en) | Image-based wood region and dominant color extraction 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 | ||
| AD01 | Patent right deemed abandoned |
Effective date of abandoning: 20190507 |
|
| AD01 | Patent right deemed abandoned |