CN110097532A - A kind of method of bullet open defect detection - Google Patents
A kind of method of bullet open defect detection Download PDFInfo
- Publication number
- CN110097532A CN110097532A CN201910035177.8A CN201910035177A CN110097532A CN 110097532 A CN110097532 A CN 110097532A CN 201910035177 A CN201910035177 A CN 201910035177A CN 110097532 A CN110097532 A CN 110097532A
- Authority
- CN
- China
- Prior art keywords
- image
- area
- shell case
- region
- max
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
Abstract
The invention discloses a kind of method of bullet open defect detection, the first step acquires image, i.e., acquires shell case image by color camera；The shell case image acquired in the first step is switched to H by second step, translated image1S1I1Three width images；Third step, image rectification, i.e., the I being converted into second step1In image, image is corrected, generates new image；4th step converts new image, i.e., the newly-generated image in third step is converted to H2S2I2Image；5th step, the defect screening of shell case, i.e., by the S in the 4th step2Dual threshold binary conversion treatment is carried out according to the detection zone of setting in figure, extracts bleed-out, wrinkle defect region, and by bleed-out, wrinkle defect region gross area A1 and area-limit (A1Min, A1Max) be compared；By the S in the 4th step2Dynamic threshold segmentation binary conversion treatment is carried out according to the detection zone of setting in figure, stria region is extracted, by stria region gross area A2 and area-limit (A2Min, A2Max) be compared.Of the invention is easy to detect quick, high-efficient.
Description
Technical field
The present invention relates to a kind of methods that bullet mass field more particularly to bullet open defect are detected.
Background technique
Bullet shell case in process of production can bullet side wall there are the bad phenomenons of bleed-out, fold, stria.Defective products makes
Used time is main at present to detect using artificial observation by the way of there are serious security risk, this method by be artificially responsible for because
Element influences, and accuracy in detection will receive the fatigue and the influence of experience of people.
Summary of the invention
The purpose of the present invention is to solve the shortcomings of the prior art and a kind of method of bullet open defect detection is provided, inspection
Survey it is convenient and efficient, it is high-efficient.
In order to achieve the above objectives, the present invention is achieved through the following technical solutions.
A kind of method of bullet open defect detection, the first step acquire image, i.e., acquire shell case figure by color camera
Picture；
The shell case image acquired in the first step is switched to H by second step, translated image1S1I1Three width images；
Third step, image rectification, i.e., the I being converted into second step1In image, in the top edge of shell case the high H of setting n item,
The hough transform region of wide W, and maximum coordinate set of grey scale change (X (n), Y (n)) in each rectangular area is sought, by this
Point coordinate set is fitted the top edge center point coordinate for finding out top edge line, and finding out shell case that is in line by Hough transformation
(X (0), Y (0)), according to the angle and center point coordinate of top edge line, is corrected image referring to template position, generates new
Image；
4th step converts new image, i.e., the newly-generated image in third step is converted to H2S2I2Image；
5th step, the defect screening of shell case, i.e., by the S in the 4th step2Dual threashold is carried out according to the detection zone of setting in figure
It is worth binary conversion treatment, extracts bleed-out, wrinkle defect region, and by bleed-out, wrinkle defect region gross area A1 and area-limit
(A1Min, A1Max) be compared；
By the S in the 4th step2Dynamic threshold segmentation binary conversion treatment is carried out according to the detection zone of setting in figure, extracts line
Trace region, by stria region gross area A2 and area-limit (A2Min, A2Max) be compared.
Further, the n in the third step is 100, H 150mm, W 5mm.
Further, the area-limit (A1 in the 5th stepMin, A1Max) it is (0,100).
Further, the area-limit (A2 in the 6th stepMin, A2Max) it is (0,50).
A kind of method of bullet open defect detection of the invention, it is easy to detect quick, it is high-efficient.
Detailed description of the invention
Fig. 1 is original image and H of the invention1S1I1The schematic diagram of figure；
I in Fig. 2 Fig. 11The hough transform area schematic of figure；
I in Fig. 3 Fig. 11The schematic diagram of the top edge line of figure；
Fig. 4 is correction chart and H2S2I2The schematic diagram of image；
Fig. 5 is the schematic diagram of the bleed-out area image of shell case；
Fig. 6 is the schematic diagram of the plication region image of shell case；
Fig. 7 is the schematic diagram of the stria area image of shell case；
Specific embodiment
Below with reference to embodiment, the present invention will be further described, but is not limited to the content on specification.
It is as shown in the figure: a kind of method of bullet open defect detection, it the following steps are included:
The first step acquires image, i.e., acquires shell case image by color camera；
The shell case image acquired in the first step is switched to H by second step, translated image1S1I1Three width images are (such as one institute of figure
Show)；
Third step, image rectification, i.e., the I being converted into second step1In image, in the top edge of shell case the high H of setting n item,
The hough transform region (as shown in Figure 2) (n=100, H=150mm, W=5mm) of wide W, and seek grey in each rectangular area
Degree maximum coordinate set (X (n), Y (n)) of variation, which is in line by Hough transformation fitting and is found out
Edge line (as shown in Figure 3), and the top edge center point coordinate (X (0), Y (0)) of shell case is found out, according to the angle of top edge line
Degree and center point coordinate, are corrected image referring to template position, generate new image；Template position is to ask from template image
The angle and center point coordinate of the right hand edge line taken, the angle and centre coordinate of new images right hand edge line subtract the angle of template position
Degree and coordinate, acquire image rotation angle and translational movement, carry out rotation and translation correction to new images.
4th step converts new image, i.e., the newly-generated image in third step is converted to H2S2I2Image (such as figure four
It is shown)；
5th step, the defect screening of shell case, i.e., by the S in the 4th step2Dual threashold is carried out according to the detection zone of setting in figure
It is worth binary conversion treatment, detection zone is to enclose the cartridge case region taken manually, extracts bleed-out, wrinkle defect region (such as figure five, figure
Shown in six), and by bleed-out, the wrinkle defect region gross area (mm2) A1 and area-limit mm2(A1Min, A1Max) be compared, surpass
Threshold range is bad out；By the S in the 4th step2It is carried out at dynamic threshold segmentation binaryzation in figure according to the detection zone of setting
Reason is extracted stria region (as shown in figure seven), by stria region gross area A2 (mm2) and area-limit mm2(A2Min, A2Max) into
Row compares, and is bad beyond threshold range.
Specific embodiment one:
The first step acquires image, i.e., acquires shell case image by color camera；
The shell case image acquired in the first step is switched to H by second step, translated image1S1I1Three width images；
Third step, image rectification, i.e., the I being converted into second step1In image, n=100 item is set in the top edge of shell case
The hough transform region of high H=150, width W=5, and seek maximum coordinate set (X of grey scale change in each rectangular area
(n), Y (n)), this coordinate set is in line by Hough transformation fitting and finds out top edge line (as shown in Figure 3), and is asked
The top edge center point coordinate (661,22) of shell case out, according to the angle (- 1 °) and center point coordinate of top edge line (661,
22), image is corrected referring to template position (angle (0 °), center point coordinate (657,45)), generates new image；
4th step converts new image, i.e., the newly-generated image in third step is converted to H2S2I2Image；
5th step, the defect screening of shell case, i.e., by the S in the 4th step2Dual threashold is carried out according to the detection zone of setting in figure
It is worth binary conversion treatment, extracts bleed-out, wrinkle defect region, and by bleed-out, the wrinkle defect region gross area 1201 and area-limit
(0,100) is compared, A1=1201, exceeds threshold range, which is bad products；
By the S in the 4th step2Dynamic threshold segmentation binary conversion treatment is carried out according to the detection zone of setting in figure, extracts line
Stria region gross area A2 and area-limit (0,50) are compared, A2=66 by trace region, exceed threshold range, the shell case
For bad products.
Specific embodiment two:
The first step acquires image, i.e., acquires shell case image by color camera；
The shell case image acquired in the first step is switched to H by second step, translated image1S1I1Three width images；
Third step, image rectification, i.e., the I being converted into second step1In image, n=100 item is set in the top edge of shell case
The hough transform region of high H=150, width W=5, and seek maximum coordinate set (X of grey scale change in each rectangular area
(n), Y (n)), this coordinate set is in line by Hough transformation fitting and finds out top edge line (as shown in Figure 3), and is asked
The top edge center point coordinate (651,33) of shell case out, according to the angle (- 1.5 °) and center point coordinate of top edge line (651,
33), image is corrected referring to template position (angle (0 °), center point coordinate (657,45)), generates new image；
4th step converts new image, i.e., the newly-generated image in third step is converted to H2S2I2Image；
5th step, the defect screening of shell case, i.e., by the S in the 4th step2Dual threashold is carried out according to the detection zone of setting in figure
Be worth binary conversion treatment, extract bleed-out, wrinkle defect region, and by bleed-out, the wrinkle defect region gross area 22 and area-limit (0,
100) it is compared, A1=22, without departing from threshold range, which is quality product；
By the S in the 4th step2Dynamic threshold segmentation binary conversion treatment is carried out according to the detection zone of setting in figure, extracts line
The stria region gross area 10 and area-limit (0,50) are compared, A2=10, without departing from threshold range, the bullet by trace region
Shell is quality product.
A kind of method of bullet open defect detection of the invention, it is easy to detect quick, it is high-efficient.
Obviously, above embodiment of the invention be only to clearly illustrate example of the present invention, and not be
Restriction to embodiments of the present invention.For those of ordinary skill in the art, on the basis of the above description also
It can make other variations or changes in different ways.Here all embodiments can not be exhaustive.It is all to belong to this
The obvious changes or variations that the technical solution of invention is extended out are still in the scope of protection of the present invention.
Claims (4)
1. a kind of method of bullet open defect detection, which is characterized in that it the following steps are included:
The first step acquires image, i.e., acquires shell case image by color camera；
The shell case image acquired in the first step is switched to H by second step, translated image1S1I1Three width images；
Third step, image rectification, i.e., the I being converted into second step1In image, the high H of setting n item, width W in the top edge of shell case
Hough transform region, and maximum coordinate set of grey scale change (X (n), Y (n)) in each rectangular area is sought, by the coordinate
Collection is fitted by Hough transformation and is in line and finds out top edge line, and find out shell case top edge center point coordinate (X (0),
Y (0)), according to the angle and center point coordinate of top edge line, image is corrected referring to template position, generates new image；
4th step converts new image, i.e., the newly-generated image in third step is converted to H2S2I2Image；
5th step, the defect screening of shell case, i.e., by the S in the 4th step2Dual threshold two-value is carried out according to the detection zone of setting in figure
Change processing, extracts bleed-out, wrinkle defect region, and by bleed-out, wrinkle defect region gross area A1 and area-limit (A1Min,
A1Max) be compared；
By the S in the 4th step2Dynamic threshold segmentation binary conversion treatment is carried out according to the detection zone of setting in figure, extracts stria area
Domain, by stria region gross area A2 and area-limit (A2Min, A2Max) be compared.
2. a kind of method of bullet open defect detection according to claim 1, it is characterised in that: in the third step
N is 100, H 150mm, W 5mm.
3. a kind of method of bullet open defect detection according to claim 1, it is characterised in that: in the 5th step
Area-limit (A1Min, A1Max) it is (0,100).
4. a kind of method of bullet open defect detection according to claim 1, it is characterised in that: in the 6th step
Area-limit (A2Min, A2Max) it is (0,50).
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910035177.8A CN110097532A (en) | 2019-01-15 | 2019-01-15 | A kind of method of bullet open defect detection |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910035177.8A CN110097532A (en) | 2019-01-15 | 2019-01-15 | A kind of method of bullet open defect detection |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110097532A true CN110097532A (en) | 2019-08-06 |
Family
ID=67443694
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910035177.8A Pending CN110097532A (en) | 2019-01-15 | 2019-01-15 | A kind of method of bullet open defect detection |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110097532A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113096123A (en) * | 2021-05-07 | 2021-07-09 | 湘潭大学 | Multi-fuzzy reasoning cascaded primer side defect classification and damage degree analysis method |
| CN115287860A (en) * | 2022-09-26 | 2022-11-04 | 江苏祥源纺织科技有限公司 | Textile fabric ironing degree control method based on automatic ironing equipment |
| CN116681752A (en) * | 2023-08-03 | 2023-09-01 | 山东墨氪智能科技有限公司 | Method and device for calculating void ratio of void defects of DBC solder layer |
| CN117474902A (en) * | 2023-12-25 | 2024-01-30 | 山东明佳科技有限公司 | Method, system, equipment and storage medium for detecting missing of barrel fabric package |
-
2019
- 2019-01-15 CN CN201910035177.8A patent/CN110097532A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113096123A (en) * | 2021-05-07 | 2021-07-09 | 湘潭大学 | Multi-fuzzy reasoning cascaded primer side defect classification and damage degree analysis method |
| CN115287860A (en) * | 2022-09-26 | 2022-11-04 | 江苏祥源纺织科技有限公司 | Textile fabric ironing degree control method based on automatic ironing equipment |
| CN116681752A (en) * | 2023-08-03 | 2023-09-01 | 山东墨氪智能科技有限公司 | Method and device for calculating void ratio of void defects of DBC solder layer |
| CN116681752B (en) * | 2023-08-03 | 2023-10-27 | 山东墨氪智能科技有限公司 | Method and device for calculating void ratio of void defects of DBC solder layer |
| CN117474902A (en) * | 2023-12-25 | 2024-01-30 | 山东明佳科技有限公司 | Method, system, equipment and storage medium for detecting missing of barrel fabric package |
| CN117474902B (en) * | 2023-12-25 | 2024-03-12 | 山东明佳科技有限公司 | Method, system, equipment and storage medium for detecting missing of barrel fabric package |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110097532A (en) | A kind of method of bullet open defect detection | |
| CN112508826B (en) | Printed matter defect detection method | |
| CN105067638B (en) | Tire fetal membrane face character defect inspection method based on machine vision | |
| Feng et al. | An efficient detection method for rare colored capsule based on RGB and HSV color space | |
| CN107610104A (en) | Crack detecting method at a kind of elevator compensation chain R based on machine vision | |
| CN111667475B (en) | Machine vision-based Chinese date grading detection method | |
| CN107490582A (en) | A kind of streamline Work Piece Verification System Based | |
| CN111402238A (en) | Defect identification system realized through machine vision | |
| CN110096980A (en) | Character machining identifying system | |
| CN102901735B (en) | System for carrying out automatic detections upon workpiece defect, cracking, and deformation by using computer | |
| CN106651893A (en) | Edge detection-based wall body crack identification method | |
| CN108020554A (en) | A kind of steel strip surface defect recognition detection method | |
| CN109781737A (en) | A kind of detection method and its detection system of hose surface defect | |
| CN110807763A (en) | Method and system for detecting ceramic tile surface bulge | |
| CN110648330A (en) | Defect detection method for camera glass | |
| CN107256549B (en) | Bamboo strip defect detection method based on machine vision | |
| CN111968082A (en) | Product packaging defect detection and identification method based on machine vision | |
| Ma et al. | The defect detection of personalized print based on template matching | |
| CN108805854B (en) | Method for rapidly counting tablets and detecting completeness of tablets in complex environment | |
| CN107609482A (en) | A kind of Chinese text image inversion method of discrimination based on Chinese-character stroke feature | |
| Junxiong et al. | Feature extraction of jujube fruit wrinkle based on the watershed segmentation | |
| Tribak et al. | Remote solar panels identification based on patterns localization | |
| KR101360653B1 (en) | Apparatus for detecting seem crack of rolled steel | |
| CN109886912A (en) | A kind of thrust bearing retainer detection method of surface flaw | |
| KR101858829B1 (en) | Segregation analysis apparatus and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20191108 Address after: 650300 Taiping new town sub district office, Anning City, Kunming City, Yunnan Province Applicant after: Yunnan Anning Chemical Plant Co., Ltd Address before: 650300 Industrial Park of Street Office of Taiping New Town, Anning City, Kunming City, Yunnan Province Applicant before: Yunnan vision intelligent equipment Co., Ltd. |
|
| TA01 | Transfer of patent application right | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20190806 |
|
| WD01 | Invention patent application deemed withdrawn after publication |