JPH0721465B2 - Container inspection method - Google Patents
Container inspection methodInfo
- Publication number
- JPH0721465B2 JPH0721465B2 JP63326268A JP32626888A JPH0721465B2 JP H0721465 B2 JPH0721465 B2 JP H0721465B2 JP 63326268 A JP63326268 A JP 63326268A JP 32626888 A JP32626888 A JP 32626888A JP H0721465 B2 JPH0721465 B2 JP H0721465B2
- Authority
- JP
- Japan
- Prior art keywords
- seam
- container
- straight line
- image data
- joint
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Lifetime
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/90—Investigating the presence of flaws or contamination in a container or its contents
- G01N21/9018—Dirt detection in containers
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/0078—Testing material properties on manufactured objects
- G01N33/0081—Containers; Packages; Bottles
Landscapes
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Medicinal Chemistry (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Closed-Circuit Television Systems (AREA)
Description
【発明の詳細な説明】 〔産業上の利用分野〕 この発明は、継ぎ目をもつ容器の汚れ不良等による製品
不良を、継ぎ目と区別して判別することが可能な検査方
法に関する。Description: TECHNICAL FIELD The present invention relates to an inspection method capable of distinguishing a product defect such as a stain defect of a container having a joint from the joint.
〔従来の技術〕 この種の検査として従来は、例えば継ぎ目のある領域
（側面部）全体の検出感度を下げて検査するものがあ
る。[Prior Art] Conventionally, as this type of inspection, for example, there is an inspection in which the detection sensitivity of the entire region (side surface portion) having a joint is lowered.
しかしながら、このように検出感度を下げると、検出可
能な汚れの大きさや濃度が継ぎ目の出方に左右され、特
に面積が小さな淡い汚れは検出が極めて困難になると言
う問題がある。However, if the detection sensitivity is lowered in this way, there is a problem that the size and concentration of detectable dirt depend on the appearance of the seam, and it becomes extremely difficult to detect light dirt with a small area.
したがって、この発明の課題は継ぎ目にかかわりなく汚
れを高感度に検出できるようにすることにある。Therefore, an object of the present invention is to detect dirt with high sensitivity regardless of the joint.
継ぎ目をもつ容器内面を所定角度方向から撮像して得ら
れる撮像信号を少なくとも２値化した後、その２値化さ
れた画像データを圧縮し、この圧縮された画像データか
ら直線成分を抽出した後、この直線成分が容器の頂点を
向いているか否かにより汚れか継ぎ目かを判別し、その
結果継ぎ目と判定されたときは、この継ぎ目に許容幅を
もたせた継ぎ目帯により画像データをマスクして良否判
別する。After binarizing at least an image pickup signal obtained by picking up the inner surface of the container having a joint from a predetermined angle direction, compressing the binarized image data, and extracting a linear component from the compressed image data , It is determined whether this straight line component is a stain or a seam depending on whether it is facing the apex of the container. Determine good or bad.
汚れおよび継ぎ目を示すデータを圧縮して抽出される直
線は、これが継ぎ目であるならば容器の頂点方向に向く
筈であるから、その方向から継ぎ目か否かを判別し、継
ぎ目と判定されたときは、この継ぎ目直線に許容幅をも
たせた継ぎ目帯にて画像データをマスクして判別するこ
とにより、汚れを高精度に検出し得るようにする。The straight line that is extracted by compressing the data indicating dirt and seams should be directed to the apex direction of the container if this is a seam, so it is judged from that direction whether it is a seam, and when it is judged to be a seam. The image data is masked by the seam band in which the permissible width is given to the seam straight line, and the dirt is detected with high accuracy.
第１図はこの発明の実施例を示すフローチャートであ
る。FIG. 1 is a flow chart showing an embodiment of the present invention.
これは、良く知られている画像処理装置による処理手順
を示すもので、先ず最初は継ぎ目をもつ容器内面を所定
角度方向から撮像して得られる撮像信号を所定のしきい
値レベルで２値化する（参照）。次いで、１走査ライ
ン毎に例えば画像の立上り点，立下り点およびそのラン
長さを抽出することにより、画像の圧縮を行なう（参
照）。したがって、容器内面の２値化画像が例えば第２
図の如く示されるものとすると、上記圧縮操作により、
汚れを示す孤立点３のデータが継ぎ目２を示すデータの
立上り点として取り込まれることになる。図示されない
処理装置は上記のように圧縮されたデータに対し、例え
ば最小二乗法を適用して線分化し、直線の方程式を求め
る（参照）。This shows a processing procedure by a well-known image processing device. First, an image pickup signal obtained by picking up an image of an inner surface of a container having a joint from a predetermined angle direction is binarized at a predetermined threshold level. Yes (see). Next, the image is compressed by extracting, for example, the rising and falling points of the image and the run length thereof for each scanning line (see). Therefore, the binarized image of the inner surface of the container is, for example, the second image.
As shown in the figure, the compression operation
The data of the isolated point 3 indicating dirt is taken in as the rising point of the data indicating the seam 2. A processing device (not shown) divides the data compressed as described above into lines by applying, for example, the least squares method, and obtains a straight line equation (see).
ところで、このように抽出される直線成分は、例えばこ
れが紙コップの継ぎ目であるならば第３図のように、逆
円錐の頂点４に収束する筈である。そこで、抽出された
直線が容器の頂点方向を向いているか否かにより、継ぎ
目を含む成分か否かを判断する（参照）。例えば、TV
カメラ等の撮像装置を容器の斜め上方に複数台配置し、
その撮像視野が広角とならないように容器内面を撮像し
た後、 （イ）上記抽出された直線と画面上のＸ軸とのなす角が
所定値以上になっているか否か、 または、 （ロ）画面上に第２図に示すような座標範囲Ｘ（X0→
X1）,Y（Y0）を設定し、上記抽出された直線（の延長
線）がこの座標範囲を通過するか否か、等を判定するこ
とにより抽出された直線が容器の頂点方向を向いている
か否かを判断できる。その結果、継ぎ目を含まないと判
定された場合は不良（汚れあり）とする（参照）。By the way, the straight line component thus extracted should be converged on the vertex 4 of the inverse cone as shown in FIG. 3 if this is a joint of a paper cup. Therefore, it is determined whether or not the extracted straight line is a component including a seam, depending on whether or not the extracted straight line faces the apex direction of the container (see). For example, TV
Arrange multiple imaging devices such as cameras diagonally above the container,
After the inside surface of the container is imaged so that the imaging field of view does not have a wide angle, (a) whether the angle formed by the extracted straight line and the X axis on the screen is a predetermined value or more, or (b) The coordinate range X (X 0 →
X 1 ), Y (Y 0 ) is set, and whether the extracted straight line (extension line of the above) passes through this coordinate range, etc. You can judge whether it is suitable. As a result, when it is determined that the seam is not included, it is determined to be defective (contaminated) (see).
一方、継ぎ目を含むものと判定された場合は、例えば第
４図のように継ぎ目成分２に所定の許容幅をもたせた継
ぎ目帯５を設定し、この継ぎ目帯５によりマスクして画
像データを抽出する（参照）。その結果、第４図の如
く汚れ３があれば不良とし（，参照）、そうでなけ
れば良とする（，参照）。なお、上記継ぎ目帯５と
しては、継ぎ目とみなし得る直線に対しその左右に例え
ば４画素程度を許容するものとする。On the other hand, when it is determined that a seam is included, a seam band 5 having a predetermined allowable width is set in the seam component 2 as shown in FIG. 4, and the image data is extracted by masking with the seam band 5. Yes (see). As a result, if there is the dirt 3 as shown in FIG. 4, it is determined to be defective (see), and otherwise it is determined to be good (see). As the seam band 5, for example, about 4 pixels are allowed to the left and right of a straight line that can be regarded as a seam.
この発明によれば、圧縮された画像データから継ぎ目成
分を取り出し、汚れを継ぎ目から分離して検出するよう
にしたので、継ぎ目領域全体の感度を下げて検出するも
のに比べて、より高精度に汚れを検出することができる
利点がもたらされる。According to the present invention, the seam component is extracted from the compressed image data, and the dirt is detected separately from the seam. Therefore, the accuracy is higher than that in the case of detecting by lowering the sensitivity of the entire seam area. The advantage is that dirt can be detected.
第１図はこの発明の実施例を示すフローチャート、第２
図はデータ圧縮方法の具体例を説明するための説明図、
第３図は継ぎ目と容器の頂点との関係を説明するための
説明図、第４図は継ぎ目帯を説明するための説明図であ
る。 符号説明 １……容器、２……継ぎ目、３……孤立点（不良点）、
４……頂点、５……継ぎ目帯。FIG. 1 is a flow chart showing an embodiment of the present invention,
The figure is an explanatory diagram for explaining a concrete example of the data compression method,
FIG. 3 is an explanatory diagram for explaining the relationship between the joint and the top of the container, and FIG. 4 is an explanatory diagram for explaining the joint band. Code description 1 ... Container, 2 ... Seam, 3 ... Isolated point (defective point),
4 ... Apex, 5 ... Joint band.
───────────────────────────────────────────────────── フロントページの続き (56)参考文献 特開 昭58−21548（ＪＰ，Ａ) 特開 昭58−21546（ＪＰ，Ａ) 特開 昭57−21547（ＪＰ，Ａ) ─────────────────────────────────────────────────── ─── Continuation of front page (56) References JP-A-58-21548 (JP, A) JP-A-58-21546 (JP, A) JP-A-57-21547 (JP, A)
Claims (1)
撮像して得られる撮像信号を少なくとも２値化した後、
その２値化された画像データを圧縮し、この圧縮された
画像データから直線成分を抽出した後、この直線成分が
容器の頂点を向いているか否かにより汚れか継ぎ目かを
判別し、その結果継ぎ目と判定されたときは、この継ぎ
目に許容幅をもたせた継ぎ目帯により画像データをマス
クして良否判別することを特徴とする容器検査方法。1. An image pickup signal obtained by picking up an image of an inner surface of a container having a joint from a predetermined angle direction,
After compressing the binarized image data and extracting the straight line component from the compressed image data, it is determined whether the straight line component is facing the apex of the container to determine whether it is a stain or a seam. A container inspection method characterized in that, when it is determined to be a seam, the image data is masked with a seam band having an allowable width at the seam to determine whether the seam is good or bad.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP63326268A JPH0721465B2 (en) | 1988-12-26 | 1988-12-26 | Container inspection method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| JP63326268A JPH0721465B2 (en) | 1988-12-26 | 1988-12-26 | Container inspection method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| JPH02171640A JPH02171640A (en) | 1990-07-03 |
| JPH0721465B2 true JPH0721465B2 (en) | 1995-03-08 |
Family
ID=18185873
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| JP63326268A Expired - Lifetime JPH0721465B2 (en) | 1988-12-26 | 1988-12-26 | Container inspection method |
Country Status (1)
| Country | Link |
|---|---|
| JP (1) | JPH0721465B2 (en) |
Families Citing this family (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP3044951B2 (en) * | 1992-11-25 | 2000-05-22 | 富士電機株式会社 | Circular container inner surface inspection device |
| US5412203A (en) * | 1991-07-15 | 1995-05-02 | Fuji Electric Co., Ltd. | Cylindrical container inner surface tester |
| JP5750971B2 (en) * | 2011-03-25 | 2015-07-22 | 凸版印刷株式会社 | Defect inspection equipment |
-
1988
- 1988-12-26 JP JP63326268A patent/JPH0721465B2/en not_active Expired - Lifetime
Also Published As
| Publication number | Publication date |
|---|---|
| JPH02171640A (en) | 1990-07-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US7116814B2 (en) | Image-based container defects detector | |
| JPH0721465B2 (en) | Container inspection method | |
| JP4293653B2 (en) | Appearance inspection method | |
| JP3456096B2 (en) | Shape inspection method | |
| JPH09161056A (en) | Circular container inner surface inspection method | |
| JPH1114317A (en) | Appearance inspection method and apparatus | |
| JP2710685B2 (en) | Defect detection method by visual inspection | |
| JPH1019801A (en) | Surface defect detector | |
| JPH08190633A (en) | Defect judging method | |
| JPH07324916A (en) | Pattern outline inspection device | |
| JP3509581B2 (en) | Appearance inspection method | |
| JP2536745B2 (en) | PCB cut condition inspection method | |
| JPH0797410B2 (en) | Image processing method | |
| JPH09113467A (en) | Method for deciding defect | |
| JP2949089B2 (en) | Image processing device | |
| JPS61126455A (en) | Image processing method | |
| JPH0352015B2 (en) | ||
| JPH0235306A (en) | Shape detecting method | |
| JP3325191B2 (en) | Shellfish identification method | |
| JP2508662Y2 (en) | Flaw detection device | |
| JPH0569536A (en) | Defect detection method and defect detection circuit in printed matter inspection apparatus | |
| JPH01214742A (en) | Checking apparatus of external appearance | |
| JP3473114B2 (en) | Image processing method | |
| JP2514727B2 (en) | Defect inspection method by visual inspection | |
| JP2996345B2 (en) | Surface inspection equipment |