TWI583943B - Bottle flaw defect detection device and method thereof - Google Patents

Bottle flaw defect detection device and method thereof Download PDF

Info

Publication number
TWI583943B
TWI583943B TW104119231A TW104119231A TWI583943B TW I583943 B TWI583943 B TW I583943B TW 104119231 A TW104119231 A TW 104119231A TW 104119231 A TW104119231 A TW 104119231A TW I583943 B TWI583943 B TW I583943B
Authority
TW
Taiwan
Prior art keywords
bottle
glass bottles
image
bottle mouth
conveyor belt
Prior art date
Application number
TW104119231A
Other languages
Chinese (zh)
Other versions
TW201643417A (en
Inventor
sheng-yi Zheng
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed filed Critical
Priority to TW104119231A priority Critical patent/TWI583943B/en
Priority to CN201610156491.8A priority patent/CN106248685A/en
Publication of TW201643417A publication Critical patent/TW201643417A/en
Application granted granted Critical
Publication of TWI583943B publication Critical patent/TWI583943B/en

Links

Classifications

    • GPHYSICS
    • G01MEASURING; TESTING
    • G01NINVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
    • G01N21/00Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
    • G01N21/84Systems specially adapted for particular applications
    • G01N21/88Investigating the presence of flaws or contamination
    • G01N21/89Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
    • G01N21/892Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
    • G01N21/896Optical defects in or on transparent materials, e.g. distortion, surface flaws in conveyed flat sheet or rod

Landscapes

  • Engineering & Computer Science (AREA)
  • Textile Engineering (AREA)
  • Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • General Physics & Mathematics (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)

Description

瓶口缺陷檢測裝置及其方法Bottle mouth defect detecting device and method thereof

本發明相關於瓶口,尤其關於瓶口端面的檢測裝置及其方法。The invention relates to a bottle mouth, and more particularly to a device for detecting the end face of a bottle mouth and a method therefor.

玻璃瓶可以裝填液體,為市售飲料相當常見的飲品容器之一,又玻璃瓶的密封性勝於鋁箔,常常使用較易變質的美容或健康飲品,為用途相當廣泛的飲品容器。Glass bottles can be filled with liquids, which is one of the most common beverage containers for commercial beverages. The glass bottles are more sealed than aluminum foils, and often use more cosmetic or health drinks that are more susceptible to deterioration. They are widely used beverage containers.

由於瓶口的不平整、缺口、刮痕等會造成封瓶後產生洩漏現象。習知已有多種檢驗瓶口的技術存在。如台灣新型公告第191541號「檢驗瓶嘴或其類同物用之裝置」專利,其主要是採用灰度值評估比較的方式,當二相鄰區域間灰度值之差異,大於所設定的一極大限界(即有缺陷的存在)。則認為瓶子不良而將其剔退。此一影像處理方式,其需要反覆比較各相鄰區域之灰度值,尤其當解析度提高時,各相鄰區域的數量會急速增加,亦即需要比對的數量會急速增加,造成運算量龐大,無法在短時間完成判斷是否為不良品,其無法跟上現有產線的產量,因此只能採取抽檢的方式進行。Unevenness, notches, scratches, etc. of the bottle mouth may cause leakage after sealing. There are a number of techniques for verifying the finish of the bottle. For example, the Taiwan New Type Announcement No. 191541 "Installation of Bottles or Their Similar Devices" patent mainly adopts the method of gray value evaluation and comparison. When the difference of gray values between two adjacent areas is greater than the set A maximum limit (ie, the existence of a defect). The bottle is considered to be bad and it is rejected. In this image processing method, it is necessary to repeatedly compare the gray values of adjacent regions, especially when the resolution is improved, the number of adjacent regions will increase rapidly, that is, the number of comparisons will increase rapidly, resulting in an operation amount. It is too large to judge whether it is a defective product in a short period of time. It cannot keep up with the output of the existing production line, so it can only be carried out by sampling.

而台灣公告第592295號專利「瓶口牙區檢測設備」,其同樣是採用灰度比對的方式進行判斷是否有缺陷,且為了加快影像處理速度,其影像處理技術為用一維曲線近似來取代二維曲面近似,所以運算的複雜度下降許多,藉以達到速度與精度的平衡,然而,此一技術在速度仍然跟不上現行產線的需求。The Taiwan Patent No. 592295 "Botting and Teeth Detection Equipment" is also based on the method of gray scale comparison to determine whether there is a defect, and in order to speed up the image processing speed, the image processing technique uses a one-dimensional curve approximation. Instead of a two-dimensional surface approximation, the complexity of the operation is much reduced, so that the balance of speed and precision is achieved. However, this technology still cannot keep up with the demand of the current production line.

另台灣公告第371745號專利「瓶口螺紋檢查系統及其操作方法」,其將影像轉換為黑白影像,再比較特定區域的白影像面積,藉以判斷是否有缺陷發生,然而其為總量面積的比較,當不同的缺陷混雜時,有可能導致白影像面積仍然符合規範,為了增加精確程度,必須縮小特定區域的面積,其同樣會造成運算量大增,而導致在速度仍然跟不上現行產線的需求。In addition, Taiwan Patent No. 371745 "Bottle Thread Inspection System and Operation Method" converts images into black and white images, and then compares the white image area of a specific area to determine whether a defect occurs, but it is a total area. In comparison, when different defects are mixed, it may cause the white image area to still conform to the specification. In order to increase the accuracy, it is necessary to reduce the area of a specific area, which also causes an increase in the amount of calculation, and the speed still cannot keep up with the current production. Line demand.

爰此,本發明的主要目的,在於揭露一種產能可以滿足現行產線需求的瓶口缺陷檢測裝置及其方法。Accordingly, the main object of the present invention is to disclose a bottle mouth defect detecting device and method thereof that can meet the requirements of current production lines.

為達上述目的,本發明為一種瓶口缺陷檢測裝置,用於檢測複數玻璃瓶的瓶口端面平整度,其裝置包含一影像擷取單元、一影像處理單元與一玻璃瓶運送單元,其中該影像擷取單元為擷取該些玻璃瓶的一瓶口端面影像;該影像處理單元為進行Blob 演算法,取得該瓶口端面影像的斑點的數量,並依據斑點的數量來判斷該些玻璃瓶的瓶口端面是否完整;而該玻璃瓶運送單元移載該些玻璃瓶至對應該影像擷取單元處。In order to achieve the above object, the present invention is a bottle mouth defect detecting device for detecting the flatness of a bottle mouth end face of a plurality of glass bottles, the device comprising an image capturing unit, an image processing unit and a glass bottle transport unit, wherein The image capturing unit captures a bottle end face image of the glass bottles; the image processing unit performs a Blob algorithm to obtain the number of spots of the bottle end face image, and judges the glass bottles according to the number of spots. Whether the end of the bottle mouth is complete; and the glass bottle transport unit transfers the glass bottles to the corresponding image capturing unit.

而本發明方法步驟,首先為藉由該玻璃瓶運送單元移載該些玻璃瓶至對應該影像擷取單元處;接著藉由該影像擷取單元擷取該些玻璃瓶的該瓶口端面影像;接著藉由一影像處理單元進行Blob 演算法,取得該瓶口端面影像的斑點的數量,藉以判斷該些玻璃瓶的瓶口端面是否完整。若斑點的數量只有一個,表示瓶口端面非為完整的封閉環,即可判斷瓶口端面有貫穿的缺陷,即瓶口端面不完整,使用時會有漏氣之問題。In the method of the present invention, the glass bottles are transferred to the corresponding image capturing unit by the glass bottle transport unit; and the image of the bottle end is captured by the image capturing unit. Then, an image processing unit performs a Blob algorithm to obtain the number of spots of the image of the end face of the bottle mouth, thereby determining whether the end faces of the glass bottles are intact. If the number of spots is only one, indicating that the end face of the bottle mouth is not a complete closed ring, it can be judged that there is a flaw in the end face of the bottle mouth, that is, the end face of the bottle mouth is incomplete, and there is a problem of air leakage when used.

據此,本發明透過該影像處理單元進行Blob 演算法取得該瓶口端面影像的斑點的數量,即可判斷該些玻璃瓶的瓶口端面是否完整,即僅需簡單的Blob 演算法與簡單的邏輯判斷,因此處理速度相當的快速,可以滿足現行產線之產能需求。Accordingly, the present invention performs the Blob algorithm through the image processing unit to obtain the number of spots of the end face image of the bottle mouth, and can determine whether the end faces of the glass bottles are complete, that is, only a simple Blob algorithm and a simple Logical judgment, so the processing speed is quite fast, which can meet the capacity requirements of the current production line.

10‧‧‧影像擷取單元10‧‧‧Image capture unit

11‧‧‧感光耦合元件11‧‧‧Photosensitive coupling element

12‧‧‧對焦鏡頭12‧‧‧focus lens

13‧‧‧打光光源13‧‧‧Light source

131‧‧‧發光二極體131‧‧‧Lighting diode

20‧‧‧影像處理單元20‧‧‧Image Processing Unit

30‧‧‧玻璃瓶運送單元30‧‧‧ glass bottle transport unit

31‧‧‧輸送帶31‧‧‧Conveyor belt

32‧‧‧分瓶裝置32‧‧‧Secondary device

321‧‧‧推桿321‧‧‧Put

33‧‧‧異常暫存區33‧‧‧Asymmetric temporary storage area

90、90A‧‧‧玻璃瓶90, 90A‧‧‧ glass bottles

91‧‧‧瓶口端面影像91‧‧‧End of mouth image

圖1,為本發明檢測裝置的結構前視圖。Figure 1 is a front elevational view showing the structure of the detecting device of the present invention.

圖2,為本發明檢測裝置的結構俯視圖。Figure 2 is a plan view showing the structure of the detecting device of the present invention.

圖3,為本發明經Blob 演算的完整瓶口端面影像示意圖。FIG. 3 is a schematic diagram of a complete bottle mouth end image according to the Blob calculation of the present invention.

圖4,為本發明經Blob 演算的不完整瓶口端面影像示意圖。4 is a schematic view of an incomplete bottle end face image according to the Blob calculation of the present invention.

圖5A~圖5C,為本發明分瓶裝置動作示意圖。5A-5C are schematic views showing the operation of the bottle dividing device of the present invention.

有關本發明技術內容、特點與功效,在以下配合參考圖式之較佳實施例的詳細說明中,將可清楚的呈現。The detailed description of the preferred embodiments of the present invention will be apparent from

請參閱「圖1」與「圖2」所示,本發明為一種瓶口缺陷檢測裝置及其方法,用於檢測複數玻璃瓶90的瓶口端面平整度,其裝置包含一影像擷取單元10、一影像處理單元20與一玻璃瓶運送單元30,其中該影像擷取單元10擷取該些玻璃瓶90的一瓶口端面影像91(如圖3所示),該影像擷取單元10可以包含一感光耦合元件11、擷取影像對焦於該感光耦合元件11內的一對焦鏡頭12與一打光光源13,該打光光源13可以為複數發光二極體131,且該些發光二極體131環繞該對焦鏡頭12。Referring to FIG. 1 and FIG. 2, the present invention is a bottle mouth defect detecting device and method thereof for detecting the flatness of a bottle mouth end face of a plurality of glass bottles 90, the device comprising an image capturing unit 10 An image processing unit 20 and a glass bottle transport unit 30, wherein the image capturing unit 10 captures a bottle end face image 91 (shown in FIG. 3) of the glass bottles 90, and the image capturing unit 10 can A focusing lens 12 and a focusing light source 13 are disposed in the photosensitive coupling element 11. The light source 13 can be a plurality of LEDs 131, and the LEDs The body 131 surrounds the focus lens 12.

該影像處理單元20進行Blob 演算法,取得該瓶口端面影像91的斑點的數量,並依據斑點的數量來判斷該些玻璃瓶90的瓶口端面是否完整。而所謂Blob 演算法,為一種相當成熟的影像處理技術。將一個灰階影像透過任意的阈值基準,轉換為0或1的一個黑白影像處理叫做『二值化處理』(通常爲黑(0)、白(1))。而對完成二值化處理的黑白影像進行分析的方法叫做『BLOB』。亦即Blob 演算法可以分析黑白影像中,黑(0)、白(1)區塊的有無、數量、面積、位置、長度、方向等對象的形狀特點,是影像處理的最基本方式之一。The image processing unit 20 performs a Blob algorithm to obtain the number of spots of the bottle end face image 91, and determines whether the end faces of the glass bottles 90 are complete according to the number of spots. The so-called Blob algorithm is a fairly mature image processing technology. A black-and-white image processing that converts a grayscale image through an arbitrary threshold reference to 0 or 1 is called "binarization processing" (usually black (0), white (1)). The method of analyzing the black and white image that completes the binarization process is called "BLOB". That is to say, the Blob algorithm can analyze the shape characteristics of black (0) and white (1) blocks, such as the presence, size, area, position, length and direction of black and white images, which is one of the most basic methods of image processing.

該玻璃瓶運送單元30移載該些玻璃瓶90至對應該影像擷取單元10處,該玻璃瓶運送單元30可以具有一輸送帶31、一分瓶裝置32與一異常暫存區33,該輸送帶31用於輸送該些玻璃瓶90經過該影像擷取單元10,且當該影像處理單元20判斷該些玻璃瓶90的瓶口端面為不完整時,藉由該分瓶裝置32位移至該異常暫存區33存放,並該分瓶裝置32可以為一推桿321,且該推桿321與該異常暫存區33分別設置於該輸送帶31的相對兩側,且該推桿321具有沒穿過該輸送帶31的一起始位置與穿入該輸送帶31的一推送位置。The glass bottle transport unit 30 transfers the glass bottles 90 to the corresponding image capturing unit 10, and the glass bottle transport unit 30 can have a conveyor belt 31, a bottle dividing device 32 and an abnormal temporary storage area 33. The conveyor belt 31 is configured to transport the glass bottles 90 through the image capturing unit 10, and when the image processing unit 20 determines that the bottle end faces of the glass bottles 90 are incomplete, the bottle dividing device 32 is displaced to The abnormal storage area 33 is stored, and the dispensing device 32 can be a push rod 321 , and the push rod 321 and the abnormal temporary storage area 33 are respectively disposed on opposite sides of the conveyor belt 31 , and the push rod 321 There is a starting position that does not pass through the conveyor belt 31 and a pushing position that penetrates the conveyor belt 31.

而本發明的方法,其步驟分述如下:The method of the present invention, the steps are as follows:

首先為藉由該玻璃瓶運送單元30移載該些玻璃瓶90至對應該影像擷取單元10處。該玻璃瓶運送單元30可以具有一輸送帶31、一分瓶裝置32與一異常暫存區33,該輸送帶31用於輸送該些玻璃瓶90經過該影像擷取單元10,即可移載該些玻璃瓶90至對應該影像擷取單元10處。First, the glass bottles 90 are transferred by the glass bottle transport unit 30 to the corresponding image capturing unit 10. The glass bottle transport unit 30 can have a conveyor belt 31, a bottle dividing device 32 and an abnormal temporary storage area 33. The conveyor belt 31 is used to transport the glass bottles 90 through the image capturing unit 10, and can be transferred. The glass bottles 90 are corresponding to the image capturing unit 10.

請一併參閱「圖3」與「圖4」所示,其完整與不完整之該瓶口端面影像91經Blob 演算後之示意圖,本發明接著為藉由該影像擷取單元10擷取該些玻璃瓶90的該瓶口端面影像91,該影像擷取單元10可以包含該感光耦合元件11、該對焦鏡頭12與該打光光源13,其中該對焦鏡頭12可以因應該些玻璃瓶90的高度調整該對焦鏡頭12的焦距,亦即可以適用各種尺寸的該些玻璃瓶90。Please refer to FIG. 3 and FIG. 4 for a complete and incomplete schematic diagram of the end face image 91 of the bottle mouth after Blob calculation. The present invention then captures the image by the image capturing unit 10. The image capturing unit 10 of the glass bottle 90 can include the photosensitive coupling element 11 , the focusing lens 12 and the lighting source 13 , wherein the focusing lens 12 can be used for the glass bottle 90 The focal length of the focus lens 12 is adjusted in height, that is, the glass bottles 90 of various sizes can be applied.

接著為藉由該影像處理單元20進行Blob 演算法,取得該瓶口端面影像91的斑點的數量,該瓶口端面影像91 經Blob 演算法可能為「圖3」或「圖4」所示,即可依據斑點的數量,判斷該些玻璃瓶90的瓶口端面是否完整。更詳細說,若瓶口端面有貫穿的缺陷,即瓶口端面不完整時,此時該瓶口端面影像91經過Blob 演算法分析後,斑點的數量只有一個(如「圖4」),因此當斑點的數量只有一個時,即可判斷瓶口端面有貫穿的缺陷,使用時會有漏氣之問題;反過來說,當瓶口端面完整時,此時該瓶口端面影像91經過Blob 演算法分析後,斑點的數量會有二個(如「圖3」),因此當斑點的數量有二個時,即可判定該些玻璃瓶90的瓶口端面為完整。Then, the Blob algorithm is used by the image processing unit 20 to obtain the number of spots of the end face image 91 of the bottle mouth. The image of the end face image 91 of the bottle mouth may be as shown in FIG. 3 or FIG. 4 by the Blob algorithm. According to the number of spots, it can be judged whether the end faces of the glass bottles 90 are intact. In more detail, if the end face of the bottle mouth has a through defect, that is, when the end face of the bottle mouth is incomplete, the image of the end face of the bottle mouth is analyzed by the Blob algorithm, and the number of spots is only one (as shown in Fig. 4). When the number of spots is only one, it can be judged that there is a flaw in the end face of the bottle mouth, and there is a problem of air leakage when used; on the other hand, when the end face of the bottle mouth is complete, the image of the end face of the bottle mouth is subjected to Blob calculation. After the analysis, there will be two spots (such as "Fig. 3"), so when there are two spots, it can be determined that the end faces of the glass bottles 90 are intact.

請一併參閱「圖5A」~「圖5C」所示,最後,當該影像處理單元20判斷該些玻璃瓶90A的瓶口端面為不完整時,可以藉由該分瓶裝置32位移至該異常暫存區33存放,以該分瓶裝置32為該推桿321為例加以說明,由於該推桿321與該異常暫存區33分別設置於該輸送帶31的相對兩側,當該推桿321由該起始位置位移至該推送位置時,即可將該瓶口端面為不完整的該些玻璃瓶90A推移入該異常暫存區33(如「圖5A」),且為了動作速度上之需求,該些不完整的玻璃瓶90A為藉由慣性滑入該異常暫存區33,亦即該推桿321只須伸入該輸送帶31約四分之一到三分之一就縮回(如「圖5A」~「圖5C」),即可推移該些不完整的玻璃瓶90A滑移進入該異常暫存區33。Please refer to FIG. 5A to FIG. 5C. Finally, when the image processing unit 20 determines that the end faces of the glass bottles 90A are incomplete, the image separation unit 32 can be displaced to the The abnormal temporary storage area 33 is stored, and the splitting device 32 is used as an example of the push rod 321 . Since the push rod 321 and the abnormal temporary storage area 33 are respectively disposed on opposite sides of the conveyor belt 31, when the push When the rod 321 is displaced from the starting position to the pushing position, the glass bottles 90A whose incomplete end faces are moved into the abnormal temporary storage area 33 (as shown in FIG. 5A), and for the speed of movement In the above requirement, the incomplete glass bottle 90A is slid into the abnormal temporary storage area 33 by inertia, that is, the push rod 321 only needs to extend into the conveyor belt 31 by about one quarter to one third. Retracting (such as "Fig. 5A" - "Fig. 5C"), the incomplete glass bottle 90A can be moved into the abnormal temporary storage area 33.

如上所述,本發明透過該影像處理單元進行Blob 演算法,取得該瓶口端面影像的斑點的數量,即可判斷該些玻璃瓶的瓶口端面是否完整,並可利用該分瓶裝置將不完整的該些玻璃瓶檢出,其僅需簡單的Blob 演算法與簡單的邏輯判斷,影像運算的負擔相當的小,因此在處理速度上相當的快速,可以滿足現行產線之產能需求。As described above, the present invention performs a Blob algorithm through the image processing unit to obtain the number of spots of the image of the end face of the bottle mouth, and can determine whether the end faces of the glass bottles are intact, and the bottle dividing device can be used. The complete glass bottles are detected, which requires only a simple Blob algorithm and simple logic judgment. The burden of image calculation is relatively small, so the processing speed is quite fast, which can meet the production capacity requirements of the current production line.

惟以上所述者,僅為本發明之較佳實施例而已,當不能以此限定本發明實施之範圍,即大凡依本發明申請專利範圍及發明說明內容所作的簡單之等效變化與修飾,皆仍屬本發明專利涵蓋之範圍內。The above is only the preferred embodiment of the present invention, and the scope of the present invention is not limited thereto, that is, the simple equivalent changes and modifications made by the scope of the invention and the description of the invention are All remain within the scope of the invention patent.

 

10‧‧‧影像擷取單元 10‧‧‧Image capture unit

11‧‧‧感光耦合元件 11‧‧‧Photosensitive coupling element

12‧‧‧對焦鏡頭 12‧‧‧focus lens

13‧‧‧打光光源 13‧‧‧Light source

131‧‧‧發光二極體 131‧‧‧Lighting diode

20‧‧‧影像處理單元 20‧‧‧Image Processing Unit

30‧‧‧玻璃瓶運送單元 30‧‧‧ glass bottle transport unit

31‧‧‧輸送帶 31‧‧‧Conveyor belt

32‧‧‧分瓶裝置 32‧‧‧Secondary device

321‧‧‧推桿 321‧‧‧Put

90、90A‧‧‧玻璃瓶 90, 90A‧‧‧ glass bottles

Claims (10)

【第1項】[Item 1]
一種瓶口缺陷檢測裝置,用於檢測複數玻璃瓶的瓶口端面平整度,其包含:
一影像擷取單元,該影像擷取單元擷取該些玻璃瓶的一瓶口端面影像;
一影像處理單元,該影像處理單元進行Blob 演算法,取得該瓶口端面影像的斑點的數量,並依據斑點的數量來判斷該些玻璃瓶的瓶口端面是否完整;以及
一玻璃瓶運送單元,該玻璃瓶運送單元移載該些玻璃瓶至對應該影像擷取單元處。

A bottle mouth defect detecting device for detecting the flatness of a bottle mouth end face of a plurality of glass bottles, comprising:
An image capturing unit, the image capturing unit captures a bottle end face image of the glass bottles;
An image processing unit, the image processing unit performs a Blob algorithm, obtains the number of spots of the image of the end face of the bottle mouth, and determines whether the end faces of the glass bottles are complete according to the number of spots; and a glass bottle transport unit, The glass bottle transport unit transfers the glass bottles to the corresponding image capturing unit.
【第2項】[Item 2]
如申請專利範圍第1項所述之瓶口缺陷檢測裝置,其中該影像擷取單元包含一感光耦合元件、擷取影像對焦於該感光耦合元件內的一對焦鏡頭與一打光光源。

The bottle mouth defect detecting device of claim 1, wherein the image capturing unit comprises a photosensitive coupling element, and the capturing image focuses on a focusing lens and a light source in the photosensitive coupling element.
【第3項】[Item 3]
如申請專利範圍第2項所述之瓶口缺陷檢測裝置,其中該打光光源為複數發光二極體,且該些發光二極體環繞該對焦鏡頭。

The bottle mouth defect detecting device of claim 2, wherein the light source is a plurality of light emitting diodes, and the light emitting diodes surround the focus lens.
【第4項】[Item 4]
如申請專利範圍第1項所述之瓶口缺陷檢測裝置,其中該玻璃瓶運送單元具有一輸送帶、一分瓶裝置與一異常暫存區,該輸送帶用於輸送該些玻璃瓶經過該影像擷取單元,且當該影像處理單元判斷該些玻璃瓶的瓶口端面為不完整時,藉由該分瓶裝置位移至該異常暫存區存放。

The bottle mouth defect detecting device according to claim 1, wherein the glass bottle transport unit has a conveyor belt, a bottle dividing device and an abnormal temporary storage area, wherein the conveyor belt is used to transport the glass bottles through the The image capturing unit, and when the image processing unit determines that the end faces of the glass bottles are incomplete, the bottle dividing device is displaced to the abnormal temporary storage area for storage.
【第5項】[Item 5]
如申請專利範圍第4項所述之瓶口缺陷檢測裝置,其中該分瓶裝置為一推桿,且該推桿與該異常暫存區分別設置於該輸送帶的相對兩側,且該推桿具有沒穿過該輸送帶的一起始位置與穿入該輸送帶的一推送位置。

The bottle mouth defect detecting device of claim 4, wherein the bottle dividing device is a push rod, and the push rod and the abnormal temporary storage area are respectively disposed on opposite sides of the conveyor belt, and the pushing The rod has a starting position that does not pass through the conveyor belt and a push position that penetrates the conveyor belt.
【第6項】[Item 6]
一種瓶口缺陷檢測方法,用於檢測複數玻璃瓶的瓶口端面平整度,其步驟包含:
藉由一玻璃瓶運送單元移載該些玻璃瓶至對應一影像擷取單元處;
藉由該影像擷取單元擷取該些玻璃瓶的一瓶口端面影像;
藉由一影像處理單元進行Blob 演算法,取得該瓶口端面影像的斑點的數量,藉以判斷該些玻璃瓶的瓶口端面是否完整。

A bottle mouth defect detecting method for detecting the flatness of a bottle mouth end face of a plurality of glass bottles, the steps comprising:
Transferring the glass bottles to a corresponding image capturing unit by a glass bottle transport unit;
The image capturing unit captures a bottle end face image of the glass bottles;
The blob algorithm is performed by an image processing unit to obtain the number of spots of the image of the end face of the bottle mouth, thereby determining whether the end faces of the glass bottles are intact.
【第7項】[Item 7]
如申請專利範圍第6項所述之瓶口缺陷檢測方法,其中該影像擷取單元包含一感光耦合元件、擷取影像對焦於該感光耦合元件內的一對焦鏡頭與一打光光源,其中該對焦鏡頭因應該些玻璃瓶的高度調整該對焦鏡頭的焦距。

The method for detecting a bottle mouth defect according to the sixth aspect of the invention, wherein the image capturing unit comprises a photosensitive coupling element, and the focusing image is focused on the focusing lens and the light source in the photosensitive coupling element, wherein The focus lens adjusts the focal length of the focus lens by the height of some glass bottles.
【第8項】[Item 8]
如申請專利範圍第6項所述之瓶口缺陷檢測方法,其中該打光光源為複數發光二極體,且該些發光二極體環繞該對焦鏡頭。

The bottle mouth defect detecting method according to claim 6, wherein the light source is a plurality of light emitting diodes, and the light emitting diodes surround the focusing lens.
【第9項】[Item 9]
如申請專利範圍第6項所述之瓶口缺陷檢測方法,其中該玻璃瓶運送單元具有一輸送帶、一分瓶裝置與一異常暫存區,該輸送帶用於輸送該些玻璃瓶經過該影像擷取單元,且當該影像處理單元判斷該些玻璃瓶的瓶口端面為不完整時,藉由該分瓶裝置位移至該異常暫存區存放。

The bottle mouth defect detecting method according to claim 6, wherein the glass bottle transport unit has a conveyor belt, a bottle dividing device and an abnormal temporary storage area, and the conveyor belt is used for conveying the glass bottles through the The image capturing unit, and when the image processing unit determines that the end faces of the glass bottles are incomplete, the bottle dividing device is displaced to the abnormal temporary storage area for storage.
【第10項】[Item 10]
如申請專利範圍第9項所述之瓶口缺陷檢測方法,其中該分瓶裝置為一推桿,且該推桿與該異常暫存區分別設置於該輸送帶的相對兩側,且該推桿具有沒穿過該輸送帶的一起始位置與穿入該輸送帶的一推送位置,該推桿由該起始位置位移至該推送位置時,為將該瓶口端面為不完整的該些玻璃瓶推入該異常暫存區。

The bottle mouth defect detecting method according to claim 9, wherein the bottle dividing device is a push rod, and the push rod and the abnormal temporary storage area are respectively disposed on opposite sides of the conveyor belt, and the pushing The rod has a starting position that does not pass through the conveyor belt and a pushing position that penetrates the conveyor belt. When the pushing rod is displaced from the starting position to the pushing position, the end surface of the bottle opening is incomplete. The glass bottle is pushed into the abnormal temporary storage area.
TW104119231A 2015-06-15 2015-06-15 Bottle flaw defect detection device and method thereof TWI583943B (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
TW104119231A TWI583943B (en) 2015-06-15 2015-06-15 Bottle flaw defect detection device and method thereof
CN201610156491.8A CN106248685A (en) 2015-06-15 2016-03-18 Bottle mouth defect detection device and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
TW104119231A TWI583943B (en) 2015-06-15 2015-06-15 Bottle flaw defect detection device and method thereof

Publications (2)

Publication Number Publication Date
TW201643417A TW201643417A (en) 2016-12-16
TWI583943B true TWI583943B (en) 2017-05-21

Family

ID=57626476

Family Applications (1)

Application Number Title Priority Date Filing Date
TW104119231A TWI583943B (en) 2015-06-15 2015-06-15 Bottle flaw defect detection device and method thereof

Country Status (2)

Country Link
CN (1) CN106248685A (en)
TW (1) TWI583943B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN105241888B (en) * 2015-09-25 2018-11-02 上海金啤包装检测科技有限公司 A kind of detection method and detection device of bottle mouth defect

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW371745B (en) * 1995-08-04 1999-10-11 Image Proc Systems Inc Bottle thread inspection system and method of operating same
US5987159A (en) * 1996-09-24 1999-11-16 Cognex Corporation System or method for detecting defect within a semi-opaque enclosure
CN101105459A (en) * 2007-05-15 2008-01-16 广州市万世德包装机械有限公司 Empty bottle mouth defect inspection method and device

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101858734B (en) * 2010-05-19 2011-06-29 山东明佳包装检测科技有限公司 Method for detecting PET bottleneck quality
CN103072718B (en) * 2012-12-27 2014-07-16 天津普达软件技术有限公司 Machine vision detection system and method for food packaging production line

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TW371745B (en) * 1995-08-04 1999-10-11 Image Proc Systems Inc Bottle thread inspection system and method of operating same
US6448549B1 (en) * 1995-08-04 2002-09-10 Image Processing Systems, Inc. Bottle thread inspection system and method of operating the same
US5987159A (en) * 1996-09-24 1999-11-16 Cognex Corporation System or method for detecting defect within a semi-opaque enclosure
CN101105459A (en) * 2007-05-15 2008-01-16 广州市万世德包装机械有限公司 Empty bottle mouth defect inspection method and device

Also Published As

Publication number Publication date
CN106248685A (en) 2016-12-21
TW201643417A (en) 2016-12-16

Similar Documents

Publication Publication Date Title
CN107203990B (en) Label breakage detection method based on template matching and image quality evaluation
TWI698628B (en) System and method for inspection of wet ophthalmic lens
US20160258880A1 (en) Inspection of sealing quality in blister packages
JPH10505680A (en) Container flange inspection system using an annular lens
CN106052792B (en) A kind of PET bottle liquid-level detecting method and device based on machine vision
CN201707305U (en) Inspection system for inspecting quality of container caps
WO2016196886A1 (en) System and method for inspecting containers using multiple radiation sources
WO2004036198A1 (en) Method and device for preparing reference image in glass bottle inspection device
CN102141379A (en) Novel glass bottle and jar detection device
JP2010112802A (en) Appearance inspection apparatus for wood and appearance inspection method for wood
CN109461156B (en) Threaded sealing plug assembly detection method based on vision
TW201702584A (en) Method for searching region of interest of electronic component, defect inspection method and device of electronic component using the searching method conducting image binarization on inspection items
JP2017219504A (en) Bottle inspection device
JP2002098650A (en) Transparent body detection method and system thereof
CN115428015A (en) Method and apparatus for optically inspecting a container in a beverage processing system
JP2017518500A (en) Inspection device for container closure lid
TWI583943B (en) Bottle flaw defect detection device and method thereof
CN105301003A (en) Method for detecting bottle cap surface production date based on machine vision
KR101562988B1 (en) Apparatus and method for detecting surface defects of hot billet
KR20140031392A (en) Container mouth portion inspection method and device
JP5959430B2 (en) Bottle cap appearance inspection device and appearance inspection method
CN103473777B (en) A kind of LED chip based on digital picture inserts detection algorithm that is deep and that insert shallow defect
US11624711B2 (en) Method and device for the optical inspection of containers
JP5679564B2 (en) Surface foreign matter inspection device
CN202119403U (en) Novel glass container detection apparatus

Legal Events

Date Code Title Description
MM4A Annulment or lapse of patent due to non-payment of fees