TW202100988A - Glass bottle inspection method and glass bottle manufacturing method - Google Patents

Abstract

This invention provides a glass bottle manufacturing method and an inspection method for automatically determining from an image whether there is a defect in a glass bottle having an engraving on the surface thereof. One embodiment of the glass bottle inspection method is a method for inspecting a glass bottle having an engraving on the surface of the body thereof, the method comprising an image acquisition step S12 for acquiring an image of the entire periphery of the body by imaging the glass bottle while rotating the same, a masking step S18 for masking an engraving area in the image that includes a pattern originating from the engraving, and a determination step S20 for determining whether there is a defect in the area of the image excluding the masked engraving area.

Description

Inspection method of glass bottle and manufacturing method of glass bottle

The present invention relates to a method for inspecting a glass bottle with an engraving on the surface of the body part and a method for manufacturing the glass bottle.

It is known that an engraved glass bottle with unevenness is applied to the surface. Glass bottles with carvings are original and high-end, which can create a better impression for consumers.

A method for inspecting a glass bottle having irregularities on the surface has been proposed in Patent Document 1, for example. The invention of Patent Document 1 optically discriminates an engraved surface formed by unevenness and a smooth surface without unevenness. [Prior Technical Literature] [Patent Literature]

[Patent Document 1] Japanese Patent Laid-Open No. 58-216906

[The problem to be solved by the invention]

However, in the invention of Patent Document 1, only a surface with unevenness and a surface without unevenness can be distinguished, and the defects of the glass bottle cannot be inspected. If you want to optically inspect an engraved glass bottle with unevenness, it is not easy to discern whether it is a shadow caused by the unevenness or a shadow caused by defects such as scratches and bubbles. Even now, the presence or absence of scratches, bubbles, etc. of glass bottles with unevenness can only rely on visual inspection.

Here, the present invention provides a method for inspecting a glass bottle and a method for manufacturing a glass bottle, which can automatically determine whether there is a defect in a glass bottle with an engraving on the surface from an image. [Technical means to solve the problem]

In order to solve at least a part of the above-mentioned problems, the present invention can be implemented in the following aspects or application examples.

In addition, in the following description, "engraving" refers to the shape design of the appearance caused by the unevenness of the surface of the glass bottle, and "pattern" refers to the appearance of the image obtained by imaging the glass bottle. The change in the intensity of light and shade of the sculpture.

[1] One aspect of the inspection method of the glass bottle of the present invention is a method of inspecting a glass bottle with an engraving on the surface of the body part, which includes: photographing the rotating glass bottle and taking the entire circumference of the body part The image acquisition process of the captured image, and the masking process of masking the engraving area in the aforementioned image that contains the pattern derived from the aforementioned engraving, and the judgment of whether there are defects in the aforementioned image except for the aforementioned engraving area that is masked process.

According to the aspect of the inspection method of the glass bottle, since it is necessary to judge whether there are defects in areas other than the engraving area, it is possible to automatically judge whether there are defects in the glass bottle with an engraving on the surface from the image.

[2] Regarding one aspect of the inspection method of the glass bottle, the disadvantages include at least the surface defects. The image acquisition process involves capturing the transmitted light that has passed through the trunk by a line sensor.

According to one aspect of the inspection method of the glass bottle, the transmitted light is captured by the line sensor, and even the defects such as the shadow of bubbles on the surface are not easy to appear, it can be automatically determined from the image.

[3] For one aspect of the glass bottle inspection method, it further includes a pattern position detection process, which uses a pattern registration image made in advance based on the shape of the aforementioned engraving, and the pattern search is obtained by the aforementioned image acquisition process The aforementioned image is detected, and the aforementioned pattern is detected, and the aforementioned masking process can mask the aforementioned engraved area including the aforementioned pattern detected by the aforementioned pattern position detection process.

According to one aspect of the inspection method of the glass bottle, since the pattern registration image made based on the shape of the engraving can be used to detect the pattern, even if the pattern is thinner, the position of the pattern can be detected stably.

[4] For one aspect of the inspection method of the above-mentioned glass bottle, the above-mentioned pattern position detection process is to search the pattern for the predetermined height range in the above-mentioned portrait.

According to one aspect of the glass bottle inspection method described above, the appearance height of the image in the image is almost constant, so by searching the pattern for the predetermined height range, the load of the inspection device can be reduced.

[5] One aspect of the method for manufacturing a glass bottle of the present invention is to form a preform from a block by a rough mold, and form the preform into the glass bottle from a finished model, and perform the glass bottle on the glass bottle. In one aspect of the inspection method, a glass bottle judged to be free of the aforementioned shortcomings is obtained.

According to the aspect of the manufacturing method of the above-mentioned glass bottle, even if it has an engraved glass bottle, since the defect can be automatically determined, a defect-free glass bottle can be manufactured. [Effects of the invention]

According to one aspect of the glass bottle inspection method of the present invention, it is possible to automatically determine whether there is a defect in a glass bottle with an engraving on the surface from the image. According to one aspect of the glass bottle manufacturing method of the present invention, even if it has an engraved glass bottle, it is possible to manufacture a glass bottle without defects.

Hereinafter, the best embodiment of the present invention will be described in detail using the drawings. In addition, the embodiments described below are not intended to limit the contents described in the scope of patent application of the present invention. In addition, all of the structures described below are not necessarily essential components of the present invention.

The inspection method of the glass bottle of the present embodiment is a method of inspecting a glass bottle with an engraving on the surface of the body part, including: taking an image of the rotating glass bottle and obtaining an image of the entire circumference of the body part. The acquisition process and the masking process of masking the engraving area in the aforementioned image containing the pattern derived from the engraving, and the judging process of judging whether there is a defect in the aforementioned image in the area other than the masked engraving area.

The manufacturing method of the glass bottle of the present embodiment is to form a preform from a block by a rough mold, to form the preform from a finished model to form a glass bottle, and to perform the glass bottle inspection method for the glass bottle. A glass bottle judged to be free of the aforementioned shortcomings was obtained.

1. Inspection device The inspection device 1 of the glass bottle 10 will be described in detail with reference to Figs. 1 and 2. FIG. 1 is a side view illustrating the inspection device 1 using the inspection method of this embodiment, and FIG. 2 is a plan view illustrating the inspection device 1.

The inspection device 1 shown in FIGS. 1 and 2 is an inspection device 1 having a glass bottle 10 with an engraving 15 on the surface. The inspection device 1 is integrated into the production line of the glass bottle 10 not shown in the figure and becomes a part of the production line. After being formed, the glass bottle 10 that is gradually cooled is transported to the inspection device 1, and the glass bottle 10 after inspection is moved to the inspection device 1. Moving in the next process.

The inspection device 1 includes: a light-emitting portion 20 having a light-emitting surface 22 that irradiates light to a glass bottle 10; an imaging portion 40 arranged to face the light-emitting portion 20 with the glass bottle 10 interposed therebetween; The image 80 (FIG. 4) of the imaged glass bottle 10 is the control part 50 of the discrimination part 52 which discriminates whether there is a defect.

Here, as shown in Fig. 1, the glass bottle 10 is inspected in an upright state, that is, in a state in which the central axis 12 is along the vertical direction. The vertical direction is the direction of gravity, and the horizontal direction is the direction perpendicular to the vertical direction.

The inspection device 1 includes a mounting table 30 that supports the glass bottle 10 while rotating around the center axis 12 and a side roller 32 that rotates the glass bottle 10 while contacting the side surface of the glass bottle 10. As shown in Figure 1, although the side roller 32 is located between the glass bottle 10 and the imaging unit 40, it is only for convenience of description. The side roller 32 is arranged so as not to prevent the imaging unit 40 from removing the glass Location of bottle 10 camera.

The glass bottle 10 is transparent or translucent. Semi-transparency refers to transparency to the extent that defects of the body portion 13 of the glass bottle 10, such as surface bubbles 18, can be discriminated by light from the light-emitting portion 20 that has passed through the glass bottle 10. The glass bottle 10 is, for example, a jar having a neck portion 11, a body portion 13, and a bottom portion 14 that are circular in cross section. The cross-sectional shape of the glass bottle 10 may be polygonal. The glass bottle 10 has an engraving 15 on the surface. The engraving 15 is an unevenness formed on the surface of the glass bottle 10, and is formed by, for example, an unevenness engraved on the surface of a molding mold.

The side roller 32 is in contact with the trunk 13 and rotates the glass bottle 10 around the center axis 12. The central axis 12 is a dotted line that becomes the rotation center axis of the glass bottle 10 rotating. The side roller 32 transmits the driving force of the motor 60 to the glass bottle 10 through a belt 35 and the like by a command from the rotation control unit 62 to rotate the glass bottle 10. The side roller 32 rotates the glass bottle 10 by a predetermined amount at a predetermined speed. The predetermined amount of rotation refers to a sufficient amount for the entire circumference of the glass bottle 10 to be imaged. The predetermined amount of rotation is set to, for example, 1.5 revolutions or more, so that the entire detected body can be grasped from one image data. The rotation detection unit 54 is a rotary encoder that can be directly or indirectly attached to the motor 60. Based on the pulse output of the rotation detecting unit 54, the image capturing unit 40 captures a predetermined number of images of the glass bottle 10.

The light emitting unit 20 is a light source for illuminating the glass bottle 10. The light emitting unit 20 is a surface light source that has a light emitting surface 22 on the side of the glass bottle 10 and can illuminate the glass bottle 10 from the side opposite to the imaging unit 40. The height of the light emitting part 20 is set to be able to irradiate the entire glass bottle 10 that is the largest to be inspected by the inspection device 1. As shown in FIG. 2, the full width W2 of the light emitting surface 22 is narrower than the full width W1 of the glass bottle 10. By making the full width W2 narrower than the full width W1, the shadow of the surface bubble 18 can be clearly captured. The full widths W1 and W2 are the full widths of the glass bottle 10 and the light emitting surface 22 when the inspection device 1 is viewed from a plan view.

As shown in FIG. 2, the light emitting surface 22 has a rectangular shape, for example, and it emits light almost entirely. The light-emitting surface 22 faces the glass bottle 10 and the imaging unit 40, and the light passing through the glass bottle 10 can reach the imaging unit 40.

As the light source of the light emitting unit 20, a known light source such as LED and organic EL can be used. The light-emitting part 20 is a diffused lighting. When using LEDs, a diffuser can be used on the light-emitting surface 22 to irradiate the glass bottle 10 with uniform light. As the diffusion plate, a known one that diffuses light from a light source such as an LED and emits it to the outside can be used. The light is diffused by the diffuser, and when most light sources are used, the unevenness of the part where the light source does not exist can be reduced.

The imaging unit 40 is arranged so that the glass bottle 10 and the light emitting unit 20 are pinched to face each other. The imaging unit 40 is arranged to image the surface of the glass bottle 10 on the extension line of the central axis 12. The imaging unit 40 is arranged to be capable of imaging at least the inspection target part of the glass bottle 10. Here, the entire vertical direction of the body portion 13 of the glass bottle 10 can enter the field of view of the imaging unit 40.

The imaging unit 40 can capture an image including the detected object (for example, the surface air bubble 18) by the light transmitted through the light emitting unit 20 of the glass bottle 10. For the imaging unit 40, for example, a known line sensor camera can be used. The imaging unit 40 captures images by the output of the rotation detection unit 54 in conjunction with the rotation of the side roller 32, and even if the rotation speed changes for any reason, the image 80 will not be affected.

The imaging unit 40 captures the entire circumference of the carcass 13 and sends the data to the image processing unit 53 of the control unit 50.

The control unit 50 includes a determination unit 52 and an image processing unit 53. The control unit 50 is, for example, a processor such as a CPU (Central Processing Unit) and GPU (Graphics Processing Unit), HDD (Hard Disk Drive), SSD (Solid State Drive), ROM ( Read-only memory, Read-Only Memory), RAM (Dynamic Random Access Memory, Random Access Memory) and other memory devices, keyboards, mice, touchpads and other input devices, liquid crystal displays, organic EL (electron Light-emitting, Electro Luminescence) displays and other display devices, I/O boards and other digital input and output boards. The control unit 50 executes the process of inspecting the glass bottle 10. The process of intermittently conveying the glass bottles 10 at a predetermined speed by the inspection device 1 is performed by a control unit different from the control unit 50, but may be performed by the control unit 50.

The determination unit 52 determines whether there is a defect based on the image acquired from the imaging unit 40. The defect determined by the determining unit 52 is, for example, a superficial defect. Surface defects refer to surface bubbles 18, dirt, and foreign objects existing on the inner or outer surface of the glass bottle 10. The discriminating unit 52 can discriminate, for example, the internal defects of the glass bottle 10 in addition to the surface defects. The discriminating part 52 discriminates, for example, a surface bubble 18 having a vertical length of 3.0 mm or more, a horizontal length of 1.0 mm or more, and a depth of 0.05 mm or more as a defect. In addition, it is better that the determination unit 52 does not mistakenly determine the appearance of the image derived from the engraving 15 as a defect.

The control unit 50 outputs the determination result of the determination unit 52 to the outside of the glass bottle 10, and for example, excludes the glass bottle 10 determined to be defective by the line after the discharge unit of the inspection device 1. The specific processing of the control unit 50 is described in the following "3. Inspection Method".

2. Manufacturing method The manufacturing method of the glass bottle 10 of this embodiment is demonstrated. The glass bottle 10 is first formed into a blank from a block by a rough mold. The parison is formed into a bottomed cylindrical shape by blowing compressed air into a high-temperature block that has been placed in a rough mold. A spool valve can also be used with compressed air. Next, the parison is moved toward the finishing model, and compressed air is blown into the parison in the finishing model to shape the product, that is, the glass bottle 10. Since the glass bottle 10 after forming is at a high temperature, it moves toward the gradual cooling furnace and is slowly cooled. The following inspection method is implemented for the glass bottle 10 carried out from the gradual cooling furnace. In addition, after the following inspection method is implemented, the glass bottle 10 judged as having no defect can be regarded as a good product.

In this way, according to the manufacturing method of the glass bottle 10 of the present embodiment, even if the glass bottle 10 has the engraving 15, since the defect can be automatically determined, it is possible to manufacture a defect-free glass bottle 10.

3. Inspection method The inspection method of the glass bottle 10 of this embodiment using the inspection apparatus 1 in the 1st and 2nd figure is demonstrated using FIGS. 3-7. Fig. 3 is a flowchart of the inspection method of this embodiment, Fig. 4 is an example of the portrait 80, Fig. 5 is a diagram illustrating the pre-image processing S14, the pattern position detection process S16, and the masking process S18, and Fig. 6 is Fig. 7 is a diagram explaining the image preprocessing S14 and the masking process S18, and Fig. 7 is a diagram explaining the discrimination process S20.

As shown in Fig. 3, the inspection method of this embodiment is a method of inspecting a glass bottle 10 having an engraving 15 on the surface of the body portion 13, and includes at least: an image acquisition process S12, a shielding process S18, and a discrimination process S20. The inspection method of this embodiment may further include a process S10 of starting imaging before S12, may include image preprocessing S14 of applying predetermined processing to the image after S12, or may further include a pattern position detection process after S14 S16. For each process, referring to Fig. 1 and Fig. 2, the following will be described in order.

S10: The control unit 50 issues an instruction to start imaging to the imaging unit 40. The imaging unit 40 captures the transmitted light that has passed through the trunk 13 of the glass bottle 10 rotating around the center axis 12 by a line sensor in accordance with an instruction of the control unit 50. At this time, the control unit 50 calculates the rotation angle of the glass bottle 10 based on the output from the rotation detection unit 54 and continuously takes 1.5 laps (for example, 360°×1.5=540°). The disadvantage shown in FIG. 1 is, for example, surface bubbles 18. By using the line sensor to capture images of the transmitted light, even defects such as the shadow of the surface bubbles 18 that are not easy to appear can be automatically identified from the image. The image data to be captured is sent from the imaging unit 40 to the control unit 50.

S12: The control unit 50 executes an image acquisition process S12 that acquires the image 80 (FIG. 4) captured from the entire circumference of the carcass 13 from which the image capturing unit 40 is sent. The image 80 is a memory device (not shown) stored in the control unit 50. In the image 80, at least a 1.5-circle image of the carcass 13 is captured, and a 1.5-circle image of the neck 11 may be further captured. The image 80 has more than 1.5 turns of the body 13, and the control unit 50 can arrange multiple inspection areas (82-84, 88, 89) equivalent to 1 turn of the body 13 in the image without interruption. 80.

The image 80 shown in FIG. 4 shows the pattern 15a derived from the engraving 15, the seam line 16 extending in the longitudinal direction, and the surface bubble shadow 18a, and is in a state of being imaged as a dark shadow. The seam line 16 is a shadow generated by using the step formed by the mold when the glass bottle 10 is formed. The shadow determined to be a defect in the image 80 may include a shadow formed by bubbles, white stones, foreign objects, etc. from the inside in addition to the surface bubble shadow 18a formed by the surface bubbles 18. In order to distinguish these shadows clearly from the pattern 15a and the seam line 16 and judge it as a defect, a plural rectangular inspection area (82-84, 88, 89) is provided in the part where the trunk 13 in the image 80 is imaged. , Implement pre-set inspection rules in each inspection area. In Figure 4, each inspection area (82-84, 88, 89) is shown by dotted lines.

S14: The image processing unit 53 executes the image preprocessing S14 for the image 15a in order to more reliably execute the pattern position detection process S16. The image pre-processing S14 is to search the pattern 15a from the abstract shape. For example, "blur processing" can be performed. "Blur processing" can be performed by, for example, an averaging filter. The averaging filter replaces the pixel value of the eye-catching pixel with the average value of the entire pixel value within the filter size range and outputs it. filter.

In addition to the "blur processing", the image pre-processing S14 may also employ, for example, "blowing processing" which expands the black of shadows.

S16: As shown in Fig. 5, the discrimination unit 52 executes the pattern position detection process S16. Before performing the pattern position detection process S16, as shown in FIG. 5(a), the operator prepares in advance a pattern registration image 86 created based on the outline of the engraving 15. The pattern registration image 86 can also be made based on the shape of the pattern 15a derived from the sculpture 15. The pattern registration image 86 is a frame slightly larger than the engraving 15, and may be set to the same size as the rectangular first inspection area 82. The pattern registration image 86 is a memory device (not shown) stored in the control unit 50.

Next, the discrimination unit 52 executes the pattern position detection process S16. As shown in Figure 5 (b) and (c), the pattern position detection process S16 is performed for the image 80 acquired in the image acquisition process S12 using the pattern registration image 86 made in advance based on the outline of the sculpture 15 Pattern search, and pattern 15a is detected. The pattern search is to search for the detected object suitable for the pattern registration image 86 in the image 80. When the pattern registration image 86 matches the appearance of the pattern 15a to a certain extent, the detected body is detected as the pattern 15a. Since the pattern 15a is detected by using the pattern registration image 86 made according to the outline of the engraving 15, even if the shade of the pattern 15a is thin, the position of the pattern 15a can be stably detected.

In the pattern position detection process S16, a pattern search can be performed for a predetermined height range in the portrait 80. As shown in FIG. 1, the glass bottle 10 is located on the mounting table 30, and the appearance height of the pattern 15a in the image 80 to be imaged is almost constant. Here, as shown in FIG. 4, the first height H1 from the lower end of the portrait 80 is set as the lower limit, and the horizontal range of the second height H2 is set in the pattern search area 85 (a rectangular area surrounded by a dotted line) , Perform a pattern search in the pattern search area 85. In this way, the processing load of the inspection device 1 can be reduced by performing a pattern search for the predetermined height range.

S18: The image processing unit 53 executes the masking process S18. As shown in FIGS. 5(d) and (e), the masking process S18 is to mask the engraved area 81 of the image 80 including the pattern 15a derived from the engraving 15 by the mask 87. The engraving area 81 is the entire width including the pattern 15a. The engraving area 81 may be an area surrounded by the pattern registration image 86, or a range slightly narrower than the pattern registration image 86 and closer to the pattern 15a as the engraving area 81. The mask 87 is equivalent to the engraving area 81. The mask 87 is created in advance together with the pattern registration image 86. The arrangement of the mask 87 and the pattern registration image 86 may also be set in advance. Thus, if the pattern registration image 86 is confirmed to be placed in an appropriate position in the image 80 through the pattern search, the engraving area 81 is set in the image 80 and masked by the mask 87. In addition, the image processing unit 53 arranges a plurality of inspection areas (82 to 84, 88, 89) of predetermined shapes in the image 80 based on the position of the pattern 15a detected by the pattern search. By setting the position of the pattern 15a and the relative position between the positions of the inspection areas (82-84, 88, 89) in advance, when the position of the pattern 15a is determined, multiple inspection areas (82-84, 88 and 89) are automatically laid out on the portrait 80.

In addition to the above S14 to S18, for example, S14 may also use other image processing. For example, the image processing unit 53 may thicken the image 80 obtained by the image acquisition process S12 in Fig. 6(a) by performing multiple expansion processing as shown in Fig. 6(b) The image 80 is binarized as shown in Fig. 6(c), the pattern 15a detected by the pattern position detection process S16 is executed by the discrimination unit 52 and the engraving area 81 is set, so that the image processing unit 53 is as shown in Fig. 6(d) Perform the shielding process S18. In this case, in the pattern position detection process S16, the pattern 15a can be detected by the center of gravity and area of the pattern 15a obtained by the binarization process.

S20: The discrimination section 52 executes the discrimination process S20. The discrimination process S20 is to discriminate whether there is a defect in the area other than the masked engraving area 81 in the image 80. Since it is determined whether there are defects in areas other than the engraving area 81, it is possible to automatically determine whether there are defects in the glass bottle 10 having the engraving 15 on the surface from the image 80. In the discrimination process S20, the inspections specified in the first inspection area 82, the second inspection area 83, the third inspection area 84, the fourth inspection area 88, and the fifth inspection area 89 set in the image 80 are respectively determined The rules are implemented to determine whether there are shortcomings. Each inspection area has a rectangular shape set in advance, for example, with a predetermined size.

The first inspection area 82 is an area surrounding the engraving area 81 and is narrower than the second inspection area 83. In the first inspection area 82, in addition to the area covered by the mask 87, the image processing section 53 performs, for example, the surface bubbles 18 with thin (or thin) hatched lines as shown in FIG. 7(a) After the emphasis processing in the vertical and horizontal directions, if the binarization processing is performed, the hatched line as shown in Figure 7(b) becomes a continuous body without interruption. The discrimination unit 52 determines whether the detected object is a defect based on the area and maximum length of the detected object after the binarization process. If the detected object is not a defect, it is judged as "no defect", and the control unit 50 will The glass bottle 10 is treated as a good product (S22). In addition, when the detected body has a defect, it is determined that it has a defect, and the control unit 50 treats the glass bottle 10 as a defective product (S24).

The second inspection area 83 surrounds the first inspection area 82 and extends from the lower end of the image 80 to the lower end of the neck 11. The second inspection area 83 is a part other than the first inspection area 82. The image processing unit 53 performs the same image processing on the second inspection area 83 as in the first inspection area 82, and the determination unit 52 determines whether the detected object is a defect (S20). Since the possibility of erroneously determining the pattern 15a as a defect in the second inspection area 83 is low, the determination unit 52 can determine the detected object in the second inspection area 83 with higher accuracy than the first inspection area 82.

The two third inspection areas 84 are arranged on the left and right outer sides of the second inspection area 83 and extend from the lower end of the image 80 to the lower end of the neck 11. The third inspection area 84 is a part where the seam line 16 arranged in the image 80 appears. The inspection rule in the third inspection area 84 needs to be different from the detected body seam line 16. For example, as shown in Figs. 7(c) and (d), the detected body is divided into multiple numbers in the vertical direction, and the distances D1 and D2 between the two lines in the horizontal direction within the divided frame are measured. The discriminating unit 52 discriminates that the distance D1 between the two lines is wider than the predetermined width and the detected objects in the upper and lower frames are continuous, for example, as the surface bubbles 18, and the distance D2 between the two lines is more than If the predetermined width is narrower, it is judged as the seam line 16. In addition, the image processing unit 53 removes the vertical shading (seam line 16) from the image in Fig. 7(e), and further binarizes it as shown in Fig. 7(f). Then, the determination unit 52 is Judge whether it is a defect by the area of the detected body. At this time, because the vertical shadow can be eliminated by emphasizing the vertical brightness change by image processing, surface bubbles with horizontally long portions with vertical brightness changes will remain. In this way, by applying two different inspection rules at the same time, the seam line 16 will not be mistaken as a defect, and the inspection can be performed more accurately.

The fourth inspection area 88 is between the second inspection area 83 and the third inspection area 84 and extends from the lower end of the image 80 to the lower end of the neck 11. The fourth inspection area 88 is a portion facing the second inspection area 83 in the trunk 13. The image processing unit 53 and the discrimination unit 52 can perform the same processing for the fourth inspection area 88 as the second inspection area 83.

The fifth inspection area 89 is a portion corresponding to the neck 11 extending above the second inspection area 83 to the fourth inspection area 88. The fifth inspection area 89 is divided into two on the image 80 except for the position where the seam line 16 is imaged. This is because an interference shadow that perpendicularly crosses the seam line 16 occurs at a position located between the two fifth inspection areas 89. The image processing unit 53 and the discrimination unit 52 can perform, for example, the same processing as the third inspection area 84 on the fifth inspection area 89.

The present invention is not limited to the above-mentioned embodiment, and can be further variously modified, and includes substantially the same configuration (structure) as the configuration (structure) described in the embodiment. Here, the "same structure (structure)" means a structure (structure) with the same function, method, and result, or a structure (structure) with the same objective effect. In addition, the present invention includes a configuration (structure) in which non-essential parts of the configuration (structure) described in the embodiment are replaced. In addition, the present invention includes a configuration (structure) that can achieve the same effects as the configuration (structure) described in the embodiment, or a configuration (structure) that can achieve the same purpose. In addition, the present invention includes a configuration (structure) described in the embodiment with a well-known technology added thereto.

1: Inspection device 10: glass bottle 11: neck 12: Central axis 13: Carcass 14: bottom 15: Carving 15a: appearance 16: seam line 18: Surface bubbles 18a: Surface bubble shadow 19: Mouth 20: Light-emitting part 22: luminous surface 30: Mounting table 32: Side roller 35: belt 40: Camera Department 50: Control Department 52: Discrimination Department 53: Image Processing Department 54: Rotation detection section 60: Motor 62: Rotation control unit 80: Portrait 81: Carving Field 82: The first inspection area 83: The second inspection area 84: 3rd inspection area 85: Graphic search field 86: Graphic registration portrait 87: Mask 88: 4th inspection area D1, D2: the distance between the second line H1: 1st height H2: 2nd height W1, W2: full width

[Figure 1] A side view showing the inspection device. [Figure 2] A schematic plan view of the inspection device. [Figure 3] A flowchart of the inspection method of this embodiment. [Figure 4] An example of a portrait. [Figure 5] A diagram illustrating the image processing, detection process, and masking process. [Figure 6] A diagram explaining the image processing and masking process. [Figure 7] A diagram explaining the discrimination process.

Claims (5)

An inspection method for glass bottles, For glass bottles with carvings on the surface of the carcass, the method of inspection is characterized by including: The image acquisition process of photographing the rotating glass bottle and acquiring the image of the entire circumference of the body part, and The masking process of masking the engraving area of the aforementioned image containing the pattern derived from the aforementioned engraving, and The process of judging whether there is a defect in the aforementioned portrait except for the aforementioned engraving area that is shielded. Such as the inspection method of the glass bottle of claim 1, in which, The aforementioned shortcomings include at least surface defects, In the image acquisition process, the line sensor captures the transmitted light that has passed through the carcass. Such as the inspection method of the glass bottle of claim 1 or 2, in which, It further includes a pattern position detection process, which is to register an image using a pattern created in advance based on the outline of the aforementioned engraving. The pattern searches for the aforementioned image obtained by the aforementioned image acquisition process, and detects the aforementioned pattern, The aforementioned masking process is to mask the aforementioned engraved area including the aforementioned pattern detected by the aforementioned pattern position detection process. Such as the inspection method of the glass bottle of claim 3, in which, The aforementioned pattern position detection process is to search for patterns in the specified height range of the aforementioned portrait. A method for manufacturing glass bottles, which is characterized by: A rough mold is used to form a molded blank from a block, the aforementioned parison is formed into the aforementioned glass bottle from a finished model, and the aforementioned glass bottle is subjected to the inspection method of any one of claims 1 to 4 to obtain a judgement It is a glass bottle without the aforementioned shortcomings.

Images