CN111239142A - Paste appearance defect detection device and method - Google Patents
Paste appearance defect detection device and method Download PDFInfo
- Publication number
- CN111239142A CN111239142A CN202010187095.8A CN202010187095A CN111239142A CN 111239142 A CN111239142 A CN 111239142A CN 202010187095 A CN202010187095 A CN 202010187095A CN 111239142 A CN111239142 A CN 111239142A
- Authority
- CN
- China
- Prior art keywords
- camera
- paste
- light source
- shooting
- trigger sensor
- 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
Images
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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/892—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the flaw, defect or object feature examined
- G01N21/894—Pinholes
-
- 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
- G01N21/8806—Specially adapted optical and illumination features
- G01N2021/8841—Illumination and detection on two sides of object
Abstract
The embodiment of the disclosure provides paste appearance defect detection equipment and a method, which belong to the technical field of product detection, and the equipment comprises: a conveyor for a user to transport the paste in a specified direction; the first trigger sensor is arranged at a first position of the conveying device and used for detecting whether the paste arrives at the first position; a first camera, a second camera, and a fifth camera; a second trigger sensor; the third camera and the fourth camera are used for shooting the paste body at a second position in the horizontal direction; and the defect detection processor judges whether the paste has appearance defects or not according to images shot by the first camera, the second camera, the third camera, the fourth camera and the fifth camera. Through the processing scheme disclosed by the invention, whether the appearance of the paste body has defects can be automatically detected.
Description
Technical Field
The disclosure relates to the technical field of defect monitoring, in particular to paste appearance defect detection equipment and method.
Background
In the traditional lipstick manufacturing production line, the lipstick is easy to have the defects of 'tip breakage', scratches, stains and the like after demolding in the production process. The rotation angle of the paste of a lipstick product on a production line has uncertainty, and the paste image at a preset angle is difficult to be shot deterministically.
The existing lipstick or similar paste manufacturing enterprises still rely on manual inspection in the appearance detection link, and semi-automatic or automatic detection modes are not popularized by people, so that the appearance yield of products is difficult to control.
To solve this or such problems, a general device manufacturer provides a general visual inspection device or software module for a cosmetic product manufacturer, which is configured and debugged to be suitable for various product types, but the applicability of such products is different from that of the present invention. The general equipment has low accuracy because of no light source, structure and algorithm module specially designed for lipstick paste.
Disclosure of Invention
In view of the above, the embodiments of the present disclosure provide a paste appearance defect detecting apparatus and method, so as to at least partially solve the problems in the prior art.
In a first aspect, an embodiment of the present disclosure provides a paste appearance defect detection apparatus, including:
a conveyor for a user to transport the paste in a specified direction;
the first trigger sensor is arranged at a first position of the conveying device and used for detecting whether the paste arrives at the first position;
the paste body shooting device comprises a first camera, a second camera and a fifth camera, wherein the first camera and the second camera are used for shooting the paste body in the horizontal direction at a first position, and the fifth camera is used for shooting the paste body in the vertical downward direction at the first position;
the second trigger sensor is arranged at a second position of the conveying device and used for detecting whether the paste arrives at the second position;
the third camera and the fourth camera are used for shooting the paste body at a second position in the horizontal direction;
and the defect detection processor judges whether the paste has appearance defects or not according to images shot by the first camera, the second camera, the third camera, the fourth camera and the fifth camera.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
a first light source to illuminate the paste at the first location.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
a first shielding baffle disposed on an opposite side of the first light source for reflecting light of the first light source to the first position.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
a second light source illuminating the paste at the second location.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
a second shielding baffle disposed on an opposite side of the second light source for reflecting light of the second light source to the second position.
According to a specific implementation manner of the embodiment of the present disclosure, the method is characterized in that:
the first light source is a panel type LED normally-on light source, and the LED normally-on light source is lighted and triggered through an upstream trigger sensor.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
the first shielding plate and the second shielding plate are made of diffuse reflection materials.
According to a specific implementation manner of the embodiment of the present disclosure, the method is characterized in that:
for the image shot by the fifth camera, roughly positioning the image by adopting an image processing technology for determining the position and the radius of the paste body;
and judging whether the paste has preset defects in the positions and the radius areas of the paste, wherein the preset defects comprise at least one of broken tips, air holes and depressions.
According to a specific implementation manner of the embodiment of the present disclosure, the method is characterized in that:
performing image enhancement operation on the side images of the paste body shot by the first camera, the second camera, the third camera and the fourth camera;
and monitoring the defects of the image after the enhancement operation processing by using a preset deep learning model.
In a second aspect, an embodiment of the present disclosure provides a method for detecting appearance defects of a paste, including:
transporting the paste in a specified direction by a user of the transfer device;
arranging a first trigger sensor at a first position of the conveying device for detecting whether the paste arrives at the first position;
arranging a first camera, a second camera and a fifth camera, wherein the first camera and the second camera are used for shooting the paste body in the horizontal direction at the first position, and the fifth camera is used for shooting the paste body in the vertical downward direction at the first position;
arranging a second trigger sensor, wherein the second trigger sensor is arranged at a second position of the conveying device and is used for detecting whether the paste arrives at the second position;
arranging a third camera and a fourth camera, wherein the third camera and the fourth camera are used for shooting the paste body at a second position in the horizontal direction;
and a defect detection processor is arranged, and the defect detection processor judges whether the paste has appearance defects or not according to images shot by the first camera, the second camera, the third camera, the fourth camera and the fifth camera.
The paste appearance defect detection scheme in the embodiment of the disclosure comprises a conveying device, wherein a user of the conveying device is used for conveying the paste in a specified direction; the first trigger sensor is arranged at a first position of the conveying device and used for detecting whether the paste arrives at the first position; the paste body shooting device comprises a first camera, a second camera and a fifth camera, wherein the first camera and the second camera are used for shooting the paste body in the horizontal direction at a first position, and the fifth camera is used for shooting the paste body in the vertical downward direction at the first position; the second trigger sensor is arranged at a second position of the conveying device and used for detecting whether the paste arrives at the second position; the third camera and the fourth camera are used for shooting the paste body at a second position in the horizontal direction; and the defect detection processor judges whether the paste has appearance defects or not according to images shot by the first camera, the second camera, the third camera, the fourth camera and the fifth camera. By the processing scheme of the automatic detection system, automatic detection is completed by adding a detection device (an image acquisition device, a light source, an image analysis processor and other peripherals). The rotation angle of the paste of lipstick products on a production line has uncertainty, and the paste image of a preset angle is difficult to be shot deterministically, but the invention detects defects through multiple visual angles, specifically: and a plurality of cameras respectively sample the shot lipstick from the side surface and the top part each time the shot lipstick is shot. The auxiliary light source and the background lamp panel are matched to highlight the defects of the shot object. And respectively estimating the defect form system of the target under different visual angles, and comprehensively judging whether the target is a defective product.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings needed to be used in the embodiments will be briefly described below, and it is apparent that the drawings in the following description are only some embodiments of the present disclosure, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic structural diagram of a device for detecting appearance defects of a paste according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for detecting appearance defects of a paste according to an embodiment of the present disclosure.
Detailed Description
The embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.
The embodiments of the present disclosure are described below with specific examples, and other advantages and effects of the present disclosure will be readily apparent to those skilled in the art from the disclosure in the specification. It is to be understood that the described embodiments are merely illustrative of some, and not restrictive, of the embodiments of the disclosure. The disclosure may be embodied or carried out in various other specific embodiments, and various modifications and changes may be made in the details within the description without departing from the spirit of the disclosure. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict. All other embodiments, which can be derived by a person skilled in the art from the embodiments disclosed herein without making any creative effort, shall fall within the protection scope of the present disclosure.
It is noted that various aspects of the embodiments are described below within the scope of the appended claims. It should be apparent that the aspects described herein may be embodied in a wide variety of forms and that any specific structure and/or function described herein is merely illustrative. Based on the disclosure, one skilled in the art should appreciate that one aspect described herein may be implemented independently of any other aspects and that two or more of these aspects may be combined in various ways. For example, an apparatus may be implemented and/or a method practiced using any number of the aspects set forth herein. Additionally, such an apparatus may be implemented and/or such a method may be practiced using other structure and/or functionality in addition to one or more of the aspects set forth herein.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present disclosure, and the drawings only show the components related to the present disclosure rather than the number, shape and size of the components in actual implementation, and the type, amount and ratio of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated.
In addition, in the following description, specific details are provided to facilitate a thorough understanding of the examples. However, it will be understood by those skilled in the art that the aspects may be practiced without these specific details.
Referring to fig. 1, the paste appearance defect detecting apparatus in the embodiment of the present disclosure may include:
a conveyor for a user to transport the paste in a specified direction;
the first trigger sensor is arranged at a first position of the conveying device and used for detecting whether the paste arrives at the first position;
the paste body shooting device comprises a first camera, a second camera and a fifth camera, wherein the first camera and the second camera are used for shooting the paste body in the horizontal direction at a first position, and the fifth camera is used for shooting the paste body in the vertical downward direction at the first position;
the second trigger sensor is arranged at a second position of the conveying device and used for detecting whether the paste arrives at the second position;
the third camera and the fourth camera are used for shooting the paste body at a second position in the horizontal direction;
and the defect detection processor judges whether the paste has appearance defects or not according to images shot by the first camera, the second camera, the third camera, the fourth camera and the fifth camera.
Specifically, the structure of the device of the invention is shown in fig. 1, and the first camera, the second camera, the third camera and the fourth camera are used for shooting images of the side face of the paste. The fifth camera is used to take an image of the top of the paste. It should be noted that the arrangement method of the first, second, third and fourth cameras is only a preferred scheme, 3, 4, 5 and the like can be used according to the conditions of the production line field, the invention focuses on using two types of cameras, wherein one type (such as the first, second, third and fourth cameras) is used for shooting the paste and the side cylindrical surface of the shell, and the other type (such as the fifth camera) is installed right above the lipstick paste and is shot towards the lipstick head edge part vertically and used for detecting defects of the lipstick paste head edge part, such as 'sharp breakage' and the like.
As shown in fig. 1, the product is transported forward via a conveyor (e.g., a conveyor belt) and a photograph is triggered when the product passes a trigger sensor (e.g., a first trigger sensor or a second trigger sensor). In one embodiment a reflective proximity sensor is used as the trigger signal source. The upstream trigger sensor (first trigger sensor) is connected with the first camera and the second camera. And the downstream trigger sensor (second trigger sensor) is connected with the third camera and the fourth camera. The same object is photographed twice at the moment that the upstream and the downstream are triggered respectively to form images of a plurality of visual angles, and the images are synchronously transmitted to the image processing sensor. In one embodiment, a fifth camera is connected with the upstream trigger sensor and is used for shooting the paste head edge part at the upstream; in another embodiment, a fifth camera is connected to the downstream trigger sensor, i.e. shoots the cream's brim.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
a first light source to illuminate the paste at the first location.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
a first shielding baffle disposed on an opposite side of the first light source for reflecting light of the first light source to the first position.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
a second light source illuminating the paste at the second location.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
a second shielding baffle disposed on an opposite side of the second light source for reflecting light of the second light source to the second position.
According to a specific implementation manner of the embodiment of the present disclosure, the method is characterized in that:
the first light source is a panel type LED normally-on light source, and the LED normally-on light source is lighted and triggered through an upstream trigger sensor.
According to a specific implementation manner of the embodiment of the present disclosure, the apparatus further includes:
the first shielding plate and the second shielding plate are made of diffuse reflection materials.
Optionally, the first light source may be a panel-type LED normally-bright light source; optionally, the first light source is connected to the upstream trigger, and after receiving the start signal, the first light source flashes to illuminate the object. The first light source is disposed between the upstream side cameras, facing the subject.
For the downstream, optionally, the second light source may be a panel type LED normally-bright light source; the optional second light source is connected with the trigger sensor, and after receiving the trigger signal, the second light source flashes to illuminate the shot object. The second light source is disposed between the downstream lateral cameras, facing the subject.
On the opposite side of the upstream and downstream cameras from the conveyor, baffles are respectively disposed. The barrier is used to avoid interference from the surrounding environment in an image and to highlight a subject. It should be noted that the baffle is made of diffuse reflection material, and in one example, a neutral gray scale diffuse reflection acrylic board is used. In one embodiment, an LED panel light box with soft light material is used.
Preferably, all the devices are shielded by the shading box, so that the interference of ambient light on the acquisition device is avoided.
According to a specific implementation manner of the embodiment of the present disclosure, the method is characterized in that:
for the image shot by the fifth camera, roughly positioning the image by adopting an image processing technology for determining the position and the radius of the paste body;
and judging whether the paste has preset defects in the positions and the radius areas of the paste, wherein the preset defects comprise at least one of broken tips, air holes and depressions.
According to a specific implementation manner of the embodiment of the present disclosure, the method is characterized in that:
performing image enhancement operation on the side images of the paste body shot by the first camera, the second camera, the third camera and the fourth camera;
and monitoring the defects of the image after the enhancement operation processing by using a preset deep learning model.
For images taken by the overhead camera, it is preferred to first coarsely position the images using conventional image processing techniques. In one embodiment, the position and radius of the lipstick (paste) are determined by using Hough circle detection, and the region of interest is determined by the position and radius of the center of the lipstick. The perceptual area is scaled to a preset size and marked as an input image. The input image is analyzed using a first class of deep learning model. In one embodiment, the depth model serves as a sort task, namely, whether a defect exists in the region of interest is identified; in another embodiment, the depth model is used as a multi-label classification task, the number of labels is related to the number of defect types, for example, three types of defects, namely, broken tip, air hole, recess and normal four types of classification labels, mainly exist.
For the deep learning model, resnet50 may be used as the classification model and softmax as the classification loss function in one embodiment. And carrying out supervised training on the deep learning model by using a large number of pictures of lipstick with different colors and shapes. Finally, an effective first deep learning model can be obtained.
For images taken by the side cameras, it is preferable to first image-enhance the images using conventional image processing techniques. In one embodiment, the illumination is removed using a self-quotient method. Optionally, image details are enhanced using adaptive histogram equalization. The enhanced image is marked as an input image.
The input image is analyzed using a second deep learning model. In one embodiment, defect detection is used as a target locating and classifying task, and ssd, yolov3, etc. can be used as a second deep learning model, for example, to regress the location of the defect and the classification label. The output result is a series of 5 tuples, which respectively represent the horizontal and vertical coordinates of the upper left corner point of the regression frame, the width and the height of the regression frame and the classification label. According to the definition of the defect type, the defect type can be used as a binary classification task, namely whether a defect exists or not; or a multi-label task, and classifying the type of the defect; in another embodiment, the object localization model is used in its entirety in tandem with the classification model as a second deep learning model. The former is used for determining the position and the size of a target, then an interesting area is extracted from the position of each defect and marked as an input sub-image of a classification model, and the classification depth model is used for identifying the sub-image. It is determined whether the target is a defect, or which defect. In another embodiment, a binarization or self-adaptive binarization method is used for segmenting an original image, noise is removed through morphological opening-up operation, connected regions are counted, and candidate interested regions of defects are determined. The candidate regions of interest are then classified using resnet or the like as a second deep learning model. The training method of the second deep learning model is similar to the first deep learning model, and belongs to the prior art, and is not described herein again.
In a corresponding pair with the above apparatus, referring to fig. 2, an embodiment of the present disclosure further provides a method for detecting appearance defects of a paste, including:
s201, conveying the paste in a specified direction by a user through a conveying device;
s202, arranging a first trigger sensor at a first position of the conveying device, and detecting whether the paste arrives at the first position;
s203, arranging a first camera, a second camera and a fifth camera, wherein the first camera and the second camera are used for shooting the paste body at a first position in the horizontal direction, and the fifth camera is used for shooting the paste body at the first position in the vertical downward direction;
s204, arranging a second trigger sensor, wherein the second trigger sensor is arranged at a second position of the conveying device and used for detecting whether the paste arrives at the second position;
s205, arranging a third camera and a fourth camera, wherein the third camera and the fourth camera are used for shooting the paste body at a second position in the horizontal direction;
and S206, setting a defect detection processor, wherein the defect detection processor judges whether the paste has appearance defects according to images shot by the first camera, the second camera, the third camera, the fourth camera and the fifth camera.
In the process of implementing steps S201 to S206, the first, second, third, and fourth cameras are used to capture images of the side surfaces of the paste. The fifth camera is used to take an image of the top of the paste. It should be noted that the arrangement method of the first, second, third and fourth cameras is only a preferred scheme, 3, 4, 5 and the like can be used according to the conditions of the production line field, the invention focuses on using two types of cameras, wherein one type (such as the first, second, third and fourth cameras) is used for shooting the paste and the side cylindrical surface of the shell, and the other type (such as the fifth camera) is installed right above the lipstick paste and is shot towards the lipstick head edge part vertically and used for detecting defects of the lipstick paste head edge part, such as 'sharp breakage' and the like.
As shown in fig. 1, the product is transported forward via a conveyor (e.g., a conveyor belt) and a photograph is triggered when the product passes a trigger sensor (e.g., a first trigger sensor or a second trigger sensor). In one embodiment a reflective proximity sensor is used as the trigger signal source. The upstream trigger sensor (first trigger sensor) is connected with the first camera and the second camera. And the downstream trigger sensor (second trigger sensor) is connected with the third camera and the fourth camera. The same object is photographed twice at the moment that the upstream and the downstream are triggered respectively to form images of a plurality of visual angles, and the images are synchronously transmitted to the image processing sensor. In one embodiment, a fifth camera is connected with the upstream trigger sensor and is used for shooting the paste head edge part at the upstream; in another embodiment, a fifth camera is connected to the downstream trigger sensor, i.e. shoots the cream's brim.
Although the present invention is directed to a lipstick, it is not limited to a lipstick, but can be interpreted as a lipstick and a paste having the appearance characteristics of a lipstick, such as a lip gloss, etc.
The above description is only for the specific embodiments of the present disclosure, but the scope of the present disclosure is not limited thereto, and any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope of the present disclosure should be covered within the scope of the present disclosure. Therefore, the protection scope of the present disclosure shall be subject to the protection scope of the claims.
Claims (10)
1. A paste appearance defect detection device is characterized by comprising:
a conveyor for a user to transport the paste in a specified direction;
the first trigger sensor is arranged at a first position of the conveying device and used for detecting whether the paste arrives at the first position;
the paste body shooting device comprises a first camera, a second camera and a fifth camera, wherein the first camera and the second camera are used for shooting the paste body in the horizontal direction at a first position, and the fifth camera is used for shooting the paste body in the vertical downward direction at the first position;
the second trigger sensor is arranged at a second position of the conveying device and used for detecting whether the paste arrives at the second position;
the third camera and the fourth camera are used for shooting the paste body at a second position in the horizontal direction;
and the defect detection processor judges whether the paste has appearance defects or not according to images shot by the first camera, the second camera, the third camera, the fourth camera and the fifth camera.
2. The apparatus of claim 1, further comprising:
a first light source to illuminate the paste at the first location.
3. The apparatus of claim 2, further comprising:
a first shielding baffle disposed on an opposite side of the first light source for reflecting light of the first light source to the first position.
4. The apparatus of claim 1, further comprising:
a second light source illuminating the paste at the second location.
5. The apparatus of claim 4, further comprising:
a second shielding baffle disposed on an opposite side of the second light source for reflecting light of the second light source to the second position.
6. The apparatus according to any one of claims 2-5, wherein:
the first light source is a panel type LED normally-on light source, and the LED normally-on light source is lighted and triggered through an upstream trigger sensor.
7. The apparatus of any of claims 2-5, further comprising:
the first shielding plate and the second shielding plate are made of diffuse reflection materials.
8. The apparatus of claim 1, wherein:
for the image shot by the fifth camera, roughly positioning the image by adopting an image processing technology for determining the position and the radius of the paste body;
and judging whether the paste has preset defects in the positions and the radius areas of the paste, wherein the preset defects comprise at least one of broken tips, air holes and depressions.
9. The apparatus of claim 1, wherein:
performing image enhancement operation on the side images of the paste body shot by the first camera, the second camera, the third camera and the fourth camera;
and monitoring the defects of the image after the enhancement operation processing by using a preset deep learning model.
10. The method for detecting the appearance defects of the paste is characterized by comprising the following steps:
transporting the paste in a specified direction by a user of the transfer device;
arranging a first trigger sensor at a first position of the conveying device for detecting whether the paste arrives at the first position;
arranging a first camera, a second camera and a fifth camera, wherein the first camera and the second camera are used for shooting the paste body in the horizontal direction at the first position, and the fifth camera is used for shooting the paste body in the vertical downward direction at the first position;
arranging a second trigger sensor, wherein the second trigger sensor is arranged at a second position of the conveying device and is used for detecting whether the paste arrives at the second position;
arranging a third camera and a fourth camera, wherein the third camera and the fourth camera are used for shooting the paste body at a second position in the horizontal direction;
and a defect detection processor is arranged, and the defect detection processor judges whether the paste has appearance defects or not according to images shot by the first camera, the second camera, the third camera, the fourth camera and the fifth camera.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010187095.8A CN111239142A (en) | 2020-03-17 | 2020-03-17 | Paste appearance defect detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010187095.8A CN111239142A (en) | 2020-03-17 | 2020-03-17 | Paste appearance defect detection device and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111239142A true CN111239142A (en) | 2020-06-05 |
Family
ID=70875276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010187095.8A Pending CN111239142A (en) | 2020-03-17 | 2020-03-17 | Paste appearance defect detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111239142A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951218A (en) * | 2020-07-09 | 2020-11-17 | 黄鹏 | Lipstick quality inspection system of mixed deep learning model |
| CN111948213A (en) * | 2020-07-09 | 2020-11-17 | 黄鹏 | Lipstick defect detection device based on attention capsule network and detection method thereof |
| CN113129272A (en) * | 2021-03-30 | 2021-07-16 | 广东省科学院智能制造研究所 | Defect detection method and device based on denoising convolution self-encoder |
| CN114184623A (en) * | 2021-11-22 | 2022-03-15 | 厦门深度赋智科技有限公司 | Lipstick flaw detection system combined with edge equipment |
| CN116660468A (en) * | 2023-05-29 | 2023-08-29 | 荆州洗涮涮环保科技有限公司 | Intelligent monitoring and analyzing method for cosmetic production line |
-
2020
- 2020-03-17 CN CN202010187095.8A patent/CN111239142A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111951218A (en) * | 2020-07-09 | 2020-11-17 | 黄鹏 | Lipstick quality inspection system of mixed deep learning model |
| CN111948213A (en) * | 2020-07-09 | 2020-11-17 | 黄鹏 | Lipstick defect detection device based on attention capsule network and detection method thereof |
| CN113129272A (en) * | 2021-03-30 | 2021-07-16 | 广东省科学院智能制造研究所 | Defect detection method and device based on denoising convolution self-encoder |
| CN114184623A (en) * | 2021-11-22 | 2022-03-15 | 厦门深度赋智科技有限公司 | Lipstick flaw detection system combined with edge equipment |
| CN116660468A (en) * | 2023-05-29 | 2023-08-29 | 荆州洗涮涮环保科技有限公司 | Intelligent monitoring and analyzing method for cosmetic production line |
| CN116660468B (en) * | 2023-05-29 | 2024-02-13 | 广州昂博科技有限公司 | Intelligent monitoring and analyzing method for cosmetic production line |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111239142A (en) | Paste appearance defect detection device and method | |
| US11830179B2 (en) | Food inspection assisting system, food inspection assisting apparatus and computer program | |
| US8254659B2 (en) | Method and apparatus for visually inspecting an object | |
| CN104483320B (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN110146516B (en) | Fruit grading device based on orthogonal binocular machine vision | |
| CN110246122A (en) | Small size bearing quality determining method, apparatus and system based on machine vision | |
| JPWO2019151393A1 (en) | Food inspection system, food inspection program, food inspection method and food production method | |
| CN210071686U (en) | Fruit grading plant based on orthogonal binocular machine vision | |
| CN106651802A (en) | Machine vision tin soldering location detection method | |
| CN110554052A (en) | artificial board surface defect detection method and system | |
| CN111458345A (en) | Visual detection mechanism for defects of mask | |
| CN110929755A (en) | Poultry egg detection method, device and system, electronic equipment and storage medium | |
| CN102713580B (en) | Appearance inspection device | |
| US20230342909A1 (en) | System and method for imaging reflecting objects | |
| CN113333329A (en) | Cigarette defect detection system based on deep learning | |
| JP2019200775A (en) | Surface defect inspection device and surface defect inspection method | |
| CN212180649U (en) | Paste appearance defect detection equipment | |
| CN111239145A (en) | Paste surface air hole automatic detection equipment and method | |
| CN111458344A (en) | Mask defect visual detection method, equipment and storage medium | |
| CN111257339B (en) | Preserved egg crack online detection method and detection device based on machine vision | |
| CN113947598A (en) | Plastic lunch box defect detection method, device and system based on image processing | |
| CN113640303A (en) | Surface flaw detection equipment for notebook computer and detection method thereof | |
| KR102117697B1 (en) | Apparatus and method for surface inspection | |
| CN112525931A (en) | Shoe garment broken needle detection device and method based on artificial intelligence technology | |
| CN115601735A (en) | Empty disc recognition device and method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |