CN220289442U - Packaging printed matter detection device based on deep learning - Google Patents
Packaging printed matter detection device based on deep learning Download PDFInfo
- Publication number
- CN220289442U CN220289442U CN202321872795.6U CN202321872795U CN220289442U CN 220289442 U CN220289442 U CN 220289442U CN 202321872795 U CN202321872795 U CN 202321872795U CN 220289442 U CN220289442 U CN 220289442U
- Authority
- CN
- China
- Prior art keywords
- printed matter
- detection device
- conveying table
- deep learning
- matter detection
- 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.)
- Active
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 30
- 238000013135 deep learning Methods 0.000 title claims abstract description 20
- 238000004806 packaging method and process Methods 0.000 title claims abstract description 18
- 230000007246 mechanism Effects 0.000 claims abstract description 42
- 238000012856 packing Methods 0.000 claims abstract description 3
- 238000005096 rolling process Methods 0.000 claims description 34
- 230000007547 defect Effects 0.000 abstract description 10
- 238000013473 artificial intelligence Methods 0.000 abstract description 5
- 238000000034 method Methods 0.000 abstract description 4
- 230000006872 improvement Effects 0.000 description 8
- 230000033001 locomotion Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000008602 contraction Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model relates to a packaging printed matter detection device based on deep learning, which comprises a base frame, a conveying table for conveying printed matters, a fixing frame, a moving mechanism and a main camera for collecting, analyzing and detecting images, wherein the conveying table is arranged at the top of the base frame, the fixing frame is arranged above the conveying table, the bottom of the fixing frame is connected to two sides of the conveying table, the moving mechanism is arranged on the fixing frame, the main camera is arranged on the moving mechanism, and the main camera is arranged above the conveying table. Through camera and image processing software of high resolution, the system can capture and analyze the printing image fast, increases artificial intelligence and deep learning technique, and equipment can discern and classify the printing defect more accurately, can discern complicated and tiny flaw even, can detect defect and the problem of packing printing fast, accurately to ensure the quality and the uniformity of product.
Description
Technical Field
The utility model relates to the field of printed matter detection, in particular to a packaging printed matter detection device based on deep learning.
Background
After the printed matter is printed, the printed matter needs to be detected in printing quality, the existing detection device on the market at present generally adopts the most common camera detection structure, the recognition accuracy of the printed matter is not high, the recognition force is low, the manual operation is performed, and the cost is high. The printing process is manually operated to get on or off the machine, so that the operation cost is increased, and the operation safety accidents are easy. It takes a certain time to correct, often a deviation occurs and then reworking is performed, increasing time and material cost.
Disclosure of Invention
The utility model provides a packaging printed matter detection device based on deep learning, and aims to solve the problems that the existing printed matter detection device is low in identification accuracy and time and material cost are increased.
The utility model provides a packaging printed matter detection device based on deep learning, which comprises a base frame, a conveying table for conveying printed matters, a fixing frame, a moving mechanism and a main camera for collecting images, wherein the conveying table is arranged at the top of the base frame, the fixing frame is arranged above the conveying table, the bottom of the fixing frame is connected to two sides of the conveying table, the moving mechanism is arranged on the fixing frame, the main camera is arranged on the moving mechanism, and the main camera is arranged above the conveying table.
As a further improvement of the utility model, a plurality of first rolling rollers and a plurality of second rolling rollers are horizontally arranged in the middle of the conveying table, two ends of each first rolling roller are respectively connected to two sides of the conveying table, two ends of each second rolling roller are respectively connected to two sides of the conveying table, and each second rolling roller is arranged between the two first rolling rollers.
As a further improvement of the utility model, the diameter of the first roller is larger than the diameter of the second roller.
As a further improvement of the utility model, the moving mechanism comprises two transverse sliding grooves and a sliding guide rail, wherein the two transverse sliding grooves are symmetrically arranged on the inner side of the top of the fixing frame, and two ends of the sliding guide rail are in sliding connection with the two transverse sliding grooves.
As a further improvement of the utility model, an adjusting frame is arranged on the inner side of the top of the fixing frame, an adjusting rod is arranged on the top of the transverse sliding groove, and the transverse sliding groove is locked in the adjusting frame through the adjusting rod.
As a further improvement of the utility model, the moving mechanism further comprises a telescopic cylinder which is connected to the sliding guide rail in a sliding manner, and the main camera is arranged at the movable end of the telescopic cylinder.
As a further improvement of the utility model, the light source device further comprises two light source mechanisms for providing light sources, wherein the two light source mechanisms are respectively arranged at two sides of the conveying table, and the light source mechanisms are positioned below the fixing frame.
As a further improvement of the utility model, the light source mechanism comprises a light emitting plate, a mounting frame and a secondary camera, wherein one end of the mounting frame is connected with the conveying table, the light emitting plate is arranged at the other end of the mounting frame, and the secondary camera is arranged on the light emitting plate.
As a further improvement of the utility model, the automatic conveying device also comprises an infrared mechanism, wherein the infrared mechanism is arranged on two sides of the conveying table and positioned on the front side and the rear side of the fixing frame, the infrared mechanism comprises an infrared sensor and a telescopic rod, one end of the telescopic rod is connected with the conveying table, and the infrared sensor is arranged on the other end of the telescopic rod.
The beneficial effects of the utility model are as follows: through camera and image processing software of high resolution, the system can capture and analyze the printing image fast, increases artificial intelligence and deep learning technique, and equipment can discern and classify the printing defect more accurately, can discern complicated and tiny flaw even, can detect defect and the problem of packing printing fast, accurately to ensure the quality and the uniformity of product.
Drawings
FIG. 1 is a schematic diagram of the front end of the detection device of the present utility model;
FIG. 2 is a schematic view of the rear end of the detection device of the present utility model.
Reference numerals: the device comprises a base frame 1, a conveying table 2, a fixing frame 3, a main camera 4, a first rolling roller 5, a second rolling roller 6, a transverse chute 7, a sliding guide rail 8, a telescopic cylinder 9, an adjusting rod 10, an adjusting frame 11, an infrared sensor 12, a telescopic rod 13, a fixing frame 14, a luminous plate 15 and a sub camera 16.
Description of the embodiments
The present utility model will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present utility model more apparent. It should be noted that the words "front", "back", "left", "right", "upper" and "lower" used in the following description refer to directions in the drawings, and the words "bottom" and "top", "inner" and "outer" refer to directions toward or away from, respectively, the geometric center of a particular component.
As shown in fig. 1-2, the utility model provides a packaging printed matter detection device based on deep learning, which comprises a base frame 1, a conveying table 2 for conveying printed matters, a fixing frame 3, a moving mechanism and a main camera 4 for collecting images, wherein the conveying table 2 is arranged at the top of the base frame 1, the fixing frame 3 is arranged above the conveying table 2, the bottom of the fixing frame 3 is connected to two sides of the conveying table 2, the moving mechanism is arranged on the fixing frame 3, the main camera 4 is arranged on the moving mechanism, and the main camera 4 is arranged above the conveying table 2.
As an embodiment of the present utility model, a plurality of first rolling rollers 5 and a plurality of second rolling rollers 6 are horizontally disposed in the middle of the conveying table 2, two ends of the first rolling rollers 5 are respectively connected to two sides of the conveying table 2, two ends of the second rolling rollers 6 are respectively connected to two sides of the conveying table 2, and the second rolling rollers 6 are disposed between the two first rolling rollers 5.
As another embodiment of the present utility model, the diameter of the first rolling roller 5 is larger than the diameter of the second rolling roller 6.
As another embodiment of the present utility model, the moving mechanism includes two lateral sliding grooves 7 and a sliding rail 8, the two lateral sliding grooves 7 are symmetrically disposed on the inner side of the top of the fixing frame 3, and two ends of the sliding rail 8 are slidably connected with the two lateral sliding grooves 7.
As another embodiment of the present utility model, an adjusting frame 11 is disposed on the inner side of the top of the fixing frame 3, an adjusting rod 10 is disposed on the top of the transverse sliding groove 7, and the transverse sliding groove 7 is locked in the adjusting frame 11 through the adjusting rod 10.
As another embodiment of the present utility model, the moving mechanism further includes a telescopic cylinder 9, the telescopic cylinder 9 is slidably connected to the sliding rail 8, and the main camera 4 is disposed at a movable end of the telescopic cylinder 9.
As another embodiment of the present utility model, the apparatus further comprises two light source mechanisms for providing light sources, wherein the two light source mechanisms are respectively arranged at two sides of the conveying table 2, and the light source mechanisms are positioned below the fixing frame 3.
As another embodiment of the present utility model, the light source mechanism includes a light emitting plate 15, a mounting frame 14, and a sub camera 16, one end of the mounting frame 14 is connected to the conveying table 2, the light emitting plate 15 is disposed at the other end of the mounting frame 14, and the sub camera 16 is disposed on the light emitting plate 15.
As another embodiment of the present utility model, the present utility model further includes an infrared mechanism, the infrared mechanism is disposed on two sides of the conveying table 2 and is disposed on two front and rear sides of the fixing frame 3, the infrared mechanism includes an infrared sensor 12 and a telescopic rod 13, one end of the telescopic rod 13 is connected to the conveying table 2, and the infrared sensor 12 is disposed on the other end of the telescopic rod 13.
The utility model provides a packaging printed matter detection device based on deep learning, which can quickly capture and analyze a printed image through a high-resolution camera and image processing software, increases artificial intelligence and deep learning technology, can more accurately identify and classify printing defects, even can identify complex and tiny flaws, and can quickly and accurately detect defects and problems of packaging printing, thereby ensuring the quality and consistency of products.
The printed packaging printed matter is transmitted to the conveying table 2, the first rolling roller 5 and the second rolling roller 6 are driven to move in the direction of the fixed frame 3, the second rolling roller 6 is arranged between the two first rolling rollers 5, the diameter of the first rolling roller 5 is larger than that of the second rolling roller 6, and the second rolling roller 6 can compensate an oversized gap between the first rolling rollers 5 to avoid clamping in the transmission process. Before entering the fixing frame 3, the infrared sensor 12 analyzes chemical components of printed matter materials and transmits data to a background system, so that the reasons of color difference can be conveniently determined, and consistency of product quality is ensured, wherein the infrared sensor 12 is connected with the conveying table 2 through the telescopic rod 13, the telescopic rod 13 can be adjusted in height in the vertical direction, and the height of the infrared sensor 12 can be adjusted according to the height of printed matter.
After entering the range of the fixing frame 3, the first rolling roller 5 and the second rolling roller 6 temporarily stop rotating, the light emitting plate 15 emits light sources to illuminate the printed matter, two light emitting plates 15 are arranged for better providing the light sources, the two light emitting plates are respectively arranged at two sides of the conveying table 2, the main camera 4 and the auxiliary camera 16 are used for shooting images of the printed matter, the main camera 4 is responsible for shooting the whole world, and the auxiliary camera 16 is responsible for local characteristics of the product, such as two-dimensional codes, bar codes and the like. The main camera 4 and the auxiliary camera 16 both adopt high-resolution cameras, and after receiving the image information, the background system analyzes and processes the image to detect various defects such as chromatic aberration, scratches, and omission. The system integrates an artificial intelligence technology, a training model is manufactured by marking pictures of a plurality of product defects, the artificial intelligence carries out deep learning, and the detection precision and speed of equipment are improved. More complex and tiny printing defects can be identified by training a model, and real-time monitoring is achieved. And the data processing capacity of the detection equipment is optimized, and the rapid processing and analysis of a large amount of images and data are realized. Through efficient algorithm and parallel calculation, the detection time is shortened, and the production efficiency is improved. When receiving the images transmitted by the main camera 4 and the auxiliary camera 16, the system can immediately evaluate the printing quality of the printed matter and draw a conclusion, and warn the unqualified printed matter, thereby more accurately identifying the characteristics and defects of the product.
In order to adapt to more specifications of printed matters, the main camera 4 is arranged on the moving mechanism, the movement of the main camera 4 in front and back is realized through the movement of the sliding guide rail 8 in the two transverse sliding grooves 7, and the vertical height of the transverse sliding grooves 7 can be adjusted by adjusting the screwing positions of the adjusting rod 10 and the adjusting frame 11. Through the telescopic cylinder 9 is in the removal on the sliding guide 8 realizes the removal about main camera 4, telescopic cylinder 9 is vertical to be set up, through telescopic the expansion and contraction of telescopic cylinder 9's active end realizes the reciprocates of main camera 4. The moving mechanism can be used for realizing the movement of the main camera 4 in the six directions of up, down, front, back, left and right, shooting of printed matters with different specifications, and improving the applicability of the detection device. After the detection is completed, the first rolling roller 5 and the second rolling roller 6 are started to drive the printed matter to leave the detection platform, and the infrared mechanism is further arranged at the output end to further detect the printed matter. And a plurality of different sensors can be arranged at the input end and the output end of the printed matter and used for detecting the shape, the position and the motion state of the object so as to improve the adaptability of the detection equipment to packages of different materials, sizes and shapes.
The foregoing is a further detailed description of the utility model in connection with the preferred embodiments, and it is not intended that the utility model be limited to the specific embodiments described. It will be apparent to those skilled in the art that several simple deductions or substitutions may be made without departing from the spirit of the utility model, and these should be considered to be within the scope of the utility model.
Claims (9)
1. The utility model provides a packing printed matter detection device based on degree of depth study, its characterized in that includes bed frame, is used for carrying transfer table, mount, mobile mechanism of printed matter and is used for collecting the main camera of image, the transfer table is located the top of bed frame, the mount is located the top of transfer table, the bottom of mount connect in the both sides of transfer table, mobile mechanism locates on the mount, main camera is located mobile mechanism, main camera is located the top of transfer table.
2. The deep learning-based packaging printed matter detection device according to claim 1, wherein a plurality of first rolling rollers and a plurality of second rolling rollers are horizontally arranged in the middle of the conveying table, two ends of the first rolling rollers are respectively connected to two sides of the conveying table, two ends of the second rolling rollers are respectively connected to two sides of the conveying table, and the second rolling rollers are arranged between the two first rolling rollers.
3. The deep learning based packaging printed matter detection device of claim 2, wherein a diameter of the first roller is greater than a diameter of the second roller.
4. The deep learning-based packaging printed matter detection device according to claim 1, wherein the moving mechanism comprises two transverse sliding grooves and a sliding guide rail, the two transverse sliding grooves are symmetrically arranged on the inner side of the top of the fixing frame, and two ends of the sliding guide rail are in sliding connection with the two transverse sliding grooves.
5. The deep learning based packaging printed matter detection device of claim 4, wherein an adjusting frame is arranged on the inner side of the top of the fixing frame, an adjusting rod is arranged on the top of the transverse sliding groove, and the transverse sliding groove is locked in the adjusting frame through the adjusting rod.
6. The deep learning based packaging printed matter detection device of claim 4, wherein the moving mechanism further comprises a telescopic cylinder, the telescopic cylinder is slidably connected to the sliding guide rail, and the main camera is arranged at a movable end of the telescopic cylinder.
7. The deep learning based packaging printed matter detection device of claim 1, further comprising two light source mechanisms for providing light sources, wherein the two light source mechanisms are respectively arranged at two sides of the conveying table, and the light source mechanisms are arranged below the fixing frame.
8. The deep learning-based packaging printed matter detection device of claim 7, wherein the light source mechanism comprises a light emitting plate, a mounting frame and a secondary camera, one end of the mounting frame is connected with the conveying table, the light emitting plate is arranged at the other end of the mounting frame, and the secondary camera is arranged on the light emitting plate.
9. The deep learning based packaging printed matter detection device of claim 1, further comprising an infrared mechanism, wherein the infrared mechanism is arranged on two sides of the conveying table and is positioned on front and rear sides of the fixing frame, the infrared mechanism comprises an infrared sensor and a telescopic rod, one end of the telescopic rod is connected with the conveying table, and the infrared sensor is arranged on the other end of the telescopic rod.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202321872795.6U CN220289442U (en) | 2023-07-17 | 2023-07-17 | Packaging printed matter detection device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202321872795.6U CN220289442U (en) | 2023-07-17 | 2023-07-17 | Packaging printed matter detection device based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN220289442U true CN220289442U (en) | 2024-01-02 |
Family
ID=89341535
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202321872795.6U Active CN220289442U (en) | 2023-07-17 | 2023-07-17 | Packaging printed matter detection device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN220289442U (en) |
-
2023
- 2023-07-17 CN CN202321872795.6U patent/CN220289442U/en active Active
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109115785B (en) | Casting polishing quality detection method and device and use method thereof | |
| CN110935644B (en) | Bearing needle roller size detection system and method based on machine vision | |
| CN109374635B (en) | Mask defect detection device and method | |
| CN110246122A (en) | Small size bearing quality determining method, apparatus and system based on machine vision | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN111220544A (en) | Lens quality detection device and detection method | |
| CN110026449B (en) | Online measurement system and method based on machine vision | |
| CN220289442U (en) | Packaging printed matter detection device based on deep learning | |
| CN210863574U (en) | Detection marking equipment for internal flaws of solar crystal column | |
| CN212093316U (en) | Wood defect detection device based on kinect camera | |
| CN210279874U (en) | Lithium ion battery size inspection equipment | |
| KR102230015B1 (en) | Checking apparatus for drum | |
| CN211825732U (en) | Non-contact film pressing backlight panel detection device and backlight panel automatic detection line | |
| CN209247650U (en) | Product quality on-line measuring device | |
| CN114563416A (en) | Method for detecting board surface quality of artificial board | |
| CN205364850U (en) | Take laser marking of CIS scanning to detect and alarm device | |
| CN212301350U (en) | Optical imaging display system for detecting defects of coating on inner wall of steel pipe | |
| CN211785189U (en) | Device for automatically detecting defects and stopping machine | |
| CN211138491U (en) | Automatic register system of calico printing machine | |
| CN209736098U (en) | Flexible detection and analysis system for major surface and internal defects of casting | |
| CN111330869A (en) | Visual detection method and system for on-line grading of lens | |
| CN110646436A (en) | Detection identification equipment for internal flaws of solar crystal column and detection method thereof | |
| CN213580627U (en) | Semi-automatic detection device for rubber sealing ring | |
| CN217451060U (en) | Automatic glass inspection device | |
| CN204479041U (en) | A kind of automatic detection device of keystone-type piston ring tread angle |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant |