CN211877812U - Glass detection device based on deep learning - Google Patents
Glass detection device based on deep learning Download PDFInfo
- Publication number
- CN211877812U CN211877812U CN201922286032.3U CN201922286032U CN211877812U CN 211877812 U CN211877812 U CN 211877812U CN 201922286032 U CN201922286032 U CN 201922286032U CN 211877812 U CN211877812 U CN 211877812U
- Authority
- CN
- China
- Prior art keywords
- glass
- deep learning
- industrial camera
- clamping groove
- roller
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Expired - Fee Related
Links
Images
Landscapes
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The utility model discloses a glass detection device based on degree of depth study, including fixed glass transfer unit and collection image part, fixed glass transfer unit includes the conveyer belt and is used for fixed glass's fixing device, fixing device is including two spinal branch props the iron set up two transparent draw-in groove and light filling lamp and setting on the support iron set are in gyro wheel on the conveyer belt, and set up control button and flexible flat board on the gyro wheel, it is in including matching the setting to gather the image part fixed glass transfer unit's industry camera. According to the method, after the glass to be detected is sent to the image acquisition part through the conveyor belt, the distance between the high-definition camera and the glass is adjusted through the position sensor, and the fact that the industrial camera can extract complete, clear and effective glass information is guaranteed; adopt this application device to replace artifical and traditional detection device, can promote glass degree of automation, improve detection efficiency by a wide margin, reduce the cost of labor.
Description
Technical Field
The utility model relates to a glass detects technical field, in particular to glass detection device based on degree of depth study.
Background
The glass is widely applied to building materials and products thereof by virtue of the advantages of attractiveness, practicability, wind pressure resistance, cold and summer heat resistance, impact property, light transmittance and the like, wherein the glass is used as an appearance core component of various buildings to reflect the decoration style and the whole quality framework of the buildings, and the glass needs to be subjected to defect detection in order to meet the diversified decoration style effect in building decoration implementation. The existing glass detection device has low efficiency, is easy to show wrong detection and missed detection, and is not suitable for popularization and application.
SUMMERY OF THE UTILITY MODEL
The to-be-solved technical problem of the utility model is to provide a glass detection device based on degree of depth study, the device is convenient for improve glass detection efficiency to can reduce the probability of false retrieval, hourglass examining.
In order to solve the technical problem, the utility model discloses a scheme does:
a glass detection device based on deep learning comprises a fixed glass conveying part and an image collecting part, wherein the fixed glass conveying part comprises a conveyor belt and a fixing device for fixing glass, the fixing device comprises two vertical supporting iron rods, a transparent clamping groove and a light supplementing lamp which are arranged on the two supporting iron rods, a roller arranged on the conveying belt, a control button and a telescopic flat plate which are arranged on the roller, the image acquisition component comprises an industrial camera matched with the fixed glass conveying component, an automatic photosensitive light supplement lamp arranged outside the industrial camera, a horizontal slide rail connected above the industrial camera, and a position sensor arranged on the horizontal slide rail, the industrial camera is in communication connection with an external deep learning detection module, and the position sensor is in communication connection with the industrial camera.
The transparent clamping groove is fixed on the supporting iron rod through a knob, the transparent clamping groove is made of transparent materials, and clamping teeth are arranged at the edge of the transparent clamping groove at intervals.
The automatic device is used for adjusting the width of the transparent clamping groove at two sides, and is composed of a control button, a telescopic flat plate and a roller, wherein the roller is provided with a buckle.
The control button is in control connection with the telescopic flat plate and the roller through built-in weak current traction.
The deep learning detection module comprises a deep learning chip, a pre-trained AlexNet network and a set UI interface.
The pre-trained AlexNet network is an Alex-Net network model loaded and pre-trained by using TensorFlow.
The deep learning chip is any one of a GPU chip, an FPGA chip or an ASIC chip.
Compared with the prior art, the beneficial effects of the utility model are that:
in this application, glass that awaits measuring sends into the image acquisition part back through the conveyer belt, adjust high definition camera and glass distance through position sensor, guarantee that the industrial camera can extract completely, it is clear, effectual glass information, gather glass's physical surface information that awaits measuring through high definition camera, and send into the AlexNet network of training in advance, detect glass physical surface defect, through training in earlier stage, the AlexNet network can draw glass physical surface defect information that awaits measuring automatically (including the mar, the spot, the bubble, the definition, defective etc.) and pass through UI interface display with the result, when detecting and passing through, glass quality that awaits measuring is up to standard, glass quality testing accomplishes. Adopt this application device to replace artifical and traditional detection device, can promote glass degree of automation, improve detection efficiency by a wide margin, reduce the cost of labor.
Drawings
Fig. 1 is a schematic structural view of the present invention;
FIG. 2 is a side view of the conveyor belt of the present invention;
fig. 3 is a top view of the glass slot of the present invention.
Detailed Description
The following describes the present invention with reference to the accompanying drawings. It should be noted that the description of the embodiments is provided to help understanding of the present invention, but the present invention is not limited thereto. In addition, the technical features related to the embodiments of the present invention described below may be combined with each other as long as they do not conflict with each other.
As shown in fig. 1-3, a glass detection device based on deep learning comprises a fixed glass transmission part and an image acquisition part, wherein the fixed glass transmission part comprises a conveyor belt 9 and a fixing device for fixing glass, the fixing device comprises two vertical supporting iron rods 4, a transparent clamping groove 5 and a light supplement lamp 6 which are arranged on the two supporting iron rods 4, a roller 10 arranged on the conveyor belt 9, a control button 7 and a telescopic flat plate 8 which are arranged on the roller 10, the image acquisition part comprises an industrial camera 1 which is arranged on the fixed glass transmission part in a matching manner, an automatic photosensitive light supplement lamp 2 which is arranged outside the industrial camera 1, a horizontal slide rail 11 which is connected above the industrial camera 1, and a position sensor 3 which is arranged on the horizontal slide rail 11, the industrial camera 1 is in communication connection with an external deep learning detection module, the position sensor 3 is in communication connection with the industrial camera 1.
The transparent clamping groove 5 is fixed on the supporting iron rod 4 through a knob, the upper width and the lower width of the transparent clamping groove 5 can also be adjusted through the knob, and in the practical application process, the width between the left transparent clamping groove 5 and the right transparent clamping groove 5 is consistent with the height of the transparent clamping groove 5 on the iron rod.
The transparent clamping groove 5 is made of transparent materials, and clamping teeth are arranged at the edge of the transparent clamping groove 5 at intervals. The arrangement can be convenient for ensuring that the surface characteristics of the glass to be measured in the largest area are collected.
The automatic device is characterized by further comprising an automatic device used for adjusting the width of the transparent clamping groove 5 on two sides, the automatic device is composed of a control button 7, a telescopic flat plate 8 and a roller 10, and the roller 10 is provided with a buckle. This setting is mainly in order to satisfy the demand of various glass widths that await measuring, reinforcing glass detection device's practicality.
The control button 7 is in control connection with the telescopic flat plate 8 and the roller 10 through built-in weak current traction. The arrangement is mainly convenient for control, adjustment and fixed positioning. When using, flexible dull and stereotyped 8 can extend and the regulation that shortens when pressing control button 7 for the first time, the gyro wheel 10 that is equipped with the buckle can remove the regulation of controlling support iron set 4 of quickening about can, flexible dull and stereotyped 8 and gyro wheel 10 will be fixed when pressing control button 7 once more to reach and adjust the demand of width in order to adapt to different models glass that awaits measuring about transparent draw-in groove 5.
The deep learning detection module comprises a deep learning chip, a pre-trained AlexNet network and a set UI interface. By means of the pre-trained AlexNet network, the chip GPU can better perform automatic defect identification. Because the image acquisition device is connected with the designed UI interface through the deep learning chip, the UI interface can display input pictures and mark the defect position with a red frame.
The pre-trained AlexNet network is an Alex-Net network model loaded and pre-trained by using TensorFlow. The setting is mainly to analyze and process data through an Alex-Net network, wherein the Alex-Net network comprises a plurality of convolution layers, a pooling layer and a full-connection layer, and information feedback is carried out through a back propagation algorithm to learn and obtain convolution parameters (namely, the Alex-Net network has the capability of identifying defects).
The deep learning chip is any one of a GPU chip, an FPGA chip or an ASIC chip. In the application process, the GPU, the FPGA and the ASIC are all the existing mainstream deep learning chips and can be directly purchased in the market according to requirements.
In this application, glass that awaits measuring sends into the image acquisition part back through conveyer belt 9, adjust high definition camera and glass distance through position sensor 3, guarantee that industrial camera 1 can extract completely, it is clear, effectual glass information, gather glass's physical surface information that awaits measuring through high definition camera, and send into the AlexNet network of training in advance, detect glass physical surface defect, through training in earlier stage, AlexNet network can draw glass physical surface defect information that awaits measuring automatically (including the mar, the spot, the bubble, the definition, defect etc.) and pass through UI interface display with the result, pass through when detecting, the glass quality that awaits measuring is up to standard, glass quality testing accomplishes. Adopt this application device to replace artifical and traditional detection device, can promote glass degree of automation, improve detection efficiency by a wide margin, reduce the cost of labor.
In the present application, the number of the supporting iron rods 4 should be set appropriately according to the width, weight, and length of the glass to be measured. At the same time. In order to facilitate automatic ejection, the root of the supporting iron rod 4 for fixing the glass conveying belt component is provided with a contraction spring, when the supporting iron rod 4 starts from a starting point, the automatic ejection is vertical to the conveying belt 9, and when the supporting iron rod is conveyed to an end point, the supporting iron rod can be contracted and horizontally placed on the conveying belt to finish the operation of the whole conveying belt.
Make high definition camera 1 reciprocate through horizontal slide rail 11, guarantee that industrial camera 1 can the clear glass picture of shooing different sizes. The horizontal sliding rail 11 is provided with a position sensor, and the lower side of the horizontal sliding rail is mainly used for fixing the industrial camera 1 to finish image acquisition and fixing the position sensor to finish the adjustment of the distance between the industrial camera and the glass to be measured.
An automatic photosensitive light supplement lamp 2 is arranged on the outer side of the lens of the industrial camera 1, so that the illumination brightness can be adjusted automatically in real time; conveyer belt 9 is in buckle gyro wheel below, and the conveyer belt width needs satisfy the maximum width of glass that awaits measuring on the market.
In the present application, the glass surface defects to be measured include: scratch-like defects, spot-like defects (surface spots, built-in bubbles), defects (corner defects), point defects (black spots, defects, stains), sharpness (turbidity, blurring);
the application is in the detection of the physical surface of the glass: and the image acquisition part acquires a clear image to be detected, then carries out image processing based on deep learning, and marks the defect position according to the difference between the defect position of the image and the normal image.
The embodiments of the present invention have been described in detail with reference to the accompanying drawings, but the present invention is not limited to the described embodiments. It will be apparent to those skilled in the art that various changes, modifications, substitutions and alterations can be made in the embodiments without departing from the principles and spirit of the invention, and the scope of the invention is to be accorded the full scope of the claims.
Claims (7)
1. The utility model provides a glass detection device based on degree of deep learning which characterized in that: the device comprises a fixed glass conveying part and an image collecting part, wherein the fixed glass conveying part comprises a conveying belt (9) and a fixing device used for fixing glass, the fixing device comprises two vertical supporting iron rods (4), a transparent clamping groove (5) and a light supplement lamp (6) which are arranged on the two supporting iron rods (4), a roller (10) arranged on the conveying belt (9), a control button (7) and a telescopic flat plate (8) which are arranged on the roller (10), the image collecting part comprises an industrial camera (1) which is arranged on the fixed glass conveying part in a matching manner, an automatic photosensitive light supplement lamp (2) arranged on the outer side of the industrial camera (1), a horizontal sliding rail (11) connected above the industrial camera (1) and a position sensor (3) arranged on the horizontal sliding rail (11), the industrial camera (1) is in communication connection with an external deep learning detection module, and the position sensor (3) is in communication connection with the industrial camera (1).
2. The deep learning based glass inspection device of claim 1, wherein: the transparent clamping groove (5) is fixed on the supporting iron rod (4) through a knob, the transparent clamping groove (5) is made of transparent materials, and clamping teeth are arranged at the edge of the transparent clamping groove (5) at intervals.
3. The deep learning based glass inspection device of any of claims 1-2, wherein: the automatic device is characterized by further comprising an automatic device used for adjusting the width of the transparent clamping groove (5) at two sides, the automatic device is composed of a control button (7), a telescopic flat plate (8) and a roller (10), and the roller (10) is provided with a buckle.
4. The deep learning based glass inspection device of claim 1, wherein: the control button (7) is in control connection with the telescopic flat plate (8) and the roller (10) through built-in weak current traction.
5. The deep learning based glass inspection device of claim 1, wherein: the deep learning detection module comprises a deep learning chip, a pre-trained AlexNet network and a set UI interface.
6. The deep learning based glass inspection device of claim 5, wherein: the pre-trained AlexNet network is an Alex-Net network model loaded and pre-trained by using TensorFlow.
7. The deep learning based glass inspection device of claim 5, wherein: the deep learning chip is any one of a GPU chip, an FPGA chip or an ASIC chip.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201922286032.3U CN211877812U (en) | 2019-12-18 | 2019-12-18 | Glass detection device based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201922286032.3U CN211877812U (en) | 2019-12-18 | 2019-12-18 | Glass detection device based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN211877812U true CN211877812U (en) | 2020-11-06 |
Family
ID=73243659
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201922286032.3U Expired - Fee Related CN211877812U (en) | 2019-12-18 | 2019-12-18 | Glass detection device based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN211877812U (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113218946A (en) * | 2021-05-07 | 2021-08-06 | 宁波市芯能微电子科技有限公司 | Chip LED quantity automatic detection system |
-
2019
- 2019-12-18 CN CN201922286032.3U patent/CN211877812U/en not_active Expired - Fee Related
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113218946A (en) * | 2021-05-07 | 2021-08-06 | 宁波市芯能微电子科技有限公司 | Chip LED quantity automatic detection system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105259189B (en) | The defect imaging system and method for glass | |
| CN103323457B (en) | Fruit appearance defect real-time online detection system and detection method | |
| CN109191520B (en) | Plant leaf area measuring method and system based on color calibration | |
| CN104360501A (en) | Visual detection method and device for defects of liquid crystal display screen | |
| CN107657639A (en) | A kind of method and apparatus of quickly positioning target | |
| CN106093068A (en) | The imaging system of lithium battery pole slice surface defect detection apparatus and using method thereof | |
| CN103698341B (en) | A kind of quality of roll for cotton detection system and quality of roll for cotton image detecting method | |
| CN204924983U (en) | Lens defect automatic checkout device of grating modulation | |
| CN104777172B (en) | A kind of quick, intelligent detection device of optical lens substandard products and method | |
| CN110017899B (en) | Apparatus for complex surface color detection system | |
| CN109807076A (en) | Double-coated pressure-sensitive glue automatic optical detection method and its equipment | |
| CN211877812U (en) | Glass detection device based on deep learning | |
| CN208207914U (en) | PCB surface defect detecting device based on fast geometric alignment | |
| CN108120353B (en) | Fire transmission hole detection device and method based on intelligent camera | |
| CN106803410A (en) | LED display module testing equipment | |
| CN109668832A (en) | Cellular li-ion battery surface bulge detection device and its method based on subregion light source | |
| CN205656146U (en) | Arm -type switch appearance imperfections check out test set of machinery | |
| CN106529365A (en) | Automatic pricing machine | |
| CN104992446A (en) | Nonlinear illumination adaptive image splicing method and implementing system thereof | |
| CN103760166A (en) | Flue-cured tobacco appearance information collecting device | |
| CN203672794U (en) | Flue-cured tobacco appearance information acquisition device | |
| CN111458345A (en) | Visual detection mechanism for defects of mask | |
| CN106000903B (en) | A kind of non-contact detection system and method for being used to detect loom cloth gripper edge gap | |
| CN103091332B (en) | Detection method and detection system of U-shaped powder pipe based on machine vision | |
| CN111624793B (en) | LCD display module AOI equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20201106 Termination date: 20211218 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |