CN109598712A - Quality determining method, device, server and the storage medium of plastic foam cutlery box - Google Patents
Quality determining method, device, server and the storage medium of plastic foam cutlery box Download PDFInfo
- Publication number
- CN109598712A CN109598712A CN201811456293.9A CN201811456293A CN109598712A CN 109598712 A CN109598712 A CN 109598712A CN 201811456293 A CN201811456293 A CN 201811456293A CN 109598712 A CN109598712 A CN 109598712A
- Authority
- CN
- China
- Prior art keywords
- detection
- classification
- quality
- server
- lunch box
- 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
- 239000002984 plastic foam Substances 0.000 title claims abstract description 112
- 238000000034 method Methods 0.000 title claims abstract description 47
- 238000003860 storage Methods 0.000 title claims abstract description 21
- 238000001514 detection method Methods 0.000 claims abstract description 347
- 239000006260 foam Substances 0.000 claims abstract description 15
- 238000012372 quality testing Methods 0.000 claims abstract description 8
- 230000007547 defect Effects 0.000 claims description 68
- 238000007689 inspection Methods 0.000 claims description 41
- 238000013527 convolutional neural network Methods 0.000 claims description 26
- 238000012545 processing Methods 0.000 claims description 22
- 238000011176 pooling Methods 0.000 claims description 14
- 239000004033 plastic Substances 0.000 claims description 11
- 229920003023 plastic Polymers 0.000 claims description 11
- 238000006243 chemical reaction Methods 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 229910000831 Steel Inorganic materials 0.000 claims description 6
- 238000013507 mapping Methods 0.000 claims description 6
- 230000009467 reduction Effects 0.000 claims description 6
- 239000010959 steel Substances 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 3
- 238000013215 result calculation Methods 0.000 claims description 2
- 235000013305 food Nutrition 0.000 claims 2
- 238000005259 measurement Methods 0.000 abstract 1
- 238000004519 manufacturing process Methods 0.000 description 17
- 238000010586 diagram Methods 0.000 description 13
- 235000012054 meals Nutrition 0.000 description 7
- 238000003066 decision tree Methods 0.000 description 6
- 230000003287 optical effect Effects 0.000 description 6
- 230000006870 function Effects 0.000 description 5
- 238000000605 extraction Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000014509 gene expression Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 238000009776 industrial production Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 239000013307 optical fiber Substances 0.000 description 2
- 230000002093 peripheral effect Effects 0.000 description 2
- 230000000644 propagated effect Effects 0.000 description 2
- 238000007637 random forest analysis Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000002411 adverse Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000009412 basement excavation Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 235000013410 fast food Nutrition 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 231100000053 low toxicity Toxicity 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000002844 melting Methods 0.000 description 1
- 230000008018 melting Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 235000011888 snacks Nutrition 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 239000002023 wood Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8854—Grading and classifying of flaws
-
- 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
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Data Mining & Analysis (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Artificial Intelligence (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Computational Biology (AREA)
- Analytical Chemistry (AREA)
- Pathology (AREA)
- Immunology (AREA)
- Biochemistry (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Chemical & Material Sciences (AREA)
- Evolutionary Biology (AREA)
- Quality & Reliability (AREA)
- Signal Processing (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
Abstract
The embodiment of the invention discloses quality determining method, device, server and the storage mediums of a kind of plastic foam cutlery box.The described method includes: obtaining the image data of plastic foam cutlery box to be detected；The image data of the foam cutlery box to be detected is converted to the quality testing request of the plastic foam cutlery box to be detected；Quality testing request is sent to the server for being deployed with the model of the classification and Detection based on object detection；It receives the server and corresponding quality measurements is requested by the quality testing classification of the classification and Detection model output based on object detection.The detection efficiency of plastic foam cutlery box can be not only reduced, but also the detection accuracy of plastic foam cutlery box can be improved.
Description
Technical Field
The embodiment of the invention relates to the technical field of artificial intelligence, in particular to a quality detection method and device for a plastic foam lunch box, a server and a storage medium.
Background
In the production process of the traditional manufacturing industry, quality inspection is a key link in the production flow. Specifically, in the production process of the plastic foam lunch box, an important means for detecting the quality of the plastic foam lunch box is to detect the surface state of the plastic foam lunch box so as to judge whether the plastic foam lunch box has flaws or defects, and perform corresponding processing on the plastic foam lunch box according to the detection result. The existing detection method of the plastic foam lunch box comprises the following two methods: the first mode is a pure human working medium detection mode, depending on the experience of quality testing personnel, the quality testing personnel visually observe the appearance picture of the product and then judge according to the experience; the second mode is a machine-assisted semi-automatic quality inspection mode, which mainly filters out photos without defects by a quality inspection system with certain judgment capability, and then detects and judges the photos suspected to have defects by quality inspectors.
However, both the first quality inspection method and the second quality inspection method involve manual quality inspection processes, which require quality inspectors to perform inspection on a production site, and manually record defects and perform subsequent processing. The method has low efficiency, is easy to miss judgment and misjudge, is difficult to carry out secondary utilization and excavation on data, and has adverse effects on the health and safety of quality testing personnel or production personnel due to severe industrial production environment. For the second quality detection mode, because the quality detection system is developed based on the quality detection system of the traditional expert system or the characteristic engineering, the detection judgment rules are solidified into the machine based on experience, and iteration is difficult to follow the development of business, so that the detection precision of the quality detection system is lower and lower along with the development of the production process, and even the detection precision is reduced to a completely unavailable state. In addition, the detection and judgment rules of the traditional quality inspection system are all pre-solidified in hardware by a third-party supplier, and the upgrading process not only needs to carry out great modification on a production line, but also is expensive. The traditional quality inspection system has obvious defects in the aspects of safety, standardization, expandability and the like, and is not beneficial to the optimization and upgrading of the traditional industrial production line.
Disclosure of Invention
In view of this, embodiments of the present invention provide a method, an apparatus, a server and a storage medium for detecting the quality of a plastic foam meal box, which can not only reduce the detection efficiency of the plastic foam meal box, but also improve the detection accuracy of the plastic foam meal box.
In a first aspect, an embodiment of the present invention provides a method for detecting quality of a plastic foam lunch box, where the method includes:
acquiring image data of a plastic foam lunch box to be detected;
converting the image data of the to-be-detected foam lunch box into a quality detection request of the to-be-detected plastic foam lunch box;
sending the quality detection request to a server deployed with a classification detection model based on object detection;
and receiving a quality detection result corresponding to the quality detection classification request output by the server through the classification detection model based on the object detection.
In the above embodiment, the sending the quality detection request to a server deployed with a classification detection model based on object detection includes:
acquiring the load state of each server deployed with the classification detection model based on the object detection in a preset server configuration table;
and sending the quality detection request to a server with the minimum load, wherein the server is deployed with the classification detection model based on the object detection, according to the load state of each server deployed with the classification detection model.
In the above embodiment, the method further comprises:
according to a preset corresponding relation between a quality detection result and a defect processing operation, performing the defect processing operation corresponding to the quality detection result; wherein the defect handling operation comprises: alarm, shut down, store log or control the robotic arm.
In a second aspect, an embodiment of the present invention provides another method for detecting the quality of a blister lunch box, where the method includes:
receiving a quality detection request of the plastic foam lunch box to be detected;
and calculating a quality detection result corresponding to the quality detection request through a pre-trained classification detection model based on object detection.
In the above embodiment, the classification detection model based on object detection includes: a deep convolutional neural network and a defect location classification network; the deep convolutional neural network is used for extracting the characteristics of the steel plate picture and inputting the characteristics into the defect positioning classification network; the defect positioning classification network is used for judging whether the features extracted by the deep convolutional neural network have defects or not based on a classification detection algorithm of object detection and obtaining the category of the defects.
In the above embodiment, the deep convolutional neural network includes: a convolutional layer, a pooling layer, and a full-link layer; the convolution layer is used for scanning and convolving the image of the to-be-detected plastic foam lunch box in the quality detection request by utilizing convolution cores with different weights, extracting various meaningful features from the image, and outputting the features to a feature map; the pooling layer is used for performing dimension reduction operation on the feature map; and the full connection layer is used for mapping the extracted features to the defect positioning and classifying network.
In a third aspect, an embodiment of the present invention provides a device for detecting quality of a plastic foam lunch box, where the device includes: the system comprises an image acquisition module, an image conversion module, a request sending module and a result receiving module; wherein,
the image acquisition module is used for acquiring image data of the plastic foam lunch box to be detected;
the image conversion module is used for converting the image data of the to-be-detected foamed lunch box into a quality detection request of the to-be-detected plastic foamed lunch box;
the request sending module is used for sending the quality detection request to a server which is provided with a classification detection model based on object detection;
and the result receiving module is used for receiving a quality detection result corresponding to the quality detection classification request output by the server through the classification detection model based on the object detection.
In the foregoing embodiment, the request sending module is specifically configured to obtain, in a preset server configuration table, a load state of each server on which the classification detection model based on object detection is deployed; and sending the quality detection request to a server with the minimum load, wherein the server is deployed with the classification detection model based on the object detection, according to the load state of each server deployed with the classification detection model.
In the above embodiment, the apparatus further includes: the operation processing module is used for making a defect processing operation corresponding to the quality detection result according to the preset corresponding relation between the quality detection result and the defect processing operation; wherein the defect handling operation comprises: alarm, shut down, store log or control the robotic arm.
In a fourth aspect, an embodiment of the present invention provides another apparatus for detecting the quality of a blister lunch box, where the apparatus includes: the device comprises a request receiving module and a result calculating module; wherein,
the request receiving module is used for receiving a quality detection request of the to-be-detected plastic foam lunch box;
and the result calculation module is used for calculating a quality detection result corresponding to the quality detection request through a pre-trained classification detection model based on object detection.
In the above embodiment, the classification detection model based on object detection includes: a deep convolutional neural network and a defect location classification network; the deep convolutional neural network is used for extracting the characteristics of the steel plate picture and inputting the characteristics into the defect positioning classification network; the defect positioning classification network is used for judging whether the features extracted by the deep convolutional neural network have defects or not based on a classification detection algorithm of object detection and obtaining the category of the defects.
In the above embodiment, the deep convolutional neural network includes: a convolutional layer, a pooling layer, and a full-link layer; the convolution layer is used for scanning and convolving the image of the to-be-detected plastic foam lunch box in the quality detection request by utilizing convolution cores with different weights, extracting various meaningful features from the image, and outputting the features to a feature map; the pooling layer is used for performing dimension reduction operation on the feature map; and the full connection layer is used for mapping the extracted features to the defect positioning and classifying network.
In a fifth aspect, an embodiment of the present invention provides a server, including:
one or more processors;
a memory for storing one or more programs,
when the one or more programs are executed by the one or more processors, the one or more processors implement the method for detecting the quality of the blister lunch box according to any embodiment of the invention.
In a sixth aspect, the present invention provides a storage medium, on which a computer program is stored, wherein the program, when executed by a processor, implements the method for detecting the quality of the blister lunch box according to any embodiment of the present invention.
According to the quality detection method, the quality detection device, the quality detection server and the quality detection storage medium for the plastic foam lunch box, image data of the plastic foam lunch box to be detected are obtained firstly; then converting the image data of the foam lunch box to be detected into a quality detection request of the plastic foam lunch box to be detected; then sending the quality detection request to a server which is provided with a classification detection model based on object detection; the server calculates a quality detection result corresponding to the quality detection request through a classification detection model which is trained in advance and is based on object detection. That is, in the technical solution of the present invention, the server performs quality inspection on the plastic foam lunch box to be inspected through a classification inspection model based on object inspection trained in advance. In the two existing quality detection methods for the plastic foam lunch box, the first mode is a pure human working medium detection mode, depending on the experience of quality inspectors, the quality inspectors visually observe the appearance photos of the product and then judge according to the experience; the second mode is a machine-assisted semi-automatic quality inspection mode, which mainly filters out photos without defects by a quality inspection system with certain judgment capability, and then detects and judges the photos suspected to have defects by quality inspectors. Therefore, compared with the prior art, the quality detection method, the device, the server and the storage medium for the plastic foam meal box provided by the embodiment of the invention can not only reduce the detection efficiency of the plastic foam meal box, but also improve the detection accuracy of the plastic foam meal box; moreover, the technical scheme of the embodiment of the invention is simple and convenient to realize, convenient to popularize and wider in application range.
Drawings
FIG. 1 is a schematic flow chart of a method for inspecting the quality of a plastic foam meal box according to an embodiment of the present invention;
FIG. 2 is a schematic flow chart of a method for inspecting the quality of a foamed plastic lunch box according to the second embodiment of the present invention;
FIG. 3 is a schematic flow chart of a method for inspecting the quality of a foamed plastic lunch box according to a third embodiment of the present invention;
fig. 4 is a schematic diagram of a classification detection model based on object detection according to a third embodiment of the present invention;
fig. 5 is a schematic diagram of a deep convolutional neural network according to a third embodiment of the present invention;
fig. 6 is a schematic structural diagram of a detection system according to a third embodiment of the present invention;
FIG. 7 is a schematic structural diagram of a quality detection device for a FOUP provided in the fourth embodiment of the present invention;
FIG. 8 is a schematic structural diagram of a quality detection device for a FOUP provided in the fifth embodiment of the present invention;
fig. 9 is a schematic structural diagram of a server according to a sixth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some but not all of the relevant aspects of the present invention are shown in the drawings.
In the prior art, disposable fast food boxes are gradually changed from foam lunch boxes to environment-friendly lunch boxes, the original paper foam lunch boxes are eliminated due to the fact that the original paper foam lunch boxes are not resistant to high temperature and damage to the environment is caused in the manufacturing process, and plastic lunch boxes, paper lunch boxes, wood lunch boxes, degradable lunch boxes and the like are taken out. Among them, plastics have the characteristics of low toxicity, high melting point, strong plasticity, simple and convenient production, low relative cost and the like, so that the plastics become the mainstream materials for manufacturing disposable snack boxes. The embodiment of the invention provides a quality detection method of a plastic foam lunch box, which is used for carrying out quality detection on the surface state of the plastic foam lunch box based on a classification detection model of object detection. The method for inspecting the quality of the plastic foam lunch box based on the object inspection will be described in detail.
Example one
Fig. 1 is a flowchart of a method for detecting the quality of a blister lunch box according to an embodiment of the present invention, where the method can be executed by a device or a server for detecting the quality of a blister lunch box, where the device or the server can be implemented by software and/or hardware, and the device or the server can be integrated in any intelligent device with a network communication function. As shown in fig. 1, the method for inspecting the quality of the plastic foam lunch box can comprise the following steps:
s101, acquiring image data of the plastic foam lunch box to be detected.
In the embodiment of the invention, when the surface state of the plastic foam lunch box is subjected to quality detection, the image data of the plastic foam lunch box to be detected can be acquired through the equipment such as a camera. Because the output of plastic foam cutlery box in process of production is great, and the cost is lower, and reproducibility is stronger, consequently, when acquireing the image data of the plastic foam cutlery box that detects, can acquire the image data of the plastic foam cutlery box that detects according to preset's collection cycle. This can reduce the computational effort of the server based on the classification detection model for object detection.
S102, converting the image data of the to-be-detected foam lunch box into a quality detection request of the to-be-detected plastic foam lunch box.
In the embodiment of the invention, when the surface state of the plastic foam lunch box is subjected to quality detection, after the equipment such as a camera acquires the image data of the plastic foam lunch box to be detected, the image data of the plastic foam lunch box to be detected can be converted into the quality detection request of the plastic foam lunch box to be detected. Specifically, the image data of the foamed lunch box to be detected can be converted into the quality detection request of the plastic foamed lunch box to be detected according to a predetermined conversion format. For example, the quality inspection request for the blister lunch box to be inspected may include: quality detection commands and image data of the foam lunch box to be detected.
S103, sending the quality detection request to a server deployed with a classification detection model based on object detection.
In a specific embodiment of the present invention, before sending the quality detection request, the deployment condition of the detection model may be monitored, and the quality detection request may be sent to a server deployed with a classification detection model based on object detection according to the deployment condition of the detection model.
And S104, receiving a quality detection result corresponding to the quality detection classification request output by the server through the classification detection model based on the object detection.
In an embodiment of the present invention, the server deployed with the classification detection model based on object detection may calculate the quality detection result corresponding to the quality detection request through a pre-trained classification detection model based on object detection. Therefore, in this step, a quality detection result corresponding to the quality detection classification request output by the server through the classification detection model based on the object detection may be received.
The quality detection method of the plastic foam lunch box provided by the embodiment of the invention comprises the steps of firstly obtaining image data of the plastic foam lunch box to be detected; then converting the image data of the foam lunch box to be detected into a quality detection request of the plastic foam lunch box to be detected; then sending the quality detection request to a server which is provided with a classification detection model based on object detection; the server calculates a quality detection result corresponding to the quality detection request through a classification detection model which is trained in advance and is based on object detection. That is, in the technical solution of the present invention, the server performs quality inspection on the plastic foam lunch box to be inspected through a classification inspection model based on object inspection trained in advance. In the two existing quality detection methods for the plastic foam lunch box, the first mode is a pure human working medium detection mode, depending on the experience of quality inspectors, the quality inspectors visually observe the appearance photos of the product and then judge according to the experience; the second mode is a machine-assisted semi-automatic quality inspection mode, which mainly filters out photos without defects by a quality inspection system with certain judgment capability, and then detects and judges the photos suspected to have defects by quality inspectors. Therefore, compared with the prior art, the quality detection method of the plastic foam lunch box provided by the embodiment of the invention can not only reduce the detection efficiency of the plastic foam lunch box, but also improve the detection accuracy of the plastic foam lunch box; moreover, the technical scheme of the embodiment of the invention is simple and convenient to realize, convenient to popularize and wider in application range.
Example two
Fig. 2 is a schematic flow chart of a quality detection method for a plastic foam lunch box according to the second embodiment of the invention. As shown in fig. 2, the method for inspecting the quality of the plastic foam lunch box may include the following steps:
s201, acquiring image data of the plastic foam lunch box to be detected.
In the embodiment of the invention, when the surface state of the plastic foam lunch box is subjected to quality detection, the image data of the plastic foam lunch box to be detected can be acquired through the equipment such as a camera.
S202, converting the image data of the foam lunch box to be detected into a quality detection request of the plastic foam lunch box to be detected.
In the embodiment of the invention, when the surface state of the plastic foam lunch box is subjected to quality detection, after the equipment such as a camera acquires the image data of the plastic foam lunch box to be detected, the image data of the plastic foam lunch box to be detected can be converted into the quality detection request of the plastic foam lunch box to be detected. Specifically, the image data of the foamed lunch box to be detected can be converted into the quality detection request of the plastic foamed lunch box to be detected according to a predetermined conversion format. For example, the quality inspection request for the blister lunch box to be inspected may include: quality detection commands and image data of the foam lunch box to be detected.
And S203, acquiring the load state of each server deployed with the classification detection model based on the object detection in a preset server configuration table.
In the specific embodiment of the present invention, before the quality inspection request is sent, the deployment condition of the inspection model may be monitored, and the deployment condition of the inspection model in each server may be recorded in a preset server configuration table.
And S204, sending the quality detection request to the server with the minimum load, wherein the server is provided with the classification detection model based on the object detection, according to the load state of each server provided with the classification detection model.
In a specific embodiment of the present invention, after the load state of each server deployed with the classification detection model based on object detection is acquired in a preset server configuration table, according to the load state of each server deployed with the classification detection model, a quality detection request is sent to the server deployed with the minimum load of the classification detection model based on object detection, so as to implement balanced scheduling and improve the system operation speed.
S205, receiving a quality detection result corresponding to the quality detection classification request output by the server through the classification detection model based on the object detection.
In an embodiment of the present invention, the server deployed with the classification detection model based on object detection may calculate the quality detection result corresponding to the quality detection request through a pre-trained classification detection model based on object detection. Therefore, in this step, a quality detection result corresponding to the quality detection classification request output by the server through the classification detection model based on the object detection may be received.
Preferably, in the embodiment of the present invention, the defect processing operation corresponding to the quality detection result may also be performed according to a preset correspondence between the quality detection result and the defect processing operation; wherein the defect handling operation comprises: alarm, shut down, store log or control the robotic arm.
The quality detection method of the plastic foam lunch box provided by the embodiment of the invention comprises the steps of firstly obtaining image data of the plastic foam lunch box to be detected; then converting the image data of the foam lunch box to be detected into a quality detection request of the plastic foam lunch box to be detected; then sending the quality detection request to a server which is provided with a classification detection model based on object detection; the server calculates a quality detection result corresponding to the quality detection request through a classification detection model which is trained in advance and is based on object detection. That is, in the technical solution of the present invention, the server performs quality inspection on the plastic foam lunch box to be inspected through a classification inspection model based on object inspection trained in advance. In the two existing quality detection methods for the plastic foam lunch box, the first mode is a pure human working medium detection mode, depending on the experience of quality inspectors, the quality inspectors visually observe the appearance photos of the product and then judge according to the experience; the second mode is a machine-assisted semi-automatic quality inspection mode, which mainly filters out photos without defects by a quality inspection system with certain judgment capability, and then detects and judges the photos suspected to have defects by quality inspectors. Therefore, compared with the prior art, the quality detection method of the plastic foam lunch box provided by the embodiment of the invention can not only reduce the detection efficiency of the plastic foam lunch box, but also improve the detection accuracy of the plastic foam lunch box; moreover, the technical scheme of the embodiment of the invention is simple and convenient to realize, convenient to popularize and wider in application range.
EXAMPLE III
Fig. 3 is a schematic flow chart of a quality detection method for a plastic foam lunch box according to a third embodiment of the invention. As shown in fig. 3, the method for inspecting the quality of the plastic foam lunch box may include the following steps:
s301, receiving a quality detection request of the plastic foam lunch box to be detected.
In the embodiment of the invention, when the surface state of the plastic foam lunch box is subjected to quality detection, after the equipment such as a camera acquires the image data of the plastic foam lunch box to be detected, the image data of the plastic foam lunch box to be detected can be converted into the quality detection request of the plastic foam lunch box to be detected. Specifically, the image data of the foamed lunch box to be detected can be converted into the quality detection request of the plastic foamed lunch box to be detected according to a predetermined conversion format. For example, the quality inspection request for the blister lunch box to be inspected may include: quality detection commands and image data of the foam lunch box to be detected. Therefore, in this step, a quality inspection request for the blister lunch box to be inspected can be received.
S302, calculating a quality detection result corresponding to the quality detection request through a classification detection model which is trained in advance and is based on object detection.
In an embodiment of the present invention, the server deployed with the classification detection model based on object detection may calculate the quality detection result corresponding to the quality detection request through a pre-trained classification detection model based on object detection.
Fig. 4 is a schematic diagram of a classification detection model based on object detection according to a third embodiment of the present invention. As shown in fig. 4, the classification detection model based on object detection includes: a deep convolutional neural network and a defect location classification network; the deep convolutional neural network is used for extracting the characteristics of the steel plate picture and inputting the characteristics into the defect positioning classification network; the defect positioning classification network is used for judging whether the features extracted by the deep convolutional neural network have defects or not based on a classification detection algorithm of object detection and obtaining the category of the defects.
The detection algorithm generally comprises three parts, namely selection of a detection window, design of features, and design of a classifier. Firstly, selection of a detection window: taking the example of face detection, when a picture is given, the position of the face and the size of the face need to be framed, and the simplest method is to violently search candidate frames and traverse all possible positions of the frames in the picture from left to right and from top to bottom once. And an image pyramid is obtained by scaling the size of a group of images to perform multi-scale search. However, this method is often computationally intensive and inefficient and is not desirable in practical applications. The human face has strong prior knowledge, for example, a human face skin color space presents compact Gaussian distribution, a large part of candidate regions can be removed through skin color detection, and only a tiny part of regions are left to serve as a human face detection search range. Because the extraction of the skin color is very fast, each pixel is judged once only by utilizing some color distribution information, and the overall speed is greatly improved. However, the skin color extraction only uses simple color priors, and if a table which is very similar to the skin color, such as yellow, is encountered, the skin color extraction is likely to be misjudged as a candidate detection area of the human face. Secondly, designing the characteristics: in the traditional detection, Haar can express various edge change information of an object due to high extraction speed, and can be rapidly calculated by utilizing an integral graph to obtain wide application; LBP expresses more texture information of the object, and has good adaptability to uniformly changed illumination; HOG encodes the edge of an object by using histogram statistics, has stronger feature expression capability and is widely applied to object detection, tracking and identification. The traditional feature design is often driven by experience of researchers, the updating period is often long, the object can be described from different dimensions by combining and optimizing different features, and the detection precision can be further improved, for example, ACF detection is combined with 20 different feature expressions. Thirdly, designing a classifier: conventional classifiers include Adaboost, SVM, Decision Tree, and the like. (1) Adaboost: a weak classifier is usually low in judgment precision, and the weak classifiers with high classification precision are adaptively selected and weighted through Adaboost, so that the detection performance is improved. For example, in the face detection, a candidate window needs to determine whether the candidate window is a face, where some weak classifiers are color histogram components, and if the yellow component is greater than 100, the candidate window may be considered as a candidate region of the face, which is a very simple weak classifier. However, the decision of a single classifier that is so weak is not accurate, and then it is necessary to introduce additional components to assist. For example, the red component is introduced to be larger than 150, and several conditions are superposed to form a stronger classifier. (2) SVM classifier: the SVM obtains a support vector of a classification plane by maximizing a classification interval, has good classification precision on a linearly separable small data set, and maps a low dimension to a high dimension by introducing a kernel function, so that the SVM is linearly separable and is widely used in a detection scene. (3) Decision tree: a Decision Tree (Decision Tree) is a Tree structure in which each internal node represents a test on an attribute, each branch represents a test output, and each leaf node represents a category. Taking binary tree as an example, if there are two classifications from the root of the tree, we need to distinguish whether it is a face or a non-face, the left is a non-face, and the right is a face. When the I enters the first binary tree classifier node for judgment, if the I is a non-face, the result is directly output, and if the I is a face candidate, the I enters the next layer for further classification. And (4) constructing a decision tree by learning the classifier of each node, and finally forming a strong classifier. (4) Random forest: ensemble is carried out on the decision tree, and random forests are combined to better improve the classification or regression precision.
Fig. 5 is a schematic diagram of a deep convolutional neural network according to a third embodiment of the present invention. As shown in fig. 5, the deep convolutional neural network includes: a convolutional layer, a pooling layer, and a full-link layer; the convolution layer is used for scanning and convolving the image of the to-be-detected plastic foam lunch box in the quality detection request by utilizing convolution checks with different weights, extracting various meaningful features from the image and outputting the features to the feature map; the pooling layer is used for performing dimension reduction operation on the feature map; and the full connection layer is used for mapping the extracted features to the defect positioning classification network. The deep neural network model with convolution and pooling operations can have higher robustness on deformation, blurring, illumination change and the like of images on a production line and have higher generalization performance on classification tasks. And the full connection layer maps the extracted features to a defect positioning classification network. For the characteristics of different production scenes and data, a deep neural network model formed by different depths, different numbers of neurons and different convolution pooling organization modes can be designed, and then the model is trained by adopting marked historical data and adopting a mode of signal forward propagation and error backward propagation. And when the error value between the output of the model and the label is smaller than a preset threshold value meeting the service requirement, stopping training.
Fig. 6 is a schematic structural diagram of a detection system according to a third embodiment of the present invention. As shown in fig. 6, in the implementation, a camera can be used to collect image data of the plastic foam lunch box to be detected, and send the image data to a console and a production database; and after receiving the image data of the plastic foam lunch box to be detected, the console sends the quality detection request to the server with the minimum load, in which the classification detection model based on the object detection is deployed, according to the load state of each server in which the classification detection model based on the object detection is deployed. And after the calculation of a server which is provided with a classification detection model based on object detection, outputting a quality detection result and sending the quality detection result to a controller. And the controller controls the alarm to give an alarm according to the quality detection result and stores the quality detection log into a production database. Then, an update operation is performed on the detection model, and the detection model can be updated by updating the data in the production database into the training database and then executing the method provided by the embodiment of the invention by the training engine.
The quality detection method of the plastic foam lunch box provided by the embodiment of the invention comprises the steps of firstly obtaining image data of the plastic foam lunch box to be detected; then converting the image data of the foam lunch box to be detected into a quality detection request of the plastic foam lunch box to be detected; then sending the quality detection request to a server which is provided with a classification detection model based on object detection; the server calculates a quality detection result corresponding to the quality detection request through a classification detection model which is trained in advance and is based on object detection. That is, in the technical solution of the present invention, the server performs quality inspection on the plastic foam lunch box to be inspected through a classification inspection model based on object inspection trained in advance. In the two existing quality detection methods for the plastic foam lunch box, the first mode is a pure human working medium detection mode, depending on the experience of quality inspectors, the quality inspectors visually observe the appearance photos of the product and then judge according to the experience; the second mode is a machine-assisted semi-automatic quality inspection mode, which mainly filters out photos without defects by a quality inspection system with certain judgment capability, and then detects and judges the photos suspected to have defects by quality inspectors. Therefore, compared with the prior art, the quality detection method of the plastic foam lunch box provided by the embodiment of the invention can not only reduce the detection efficiency of the plastic foam lunch box, but also improve the detection accuracy of the plastic foam lunch box; moreover, the technical scheme of the embodiment of the invention is simple and convenient to realize, convenient to popularize and wider in application range.
Example four
Fig. 7 is a schematic structural diagram of a quality detection device for a plastic foam lunch box according to a fourth embodiment of the invention. As shown in fig. 7, the apparatus for inspecting the quality of the plastic foam lunch box according to the embodiment of the invention may include: an image acquisition module 701, an image conversion module 702, a request sending module 703 and a result receiving module 704; wherein,
the image acquisition module 701 is used for acquiring image data of the plastic foam lunch box to be detected;
the image conversion module 702 is configured to convert the image data of the to-be-detected foamed lunch box into a quality detection request of the to-be-detected plastic foamed lunch box;
the request sending module 703 is configured to send the quality detection request to a server deployed with a classification detection model based on object detection;
the result receiving module 704 is configured to receive a quality detection result corresponding to the quality detection classification request output by the server through the object detection-based classification detection model.
Further, the request sending module 703 is specifically configured to obtain, in a preset server configuration table, a load state of each server on which the classification detection model based on object detection is deployed; and sending the quality detection request to a server with the minimum load, wherein the server is deployed with the classification detection model based on the object detection, according to the load state of each server deployed with the classification detection model.
Further, the apparatus further comprises: an operation processing module 705 (not shown in the figure) for performing a defect processing operation corresponding to the quality detection result according to a preset corresponding relationship between the quality detection result and the defect processing operation; wherein the defect handling operation comprises: alarm, shut down, store log or control the robotic arm.
The quality detection device of the plastic foam lunch box can execute the method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. The technical details not described in detail in this embodiment can be referred to the quality inspection method of the plastic foam lunch box provided by any embodiment of the present invention.
EXAMPLE five
Fig. 8 is a schematic structural diagram of a quality detection device for a plastic foam lunch box according to a fifth embodiment of the invention. As shown in fig. 8, the apparatus for inspecting the quality of the plastic foam lunch box according to the embodiment of the invention may include: a request receiving module 801 and a result calculating module 802; wherein,
the request receiving module 801 is configured to receive a quality detection request of the to-be-detected plastic foam lunch box;
the result calculating module 802 is configured to calculate a quality detection result corresponding to the quality detection request through a pre-trained classification detection model based on object detection.
Further, the classification detection model based on object detection includes: a deep convolutional neural network and a defect location classification network; the deep convolutional neural network is used for extracting the characteristics of the steel plate picture and inputting the characteristics into the defect positioning classification network; the defect positioning classification network is used for judging whether the features extracted by the deep convolutional neural network have defects or not based on a classification detection algorithm of object detection and obtaining the category of the defects.
Further, the deep convolutional neural network includes: a convolutional layer, a pooling layer, and a full-link layer; the convolution layer is used for scanning and convolving the image of the to-be-detected plastic foam lunch box in the quality detection request by utilizing convolution cores with different weights, extracting various meaningful features from the image, and outputting the features to a feature map; the pooling layer is used for performing dimension reduction operation on the feature map; and the full connection layer is used for mapping the extracted features to the defect positioning and classifying network.
The quality detection device of the plastic foam lunch box can execute the method provided by any embodiment of the invention, and has corresponding functional modules and beneficial effects of the execution method. The technical details not described in detail in this embodiment can be referred to the quality inspection method of the plastic foam lunch box provided by any embodiment of the present invention.
EXAMPLE six
Fig. 9 is a schematic structural diagram of a server according to a sixth embodiment of the present invention. FIG. 9 illustrates a block diagram of an exemplary server suitable for use in implementing embodiments of the present invention. The server 12 shown in fig. 9 is only an example, and should not bring any limitation to the function and the scope of use of the embodiment of the present invention.
As shown in fig. 9, the server 12 is in the form of a general purpose computing device. The components of the server 12 may include, but are not limited to: one or more processors or processing units 16, a system memory 28, and a bus 18 that couples various system components including the system memory 28 and the processing unit 16.
Bus 18 represents one or more of any of several types of bus structures, including a memory bus or memory controller, a peripheral bus, an accelerated graphics port, and a processor or local bus using any of a variety of bus architectures. By way of example, such architectures include, but are not limited to, Industry Standard Architecture (ISA) bus, micro-channel architecture (MAC) bus, enhanced ISA bus, Video Electronics Standards Association (VESA) local bus, and Peripheral Component Interconnect (PCI) bus.
The server 12 typically includes a variety of computer system readable media. Such media may be any available media that is accessible by server 12 and includes both volatile and nonvolatile media, removable and non-removable media.
The system memory 28 may include computer system readable media in the form of volatile memory, such as Random Access Memory (RAM)30 and/or cache memory 32. The server 12 may further include other removable/non-removable, volatile/nonvolatile computer system storage media. By way of example only, storage system 34 may be used to read from and write to non-removable, nonvolatile magnetic media (not shown in FIG. 9, and commonly referred to as a "hard drive"). Although not shown in FIG. 9, a magnetic disk drive for reading from and writing to a removable, nonvolatile magnetic disk (e.g., a "floppy disk") and an optical disk drive for reading from or writing to a removable, nonvolatile optical disk (e.g., a CD-ROM, DVD-ROM, or other optical media) may be provided. In these cases, each drive may be connected to bus 18 by one or more data media interfaces. Memory 28 may include at least one program product having a set (e.g., at least one) of program modules that are configured to carry out the functions of embodiments of the invention.
A program/utility 40 having a set (at least one) of program modules 42 may be stored, for example, in memory 28, such program modules 42 including, but not limited to, an operating system, one or more application programs, other program modules, and program data, each of which examples or some combination thereof may comprise an implementation of a network environment. Program modules 42 generally carry out the functions and/or methodologies of the described embodiments of the invention.
The server 12 may also communicate with one or more external devices 14 (e.g., keyboard, pointing device, display 24, etc.), with one or more devices that enable a user to interact with the server 12, and/or with any devices (e.g., network card, modem, etc.) that enable the server 12 to communicate with one or more other computing devices. Such communication may be through an input/output (I/O) interface 22. Also, the server 12 may communicate with one or more networks (e.g., a Local Area Network (LAN), a Wide Area Network (WAN), and/or a public network, such as the Internet) via the network adapter 20. As shown, the network adapter 20 communicates with the other modules of the server 12 via the bus 18. It should be understood that although not shown in the figures, other hardware and/or software modules may be used in conjunction with the server 12, including but not limited to: microcode, device drivers, redundant processing units, external disk drive arrays, RAID systems, tape drives, and data backup storage systems, among others.
The processing unit 16 executes programs stored in the system memory 28 to execute various functional applications and data processing, such as implementing the quality detection method for the blister lunch box provided by the embodiment of the present invention.
EXAMPLE seven
The seventh embodiment of the invention provides a computer storage medium.
The computer-readable storage media of embodiments of the invention may take any combination of one or more computer-readable media. The computer readable medium may be a computer readable signal medium or a computer readable storage medium. A computer readable storage medium may be, for example, but not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: an electrical connection having one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing. In the context of this document, a computer readable storage medium may be any tangible medium that can contain, or store a program for use by or in connection with an instruction execution system, apparatus, or device.
A computer readable signal medium may include a propagated data signal with computer readable program code embodied therein, for example, in baseband or as part of a carrier wave. Such a propagated data signal may take many forms, including, but not limited to, electro-magnetic, optical, or any suitable combination thereof. A computer readable signal medium may also be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.
Program code embodied on a computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
Computer program code for carrying out operations for aspects of the present invention may be written in any combination of one or more programming languages, including an object oriented programming language such as Java, Smalltalk, C + + or the like and conventional procedural programming languages, such as the "C" programming language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet using an Internet service provider).
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (14)
1. A method of quality testing a blister food box, said method comprising:
acquiring image data of a plastic foam lunch box to be detected;
converting the image data of the to-be-detected foam lunch box into a quality detection request of the to-be-detected plastic foam lunch box;
sending the quality detection request to a server deployed with a classification detection model based on object detection;
and receiving a quality detection result corresponding to the quality detection classification request output by the server through the classification detection model based on the object detection.
2. The method of claim 1, wherein sending the quality detection request to a server deployed with a classification detection model based on object detection comprises:
acquiring the load state of each server deployed with the classification detection model based on the object detection in a preset server configuration table;
and sending the quality detection request to a server with the minimum load, wherein the server is deployed with the classification detection model based on the object detection, according to the load state of each server deployed with the classification detection model.
3. The method of claim 1, further comprising:
according to a preset corresponding relation between a quality detection result and a defect processing operation, performing the defect processing operation corresponding to the quality detection result; wherein the defect handling operation comprises: alarm, shut down, store log or control the robotic arm.
4. A method of quality testing a blister food box, said method comprising:
receiving a quality detection request of the plastic foam lunch box to be detected;
and calculating a quality detection result corresponding to the quality detection request through a pre-trained classification detection model based on object detection.
5. The method of claim 4, wherein the object detection-based classification detection model comprises: a deep convolutional neural network and a defect location classification network; the deep convolutional neural network is used for extracting the characteristics of the steel plate picture and inputting the characteristics into the defect positioning classification network; the defect positioning classification network is used for judging whether the features extracted by the deep convolutional neural network have defects or not based on a classification detection algorithm of object detection and obtaining the category of the defects.
6. The method of claim 5, wherein the deep convolutional neural network comprises: a convolutional layer, a pooling layer, and a full-link layer; the convolution layer is used for scanning and convolving the image of the to-be-detected plastic foam lunch box in the quality detection request by utilizing convolution cores with different weights, extracting various meaningful features from the image, and outputting the features to a feature map; the pooling layer is used for performing dimension reduction operation on the feature map; and the full connection layer is used for mapping the extracted features to the defect positioning and classifying network.
7. A device for detecting the quality of a blister lunch box, said device comprising: the system comprises an image acquisition module, an image conversion module, a request sending module and a result receiving module; wherein,
the image acquisition module is used for acquiring image data of the plastic foam lunch box to be detected;
the image conversion module is used for converting the image data of the to-be-detected foamed lunch box into a quality detection request of the to-be-detected plastic foamed lunch box;
the request sending module is used for sending the quality detection request to a server which is provided with a classification detection model based on object detection;
and the result receiving module is used for receiving a quality detection result corresponding to the quality detection classification request output by the server through the classification detection model based on the object detection.
8. The apparatus of claim 7, wherein:
the request sending module is specifically configured to obtain, in a preset server configuration table, a load state of each server on which the object detection-based classification detection model is deployed; and sending the quality detection request to a server with the minimum load, wherein the server is deployed with the classification detection model based on the object detection, according to the load state of each server deployed with the classification detection model.
9. The apparatus of claim 7, further comprising: the operation processing module is used for making a defect processing operation corresponding to the quality detection result according to the preset corresponding relation between the quality detection result and the defect processing operation; wherein the defect handling operation comprises: alarm, shut down, store log or control the robotic arm.
10. A device for detecting the quality of a blister lunch box, said device comprising: the device comprises a request receiving module and a result calculating module; wherein,
the request receiving module is used for receiving a quality detection request of the to-be-detected plastic foam lunch box;
and the result calculation module is used for calculating a quality detection result corresponding to the quality detection request through a pre-trained classification detection model based on object detection.
11. The apparatus of claim 10, wherein the object detection-based classification detection model comprises: a deep convolutional neural network and a defect location classification network; the deep convolutional neural network is used for extracting the characteristics of the steel plate picture and inputting the characteristics into the defect positioning classification network; the defect positioning classification network is used for judging whether the features extracted by the deep convolutional neural network have defects or not based on a classification detection algorithm of object detection and obtaining the category of the defects.
12. The apparatus of claim 11, wherein the deep convolutional neural network comprises: a convolutional layer, a pooling layer, and a full-link layer; the convolution layer is used for scanning and convolving the image of the to-be-detected plastic foam lunch box in the quality detection request by utilizing convolution cores with different weights, extracting various meaningful features from the image, and outputting the features to a feature map; the pooling layer is used for performing dimension reduction operation on the feature map; and the full connection layer is used for mapping the extracted features to the defect positioning and classifying network.
13. A server, comprising:
one or more processors;
a memory for storing one or more programs,
when executed by the one or more processors, cause the one or more processors to implement a method of quality inspection of blister boxes according to any of claims 1 to 3 or 4 to 6.
14. A storage medium on which a computer program is stored, wherein the program, when executed by a processor, implements a method of quality inspection of a blister lunch box according to any one of claims 1 to 3 or 4 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811456293.9A CN109598712A (en) | 2018-11-30 | 2018-11-30 | Quality determining method, device, server and the storage medium of plastic foam cutlery box |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811456293.9A CN109598712A (en) | 2018-11-30 | 2018-11-30 | Quality determining method, device, server and the storage medium of plastic foam cutlery box |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109598712A true CN109598712A (en) | 2019-04-09 |
Family
ID=65959394
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811456293.9A Pending CN109598712A (en) | 2018-11-30 | 2018-11-30 | Quality determining method, device, server and the storage medium of plastic foam cutlery box |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109598712A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260669A (en) * | 2020-02-17 | 2020-06-09 | 北京推想科技有限公司 | Lung lobe segmentation method and device based on CT image |
| CN112634194A (en) * | 2020-10-20 | 2021-04-09 | 天津大学 | Self-learning detection method for fabric defects in warp knitting process |
| CN113159448A (en) * | 2021-05-12 | 2021-07-23 | 烟台应辉智能科技有限公司 | Automatic analysis and discrimination method based on environmental protection big data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154508A (en) * | 2018-01-09 | 2018-06-12 | 北京百度网讯科技有限公司 | Method, apparatus, storage medium and the terminal device of product defects detection positioning |
| CN108230318A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Ladle defects detection sorting technique, device, equipment and computer-readable medium |
| CN108230317A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Steel plate defect detection sorting technique, device, equipment and computer-readable medium |
| CN108320278A (en) * | 2018-01-09 | 2018-07-24 | 北京百度网讯科技有限公司 | Product defects detect localization method, device, equipment and computer-readable medium |
| CN108564104A (en) * | 2018-01-09 | 2018-09-21 | 北京百度网讯科技有限公司 | Product defects detection method, device, system, server and storage medium |
-
2018
- 2018-11-30 CN CN201811456293.9A patent/CN109598712A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108154508A (en) * | 2018-01-09 | 2018-06-12 | 北京百度网讯科技有限公司 | Method, apparatus, storage medium and the terminal device of product defects detection positioning |
| CN108230318A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Ladle defects detection sorting technique, device, equipment and computer-readable medium |
| CN108230317A (en) * | 2018-01-09 | 2018-06-29 | 北京百度网讯科技有限公司 | Steel plate defect detection sorting technique, device, equipment and computer-readable medium |
| CN108320278A (en) * | 2018-01-09 | 2018-07-24 | 北京百度网讯科技有限公司 | Product defects detect localization method, device, equipment and computer-readable medium |
| CN108564104A (en) * | 2018-01-09 | 2018-09-21 | 北京百度网讯科技有限公司 | Product defects detection method, device, system, server and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111260669A (en) * | 2020-02-17 | 2020-06-09 | 北京推想科技有限公司 | Lung lobe segmentation method and device based on CT image |
| CN112634194A (en) * | 2020-10-20 | 2021-04-09 | 天津大学 | Self-learning detection method for fabric defects in warp knitting process |
| CN113159448A (en) * | 2021-05-12 | 2021-07-23 | 烟台应辉智能科技有限公司 | Automatic analysis and discrimination method based on environmental protection big data |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110148130B (en) | Method and device for detecting part defects | |
| WO2018108129A1 (en) | Method and apparatus for use in identifying object type, and electronic device | |
| CN111080693A (en) | Robot autonomous classification grabbing method based on YOLOv3 | |
| CN109977191B (en) | Problem map detection method, device, electronic equipment and medium | |
| CN109086811B (en) | Multi-label image classification method and device and electronic equipment | |
| CN112861575A (en) | Pedestrian structuring method, device, equipment and storage medium | |
| CN113487610B (en) | Herpes image recognition method and device, computer equipment and storage medium | |
| CN111553950A (en) | Steel coil centering judgment method, system, medium and electronic terminal | |
| CN109598712A (en) | Quality determining method, device, server and the storage medium of plastic foam cutlery box | |
| Geng et al. | An improved helmet detection method for YOLOv3 on an unbalanced dataset | |
| CN112749673A (en) | Method and device for intelligently extracting stock of oil storage tank based on remote sensing image | |
| CN113780145A (en) | Sperm morphology detection method, sperm morphology detection device, computer equipment and storage medium | |
| CN114565780A (en) | Target identification method and device, electronic equipment and storage medium | |
| CN114429577B (en) | Flag detection method, system and equipment based on high confidence labeling strategy | |
| CN114120208A (en) | Flame detection method, device, equipment and storage medium | |
| CN112529836A (en) | High-voltage line defect detection method and device, storage medium and electronic equipment | |
| CN109470708A (en) | Quality determining method, device, server and the storage medium of plastic foam cutlery box | |
| CN117197653A (en) | Landslide hazard identification method and system based on deep learning | |
| Shishkin et al. | Implementation of yolov5 for detection and classification of microplastics and microorganisms in marine environment | |
| KR20130013462A (en) | Foreground extraction apparatus and method using ccb and mt lbp | |
| CN115565072A (en) | Road garbage recognition and positioning method and device, electronic equipment and medium | |
| CN113139077B (en) | Method, device, terminal and storage medium for identifying ship identity | |
| CN114842192A (en) | Aero-engine blade damage identification model, damage identification method and system | |
| Chen et al. | Underwater target detection and embedded deployment based on lightweight YOLO_GN | |
| CN114283280A (en) | Water surface floating garbage identification method based on improved convolutional neural network |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190409 |
|
| RJ01 | Rejection of invention patent application after publication |