CN109344799A - Item identification method, device and equipment, storage medium, electronic device - Google Patents
Item identification method, device and equipment, storage medium, electronic device Download PDFInfo
- Publication number
- CN109344799A CN109344799A CN201811246481.9A CN201811246481A CN109344799A CN 109344799 A CN109344799 A CN 109344799A CN 201811246481 A CN201811246481 A CN 201811246481A CN 109344799 A CN109344799 A CN 109344799A
- Authority
- CN
- China
- Prior art keywords
- detection
- article
- image
- assembly line
- detected
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C3/00—Registering or indicating the condition or the working of machines or other apparatus, other than vehicles
- G07C3/14—Quality control systems
- G07C3/143—Finished product quality control
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/06—Recognition of objects for industrial automation
Abstract
The embodiment of the invention provides a kind of item identification method, device and equipment, storage medium, electronic devices, the described method includes: not passing through the article of detection on identification assembly line, wherein, when the article for not passing through detection is the product to be detected on the assembly line, issue warning note, when the article for not passing through detection is not the product to be detected on the assembly line, warning note is not issued.It solves the problem of can not differentiating substandard product and chaff interferent due to the detection on assembly line in the prior art, pipeline-exception is caused to alarm, personnel's energy and time cost is greatly saved, improves production efficiency.
Description
Technical field
The present invention relates to technical field of intelligent equipment, in particular to a kind of item identification method, device and equipment,
Storage medium, electronic device.
Background technique
In the vision-based detection project with auto instrument automatic needle press, the object of assembly line delivery is other than equipment to be checked, and there are also portions
Divide the chaff interferents such as rework equipments, tooling case.In the detection process, whether vision inspection apparatus detection object meets certain feature
It is required that and issuing OK and NG signal;Since kind of object cannot be distinguished, when rework equipments, tooling case etc. interfere logistics view
When feeling detecting instrument, it frequently can lead to the phenomenon that alarming and stopping line, will cause the waste of personnel's energy, increase the unnecessary time
Cost reduces production efficiency.
For in the related technology, since the detection on assembly line can not differentiate substandard product and chaff interferent, flowing water is caused
The problem of line abnormal alarm, there has been no reasonable solutions.
Summary of the invention
The embodiment of the invention provides a kind of item identification method, device and equipment, storage medium, electronic devices, so that
It is few to solve to cause pipeline-exception report in the related technology since the detection on assembly line differentiate substandard product and chaff interferent
Alert problem.
According to one embodiment of present invention, a kind of item identification method is provided, comprising: do not pass through on identification assembly line
The article of detection, wherein when the article for not passing through detection is the product to be detected on the assembly line, issues alarm and mention
Show, when the article for not passing through detection is not the product to be detected on the assembly line, does not issue warning note.
Preferably, before identifying the article for not passing through detection on assembly line, the method also includes: on the assembly line
Article carry out feature detection;When the article is not detected by the feature, acquisition is described not to pass through the article of detection
Image.
It preferably, include: not lead to using the identification of sample training model is described not by the article detected on identification assembly line
Cross the image of the article of detection, wherein include training set in the sample training model, include underproof in the training set
The image collection of product to be detected and the image collection of chaff interferent.
Preferably, identify that described does not include: to work as to identify institute by the image of the article detected using sample training model
State not by detection article be underproof product to be detected when, issue warning note;Described detection is not passed through when identifying
Article be chaff interferent when, do not issue warning note.
Preferably, when identifying that described is not underproof product to be detected by the article of detection, warning note is issued
Afterwards, the method also includes: output detection information, stop the operating of the assembly line.
Preferably, after the image that the article for not passing through detection is identified using sample training model, the method is also
It include: to be trained described be not stored in the sample training model by the image of the article of detection.
Preferably, described be not stored in the sample training model by the image of the article of detection is trained packet
It includes: not being stored in described in the training set by the image of the article of detection according to the classification after identification;It is stored into the instruction
The described image for practicing collection is converted into gray level image, and carries out edge detection process with edge detection operator, extracts the line of image
Manage feature;It converts original RGB color image to the color model of HSV triple channel, extracts tone therein, saturation degree, bright
The information of degree, and extract the connected region information of Similar color value;Extract the characteristic information of the color histogram of described image;
All characteristic informations extracted are put into the sample training model and are trained.
According to another embodiment of the present invention, a kind of item identification devices are additionally provided, comprising: identification module, for knowing
Do not pass through the article of detection on other assembly line;Alarm module, when it is described not by detection article be the assembly line on to
When testing product, warning note is issued, when the article for not passing through detection is not the product to be detected on the assembly line,
Do not issue warning note.
According to another embodiment of the present invention, a kind of article identification equipment is additionally provided, comprising: recognition means, for knowing
Do not pass through the article of detection on other assembly line;Alarm appliance, when it is described not by detection article be the assembly line on to
When testing product, warning note is issued, when the article for not passing through detection is not the product to be detected on the assembly line,
Do not issue warning note.
Preferably, the equipment further include: detection device, for carrying out feature detection to the article on the assembly line;
Image acquisition device, for when the article is not detected by the feature, acquisition to be described not by the figure of the article detected
Picture.
Preferably, the recognition means are also used to: being identified using sample training model described not by the article of detection
Image, wherein include training set in the sample training model, include the figure of underproof product to be detected in the training set
Image set closes and the image collection of chaff interferent.
Preferably, the equipment further include: training device, for not being stored in institute by the image of the article of detection for described
It states and is trained in sample training model.
Preferably, the trained device is also used to: by the image of the article for not passing through detection according to the class after identification
It is not stored in the training set;The described image for being stored into the training set is converted into gray level image, and uses edge detection operator
Edge detection process is carried out, the textural characteristics of image are extracted;Convert original RGB color image to the face of HSV triple channel
Color model extracts tone therein, saturation degree, the information of lightness, and extracts the connected region information of Similar color value;It extracts
The characteristic information of the color histogram of described image;All characteristic informations extracted are put into the sample training model
In be trained.
According to another embodiment of the invention, a kind of storage medium is additionally provided, meter is stored in the storage medium
Calculation machine program, wherein the computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
According to another embodiment of the invention, a kind of electronic device, including memory and processor are additionally provided, it is special
Sign is, computer program is stored in the memory, and the processor is arranged to run the computer program to hold
Step in row any of the above-described embodiment of the method.
Through the embodiment of the present invention, to not identified further by the article of detection on assembly line, when not passing through
When the article of detection is the product to be detected on assembly line, warning note is issued, is not assembly line when not passing through the article of detection
On product to be detected when, do not issue warning note.It solves in the prior art since the detection on assembly line can not differentiate not
Qualified products and chaff interferent, are greatly saved personnel's energy and time cost, improve the problem of causing pipeline-exception to alarm
Production efficiency.
Detailed description of the invention
The drawings described herein are used to provide a further understanding of the present invention, constitutes part of this application, this hair
Bright illustrative embodiments and their description are used to explain the present invention, and are not constituted improper limitations of the present invention.In the accompanying drawings:
Fig. 1 is a kind of hardware block diagram of the mobile terminal of item identification method of the embodiment of the present invention;
Fig. 2 is the flow chart of middle item identification method according to embodiments of the present invention;
Fig. 3 is the another flow chart of the item identification method of the embodiment of the present invention;
Fig. 4 is the structural block diagram of item identification devices according to an embodiment of the present invention;
Fig. 5 is the structural block diagram of article identification equipment according to an embodiment of the present invention.
Specific embodiment
Hereinafter, the present invention will be described in detail with reference to the accompanying drawings and in combination with Examples.It should be noted that not conflicting
In the case of, the features in the embodiments and the embodiments of the present application can be combined with each other.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.
Embodiment 1
Embodiment of the method provided by the embodiment of the present application one can be in mobile terminal, terminal or similar fortune
It calculates and is executed in device.For running on mobile terminals, Fig. 1 is a kind of movement of item identification method of the embodiment of the present invention
The hardware block diagram of terminal.As shown in Figure 1, mobile terminal 10 may include at one or more (only showing one in Fig. 1)
It manages device 102 (processing unit that processor 102 can include but is not limited to Micro-processor MCV or programmable logic device FPGA etc.)
Memory 104 for storing data, optionally, above-mentioned mobile terminal can also include the transmission device for communication function
106 and input-output equipment 108.It will appreciated by the skilled person that structure shown in FIG. 1 is only to illustrate, simultaneously
The structure of above-mentioned mobile terminal is not caused to limit.For example, mobile terminal 10 may also include it is more than shown in Fig. 1 or less
Component, or with the configuration different from shown in Fig. 1.
Memory 104 can be used for storing computer program, for example, the software program and module of application software, such as this hair
The corresponding computer program of the acquisition methods of data information in bright embodiment, processor 102 are stored in memory by operation
Computer program in 104 realizes above-mentioned method thereby executing various function application and data processing.Memory 104
May include high speed random access memory, may also include nonvolatile memory, as one or more magnetic storage device, flash memory,
Or other non-volatile solid state memories.In some instances, memory 104 can further comprise relative to processor 102
Remotely located memory, these remote memories can pass through network connection to mobile terminal 10.The example packet of above-mentioned network
Include but be not limited to internet, intranet, local area network, mobile radio communication and combinations thereof.
Transmitting device 106 is used to that data to be received or sent via a network.Above-mentioned network specific example may include
The wireless network that the communication providers of mobile terminal 10 provide.In an example, transmitting device 106 includes a Network adaptation
Device (Network Interface Controller, referred to as NIC), can be connected by base station with other network equipments to
It can be communicated with internet.In an example, transmitting device 106 can for radio frequency (Radio Frequency, referred to as
RF) module is used to wirelessly be communicated with internet.
The embodiment of the invention provides a kind of item identification methods.Fig. 2 is middle article identification side according to embodiments of the present invention
The flow chart of method, as shown in Fig. 2, this method comprises:
Step S201 is identified on assembly line not by the article of detection, wherein when the article for not passing through detection is assembly line
On product to be detected when, issue warning note, when not by detection article be not the product to be detected on assembly line when, no
Issue warning note.
It by the above method, identifies on assembly line not by the article of detection, wherein when the article for not passing through detection is stream
When product to be detected on waterline, warning note is issued, when not by product to be detected that the article of detection is not on assembly line
When, do not issue warning note.It solves in the prior art since the detection on assembly line can not differentiate substandard product and interference
Object, is greatly saved personnel's energy and time cost, improves production efficiency the problem of causing pipeline-exception to alarm.
A preferred embodiment according to an embodiment of the present invention, before above-mentioned steps S201, the method also includes: it is right
Article on assembly line carries out feature detection;When article is not detected by the feature, acquisition does not pass through the article of detection
Image.
A preferred embodiment according to an embodiment of the present invention, above-mentioned steps S201 can be realized by following steps:
Do not pass through the image of the article of detection using the identification of sample training model, wherein include training set, training in sample training model
Concentrate includes the image collection of underproof product to be detected and the image collection of chaff interferent.
A preferred embodiment according to an embodiment of the present invention does not pass through the object of detection using the identification of sample training model
The image of product can be realized by following steps: when identifying is not underproof product to be detected by the article of detection,
Issue warning note, wherein after issuing warning note, detection information can also be exported, stop the operating of assembly line;When identifying
When being not chaff interferent by the article of detection, warning note is not issued, the operating for stopping assembly line, assembly line are not had to without alarming
It can continue to run well.
A preferred embodiment according to an embodiment of the present invention does not pass through detection using the identification of sample training model is described
Article image after, the method also includes: will not by detection article image be stored in sample training model in into
Row training.
A preferred embodiment according to an embodiment of the present invention, above-mentioned training method can be realized by following steps:
1) it will be stored in training set by the image of the article of detection according to the classification after identification;
2) image for being stored into training set is converted into gray level image, and carries out edge detection process with edge detection operator,
Extract image textural characteristics (edge detection operator mentioned in the embodiment of the present invention can be Sobel edge detection operator,
It is also possible to Canny edge detection operator);
3) convert original RGB color image to the color model of HSV triple channel, extract tone therein, saturation degree,
The information of lightness, and extract the connected region information of Similar color value;
4) characteristic information of the color histogram of image is extracted;
5) by above-mentioned steps 2) it is put into sample training model and instructs to all characteristic informations extracted in 4)
Practice.
Technical solution in embodiment for a better understanding of the present invention, below with reference to Fig. 3 to object in the embodiment of the present invention
The specific steps of product recognition methods are specifically described.Fig. 3 is the another flow chart of the item identification method of the embodiment of the present invention.
As shown in figure 3, the described method comprises the following steps:
1, object flows to the position of vision inspection apparatus, real-time dynamicly carries out product feature detection.
2, feature detects the object passed through, labeled as detection OK;Feature detects unacceptable object, needs to carry out object kind
The operation that class is distinguished.
If being 3, normal detection device by identifying and distinguishing among out, which is exactly underproof product, mark
It is denoted as detection NG;If it is other kinds of object (i.e. chaff interferent) that identification, which is distinguished, which is not to be detected set
It is standby, do not need warning note.
4, detection information is exported.If it is the product of detection NG, then will carry out alarm stops line operation.
The technical solution provided in the embodiment of the present invention, by the supervised learning mode of machine learning, to the texture of image,
The characteristic informations such as color, color histogram are trained, and obtained model are used in the classification of NG (not passing through detection) picture,
The NG picture which is product to be detected is distinguished, which is the picture of chaff interferent, so that distinguishing object is product to be detected
Or chaff interferent.The normal detection for not influencing product to be detected is distinguished and is rejected non-detection product, reduces the alarm of detecting instrument
Phenomenon occurs, and assembly line is avoided often to stop line.
Embodiment 2
A kind of item identification devices are additionally provided in the present embodiment, for executing the step in any of the above-described embodiment of the method
Suddenly, details are not described herein again for the content having been noted above.Fig. 4 is the structural frames of item identification devices according to an embodiment of the present invention
Figure does not pass through the article of detection as shown in figure 4, the device includes: identification module 40 for identification on assembly line;Alarm module
42, when being the product to be detected on assembly line not by the article of detection, warning note is issued, when the article for not passing through detection
When not being the product to be detected on assembly line, warning note is not issued.
By above-mentioned apparatus, identification module 40 is identified on assembly line not by the article of detection;Alarm module 42 is not leading to
When the article for crossing detection is the product to be detected on assembly line, warning note is issued, be not flowing water not by the article of detection
When product to be detected on line, warning note is not issued.It solves in the prior art since the detection on assembly line can not differentiate
The problem of causing pipeline-exception to alarm, personnel's energy and time cost is greatly saved in substandard product and chaff interferent, improves
Production efficiency.
For realizing the step in any of the above-described embodiment of the method in the device, if necessary, may include various function
It can module, in the above way embodiment.
A kind of article identification equipment is additionally provided in the present embodiment, for executing the step in any of the above-described embodiment of the method
Suddenly, details are not described herein again for the content having been noted above.Fig. 5 is the structural frames of article identification equipment according to an embodiment of the present invention
Figure does not pass through the article of detection as shown in figure 5, the equipment includes: recognition means 50 for identification on assembly line;Alarm appliance
52, when being the product to be detected on assembly line not by the article of detection, warning note is issued, when the article for not passing through detection
When not being the product to be detected on assembly line, warning note is not issued.
A preferred embodiment according to an embodiment of the present invention, above equipment further include: detection device, for flowing water
Article on line carries out feature detection;Image acquisition device, for when article is not detected by feature, acquisition not to pass through detection
Article image.
A preferred embodiment according to an embodiment of the present invention, the recognition means are also used to: utilizing sample training mould
Type identification does not pass through the image of the article of detection, wherein includes training set in sample training model, includes unqualified in training set
Product to be detected image collection and chaff interferent image collection.
A preferred embodiment according to an embodiment of the present invention, the equipment further include: training device, for that will not lead to
It crosses in the image deposit sample training model of the article of detection and is trained.
A preferred embodiment according to an embodiment of the present invention, training device are also used to: will be not by the article of detection
Image according to after identification classification deposit training set in;The image for being stored into training set is converted into gray level image, and uses edge
Detective operators carry out edge detection process, extract the textural characteristics of image;HSV tri- is converted by original RGB color image
The color model in channel extracts tone therein, saturation degree, the information of lightness, and extracts the connected region of Similar color value
Information;Extract the characteristic information of the color histogram of described image;All characteristic informations extracted are put into sample instruction
Practice and is trained in model.
The technical solution provided in the embodiment of the present invention, by the supervised learning mode of machine learning, to the texture of image,
The characteristic informations such as color, color histogram are trained, and obtained model are used in the classification of NG (not passing through detection) picture,
The NG picture which is product to be detected is distinguished, which is the picture of chaff interferent, so that distinguishing object is product to be detected
Or chaff interferent.The normal detection for not influencing product to be detected is distinguished and is rejected non-detection product, reduces the alarm of detecting instrument
Phenomenon occurs, and assembly line is avoided often to stop line.
Embodiment 3
The embodiments of the present invention also provide a kind of storage medium, computer program is stored in the storage medium, wherein
The computer program is arranged to execute the step in any of the above-described embodiment of the method when operation.
Optionally, in the present embodiment, above-mentioned storage medium can be set to store by executing based on following steps
Calculation machine program:
S1, identify assembly line on by detection article, wherein when not by detection article be assembly line on to
When testing product, warning note is issued, when not being the product to be detected on assembly line not by the article of detection, does not issue report
Alert prompt.
Optionally, storage medium is also configured to store the computer program for executing following steps:
Feature detection is carried out to the article on assembly line;When article is not detected by the feature, acquisition does not pass through inspection
The image of the article of survey.
Optionally, storage medium is also configured to store the computer program for executing following steps:
Do not pass through the image of the article of detection using the identification of sample training model, wherein include instruction in sample training model
Practice collection, includes the image collection of underproof product to be detected and the image collection of chaff interferent in training set.
Optionally, storage medium is also configured to store the computer program for executing following steps:
It is trained not being stored in sample training model by the image of the article of detection.
Optionally, in the present embodiment, above-mentioned storage medium can include but is not limited to: USB flash disk, read-only memory (Read-
Only Memory, referred to as ROM), it is random access memory (Random Access Memory, referred to as RAM), mobile hard
The various media that can store computer program such as disk, magnetic or disk.
The embodiments of the present invention also provide a kind of electronic device, including memory and processor, stored in the memory
There is computer program, which is arranged to run computer program to execute the step in any of the above-described embodiment of the method
Suddenly.
Optionally, above-mentioned electronic device can also include transmission device and input-output equipment, wherein the transmission device
It is connected with above-mentioned processor, which connects with above-mentioned processor.
Optionally, in the present embodiment, above-mentioned processor can be set to execute following steps by computer program:
S1, identify assembly line on by detection article, wherein when not by detection article be assembly line on to
When testing product, warning note is issued, when not being the product to be detected on assembly line not by the article of detection, does not issue report
Alert prompt.
Optionally, processor is also configured to store the computer program for executing following steps:
Feature detection is carried out to the article on assembly line;When article is not detected by the feature, acquisition does not pass through inspection
The image of the article of survey.
Optionally, processor is also configured to store the computer program for executing following steps:
Do not pass through the image of the article of detection using the identification of sample training model, wherein include instruction in sample training model
Practice collection, includes the image collection of underproof product to be detected and the image collection of chaff interferent in training set.
Optionally, processor is also configured to store the computer program for executing following steps:
It is trained not being stored in sample training model by the image of the article of detection.
Specific example in the present embodiment can refer to example described in above-described embodiment and optional embodiment, this
Details are not described herein for embodiment.
Obviously, those skilled in the art should be understood that each module of the above invention or each step can be with general
Computing device realize that they can be concentrated on a single computing device, or be distributed in multiple computing devices and formed
Network on, optionally, they can be realized with the program code that computing device can perform, it is thus possible to which they are stored
It is performed by computing device in the storage device, and in some cases, it can be to be different from shown in sequence execution herein
Out or description the step of, perhaps they are fabricated to each integrated circuit modules or by them multiple modules or
Step is fabricated to single integrated circuit module to realize.In this way, the present invention is not limited to any specific hardware and softwares to combine.
The foregoing is only a preferred embodiment of the present invention, is not intended to restrict the invention, for the skill of this field
For art personnel, the invention may be variously modified and varied.It is all within principle of the invention, it is made it is any modification, etc.
With replacement, improvement etc., should all be included in the protection scope of the present invention.
Claims (15)
1. a kind of item identification method characterized by comprising
It identifies on assembly line not by the article of detection, wherein when the article for not passing through detection is on the assembly line
When product to be detected, warning note is issued, when the article for not passing through detection is not the product to be detected on the assembly line
When, do not issue warning note.
2. the method according to claim 1, wherein identification assembly line on by detection article before, institute
State method further include:
Feature detection is carried out to the article on the assembly line;
When the article is not detected by the feature, acquisition is described not to pass through the image of the article of detection.
3. according to the method described in claim 2, it is characterized in that, not including: by the article detected on identification assembly line
It is identified using sample training model described not by the image of the article of detection, wherein wrapped in the sample training model
Training set is included, includes the image collection of underproof product to be detected and the image collection of chaff interferent in the training set.
4. according to the method described in claim 3, it is characterized in that, being identified using sample training model described not by detection
The image of article includes:
When identifying the article for not passing through detection is underproof product to be detected, warning note is issued;
When identifying the article for not passing through detection is chaff interferent, warning note is not issued.
5. according to the method described in claim 4, it is characterized in that, when identifying that described is not unqualified by the article of detection
Product to be detected, issue warning note after, the method also includes:
Detection information is exported, the operating of the assembly line is stopped.
6. according to the method described in claim 3, it is characterized in that, being identified using sample training model described not by detection
After the image of article, the method also includes:
Described be not stored in the sample training model by the image of the article of detection is trained.
7. according to the method described in claim 6, it is characterized in that, by described in the not image deposit by the article of detection
It is trained in sample training model and includes:
It is not stored in described in the training set by the image of the article of detection according to the classification after identification;
The described image for being stored into the training set is converted into gray level image, and is carried out at edge detection with edge detection operator
Reason, extracts the textural characteristics of image;
It converts original RGB color image to the color model of HSV triple channel, extracts tone therein, saturation degree, lightness
Information, and extract the connected region information of Similar color value;
Extract the characteristic information of the color histogram of described image;
All characteristic informations extracted are put into the sample training model and are trained.
8. a kind of item identification devices characterized by comprising
Identification module does not pass through the article of detection for identification on assembly line;
Alarm module issues warning note when the article for not passing through detection is the product to be detected on the assembly line,
When the article for not passing through detection is not the product to be detected on the assembly line, warning note is not issued.
9. a kind of article identifies equipment characterized by comprising
Recognition means do not pass through the article of detection for identification on assembly line;
Alarm appliance issues warning note when the article for not passing through detection is the product to be detected on the assembly line,
When the article for not passing through detection is not the product to be detected on the assembly line, warning note is not issued.
10. equipment according to claim 9, which is characterized in that the equipment further include:
Device is detected, for carrying out feature detection to the article on the assembly line;
Image acquisition device, for not passing through the article of detection described in acquisition when the article is not detected by the feature
Image.
11. equipment according to claim 10, which is characterized in that the recognition means are also used to:
It is identified using sample training model described not by the image of the article of detection, wherein wrapped in the sample training model
Training set is included, includes the image collection of underproof product to be detected and the image collection of chaff interferent in the training set.
12. equipment according to claim 11, which is characterized in that the equipment further include:
Training device, for described be not stored in the sample training model by the image of the article of detection to be trained.
13. equipment according to claim 12, which is characterized in that the trained device is also used to:
It is not stored in described in the training set by the image of the article of detection according to the classification after identification;
The described image for being stored into the training set is converted into gray level image, and is carried out at edge detection with edge detection operator
Reason, extracts the textural characteristics of image;
It converts original RGB color image to the color model of HSV triple channel, extracts tone therein, saturation degree, lightness
Information, and extract the connected region information of Similar color value;
Extract the characteristic information of the color histogram of described image;
All characteristic informations extracted are put into the sample training model and are trained.
14. a kind of storage medium, which is characterized in that be stored with computer program in the storage medium, wherein the computer
Program is arranged to execute method described in any one of claim 1 to 7 when operation.
15. a kind of electronic device, including memory and processor, which is characterized in that be stored with computer journey in the memory
Sequence, the processor are arranged to run the computer program to execute side described in any one of claim 1 to 7
Method.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811246481.9A CN109344799B (en) | 2018-10-24 | 2018-10-24 | Article identification method, article identification device, article identification equipment, storage medium and electronic device |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811246481.9A CN109344799B (en) | 2018-10-24 | 2018-10-24 | Article identification method, article identification device, article identification equipment, storage medium and electronic device |
Publications (2)
Publication Number | Publication Date |
---|---|
CN109344799A true CN109344799A (en) | 2019-02-15 |
CN109344799B CN109344799B (en) | 2022-02-25 |
Family
ID=65311669
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811246481.9A Active CN109344799B (en) | 2018-10-24 | 2018-10-24 | Article identification method, article identification device, article identification equipment, storage medium and electronic device |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109344799B (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113156529A (en) * | 2021-05-07 | 2021-07-23 | 广东电网有限责任公司计量中心 | Start-stop control method, system, terminal and storage medium of metrological verification assembly line |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN105608475A (en) * | 2016-02-15 | 2016-05-25 | 西安科技大学 | Infrared monitoring early warning system for belt conveyer key part |
US9483820B2 (en) * | 2014-05-20 | 2016-11-01 | General Electric Company | Method and system for detecting a damaged component of a machine |
CN106651831A (en) * | 2016-09-30 | 2017-05-10 | 广西师范大学 | Bamboo piece defect detection method and bamboo piece defect detection system |
CN106903072A (en) * | 2017-03-21 | 2017-06-30 | 湖南师范大学 | Defect inspection method |
CN108229370A (en) * | 2017-12-29 | 2018-06-29 | 广州市穗佳物流有限公司 | A kind of articles from the storeroom intelligent identifying system based on cargo image recognition technology |
CN108647588A (en) * | 2018-04-24 | 2018-10-12 | 广州绿怡信息科技有限公司 | Goods categories recognition methods, device, computer equipment and storage medium |
-
2018
- 2018-10-24 CN CN201811246481.9A patent/CN109344799B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US9483820B2 (en) * | 2014-05-20 | 2016-11-01 | General Electric Company | Method and system for detecting a damaged component of a machine |
CN105608475A (en) * | 2016-02-15 | 2016-05-25 | 西安科技大学 | Infrared monitoring early warning system for belt conveyer key part |
CN106651831A (en) * | 2016-09-30 | 2017-05-10 | 广西师范大学 | Bamboo piece defect detection method and bamboo piece defect detection system |
CN106903072A (en) * | 2017-03-21 | 2017-06-30 | 湖南师范大学 | Defect inspection method |
CN108229370A (en) * | 2017-12-29 | 2018-06-29 | 广州市穗佳物流有限公司 | A kind of articles from the storeroom intelligent identifying system based on cargo image recognition technology |
CN108647588A (en) * | 2018-04-24 | 2018-10-12 | 广州绿怡信息科技有限公司 | Goods categories recognition methods, device, computer equipment and storage medium |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113156529A (en) * | 2021-05-07 | 2021-07-23 | 广东电网有限责任公司计量中心 | Start-stop control method, system, terminal and storage medium of metrological verification assembly line |
Also Published As
Publication number | Publication date |
---|---|
CN109344799B (en) | 2022-02-25 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108351967A (en) | A kind of plurality of human faces detection method, device, server, system and storage medium | |
CN111797725A (en) | Equipment state detection method, device and system | |
CN107884415A (en) | Recognition methods, device and the industrial camera of faulty goods | |
CN107103330A (en) | A kind of LED status recognition methods and device | |
CN106355367A (en) | Warehouse monitoring management device | |
US11657599B2 (en) | Method for detecting appearance of six sides of chip multi-layer ceramic capacitor based on artificial intelligence | |
CN108984369A (en) | Caton prediction technique, device and mobile terminal | |
CN113313280B (en) | Cloud platform inspection method, electronic equipment and nonvolatile storage medium | |
CN113989503A (en) | Production line inspection system and method, electronic equipment and storage medium | |
CN110826372A (en) | Method and device for detecting human face characteristic points | |
CN110927167A (en) | Egg detection method and device, electronic equipment and storage medium | |
CN107403169B (en) | Signal lamp detection recognition method and device | |
CN115239626A (en) | Defect detection method, optical detection device, electronic device, and storage medium | |
CN109344799A (en) | Item identification method, device and equipment, storage medium, electronic device | |
CN112712504B (en) | Cloud-based workpiece detection method and system and computer-readable storage medium | |
CN113469137A (en) | Abnormal behavior recognition method and device, storage medium and electronic device | |
CN103913150A (en) | Consistency detection method for electron components of intelligent ammeter | |
US20220284699A1 (en) | System and method of object detection using ai deep learning models | |
CN116718600B (en) | Detection device for intelligent detection of wire harness product | |
CN110751055B (en) | Intelligent manufacturing system | |
KR102174424B1 (en) | Method for Inspecting Component basesd Server and system and apparatus therefor | |
CN110399782A (en) | Children look after scene reply device and method automatically | |
CN113516632A (en) | Detection method, device, system, storage medium and electronic device | |
CN113267506A (en) | Wood board AI visual defect detection device, method, equipment and medium | |
CN114362982A (en) | Flow subdivision identification method, system, electronic device and storage medium |
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 | ||
GR01 | Patent grant | ||
GR01 | Patent grant |