CN108362708A - Pen core scribing line standardized detection system based on machine vision and method - Google Patents
Pen core scribing line standardized detection system based on machine vision and method Download PDFInfo
- Publication number
- CN108362708A CN108362708A CN201810127044.9A CN201810127044A CN108362708A CN 108362708 A CN108362708 A CN 108362708A CN 201810127044 A CN201810127044 A CN 201810127044A CN 108362708 A CN108362708 A CN 108362708A
- Authority
- CN
- China
- Prior art keywords
- pen core
- detected
- image
- scribing line
- crossed
- 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
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Image Analysis (AREA)
Abstract
The pen core scribing line standardized detection system and method that present disclose provides a kind of based on machine vision, are related to technical field of image processing.The system includes：Pen core delivery module；Encoder, for being encoded to the pen core to be detected according to the carrying sequence of the pen core to be detected；Pen core detecting module；Scribing line control module, crosses for controlling the pen core to be detected；Image capture module, for recording the encoded radio and the image for acquiring the pen core scribing line to be detected that the encoder is currently generated；Image analysis module, the parameter preset crossed for obtaining the pen core to be detected from the image that the pen core to be detected is crossed, and judge whether the pen core scribing line to be detected is qualified according to the parameter preset；Pen core screening module；Defect analysis module, the defect for crossing to unqualified pen core are analyzed；Statistical module, for counting qualification rate and ratio of defects.The disclosure improves the precision and efficiency of pen core scribing line detection.
Description
Technical field
This disclosure relates to which technical field of image processing, crosses in particular to a kind of pen core based on machine vision and marks
Standardization detecting system and based on machine vision pen core scribing line standardization detection method.
Background technology
The various pen cores that use are write before manufacture, quality testing that will be Jing Guo various aspects.Wherein critically important one
Be detected as by pen core cross detection write it is whether fluent, whether handwriting trace has the abnormal phenomenon such as breakpoint, blank, to ensure
The quality of manufacture pen core.
Currently, most of producers all carry out scribing line detection by manual type, this not only expends a large amount of man power and material,
Detection efficiency is low, and artificial crossed causes missing inspection or flase drop inevitably someone will be factor, is detected so as to cause pen core
Precision is poor.It can pass through system for automatic marker making and the system for realizing the pen core detected automatically scribing line detection therefore, it is necessary to a kind of.
It should be noted that information is only used for reinforcing the reason to the background of the disclosure disclosed in above-mentioned background technology part
Solution, therefore may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Invention content
The disclosure be designed to provide it is a kind of based on machine vision pen core scribing line standardized detection system and be based on machine
The pen core scribing line standardization detection method of device vision, and then overcome the limitation due to the relevant technologies at least to a certain extent and lack
The problem of precision difference is detected caused by falling into.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to one aspect of the disclosure, a kind of pen core scribing line standardized detection system based on machine vision, packet are provided
It includes：
Pen core delivery module is used for carrying pen core to be detected；
Encoder, for being encoded to the pen core to be detected according to the carrying sequence of the pen core to be detected；
Pen core detecting module, for detecting the default position of pen core process to be detected described in the pen core delivery module carrying
When setting, standby signal is sent out；
Scribing line control module, for when the pen core to be detected passes through the predeterminated position, controlling the pen to be detected
Core is crossed；
Image capture module is drawn for recording encoded radio that the encoder is currently generated and acquiring the pen core to be detected
The image of line；
Image analysis module, for obtaining what the pen core to be detected was crossed from the image that the pen core to be detected is crossed
Parameter preset, and judge whether the pen core scribing line to be detected is qualified according to the parameter preset；
Pen core screening module, for filtering out the qualified pen core of detection and rejecting the underproof pen core of detection；
Defect analysis module, the defect for crossing to unqualified pen core are analyzed；
Statistical module, for counting qualification rate and ratio of defects.
In a kind of exemplary embodiment of the disclosure, the pen core detecting module includes：
Photoelectric sensor, setting are used for the pen to be detected described in the pen core delivery module carrying in the predeterminated position
Core sends out the standby signal when passing through the predeterminated position.
In a kind of exemplary embodiment of the disclosure, described image acquisition module includes：
Image pick-up card for receiving the standby signal, and records the coding after receiving the standby signal
The encoded radio that device is currently generated；
Industrial camera, for after described image capture card receives the standby signal, acquiring the pen core to be detected
The image of scribing line.
In a kind of exemplary embodiment of the disclosure, described image analysis module includes：
Image processing unit is pre-processed for the image to the pen core scribing line to be detected, and is extracted described to be checked
Survey the profile of pen core scribing line image；
Pixel extraction unit is drawn for extracting the pen core to be detected from the profile that the pen core to be detected crosses image
The pixel value of line profile；
Judging unit is detected, for the pixel value for profile of crossing according to the pen core to be detected, extracts the pen to be detected
The parameter preset of core scribing line, and judge whether the pen core to be detected is qualified according to the parameter preset.
In a kind of exemplary embodiment of the disclosure, described image processing unit includes：
Filter processing unit is filtered to obtain the first middle graph for the image to the pen core scribing line to be detected
Picture；
Binary conversion treatment unit obtains the second intermediate image for carrying out binary conversion treatment to first intermediate image；
Morphological scale-space unit obtains third intermediate image for carrying out Morphological scale-space to second intermediate image；
Feature extraction unit, the image for extracting the pen core scribing line to be detected from the third intermediate image are special
Sign.
In a kind of exemplary embodiment of the disclosure, the filter processing unit is using median filter to described to be checked
The image for surveying pen core scribing line is filtered noise reduction, to obtain first intermediate image.
In a kind of exemplary embodiment of the disclosure, the binary conversion treatment unit is using Threshold segmentation to described to be checked
First intermediate image for surveying pen core scribing line is split processing, to obtain second intermediate image.
In a kind of exemplary embodiment of the disclosure, the Morphological scale-space unit is using expansion algorithm to described to be checked
Second intermediate image for surveying pen core scribing line carries out defect extraction, to obtain the third intermediate image.
In a kind of exemplary embodiment of the disclosure, the detection judging unit includes：
Parameter extraction unit, the pixel value extraction pen to be detected for profile value of being crossed according to the pen core to be detected
The parameter preset of core scribing line；
Comparison judgment unit, for drawing the parameter preset of the pen core scribing line to be detected and the standard pen core to prestore
The parameter preset of line is compared, to judge whether the pen core to be detected is qualified；
As a result recording unit, for by the encoded radio deposit chained list corresponding with the qualified pen core scribing line to be detected
In.
In a kind of exemplary embodiment of the disclosure, the parameter preset of the pen core scribing line to be detected includes described
One or more of the area of pen core to be detected scribing line, shape, width, track.
According to one aspect of the disclosure, a kind of pen core scribing line standardization detection method based on machine vision, packet are provided
It includes：
Carrying pen core to be detected；
The pen core to be detected is encoded according to the carrying of the pen core to be detected sequence；
When detecting the pen core to be detected by predeterminated position, standby signal is sent out；
When the pen core to be detected passes through the predeterminated position, controls the pen core to be detected and cross；
Record encoded radio and the image for acquiring the pen core scribing line to be detected；
The parameter preset that the pen core to be detected is crossed is obtained from the image that the pen core to be detected is crossed, and according to institute
It states parameter preset and judges whether the pen core scribing line to be detected is qualified；
It filters out the qualified pen core of detection and rejects and detect underproof pen core；
The defect of underproof pen core scribing line is analyzed；
Count qualification rate and ratio of defects.
The pen core scribing line standardized detection system based on machine vision and side that a kind of exemplary embodiment of the disclosure provides
In method, on the one hand, by extracting the image of pen core scribing line to be detected and analyzing the parameter preset of pen core to be detected scribing line,
Improve the precision of pen core detection；On the one hand, pen is realized automatically by modules in pen core scribing line standardized detection system
Core detects, and improves the operating efficiency and convenience of pen core detection；On the other hand, by encoder in sequence to pen core into
Row coding, avoids the occurrence of missing inspection, improves the reliability of pen core detection.
It should be understood that above general description and following detailed description is only exemplary and explanatory, not
The disclosure can be limited.
Description of the drawings
Its example embodiment is described in detail by referring to accompanying drawing, the above and other feature and advantage of the disclosure will become
It is more obvious.It should be evident that the accompanying drawings in the following description is only some embodiments of the present disclosure, for the common skill in this field
For art personnel, without creative efforts, other drawings may also be obtained based on these drawings.In attached drawing
In：
Fig. 1 schematically shows a kind of pen core scribing line standardization detection based on machine vision in disclosure exemplary embodiment
The block diagram of system；
Fig. 2 schematically shows the block diagram of image analysis module in disclosure exemplary embodiment；
Fig. 3 schematically shows a kind of process flow of pen core scribing line standardized detection system in disclosure exemplary embodiment
Figure；
Fig. 4 schematically shows a kind of pen core scribing line schematic diagram in disclosure exemplary embodiment；
Fig. 5 schematically shows a kind of pen core scribing line standardization detection based on machine vision in disclosure exemplary embodiment
The flow chart of method.
Specific implementation mode
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be real in a variety of forms
It applies, and is not understood as limited to embodiment set forth herein；On the contrary, thesing embodiments are provided so that the disclosure will be comprehensively and complete
It is whole, and the design of example embodiment is comprehensively communicated to those skilled in the art.Identical reference numeral indicates in figure
Same or similar part, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In example.In the following description, many details are provided to fully understand embodiment of the disclosure to provide.However,
It will be appreciated by persons skilled in the art that can be with technical solution of the disclosure without one in the specific detail or more
It is more, or other methods, constituent element, material, device, step may be used etc..In other cases, it is not shown in detail or describes
Known features, method, apparatus, realization, material or operation are to avoid fuzzy all aspects of this disclosure.
Block diagram shown in attached drawing is only functional entity, not necessarily must be corresponding with physically separate entity.
I.e., it is possible to realize these functional entitys using software form, or these are realized in the module of one or more softwares hardening
A part for functional entity or functional entity, or realized in heterogeneous networks and/or processor device and/or microcontroller device
These functional entitys.
Slack pen core is write in order to efficiently and automatically filter out, solves artificial detection in traditional detection method
The problem longer, accuracy is low, efficiency is low is taken, a kind of pen core based on machine vision stroke is provided in this example embodiment
Line standard detecting system.
The standardized detection system 100 refering to what is shown in Fig. 1, pen core based on machine vision in this example embodiment is crossed
May include：Pen core delivery module 101, encoder 102, pen core detecting module 103, scribing line control module 104, Image Acquisition mould
Block 105, image analysis module 106 and pen core screening module 107, defect analysis module 108 and statistical module 109；Wherein：
Pen core delivery module 101 is used for carrying pen core to be detected；
Encoder 102, for being encoded to the pen core to be detected according to the carrying sequence of the pen core to be detected；
Pen core detecting module 103, for detecting pen core to be detected described in the pen core delivery module carrying by pre-
If when position, sending out standby signal；
Scribing line control module 104, for when the pen core to be detected passes through the predeterminated position, control to be described to be detected
Pen core is crossed；
Image capture module 105, for recording encoded radio that the encoder is currently generated and acquiring the pen to be detected
The image of core scribing line；
Image analysis module 106 is drawn for obtaining the pen core to be detected from the image that the pen core to be detected is crossed
The parameter preset of line, and judge whether the pen core to be detected is qualified according to the parameter preset；
Pen core screening module 107, for filtering out the qualified pen core of detection and rejecting the underproof pen core of detection.
Defect analysis module 108, the defect for crossing to unqualified pen core are analyzed；
Statistical module 109, for counting qualification rate and ratio of defects.
The pen core scribing line standardized detection system based on machine vision in this example embodiment, on the one hand, Ke Yili
With digital image processing techniques, the parameter crossed according to pen core judges whether pen core is qualified, improves the accuracy rate of pen core detection；
On the one hand, it realizes that pen core detects automatically by modules in pen core scribing line standardized detection system, improves pen core detection
Operating efficiency and convenience；On the other hand, pen core is encoded in sequence by encoder, avoids the occurrence of missing inspection, carried
The high reliability of pen core detection.
It should be noted that the pen core scribing line standardized detection system 100 based on machine vision can also include existing skill
The other parts such as power module, light source module and display module in art do not do this special limit in this example embodiment
It is fixed.
Next, referring to figs. 1 to Fig. 4, each mould for standardized detection system of crossing to the pen core based on machine vision
Block is described in detail.
Pen core delivery module 101 can be used for carrying pen core to be detected.
In this example embodiment, the pen core to be detected may include multiple and different types, can be same model or
Person's different model.Pen core delivery module delivery mechanism such as can be conveyer belt or conveyer, can quickly will be to be detected
Pen core carrying is to designated position.
Encoder 102 can be used for compiling the pen core to be detected according to the carrying sequence of the pen core to be detected
Code.
In this example embodiment, encoder can be used to communication, biography to be worked out, being converted to by signal or data
The equipment of defeated and storage signal form.In this example embodiment, encoder can be according to described in pen core delivery module carrying
The sequence of pen core to be detected is encoded, and the sequentially corresponding encoded radio of carrying with the pen core to be detected is generated, so as to
Using the encoded radio as the foundation for subsequently identifying corresponding pen core to be detected, avoids the missing inspection under high speed detection and accidentally sieve
Choosing improves the reliability of pen core detection.
Pen core detecting module 103 can be used for detecting pen core warp to be detected described in the pen core delivery module carrying
When crossing predeterminated position, standby signal is sent out.
In this example embodiment, predeterminated position can be arranged according to user demand, such as in the side of above-mentioned delivery mechanism
Face or other positions.Pen core detecting module may include position sensor, can be detected first by position sensor to be checked
The position of pen core is surveyed, and whether judges the pen core to be detected by pen core delivery module carrying by predeterminated position, herein to be checked
It may include by the error range where predeterminated position that pen core, which is surveyed, by predeterminated position.Judging pen core to be detected by default
When position, standby signal is sent out.Standby signal herein can be auditory tone cues, and standby signal may be display reminding, example
Such as pen core to be detected pass through predeterminated position when, on a terminal screen display pattern mark or words identification.
Specifically, in this example embodiment, the pen core detecting module 103 may include：
Photoelectric sensor is arranged in the predeterminated position, can be used for be checked described in the pen core delivery module carrying
It surveys when pen core passes through the predeterminated position and sends out the standby signal.
In this example embodiment, pen core detecting module may include multiple photoelectric sensors, the multiple photoelectric sensing
The predeterminated position on conveyer belt periphery can be arranged in device.For example, when the position sensor of pen core detecting module detects institute
When stating pen core to be detected described in pen core delivery module carrying by the predeterminated position, since pen core surface to be detected can become
Change, photoelectric sensor can convert the variation on surface to the variation of optical signal, and further generate electric signal, and accordingly can be with
Such as sound transducer or other units for controlling pen core detecting module send out the standby signal.
Scribing line control module 104 can be used for, when the pen core to be detected passes through the predeterminated position, waiting for described in control
Detection pen core is crossed.
In this example embodiment, when pen core detecting module judges that the pen core to be detected passes through the predeterminated position,
Scribing line control module can control the pen core to be detected in a certain fixed position, and system for automatic marker making is carried out with identical angle, from
And it can judge whether pen core is qualified by judging whether the scribing line of pen core to be detected complies with standard.It is carried out certainly by controlling pen core
Dynamic scribing line, improves the efficiency of pen core detection.
Image capture module 105 can be used for when receiving the standby signal, record what the encoder was currently generated
Encoded radio and the image for acquiring the pen core scribing line to be detected.
In this example embodiment, described image acquisition module can be believed receiving the prompt that pen core detecting module is sent out
Number when, obtain the information for the pen core to be detected for being currently at predeterminated position, the information of acquisition may include：Encoder is recorded to generate
Encoded radio corresponding with the sequence of pen core to be detected of predeterminated position is currently at and acquire current pen core scribing line to be detected
Image.The image of pen core scribing line to be detected can be coloured image, or black white image.
Specifically, in this example embodiment, described image acquisition module 105 may include：
Image pick-up card can be used for receiving the standby signal and record the volume when receiving the standby signal
The encoded radio that code device is currently generated；
Industrial camera can be used for when described image capture card receives the standby signal, and acquisition is described to be detected
The image of pen core scribing line.
In this example embodiment, image pick-up card can be used for receiving the prompt letter that pen core detecting module is sent out
Number, and record after receiving the standby signal encoded radio that the encoder is currently generated.Video camera is machine vision system
System part the most vital, important like that for the vision system of people just as human eye, major function is by optical signal
It is converted into electric signal.Video camera chooses whether properly to be related to the height of image resolution ratio, while also determining entire system
The operational mode of system, therefore the type selecting of video camera is a most important link of entire the hardware design.Sensor is to take the photograph
The core component of camera, video camera can divide CCD (Charge Couple Device, charge coupling according to the difference of sensitive chip
Clutch part) video camera and CMOS (Complementary Metal Oxide Semiconductor, metal-oxide semiconductor (MOS))
Video camera.CCD camera, the Electronic saving that can will be exported in image semiconductor.Currently used CCD structures have three
Kind, full frame transfer, frame transmission and row transfer.Cmos camera, can be by light-sensitive element, amplifier, A/D converter, memory
Equal components and interface control circuit are integrated on one piece of silicon chip.After described image capture card receives the standby signal, work
Industry camera can acquire the image of the pen core scribing line to be detected.
Image analysis module 106 can be used for obtaining the pen to be detected from the image that the pen core to be detected is crossed
The parameter preset of core scribing line, and judge whether the pen core scribing line to be detected is qualified according to the parameter preset.
In this example embodiment, the pen core to be detected that image analysis module can be acquired according to image capture module is crossed
Image, obtain the parameter preset of corresponding pen core to be detected scribing line, and the parameter preset and standard that pen core to be detected is crossed
The parameter preset of pen core scribing line is compared, in the parameter preset of the parameter preset and the scribing line of standard pen core of pen core to be detected scribing line
Matching or in error range when, it can be determined that the pen core to be detected is qualified.
Specifically, in this example embodiment, refering to what is shown in Fig. 2, described image analysis module 106 may include：
Image processing unit 1061 can be used for pre-processing the image of the pen core scribing line to be detected, and extract
The profile of the pen core scribing line image to be detected；
Pixel extraction unit 1062 can be used for from the profile that the pen core to be detected crosses image extracting described to be checked
Survey the pixel value of pen core scribing line profile；
Judging unit 1063 is detected, the pixel value for the profile that can be used for crossing according to the pen core to be detected, described in extraction
The parameter preset of pen core scribing line to be detected, and judge whether the pen core scribing line to be detected is qualified according to the parameter preset.
In this example embodiment, described image processing unit can be used for the pen core scribing line to be detected to acquisition
Image carries out pretreatment operation, and obtains the profile diagram of the pen core scribing line image to be detected.For example, it may be used
The rgb functions for gray-scale Image Edge extraction provided in halcon extract the profile of the pen core scribing line image to be detected
Figure can also use the function in OpenCV to extract the profile diagram of the pen core scribing line image to be detected.Pass through image procossing list
The profile of the member extraction pen core scribing line image to be detected, in order to subsequently be carried to the characteristics of image of pen core to be detected scribing line
It takes and identifies, achieve the purpose that effectively to detect.
Further, in this example embodiment, described image processing unit 1061 may include：
Filter processing unit 10611 can be used for being filtered to obtain to the image of the pen core scribing line to be detected
First intermediate image；
Binary conversion treatment unit 10612 can be used for carrying out binary conversion treatment to first intermediate image obtaining second
Intermediate image；
Morphological scale-space unit 10613 can be used for carrying out Morphological scale-space to second intermediate image obtaining third
Intermediate image；
Feature extraction unit 10614 can be used for from the third intermediate image extracting the pen core scribing line to be detected
Characteristics of image.
In this example embodiment, the filter processing unit can be used for the pen core scribing line to be detected to acquisition
Image is filtered to obtain filtered first intermediate image.Can use mean filter, medium filtering, gaussian filtering or
Person's bilateral filtering method is filtered.By the filter processing unit, in the image that industrial camera acquisition can be solved
The noise in pen core scribing line image to be detected and unwanted part are eliminated or reduced to the problem of noise jamming, and improving image can
By property.
Specifically, in this example embodiment, median filter may be used to described to be checked in the filter processing unit
The image of survey pen core scribing line is filtered noise reduction and obtains first intermediate image.
In this example embodiment, with filter processing unit using median filter to the figure of the pen core scribing line to be detected
It is illustrated as being filtered for noise reduction.Medium filtering can be the value of any in the digital picture or Serial No. point
The Mesophyticum of each point value replaces in one neighborhood, the actual value for making the pixel value of surrounding close, to eliminate noise.It specifically can be with
It is realized, can also be realized using C language by the function medianBlur in OpenCV.
In this example embodiment, the binary conversion treatment unit can be used for carrying out two-value to first intermediate image
Change handles to obtain the second intermediate image.Second intermediate image is the gray level image after being filtered.For example, image binaryzation
Processing is that the gray value of pixel is set to 120 more than predetermined threshold value, and 0 is set to less than predetermined threshold value.It is being carried out in this example
When detection, the threshold value of image segmentation can be chosen according to the grey level histogram information of image, and using the overall situation
Threshold value is split entire image using same threshold interval.It can wherein be determined most by the method for analyzing histogram
Good threshold value, such as when histogram is rendered obvious by bi-modal case, the midpoint of two peak values can be selected as optimal threshold.Knot
After closing threshold value selection, as shown in figure 4, the black region that wherein gray scale is 120 is pen core scribing line to be detected.
In this example embodiment, the Morphological scale-space unit can be used for carrying out form to second intermediate image
Handle to obtain third intermediate image.Second intermediate image is filtered treated pen core to be detected crosses image.Into
When row binary conversion treatment, the inside of pen core scribing line image-region will appear stain and flaw etc., be formed in background area smaller
Pseudo- target point, therefore Morphological scale-space is carried out to image, to eliminate the defect point occurred in image, while pen core will not be changed
The feature of scribe area image.
Mathematical mor-phology is a kind of based on shape, and carries out the work of analyzing processing to image based on algebra of sets
Tool, can use certain shape structural element go measure and extract image in corresponding shape, with to image carry out analysis and
Identification.In this example, the stain of product ink can be found out in line segment by the expansion algorithm in morphology, and it is handled with
Obtain third intermediate image.Specifically, all background dots contacted with pen core scribing line can be merged into pen core scribing line,
Boundary is set to be expanded to outside.By each pixel of scan image, the bianry image covered with it with structural element does "or"
Operation, and bianry image is made to expand a circle.
In this example embodiment, area features are an important evidences of progress feature extraction, therefore can be according to spy
It levies the area in histogram and feature extraction is carried out to third intermediate image, and judge whether pen core scribing line is qualified with this.
It should be noted that described image processing unit can also include other parts and carry out other processing steps.
For example, before being filtered step, image gray processing that the pen core to be detected of acquisition can also be crossed handles or passes through line
Property become and bring enhancing picture contrast etc., be not limited thereto in the present exemplary embodiment.
In this example embodiment, detection judging unit can be according to the pixel of the pen core scribing line profile diagram to be detected
Value, the parameter preset of the extraction pen core scribing line to be detected, and parameter preset and standard by comparing pen core scribing line to be detected
The parameter preset of pen core scribing line, judges whether the pen core to be detected is qualified.
Specifically, in this example embodiment, the detection judging unit 1063 may include：
Parameter extraction unit 10631, the pixel value extraction institute for the profile diagram that can be used for being crossed according to the pen core to be detected
State the parameter preset of pen core scribing line to be detected；
Comparison judgment unit 10632 can be used for the parameter preset of the pen core to be detected scribing line and prestore
The parameter preset of standard pen core scribing line is compared, to judge whether the pen core scribing line to be detected is qualified；
As a result recording unit 10633 can be used for the coding corresponding with the qualified pen core scribing line to be detected
In value deposit chained list.
In this example embodiment, parameter extraction unit can be according to the pixel of the pen core scribing line profile diagram to be detected
Value, the parameter preset of the extraction pen core scribing line to be detected.Pen core scribing line to be detected is extracted in parameter extraction unit
After parameter preset, comparison judgment unit can be by the parameter preset of the scribing line of the pen core to be detected and the standard pen core to prestore
The parameter preset of scribing line is compared.Specifically, parameter preset that can be in the scribing line of pen core to be detected and the standard that prestores
The parameter preset of pen core scribing line is identical, or when presetting in error range, judges that pen core to be detected is qualified.Default error
It can be customized for smaller numerical value according to actual demand, such as can be 0.1% etc..Judge in comparison judgment unit to be checked
Survey pen core it is whether qualified after, as a result recording unit can record the corresponding encoded radio of the qualified pen core to be detected, can
Encoded radio to be stored in chained list, determine whether corresponding pen core to be detected is qualified in the follow-up process.In addition, this example is implemented
The underproof pen core to be detected of scribing line can also be shown in mode on the interface of terminal, in order to which the later stage is for statistical analysis.
Specifically, the parameter preset of the pen core scribing line to be detected may include the face of the pen core scribing line to be detected
One or more of product, shape, width, track.
In this example embodiment, parameter preset can have multiple, may include one in area, shape, width, track
It is a or multiple, can also include other parameters.It can also can jointly judge pen according to multiple parameters according to a parameter decision
Whether core is qualified.It is illustrated with area example in the present exemplary embodiment.May be used such as contourArea functions or
Threshold functions calculate the area of the pen core scribing line to be detected, the area crossed in pen core to be detected and the standard to prestore
When the area difference of pen core scribing line is larger, it is believed that pen core to be detected is unqualified
For example, cross for pen core shown in Fig. 4, it can be determined that area in unit length whether with prestore
The unit area matching of standard pen core scribing line.Area in pen core unit length to be detected is less than or substantially exceeds standard pen
When core scribing line area, it is believed that the pen core is unqualified.
Pen core screening module 107 can be used for filtering out the qualified pen core of detection and reject and detects underproof pen core.
In this example embodiment, pen core screening module may include sorting equipment, when passing through the to be detected of sorting equipment
When the encoded radio of pen core is not in the chained list, you can judge pen core to be detected for substandard product, can then notify at this time point
Device is picked to reject unqualified pen core.For example, sorting equipment can be solenoid valve sorting equipment, and sorting equipment can incite somebody to action
Unqualified pen core is sorted to substandard products collecting box.But it should be recognized that in other exemplary embodiments of the disclosure, the pen
Core screening module can also be realized using other feasible modes, it is not limited to the realization enumerated in this example embodiment
Mode.
Defect analysis module 108 can be used for analyzing the defect that unqualified pen core is crossed；
It, can be according to representing pixel based on the unit area of foregoing description to the importance of third intermediate image feature extraction
The defect that the area of points crosses to pen core is analyzed, to obtain generating the concrete reason of defect.For example, work as area
When (pixel number) is less than 6000, it is believed that pen core can be crossed and be sorted out when area is more than 7000 by pen core scribing line broken string
For product ink.
Statistical module 109, for counting qualification rate and ratio of defects.
It by the qualification rate for the pen core scribing line that statistical module general evaluation system detects, ratio of defects and can also be lacked in this system
The information such as reason are fallen into, to the quality of pen core accurately detect and record.
In addition to this, can also include system module in this example, may include Image Acquisition, flaw presentation of information and
Inquiry and etc..Following flow can be executed by writing program：First system initialization, then connects database, see whether at
Work(opens camera if success, and camera parameter, acquisition and display image is arranged, is detected using image processing algorithm
It whether there is flaw or defect in the image of pen core scribing line, flaw information shown if having and by flaw information preservation to data
In library, an Image Acquisition and processing are completed.
In conclusion all pen core to be detected scribing line can according to fig. 3 shown in step S301 to step S307
It is standardized detection, to filter out qualified pen core and reject unqualified pen core.
Design in the above-mentioned pen core scribing line standardized detection system based on machine vision can be that exploitation basis is flat with C++
Platform, in conjunction with increasing income, visibility function library OpenCV and image procossing class libraries CImg writes program to realize that standardized detection system is wanted
The function of asking.Entire software interface may include image display area, base menu region, measure setting regions, testing result
The parts such as display area, to realize through the whether qualified function of Image Acquisition automatic discrimination pen core.
In an exemplary embodiment of the disclosure, a kind of pen core scribing line standardization detection based on machine vision is additionally provided
Method, refering to what is shown in Fig. 5, the method may include：
Step S510. carryings pen core to be detected；
Step S520. encodes the pen core to be detected according to the carrying sequence of the pen core to be detected；
Step S530. sends out standby signal when detecting the pen core to be detected by predeterminated position；
Step S540. controls the pen core to be detected and is drawn when the pen core to be detected passes through the predeterminated position
Line；
Step S550. record encoded radios and the image for acquiring the pen core scribing line to be detected；
Step S560. obtains the default ginseng that the pen core to be detected is crossed from the image that the pen core to be detected is crossed
Number, and judge whether the pen core scribing line to be detected is qualified according to the parameter preset；
Step S570., which filters out the qualified pen core of detection and rejects, detects underproof pen core；
The defect that step S580. crosses to underproof pen core is analyzed；
Step S590. statistics qualification rates and ratio of defects.
Each step is based on machine corresponding in the above-mentioned pen core scribing line standardization detection method based on machine vision
It is described in detail in the pen core scribing line standardized detection system of vision, therefore details are not described herein again.
In addition, above-mentioned attached drawing is only the schematic theory of the processing included by method according to an exemplary embodiment of the present invention
It is bright, rather than limit purpose.It can be readily appreciated that the time that above-mentioned processing shown in the drawings did not indicated or limited these processing is suitable
Sequence.In addition, being also easy to understand, these processing for example can be executed either synchronously or asynchronously in multiple modules.
It should be noted that although being referred to several modules or list for acting the equipment executed in above-detailed
Member, but this division is not enforceable.In fact, according to embodiment of the present disclosure, it is above-described two or more
The feature and function of module either unit can embody in a module or unit.Conversely, an above-described mould
Either the feature and function of unit can be further divided into and embodied by multiple modules or unit block.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
His embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Adaptive change follow the general principles of this disclosure and include the undocumented common knowledge in the art of the disclosure or
Conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by claim
It points out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the attached claims.
Claims (11)
- The standardized detection system 1. a kind of pen core based on machine vision is crossed, which is characterized in that including：Pen core delivery module is used for carrying pen core to be detected；Encoder, for being encoded to the pen core to be detected according to the carrying sequence of the pen core to be detected；Pen core detecting module, for detecting pen core to be detected described in the pen core delivery module carrying by predeterminated position When, send out standby signal；Cross control module, for when the pen core to be detected passes through the predeterminated position, control the pen core to be detected into Row scribing line；Image capture module, for recording encoded radio that the encoder is currently generated and acquiring the pen core scribing line to be detected Image；Image analysis module, for obtaining the default of the pen core scribing line to be detected from the image that the pen core to be detected is crossed Parameter, and judge whether the pen core scribing line to be detected is qualified according to the parameter preset；Pen core screening module, for filtering out the qualified pen core of detection and rejecting the underproof pen core of detection；Defect analysis module, the defect for crossing to unqualified pen core are analyzed；Statistical module, for counting qualification rate and ratio of defects.
- The standardized detection system 2. pen core according to claim 1 based on machine vision is crossed, which is characterized in that described Pen core detecting module includes：Photoelectric sensor, setting is in the predeterminated position, for the pen core warp to be detected described in the pen core delivery module carrying The standby signal is sent out when crossing the predeterminated position.
- The standardized detection system 3. pen core according to claim 1 based on machine vision is crossed, which is characterized in that described Image capture module includes：Image pick-up card for receiving the standby signal, and records the encoder after receiving the standby signal and works as Previous existence at encoded radio；Industrial camera, for after described image capture card receives the standby signal, the acquisition pen core to be detected to be crossed Image.
- The standardized detection system 4. pen core according to claim 1 based on machine vision is crossed, which is characterized in that described Image analysis module includes：Image processing unit pre-processes for the image to the pen core scribing line to be detected, and extracts the pen to be detected The profile of core scribing line image；Pixel extraction unit, for extracting the pen core stitch marker to be detected from the profile that the pen core to be detected crosses image Wide pixel value；Judging unit is detected, for the pixel value for profile of being crossed according to the pen core to be detected, the pen core to be detected is extracted and draws The parameter preset of line, and judge whether the pen core to be detected is qualified according to the parameter preset.
- The standardized detection system 5. pen core according to claim 4 based on machine vision is crossed, which is characterized in that described Image processing unit includes：Filter processing unit is filtered to obtain the first intermediate image for the image to the pen core scribing line to be detected；Binary conversion treatment unit obtains the second intermediate image for carrying out binary conversion treatment to first intermediate image；Morphological scale-space unit obtains third intermediate image for carrying out Morphological scale-space to second intermediate image；Feature extraction unit, the characteristics of image for extracting the pen core scribing line to be detected from the third intermediate image.
- The standardized detection system 6. pen core according to claim 5 based on machine vision is crossed, which is characterized in that described Filter processing unit is filtered noise reduction using median filter to the image of the pen core to be detected scribing line, to obtain described the One intermediate image.
- The standardized detection system 7. pen core according to claim 5 based on machine vision is crossed, which is characterized in that described Binary conversion treatment unit is split processing using Threshold segmentation to first intermediate image of the pen core scribing line to be detected, To obtain second intermediate image.
- The standardized detection system 8. pen core according to claim 5 based on machine vision is crossed, which is characterized in that described Morphological scale-space unit carries out defect extraction using expansion algorithm to second intermediate image of the pen core scribing line to be detected, To obtain the third intermediate image.
- The standardized detection system 9. pen core according to claim 4 based on machine vision is crossed, which is characterized in that described Detecting judging unit includes：Parameter extraction unit, the pixel value extraction pen core to be detected stroke for profile value of being crossed according to the pen core to be detected The parameter preset of line；Comparison judgment unit, for what the parameter preset of the pen core scribing line to be detected and the standard pen core to prestore were crossed Parameter preset is compared, to judge whether the pen core to be detected is qualified；As a result recording unit, for the encoded radio corresponding with the qualified pen core scribing line to be detected to be stored in chained list.
- The standardized detection system 10. pen core according to claim 8 based on machine vision is crossed, which is characterized in that institute It states in the area, shape, width, track that the parameter preset that pen core to be detected is crossed includes the pen core scribing line to be detected It is one or more.
- 11. a kind of pen core scribing line standardization detection method based on machine vision, which is characterized in that including：Carrying pen core to be detected；The pen core to be detected is encoded according to the carrying of the pen core to be detected sequence；When detecting the pen core to be detected by predeterminated position, standby signal is sent out；When the pen core to be detected passes through the predeterminated position, controls the pen core to be detected and cross；Record encoded radio and the image for acquiring the pen core scribing line to be detected；The parameter preset that the pen core to be detected is crossed is obtained from the image that the pen core to be detected is crossed, and according to described pre- Setting parameter judges whether the pen core scribing line to be detected is qualified；It filters out the qualified pen core of detection and rejects and detect underproof pen core；The defect of underproof pen core scribing line is analyzed；Count qualification rate and ratio of defects.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810127044.9A CN108362708A (en) | 2018-02-08 | 2018-02-08 | Pen core scribing line standardized detection system based on machine vision and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810127044.9A CN108362708A (en) | 2018-02-08 | 2018-02-08 | Pen core scribing line standardized detection system based on machine vision and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108362708A true CN108362708A (en) | 2018-08-03 |
Family
ID=63005332
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810127044.9A Pending CN108362708A (en) | 2018-02-08 | 2018-02-08 | Pen core scribing line standardized detection system based on machine vision and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108362708A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109444167A (en) * | 2018-12-12 | 2019-03-08 | 深圳格瑞克机械有限公司 | A kind of eyeliner automatic detection device |
| CN110174063A (en) * | 2019-06-11 | 2019-08-27 | 上海工程技术大学 | A kind of neutral pen ink height detecting system and detection method based on machine vision |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007255959A (en) * | 2006-03-22 | 2007-10-04 | Lasertec Corp | Inspection apparatus, inspection method, and manufacturing method of pattern substrate using the inspection apparatus and the inspection method |
| CN102445457A (en) * | 2011-10-18 | 2012-05-09 | 上海桂莘实业有限公司 | Assembly line-embedded automatic refill drawing detection device |
| CN104006758A (en) * | 2013-02-26 | 2014-08-27 | 张继红 | Automatic detection method for pen refill quality |
| CN105628096A (en) * | 2015-12-29 | 2016-06-01 | 丁云峰 | Ball point pen refill automatic marking inspection device |
| CN105973148A (en) * | 2016-07-20 | 2016-09-28 | 上海晨光文具股份有限公司 | Pen point appearance size standardization detection system based on machine vision |
-
2018
- 2018-02-08 CN CN201810127044.9A patent/CN108362708A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2007255959A (en) * | 2006-03-22 | 2007-10-04 | Lasertec Corp | Inspection apparatus, inspection method, and manufacturing method of pattern substrate using the inspection apparatus and the inspection method |
| CN102445457A (en) * | 2011-10-18 | 2012-05-09 | 上海桂莘实业有限公司 | Assembly line-embedded automatic refill drawing detection device |
| CN104006758A (en) * | 2013-02-26 | 2014-08-27 | 张继红 | Automatic detection method for pen refill quality |
| CN105628096A (en) * | 2015-12-29 | 2016-06-01 | 丁云峰 | Ball point pen refill automatic marking inspection device |
| CN105973148A (en) * | 2016-07-20 | 2016-09-28 | 上海晨光文具股份有限公司 | Pen point appearance size standardization detection system based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| 杨欧: "《基于物联网平台的智能服务机器人设计》", 31 January 2018, 西安交通大学出版社 * |
| 童季刚: "一种机器视觉的瓶罐缺陷检测系统设计", 《机电工程技术》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109444167A (en) * | 2018-12-12 | 2019-03-08 | 深圳格瑞克机械有限公司 | A kind of eyeliner automatic detection device |
| CN109444167B (en) * | 2018-12-12 | 2024-03-26 | 广东格瑞克智能科技有限公司 | Automatic detection device for eyeliner |
| CN110174063A (en) * | 2019-06-11 | 2019-08-27 | 上海工程技术大学 | A kind of neutral pen ink height detecting system and detection method based on machine vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111951237B (en) | Visual appearance detection method | |
| CN110672617B (en) | Method for detecting defects of silk-screen area of glass cover plate of smart phone based on machine vision | |
| CN106875373B (en) | Mobile phone screen MURA defect detection method based on convolutional neural network pruning algorithm | |
| CN112036755B (en) | Supervision method and system for quality detection of building engineering | |
| CN109550712A (en) | A kind of chemical fiber wire tailfiber open defect detection system and method | |
| CN114926463B (en) | Production quality detection method suitable for chip circuit board | |
| JP2020106467A (en) | Defect inspection device, defect inspection method, and program therefor | |
| CN109508664A (en) | A kind of vegetable identification pricing method based on deep learning | |
| TWI642126B (en) | Semiconductor wafer analyzing sytem and method thereof | |
| CN105973148A (en) | Pen point appearance size standardization detection system based on machine vision | |
| CN108776964A (en) | A kind of ship weld defect image detecting system and method based on Adaboost and Haar features | |
| CN112150460A (en) | Detection method, detection system, device, and medium | |
| CN113222938A (en) | Chip defect detection method and system and computer readable storage medium | |
| CN107590511A (en) | A kind of defect identification method and identifying system the defects of for automatic check machine | |
| CN108362708A (en) | Pen core scribing line standardized detection system based on machine vision and method | |
| CN111077150A (en) | Intelligent excrement analysis method based on computer vision and neural network | |
| CN114549493A (en) | Magnetic core defect detection system and method based on deep learning | |
| CN111210417B (en) | Cloth defect detection method based on convolutional neural network | |
| CN113870202A (en) | Far-end chip defect detection system based on deep learning technology | |
| CN117455917B (en) | Establishment of false alarm library of etched lead frame and false alarm on-line judging and screening method | |
| CN113076860B (en) | Bird detection system under field scene | |
| CN115170501A (en) | Defect detection method, system, electronic device and storage medium | |
| KR20180092033A (en) | Component registration device | |
| CN107742287A (en) | Sheath detecting system and method | |
| KR20080079798A (en) | Method of face detection and recognition |
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: 20180803 |
|
| RJ01 | Rejection of invention patent application after publication |