CN107014822B - Non-woven fabric mask defect visual detection system and method - Google Patents
Non-woven fabric mask defect visual detection system and method Download PDFInfo
- Publication number
- CN107014822B CN107014822B CN201710117286.5A CN201710117286A CN107014822B CN 107014822 B CN107014822 B CN 107014822B CN 201710117286 A CN201710117286 A CN 201710117286A CN 107014822 B CN107014822 B CN 107014822B
- Authority
- CN
- China
- Prior art keywords
- woven fabric
- image
- fabric mask
- product
- mask
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8914—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined
- G01N21/8915—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles characterised by the material examined non-woven textile material
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N21/8901—Optical details; Scanning details
- G01N2021/8908—Strip illuminator, e.g. light tube
-
- 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
- G01N21/89—Investigating the presence of flaws or contamination in moving material, e.g. running paper or textiles
- G01N2021/8909—Scan signal processing specially adapted for inspection of running sheets
Abstract
The invention discloses a visual detection system and a method for defects of a non-woven fabric mask, wherein the system comprises the following components: the image acquisition device is used for acquiring an image of a non-woven fabric mask product to be detected; the detection base is used for supporting the non-woven fabric mask product and is positioned below the image acquisition device; the photoelectric sensor is arranged on the detection base and used for detecting whether the non-woven fabric mask product is in place or not; the NG processing device is used for processing the non-woven fabric mask product to a preset position according to a preset program; the cylinder is fixedly connected with the NG processing device; a first belt and a second belt; a motor; the motor driver is used for driving the motor to drive the first belt and the second belt to move and is electrically connected with the motor; and the industrial personal computer is respectively connected with the image acquisition device, the air cylinder, the photoelectric sensor and the motor driver. The beneficial effects of the invention are as follows: the qualification rate of products is improved, the quality risk of products leaving factories is reduced, and the defects of the non-woven fabric mask are identified by fully utilizing the image processing and mode identification technology.
Description
Technical Field
The invention relates to the technical field of machine vision image detection and mode identification, in particular to a non-woven fabric mask defect vision detection system and method.
Background
In recent years, with the rapid development of image processing and pattern recognition technologies, more and more engineering projects are used to solve practical problems by using image processing algorithms, such as dimension measurement, classification and recognition of workpiece products, detection of surface defects of products, license plate number recognition, barcode recognition, and the like. Along with the continuous improvement of economic level, the using amount of urban automobiles is more and more, the exhausted tail gas forms serious haze, the mask is a necessary product for people life in haze weather, doctors, nurses and patients can not leave the mask product in hospitals, most masks are produced by non-woven fabrics at present, the non-woven fabrics mask can generate various defects of poor ear band welding, no nose strip installation, different lengths of ear band and nose strips, overlapped and welded masks, black spots of production equipment, oil stains and the like on the mask body, the defects can cause that the mask can not be well fixed on the face of a user, and the body health of the user can be affected even a few, the defects of the non-woven fabrics mask products are identified by manual detection, the detection efficiency of the manual defects is low, the cost is high, if the manual online detection is carried out on a production line, there is also certain safety risk, and the long-time detection of manual work has the phenomenon of louing examining moreover.
Disclosure of Invention
The invention aims to solve the technical problems of low production efficiency, high cost and unsafety in manual detection of non-woven fabric mask products in the prior art, and provides a non-woven fabric mask defect visual detection system and a non-woven fabric mask defect visual detection method.
The technical scheme adopted by the invention for solving the technical problems is as follows:
a non-woven fabric mask defect visual inspection system is constructed, comprising:
the image acquisition device is used for acquiring an image of a non-woven fabric mask product to be detected;
the detection base is used for supporting the non-woven fabric mask product and is positioned below the image acquisition device;
the photoelectric sensor is arranged on the detection base and used for detecting whether the non-woven fabric mask product is in place or not;
the NG processing device is used for processing the non-woven fabric mask product to a preset position according to a preset program;
the cylinder is used for driving the NG processing device to process the non-woven fabric mask product to a preset position and is fixedly connected with the NG processing device;
the first belt and the second belt are respectively arranged on two sides of the non-woven fabric mask product and are used for driving the non-woven fabric mask product to move on the detection base;
a motor for driving the first belt and the second belt;
the motor driver is used for driving the motor to drive the first belt and the second belt to move and is electrically connected with the motor;
and the industrial personal computer is respectively connected with the image acquisition device, the air cylinder, the photoelectric sensor and the motor driver.
The visual detection system for the defects of the non-woven fabric mask further comprises:
l ED light source, be used for doing non-woven fabrics gauze mask product light filling, set up in detect the base downside, electric connection in the industrial computer.
The visual detection system for the defects of the non-woven fabric mask further comprises:
a vertical support;
and one end of the horizontal support is fixedly connected with the vertical support, and the other end of the horizontal support is fixedly connected with the image acquisition device.
In the visual inspection system for defects of a non-woven fabric mask according to the present invention, the image capturing device includes:
the side surface of the industrial camera is provided with an opening, the horizontal support penetrates through the opening to fix the industrial camera, and the industrial camera is electrically connected with the industrial personal computer;
and the industrial lens is arranged on the lower surface of the industrial camera so as to be aligned with the non-woven fabric mask product.
In the visual detection system for the defects of the non-woven fabric mask, the centers of the non-woven fabric mask product and the detection base are positioned on the same central axis.
In the visual inspection system for defects of a non-woven fabric mask, the industrial personal computer comprises:
the gigabit network interface is connected to the image acquisition device to transmit image data of the non-woven fabric mask product;
the I/O control interface is connected to the photoelectric sensor and the air cylinder;
an RS232 interface connected to the motor driver;
and the VGA interface is connected to a preset display.
In the visual inspection system for defects of a non-woven fabric mask, the industrial personal computer comprises:
a digital light source control interface connected to the L ED light source.
On the other hand, the non-woven fabric mask defect visual detection method is provided, and the non-woven fabric mask defect visual detection system comprises:
acquiring an image of a non-woven fabric mask product by the image acquisition device, and transmitting the image to the industrial personal computer;
converting the image into a gray-scale image by the industrial personal computer, calculating the deviation between the gray-scale image and a preset standard non-woven fabric mask product, and acquiring the positioning information of the non-woven fabric mask product by a contour extraction algorithm and a minimum external quadrilateral algorithm;
judging whether the non-woven fabric mask product has defects according to the positioning information;
and controlling the NG processing device to process the non-woven fabric mask product to a preset position according to a preset program.
In the visual inspection method for defects of a non-woven fabric mask, the image is converted into a gray scale image by the industrial personal computer, the deviation between the gray scale image and a preset standard non-woven fabric mask product is calculated, and the positioning information of the non-woven fabric mask product is acquired by a contour extraction algorithm and a minimum external quadrilateral algorithm, and the method comprises the following steps:
converting the image into a gray-scale image by the industrial personal computer, and carrying out binarization processing on the gray-scale image;
calculating the difference value between the gray level image after binarization processing and a preset standard non-woven fabric mask product, and taking the absolute value of the difference value to obtain a difference image;
and carrying out image dislocation area processing on the difference image to obtain a dislocation image, wherein the image dislocation area processing comprises the following steps: traversing the pixel value of the difference image, setting the pixel value of a preset position as 0 or 255, and keeping the rest pixels unchanged;
and detecting the image contour of the avoiding image by adopting a contour extraction algorithm, and performing external quadrilateral fitting processing on the contour with the largest area by adopting a minimum external quadrilateral algorithm so as to obtain coordinates of four vertexes of an external quadrilateral.
In the visual inspection method for defects of a non-woven fabric mask, the step of judging whether the non-woven fabric mask product has defects according to the positioning information comprises the following steps:
judge whether non-woven fabrics gauze mask product has the dirty defect of gauze mask body: acquiring a mask body through positioning information, performing fixed threshold binarization processing on an image in the mask body, calculating the total number of mask pixels of non-zero pixels, and judging whether the total number of the mask pixels is within a preset first threshold range, if so, judging that no mask body is dirty, and if not, judging that the mask body is dirty;
judging whether the non-woven fabric mask product has ear band defects: acquiring an ear zone region through positioning information, setting a connection point of the ear zone region and the mask body into four fixed regions, carrying out fixed threshold value binarization processing on the four fixed regions, acquiring a communication region with the largest area by adopting a communication region extraction algorithm, calculating characteristic parameters of a plurality of communication regions, and judging whether the characteristic parameters are within a preset second threshold value range, if so, judging that no ear zone defect exists, and if not, judging that the ear zone defect exists;
judging whether the non-woven fabric mask product has a product overlapping defect: acquiring a nose strip area in the mask body through the positioning information, performing fixed threshold binarization processing on the nose strip area, calculating the total number of nose strip pixels of non-zero pixels, and judging whether the total number of the nose strip pixels is within a preset third threshold range, if so, judging that the mask has a product overlapping defect, and if not, judging that the mask has no product overlapping defect;
judging whether the non-woven fabric mask product has nose strip defects: and carrying out self-adaptive threshold value binarization processing and corrosion operation on the image in the bag body region, obtaining all connected regions in the bag body region by adopting a connected region extraction algorithm, calculating the total characteristic parameters of the connected regions, judging whether the total characteristic parameters are within a preset fourth threshold value range, if so, judging that no nose strip defect exists, and if not, judging that the nose strip defect exists.
The non-woven fabric mask defect visual detection system and the non-woven fabric mask defect visual detection method have the following beneficial effects: the problems of low production efficiency, high cost, unsafety and the like of manual detection of defects of the non-woven fabric mask are solved, the problem of manual omission is solved, the qualification rate of products is improved, and the quality risk of products leaving a factory is reduced; make full use of image processing and pattern recognition technology discernment non-woven fabrics gauze mask defect has replaced artifical the detection, has reduced the manufacturing cost of enterprise, has improved the production efficiency of enterprise, has promoted the economic benefits of enterprise.
Drawings
Fig. 1 is a schematic structural diagram of a non-woven fabric mask defect visual inspection system according to an embodiment of the present invention;
FIG. 2 is a block diagram of an image processing software platform according to an embodiment of the present invention;
fig. 3 is a flowchart of a visual inspection method for defects of a non-woven fabric mask according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
The invention provides a visual detection system and method for defects of a non-woven fabric mask, and aims to solve the problems of low production efficiency, high cost, unsafety and the like of manual detection of the defects of the non-woven fabric mask, solve the problem of manual omission, improve the qualification rate of products and reduce the quality risk of products delivered from factories; make full use of image processing and pattern recognition technology discernment non-woven fabrics gauze mask defect has replaced artifical the detection, has reduced the manufacturing cost of enterprise, has improved the production efficiency of enterprise, has promoted the economic benefits of enterprise.
Referring to fig. 1, fig. 1 is a schematic structural diagram of a visual detection system for defects of a non-woven fabric mask according to an embodiment of the present invention, where the visual detection system for defects of a non-woven fabric mask includes an image acquisition device, a detection base 5, a photoelectric sensor 8, an NG processing device 102, a cylinder 101, a first belt 6 and a second belt 7, a motor 19, a motor driver 18, an industrial personal computer 9, an L ED light source 3, a vertical support, and a horizontal support.
The image acquisition device is used for acquiring an image of a non-woven fabric mask product 4 to be detected; the image acquisition device comprises an industrial camera 1 and an industrial lens 2, an opening is formed in the side face of the industrial camera 1, the horizontal support penetrates through the opening to fix the industrial camera 1, and the industrial camera 1 is electrically connected with the industrial personal computer 9; an industrial lens 2 is disposed on a lower surface of the industrial camera 1 to be aligned with the non-woven fabric mask product 4.
The detection base 5 is used for supporting the non-woven fabric mask product 4, and the detection base 5 is positioned below the image acquisition device; the non-woven fabric mask product 4 and the center of the detection base 5 are positioned on the same central axis.
The photoelectric sensor 8 is arranged on the detection base 5 and is used for detecting whether the non-woven fabric mask product 4 is in place or not;
the NG processing device 102 is configured to process the non-woven fabric mask product 4 to a preset position according to a preset program;
the cylinder 101 is used for driving the NG processing device 102 to process the non-woven fabric mask product 4 to a preset position and is fixedly connected with the NG processing device 102; the cylinder 101 is a cylindrical metal member that guides a piston to linearly reciprocate in the cylinder. Air converts thermal energy into mechanical energy by expansion in an engine cylinder; the gas is compressed by a piston in a compressor cylinder to increase pressure. The housing of a turbine, a rotary piston engine or the like is often also referred to as a "cylinder".
The first belt 6 and the second belt 7 are respectively arranged on two sides of the non-woven fabric mask product 4 and are used for driving the non-woven fabric mask product 4 to move on the detection base 5;
the motor 19 is used for driving the first belt 6 and the second belt 7;
the motor driver 18 is used for driving the motor 19 to drive the first belt 6 and the second belt 7 to move and is electrically connected to the motor 19;
the industrial personal computer 9 is respectively connected with the image acquisition device, the air cylinder 101, the photoelectric sensor 8 and the motor driver 18, the industrial personal computer 9 comprises a gigabit network interface 14, an I/O control interface 10, an RS232 interface 13, a VGA interface 15 and a digital light source control interface 12, the gigabit network interface 14 is connected with the image acquisition device to transmit image data of the non-woven fabric mask product 4, the I/O control interface 10 is connected with the photoelectric sensor 8 and the air cylinder 101, the RS232 interface 13 is connected with the motor driver 18, the VGA interface 15 is connected with a preset display 17, and the digital light source control interface 12 is connected with the L ED light source 3.
L ED light source 3, be used for doing 4 light fillings of non-woven fabrics gauze mask product, set up in detect 5 downside, electric connection in industrial computer 9.
The industrial personal computer 9 is connected with the photoelectric sensor 8 through an I/O control interface 10, the industrial personal computer 9 is connected with the air cylinder 101 through the I/O control interface 10, is connected with the motor driver 18 through an RS232 interface 13, is connected with the ED light source L through a digital light source control interface 12, is connected with the display 17 through a VGA image display interface 15, and executes various electric algorithms for the industrial personal computer 9 in the power supply 9, wherein the support structure consists of the horizontal support 20 and the vertical support 21, the horizontal support 20 is connected with the vertical support 21, the industrial camera 1 is connected with the horizontal support 20, the industrial lens 2 is connected below the industrial camera 1, the industrial camera 1 and the industrial lens 2 are combined and used for acquiring image data of a non-woven fabric mask product 4 to be detected, the industrial camera 1 is connected with the industrial lens 2 and transmitted to the industrial personal computer 9 through a gigabit network card 14, the detection base 5 is made of a transparent material and is positioned below the industrial lens 2, the detection base 5 is provided with the L ED light source 3 below the detection base 5, the photoelectric sensor 8 is arranged on the detection base 5 and used for detecting whether the non-woven fabric mask product 4.
In the system device, the photoelectric sensor 8 always transmits a low level signal to the I/O control interface 10, and the defect detection of the non-woven fabric mask is not carried out at the moment; when the non-woven fabric mask product 4 is detected to be in place, the non-woven fabric mask product in-place mark is set to be 1, and at the moment, the photoelectric sensor 8 transmits a high-level signal to the I/O control interface 10, continues for a period of time and then recovers to a low level; image processing software in the industrial personal computer 9 reads an I/O control interface 10 signal once at intervals, if the received I/O control interface 10 signal is high level, defect algorithm detection is immediately carried out on the currently collected non-woven fabric mask product image, the detection result is output to the motor driver 18 through the RS232 interface 13, the motor driver 18 drives the motor 19 to drive the first belt 6 and the second belt 7 to drive the non-woven fabric mask product 4 to move at the detection position, the non-woven fabric mask 4 is located between the first belt 6 and the second belt 7 when moving, after detection is completed, the cylinder 101 controls the NG processing device 102 to move defective products to the defective position, and if the received signal is low level, the image processing software of the industrial personal computer does not carry out defect detection.
The method comprises the steps of configuring algorithm execution software in a CPU11 of an industrial personal computer 9, as shown in FIG. 2, FIG. 2 is a structural block diagram of an image processing software platform provided by an embodiment of the invention, a software framework comprises a control area 23 (comprising a start-stop control 27, a user control 28, a camera control 29, a light source control 30 and an I/O control 31), a display area 24 (comprising an image display 32 and a result display 33), a parameter area 25 (comprising an image parameter 34, a hardware parameter 35, a defect parameter 36 and a system parameter 37) and a message area 26 (comprising a debugging message 38, an operation message 39, a system message 40 and a defect message 41), the start-stop control 27 comprises a start-up state and a stop-down state of a system, the user control 28 comprises management and control of a user account, a password and a login state, the camera control 29 comprises an open camera which enables the camera to start image acquisition work and a close-down camera which enables the camera to end image acquisition work, the light source control 30 comprises an open light source which enables the L ED light source 3 to start working and a close-up light source, a control which enables the L light source 3 to end work, a control function of digital adjustment of the camera, the function of the I/O control, a function of the digital adjustment of the camera control, a function of the camera control comprises a function of the I/O display of the camera to display of the camera, a display of the display of a working state, a working state of the display of a working system, a working state of the display of a working system, a working state of a working system, a working system display module of a working system, a working system display module of a working system, a working.
Referring to fig. 3, fig. 3 is a flowchart of a non-woven fabric mask defect visual inspection method according to an embodiment of the present invention, the non-woven fabric mask defect visual inspection method is implemented by using the non-woven fabric mask defect visual inspection system, and the non-woven fabric mask defect visual inspection method includes steps S1-S4:
s1, acquiring the image of the non-woven fabric mask product 4 by the image acquisition device, and transmitting the image to the industrial personal computer 9; and acquiring images of the non-woven fabric mask product 4 to be detected in real time by adopting an industrial camera 1 and an industrial lens 2 which are connected with an industrial personal computer 9.
S2, converting the image into a gray-scale image by the industrial personal computer 9, calculating the deviation between the gray-scale image and a preset standard non-woven fabric mask product 4, and acquiring the positioning information of the non-woven fabric mask product 4 by a contour extraction algorithm and a minimum external quadrilateral algorithm; the step S2 includes sub-steps S21-S24:
s21, converting the image into a gray-scale image by the industrial personal computer 9, and carrying out binarization processing on the gray-scale image;
s22, calculating the difference value between the gray scale image after binarization processing and a preset standard non-woven fabric mask product 4, and taking the absolute value of the difference value to obtain a difference value image;
s23, carrying out image avoidance region processing on the difference image to obtain an avoidance image, wherein the image avoidance region processing comprises: traversing the pixel value of the difference image, setting the pixel value of a preset position as 0 or 255, and keeping the rest pixels unchanged;
s24, carrying out image contour detection on the avoidance image by adopting a contour extraction algorithm, and carrying out external quadrilateral fitting processing on the contour with the largest area by adopting a minimum external quadrilateral algorithm so as to obtain coordinates of four vertexes of an external quadrilateral. Namely, the mask product positioning processing is carried out on the processed image by utilizing a contour extraction algorithm and a minimum circumscribed rectangle algorithm. When the positioning is unsuccessful, judging to be used as positioning defect treatment; otherwise, image translation and rotation transformation are carried out on the processed image of the avoidance area, and difference value operation, corrosion and expansion processing are carried out on the transformed result image and the standard product image.
S3, judging whether the non-woven fabric mask product 4 has defects according to the positioning information; the defects of the non-woven fabric mask can be divided into four types, wherein the first type is the defect of dirtiness of the mask body, the second type is the defect of ear bands, the third type is the defect of overlapping of mask products, and the fourth type is the defect of nose strips, and the step S3 comprises the substeps S31-S34:
s31, judging whether the non-woven fabric mask product 4 has the defect that the mask body is dirty or not: acquiring a mask body through positioning information, performing fixed threshold binarization processing on an image in the mask body, calculating the total number of mask pixels of non-zero pixels, and judging whether the total number of the mask pixels is within a preset first threshold range, if so, judging that no mask body is dirty, and if not, judging that the mask body is dirty;
s32, judging whether the non-woven fabric mask product 4 has ear band defects: acquiring an ear zone region through positioning information, setting a connection point of the ear zone region and the mask body into four fixed regions, carrying out fixed threshold value binarization processing on the four fixed regions, acquiring a communication region with the largest area by adopting a communication region extraction algorithm, calculating characteristic parameters of a plurality of communication regions, and judging whether the characteristic parameters are within a preset second threshold value range, if so, judging that no ear zone defect exists, and if not, judging that the ear zone defect exists;
s33, judging whether the non-woven fabric mask product 4 has a product overlapping defect: acquiring a nose strip area in the mask body through the positioning information, performing fixed threshold binarization processing on the nose strip area, calculating the total number of nose strip pixels of non-zero pixels, and judging whether the total number of the nose strip pixels is within a preset third threshold range, if so, judging that the mask has a product overlapping defect, and if not, judging that the mask has no product overlapping defect;
s34, judging whether the non-woven fabric mask product 4 has nose strip defects: and carrying out self-adaptive threshold value binarization processing and corrosion operation on the image in the bag body region, obtaining all connected regions in the bag body region by adopting a connected region extraction algorithm, calculating the total characteristic parameters of the connected regions, judging whether the total characteristic parameters are within a preset fourth threshold value range, if so, judging that no nose strip defect exists, and if not, judging that the nose strip defect exists. The characteristic parameters of the connected region of the image comprise the shape, the center, the area, the length and the circularity index of the connected region.
S4, controlling the NG processing device 102 to process the non-woven mask product 4 to a predetermined position according to a predetermined program.
The main algorithm of the non-woven fabric mask defect visual detection is that the mask positioning time is 30 ms/piece, the dirty defect detection rate of the mask body is 55 ms/piece, the mask ear band defect detection rate is 30 ms/piece, the mask product overlapping defect detection rate is 20 ms/piece, the nose strip defect detection rate is 25 ms/piece, the detection rate of all four items is 160 ms/piece, the average detection precision of the non-woven fabric mask defects reaches more than 98%, and the non-woven fabric mask defect visual detection completely accords with the application of actual industrial production.
The detection results for various non-woven fabric masks are shown in the following table:
various operations of embodiments are provided herein. In one embodiment, the one or more operations described may constitute computer readable instructions stored on one or more computer readable media, which when executed by an electronic device, will cause the computing device to perform the operations described. The order in which some or all of the operations are described should not be construed as to imply that these operations are necessarily order dependent. Those skilled in the art will appreciate alternative orderings having the benefit of this description. Moreover, it should be understood that not all operations are necessarily present in each embodiment provided herein.
Also, as used herein, the word "preferred" is intended to serve as an example, instance, or illustration. Any aspect or design described herein as "preferred" is not necessarily to be construed as advantageous over other aspects or designs. Rather, use of the word "preferred" is intended to present concepts in a concrete fashion. The term "or" as used in this application is intended to mean an inclusive "or" rather than an exclusive "or". That is, unless specified otherwise or clear from context, "X employs A or B" is intended to include either of the permutations as a matter of course. That is, if X employs A; b is used as X; or X employs both A and B, then "X employs A or B" is satisfied in any of the foregoing examples.
Also, although the disclosure has been shown and described with respect to one or an implementation, equivalent alterations and modifications will occur to others skilled in the art based upon a reading and understanding of this specification and the annexed drawings. The present disclosure includes all such modifications and alterations, and is limited only by the scope of the appended claims. In particular regard to the various functions performed by the above described components (e.g., elements, etc.), the terms used to describe such components are intended to correspond, unless otherwise indicated, to any component which performs the specified function of the described component (e.g., that is functionally equivalent), even though not structurally equivalent to the disclosed structure which performs the function in the herein illustrated exemplary implementations of the disclosure. In addition, while a particular feature of the disclosure may have been disclosed with respect to only one of several implementations, such feature may be combined with one or other features of the other implementations as may be desired and advantageous for a given or particular application. Furthermore, to the extent that the terms "includes," has, "" contains, "or variants thereof are used in either the detailed description or the claims, such terms are intended to be inclusive in a manner similar to the term" comprising.
Each functional unit in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or a plurality of or more than one unit are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium. The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Each apparatus or system described above may execute the storage method in the corresponding method embodiment.
In summary, although the present invention has been described with reference to the preferred embodiments, the above-described preferred embodiments are not intended to limit the present invention, and those skilled in the art can make various changes and modifications without departing from the spirit and scope of the present invention, therefore, the scope of the present invention shall be determined by the appended claims.
Claims (1)
1. The non-woven fabric mask defect visual detection method is realized by adopting a non-woven fabric mask defect visual detection system, and the non-woven fabric mask defect visual detection system comprises:
the image acquisition device is used for acquiring an image of a non-woven fabric mask product to be detected;
the detection base is used for supporting the non-woven fabric mask product and is positioned below the image acquisition device;
the photoelectric sensor is arranged on the detection base and used for detecting whether the non-woven fabric mask product is in place or not;
the NG processing device is used for processing the non-woven fabric mask product to a preset position according to a preset program;
the cylinder is used for driving the NG processing device to process the non-woven fabric mask product to a preset position and is fixedly connected with the NG processing device;
the first belt and the second belt are respectively arranged on two sides of the non-woven fabric mask product and are used for driving the non-woven fabric mask product to move on the detection base;
a motor for driving the first belt and the second belt;
the motor driver is used for driving the motor to drive the first belt and the second belt to move and is electrically connected with the motor;
the industrial personal computer is respectively connected with the image acquisition device, the cylinder, the photoelectric sensor and the motor driver and comprises a gigabit network interface, an I/O control interface, an RS232 interface, a VGA interface, a digital light source control interface, a power supply and a power supply, wherein the gigabit network interface is connected to the image acquisition device to transmit image data of the non-woven fabric mask product;
l ED light source for supplementing light to the non-woven fabric mask product, arranged at the lower side of the detection base, and electrically connected to the industrial personal computer;
a vertical support;
one end of the horizontal bracket is fixedly connected to the vertical bracket, and the other end of the horizontal bracket is fixedly connected to the image acquisition device; the image acquisition device includes: the side surface of the industrial camera is provided with an opening, the horizontal support penetrates through the opening to fix the industrial camera, and the industrial camera is electrically connected with the industrial personal computer; the industrial lens is arranged on the lower surface of the industrial camera to be aligned with the non-woven fabric mask product; the centers of the non-woven fabric mask product and the detection base are positioned on the same central axis;
it is characterized by comprising:
acquiring an image of a non-woven fabric mask product by the image acquisition device, and transmitting the image to the industrial personal computer;
converting the image into a gray-scale image by the industrial personal computer, calculating the deviation between the gray-scale image and a preset standard non-woven fabric mask product, and acquiring the positioning information of the non-woven fabric mask product by a contour extraction algorithm and a minimum external quadrilateral algorithm; the method comprises the following steps: converting the image into a gray-scale image by the industrial personal computer, and carrying out binarization processing on the gray-scale image; calculating a difference value between the gray scale image after binarization processing and a preset standard non-woven fabric mask product, and taking an absolute value of the difference value to obtain a difference image; and carrying out image dislocation area processing on the difference image to obtain a dislocation image, wherein the image dislocation area processing comprises the following steps: traversing the pixel value of the difference image, setting the pixel value of a preset position as 0 or 255, and keeping the rest pixels unchanged; carrying out image contour detection on the avoiding image by adopting a contour extraction algorithm, and carrying out external quadrilateral fitting processing on the contour with the largest area by adopting a minimum external quadrilateral algorithm so as to obtain coordinates of four vertexes of an external quadrilateral;
judging whether the non-woven fabric mask product has defects according to the positioning information; the method comprises the following steps: judge whether non-woven fabrics gauze mask product has the dirty defect of gauze mask body: acquiring a mask body through positioning information, performing fixed threshold binarization processing on an image in the mask body, calculating the total number of mask pixels of non-zero pixels, and judging whether the total number of the mask pixels is within a preset first threshold range, if so, judging that no mask body is dirty, and if not, judging that the mask body is dirty; judging whether the non-woven fabric mask product has ear band defects: acquiring an ear zone region through positioning information, setting a connection point of the ear zone region and the mask body into four fixed regions, carrying out fixed threshold value binarization processing on the four fixed regions, acquiring a communication region with the largest area by adopting a communication region extraction algorithm, calculating characteristic parameters of a plurality of communication regions, and judging whether the characteristic parameters are within a preset second threshold value range, if so, judging that no ear zone defect exists, and if not, judging that the ear zone defect exists; judging whether the non-woven fabric mask product has a product overlapping defect: acquiring a nose strip area in the mask body through the positioning information, performing fixed threshold binarization processing on the nose strip area, calculating the total number of nose strip pixels of non-zero pixels, and judging whether the total number of the nose strip pixels is within a preset third threshold range, if so, judging that the mask has a product overlapping defect, and if not, judging that the mask has no product overlapping defect; judging whether the non-woven fabric mask product has nose strip defects: carrying out self-adaptive threshold value binarization processing and corrosion operation on the image in the nose strip area, obtaining all connected areas in the nose strip area by adopting a connected area extraction algorithm, calculating total characteristic parameters of the connected areas, judging whether the total characteristic parameters are within a preset fourth threshold value range, if so, judging that no nose strip defect exists, and if not, judging that the nose strip defect exists;
and controlling the NG processing device to process the non-woven fabric mask product to a preset position according to a preset program.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710117286.5A CN107014822B (en) | 2017-02-28 | 2017-02-28 | Non-woven fabric mask defect visual detection system and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710117286.5A CN107014822B (en) | 2017-02-28 | 2017-02-28 | Non-woven fabric mask defect visual detection system and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN107014822A CN107014822A (en) | 2017-08-04 |
| CN107014822B true CN107014822B (en) | 2020-08-04 |
Family
ID=59440870
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710117286.5A Active CN107014822B (en) | 2017-02-28 | 2017-02-28 | Non-woven fabric mask defect visual detection system and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107014822B (en) |
Families Citing this family (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108230315B (en) * | 2018-01-04 | 2021-05-25 | 西安理工大学 | Mask belt loss detection method based on machine vision |
| CN108535278A (en) * | 2018-04-18 | 2018-09-14 | 常州市安视智能科技有限公司 | Metal plate eyelet work product line punching defect detecting device based on machine vision and method |
| CN109459970B (en) * | 2018-10-26 | 2019-10-25 | 常州机电职业技术学院 | A kind of the elliptical aperture potentiometer angle reset system and repositioning method of view-based access control model |
| JP7055212B2 (en) * | 2018-11-20 | 2022-04-15 | 深▲セン▼市▲維▼▲圖▼▲視▼技▲術▼有限公司 | How to inspect masks online |
| CN109374634B (en) * | 2018-11-20 | 2020-07-03 | 深圳市维图视技术有限公司 | Online mask detection system and method |
| CN109374635B (en) * | 2018-11-20 | 2020-06-30 | 深圳市维图视技术有限公司 | Mask defect detection device and method |
| JP7055223B2 (en) * | 2018-11-20 | 2022-04-15 | 深▲セン▼市▲維▼▲圖▼▲視▼技▲術▼有限公司 | Mask defect inspection method |
| CN109765238A (en) * | 2018-12-12 | 2019-05-17 | 弓立（厦门）医疗用品有限公司 | A kind of product quality detection method of mask fully-automatic production detection device |
| CN109507198B (en) * | 2018-12-14 | 2021-12-07 | 航天科工智能机器人有限责任公司 | Mask detection system and method based on fast Fourier transform and linear Gaussian |
| CN109902584B (en) * | 2019-01-28 | 2022-02-22 | 深圳大学 | Mask defect identification method, device, equipment and storage medium |
| CN110599481A (en) * | 2019-09-18 | 2019-12-20 | 成都数之联科技有限公司 | Cement prefabricated plate detection system based on image recognition |
| CN110897233A (en) * | 2020-02-13 | 2020-03-24 | 广州市普理司科技有限公司 | Flexible AI vision full-automatic mask machine |
| CN111458344A (en) * | 2020-04-03 | 2020-07-28 | 广州超音速自动化科技股份有限公司 | Mask defect visual detection method, equipment and storage medium |
| CN111642833B (en) * | 2020-04-22 | 2022-09-06 | 王峰 | Medical mask production equipment and quality rapid detection method of medical mask |
| CN111659633A (en) * | 2020-06-05 | 2020-09-15 | 珠海格力智能装备有限公司 | Tooling product classification system and method |
| CN111842212A (en) * | 2020-07-21 | 2020-10-30 | 深圳市泰沃德自动化技术有限公司 | Automatic feeding structure, appearance detection device, mask appearance detection device and method |
| CN112083009A (en) * | 2020-07-23 | 2020-12-15 | 广州超音速自动化科技股份有限公司 | Method and device for detecting quality of mask through video and storage medium |
| CN112215828B (en) * | 2020-10-20 | 2022-03-15 | 广东高臻智能装备有限公司 | Automatic mask cutting position adjusting method and system based on intelligent visual detection |
| CN112924212B (en) * | 2021-01-26 | 2022-12-13 | 徐州国高新材料包装有限公司 | Stripping mechanism for melt-blown fabric and non-woven fabric |
| CN113066056B (en) * | 2021-03-15 | 2022-10-11 | 南昌大学 | Mask ear band welding spot detection method based on deep learning |
| CN113588654B (en) * | 2021-06-24 | 2024-02-02 | 宁波大学 | Three-dimensional visual detection method for engine heat exchanger interface |
| CN115876804B (en) * | 2023-02-20 | 2023-08-01 | 深圳市信仪旺实业有限公司 | Mask defect visual detection method and system |
| CN117115161B (en) * | 2023-10-24 | 2024-01-02 | 四川新康意众申新材料有限公司 | Plastic defect inspection method |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102305793A (en) * | 2011-05-11 | 2012-01-04 | 苏州天准精密技术有限公司 | Method and equipment for detecting appearance quality of product |
| KR102044788B1 (en) * | 2012-10-30 | 2019-11-18 | 삼성디스플레이 주식회사 | Inspection Apparatus for Glass substrate |
| CN104297255B (en) * | 2014-10-15 | 2015-08-26 | 西安交通大学 | A kind of dixie cup defective vision detection method and system and device |
| CN106153641A (en) * | 2016-06-20 | 2016-11-23 | 余洪山 | A kind of object defect check system based on machine vision and method |
| CN106290375A (en) * | 2016-07-14 | 2017-01-04 | 北京航信增材科技有限公司 | Based on selective laser sintering technology contactless in line defect automatic checkout system |
| CN106093059B (en) * | 2016-08-16 | 2019-11-19 | 杭州赤霄科技有限公司 | Hygiene medical treatment protective articles mask vision detection system |
-
2017
- 2017-02-28 CN CN201710117286.5A patent/CN107014822B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN107014822A (en) | 2017-08-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107014822B (en) | Non-woven fabric mask defect visual detection system and method | |
| CN100593716C (en) | On-line detecting method of machine vision system for printed calico flaw | |
| CN107014818B (en) | Laser etching defect visual detection system and method | |
| CN109064440B (en) | Loudspeaker voice coil bonding wire identification method based on machine vision | |
| CN103543161A (en) | On-line detection method of continuous casting billet surface quality | |
| CN107014821B (en) | Plastic self-sealing bag detection system and method | |
| CN102582329B (en) | Automatic laser engraving and code reading equipment for oil spraying nozzle | |
| CN109986172B (en) | Welding seam positioning method, equipment and system | |
| CN110807802B (en) | Welding method, apparatus and storage medium | |
| CN105303573A (en) | Method and system of pin detection of gold needle elements | |
| CN115456999B (en) | Saw chain surface defect automatic detection system and defect detection method based on machine vision | |
| CN113483682A (en) | Gap measuring method and system based on machine vision | |
| CN114280075A (en) | Online visual inspection system and method for surface defects of pipe parts | |
| CN110021012B (en) | Mobile phone lens window glass defect detection method based on machine vision technology | |
| AU741107B2 (en) | Bar angle measurement system | |
| CN104976959A (en) | Machine-vision-based spring size online measurement system and method thereof | |
| CN105068139B (en) | A kind of characterization processes of piston cooling nozzle installment state | |
| CN113808087A (en) | Defect management and control method and device for surface of steel plate and computer readable storage medium | |
| CN113030111A (en) | Machine vision-based automotive oil cooler cold joint detection system and method | |
| CN102768214B (en) | System and method for detecting contact lens | |
| CN111539951A (en) | Visual detection method for outline size of ceramic grinding wheel head | |
| CN116465896A (en) | Automobile part vision detection device and detection method based on artificial intelligence | |
| CN116008304A (en) | Weld joint detection method suitable for pipeline interior | |
| CN113237895A (en) | Metal surface defect detection system based on machine vision | |
| CN114897821A (en) | Height detection method for probe card probe relative test platform |
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 |