CN110632089A - Automatic cloth inspecting system and cloth inspecting method thereof - Google Patents
Automatic cloth inspecting system and cloth inspecting method thereof Download PDFInfo
- Publication number
- CN110632089A CN110632089A CN201910835013.3A CN201910835013A CN110632089A CN 110632089 A CN110632089 A CN 110632089A CN 201910835013 A CN201910835013 A CN 201910835013A CN 110632089 A CN110632089 A CN 110632089A
- Authority
- CN
- China
- Prior art keywords
- image
- image data
- fabric
- data
- detected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- D—TEXTILES; PAPER
- D06—TREATMENT OF TEXTILES OR THE LIKE; LAUNDERING; FLEXIBLE MATERIALS NOT OTHERWISE PROVIDED FOR
- D06H—MARKING, INSPECTING, SEAMING OR SEVERING TEXTILE MATERIALS
- D06H3/00—Inspecting textile materials
- D06H3/08—Inspecting textile materials by photo-electric or television means
-
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/80—Camera processing pipelines; Components thereof
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N5/00—Details of television systems
- H04N5/222—Studio circuitry; Studio devices; Studio equipment
- H04N5/262—Studio circuits, e.g. for mixing, switching-over, change of character of image, other special effects ; Cameras specially adapted for the electronic generation of special effects
- H04N5/265—Mixing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Chemical & Material Sciences (AREA)
- Signal Processing (AREA)
- Textile Engineering (AREA)
- Multimedia (AREA)
- Biochemistry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Analytical Chemistry (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Physics & Mathematics (AREA)
- Materials Engineering (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Treatment Of Fiber Materials (AREA)
Abstract
The invention provides an automatic cloth inspecting system and a cloth inspecting method, wherein the automatic cloth inspecting system is used for detecting the defects of a fabric to be detected and comprises the following steps: the device comprises an image acquisition unit and a data processing unit, wherein the image acquisition unit comprises at least two image collectors and is used for acquiring each image data of the fabric to be detected, which is acquired by each image collector; the fusion processing unit is used for receiving the image data of the image acquisition unit and carrying out fusion processing on at least two image data to obtain a complete image of the fabric to be detected; and the defect detection unit is used for detecting and analyzing the defects in the images sent by the fusion processing unit. Thereby improving inspection efficiency and reducing the rate of missed inspection.
Description
[ technical field ] A method for producing a semiconductor device
The invention belongs to the field of fabric perching, and particularly relates to an automatic perching system and a perching method thereof.
[ background of the invention ]
At present, in the weaving link of the textile industry, the defects of products need to be detected and identified, or the inspection process of the products is called as 'cloth inspection', manual observation is mainly adopted, namely, common defects are judged and eliminated by naked eyes in the cloth rolling or cloth stacking process of cloth through manual work, the efficiency is low, the inspection result is unstable, and the omission is easy. In the textile production industry, the defect detection and identification of the fabric are important links for controlling the quality of the fabric, and have very important significance before the fabric enters the market.
The existing detection aiming at the defects mainly has two modes, namely, the detection is carried out on cloth by depending on manpower. And (4) directly judging whether the defects exist on the fabric by naked eyes by cloth inspecting workers according to experience and classifying the defects. However, the manual cloth inspection is limited by the physiological structure of human eyes, continuous and high-speed detection cannot be realized, the detection speed per minute generally cannot exceed 15 meters, and the efficiency is very low. In addition, the defects on the cloth surface of the fabric are fine and small, and the defects are manually identified on the moving fabric, so that the missing inspection rate of the defects is high, and meanwhile, the long-time cloth inspection by naked eyes is easy to cause visual fatigue and extremely harm to human eyes.
And secondly, the detection is carried out by relying on automatic cloth inspecting equipment. At present, in automatic cloth inspecting equipment in the textile industry, a linear array type CCD (charge coupled device) sensor is mainly adopted to scan and image defects or flaws of a product, and the cost of a CCD imaging system is very high and is usually more than 1 ten thousand yuan due to the fact that the CCD is high in cost and needs to be matched with a special lens; in addition, the sensor can collect the brightness of one line, and the whole breadth of the target can be detected through the movement of the detected object. Although this method can achieve high resolution (because the resolution of CCDs is usually high), it is slow to detect. The line frequency of the linear array CCD is usually about 100-300Hz, that is, only about 100-300 lines can be scanned in one second, if the thickness of one line is 1 mm, only 0.1-0.3 m can be scanned in one second, and the detection speed is lower than the speed of 0.5-1 m per second of manual cloth inspection. Therefore, even though the missing rate can be improved by using the CCD instead of the manual cloth inspection, the efficiency is lowered. If a plurality of CCDs are adopted for parallel detection, the cost is multiplied, data among the CCDs are isolated, the data among the CCDs cannot be spliced, and the probability of missed detection is improved. More importantly, the cloth inspecting system adopting the CCD has the defects of high cost and low detection speed, is not accepted by the market, and has low practicability.
Therefore, providing an automatic cloth inspecting system that can be low in cost and increase the detection speed has become an urgent problem to be solved in the textile production industry.
[ summary of the invention ]
The invention aims to provide an automatic cloth inspecting system and a cloth inspecting method for overcoming the defects of the prior art, which have the advantages of low cost and capability of improving the speed of detecting plants in unit time.
In order to achieve the above object, the present invention provides an automatic cloth inspecting system for detecting defects of a fabric to be detected, comprising:
the device comprises an image acquisition unit and a data processing unit, wherein the image acquisition unit comprises at least two image collectors which are arranged at intervals and used for acquiring each image data of the fabric to be detected, which is acquired by each image collector;
the fusion processing unit is used for receiving the image data of the image acquisition unit and carrying out fusion processing on at least two image data to obtain a complete image of the fabric to be detected; and
and the defect detection unit is used for detecting and analyzing the defects in the images sent by the fusion processing unit.
In an embodiment of the present invention, the detection range of each two adjacent image collectors has a partial overlapping area, and the image data collected by each two adjacent image collectors in the partial overlapping area are the same.
In an embodiment of the present invention, the automatic perching system further includes a display control unit, and the display control unit is configured to mark and display the defect detected by the defect detection unit.
In an embodiment of the present invention, the fusion processing unit includes a receiving and converting module, configured to receive image data of each image collector, and convert each received image data into a consistent data format;
the correction module is used for calibrating the image data of each image collector;
the image splicing module is used for splicing each image data into a complete image of the fabric to be detected according to the corresponding physical address of the image collector;
the frame cache storage module is used for storing the spliced image data of the image splicing module; and
and the sending module is used for sending the spliced images of the image splicing module to the detection and analysis module.
In an embodiment of the present invention, the correction module includes a horizontal position correction module, and the horizontal position correction module is configured to correct each of the image collectors to be located at a same horizontal position; and
an overlap region correction module for obtaining calibrated image data by taking one of an average value of image data of the partially overlapped region or deleting the same data of the partially overlapped region.
In an embodiment of the present invention, at least two of the image collectors are CMOS image sensors; or
At least two of the image collectors include a CMOS image sensor and a charge coupled device sensor.
In order to achieve the above object, the present invention also provides an automatic cloth inspecting method for detecting defects of a fabric to be detected, comprising the steps of:
acquiring at least two image data of a fabric to be detected, which are acquired by at least two image collectors arranged at intervals;
receiving at least two image data, and carrying out fusion processing on the at least two image data to obtain a complete image of the fabric to be detected; and
detecting and analyzing defects in the image.
In an embodiment of the present invention, the automatic cloth inspection method further includes the steps of:
the defect is marked and displayed.
In an embodiment of the present invention, the step of receiving at least two pieces of image data and performing fusion processing on the at least two pieces of image data to obtain a complete image of the fabric to be detected includes:
receiving at least two image data of a fabric to be detected, and converting each received image data into a consistent data format;
calibrating the image data;
splicing at least two image data into a complete image of the fabric to be detected according to the physical positions of at least two corresponding image collectors;
storing the image; and
the image is transmitted for detection analysis.
In an embodiment of the present invention, the acquiring at least two image data of the fabric to be detected collected by at least two image collectors includes:
partial overlapping data exists between the image data corresponding to every two adjacent image collectors;
in calibrating the image data, comprising the steps of:
calibrating each image collector to be located at the same horizontal position; and
and acquiring an average value of the image data of the partial overlapping data or deleting one of the image data of the partial overlapping data to obtain calibrated image data.
Compared with the prior art, the automatic cloth inspecting system and the cloth inspecting method thereof provided by the invention can improve the cloth detecting width of the automatic cloth inspecting machine. According to the traditional single CCD linear camera system with the detection width of about 50 centimeters, the automatic cloth inspecting system can detect the ultra-wide cloth in the current market when a plurality of video cameras are fused.
In addition, compared with the prior art, the automatic cloth inspecting system provided by the invention can obviously improve the detection speed of the automatic cloth inspecting machine. The conventional CCD linear array camera detection system is limited by the self line frequency of the sensor, the maximum detection speed can only be within 1 m/s, and the automatic cloth inspecting system can realize the detection speed of more than 10 m/s, greatly improve the detection speed, correspondingly improve the detection efficiency and reduce the detection time cost.
In addition, compared with the prior art, the automatic cloth inspecting system provided by the invention can improve the detection precision of the defects of the woven cloth part in the vertical direction (the direction vertical to the cloth moving direction). Due to the fact that the defects of weft breakage, thin paths, dense paths and the like of the woven cloth in the vertical direction penetrating through the whole cloth cover are subjected to image data fusion by the automatic cloth inspecting system, the integral resolution ratio is remarkably improved, and therefore the detection is easier.
In addition, compared with the prior art, the automatic cloth inspecting system provided by the invention can reduce the cost of the system in a large range without influencing the detection effect of the fabric.
[ description of the drawings ]
Fig. 1 is a schematic structural block diagram of an automatic perching system in an embodiment of the present invention.
Fig. 2 is a schematic structural block diagram of a fusion processing unit of an automatic perching system in the above embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a field of view of an acquisition unit of an automatic perching system according to the above embodiment of the present invention.
Fig. 4 is a schematic structural diagram of an automatic cloth inspecting system according to the above embodiment of the present invention.
Fig. 5 is a schematic flow chart of an automatic cloth inspecting method according to the above embodiment of the present invention.
Fig. 6 is a schematic flow chart of the fusion process of the automatic perching method in the above embodiment of the present invention.
Fig. 7 is a schematic flow chart illustrating a process of calibrating image data of an automatic perching method according to the above embodiment of the present invention.
[ detailed description ] embodiments
The following description is presented to disclose the invention so as to enable any person skilled in the art to practice the invention. The preferred embodiments in the following description are given by way of example only, and other obvious variations will occur to those skilled in the art. The basic principles of the invention, as defined in the following description, may be applied to other embodiments, variations, modifications, equivalents, and other technical solutions without departing from the spirit and scope of the invention.
In the description of the present invention, it is to be understood that the terms "first," "second," and the like are used for descriptive purposes only and are not to be construed as indicating or implying relative importance. In the description of the present invention, it should be noted that, unless explicitly stated or limited otherwise, the terms "connected" and "connected" are to be interpreted broadly, and may be, for example, fixedly connected, detachably connected, or integrally connected; can be mechanically or electrically connected; they may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
The invention is further described with reference to the following figures and embodiments.
As shown in fig. 1 to 4, the automatic cloth inspecting system of the present invention is specifically described, and is used for detecting defects in a fabric to be detected, and the automatic cloth inspecting system can be used in cooperation with an existing cloth inspecting machine.
Specifically, the automatic cloth inspecting system comprises an image acquisition unit 10, a fusion processing unit 20 and a detection and analysis unit 30, wherein the image acquisition unit 10, the fusion processing unit 20 and the detection and analysis unit 30 are electrically connected in a communication manner, wherein the image acquisition unit 10 comprises at least two image collectors 11 arranged at intervals and used for acquiring each image data of the fabric to be detected, which is acquired by each image collector 11; the fusion processing unit 20 is configured to receive the image data of the image acquisition units 11, and perform fusion processing on at least two image data acquired by at least two image acquisition units 11 to obtain a complete image of the fabric to be detected; and the defect detecting unit 30 is used for detecting and analyzing defects in the images sent by the fusion processing unit 20.
Furthermore, in the present invention, each image collector 11 has a fixed detection range L, and in order to avoid omission of the detection area between every two adjacent image collectors 11, the detection ranges of every two adjacent image collectors 11 preferably overlap each other in the horizontal direction; in other words, the detection range L of each two adjacent image collectors 11 has a partial overlapping area 12, the image data collected by each two adjacent image collectors 11 in the partial overlapping area 12 are the same, and for the same image data, one of the image data may be retained in the subsequent fusion processing unit 20 or an average value of the same image data may be obtained.
In an embodiment of the present invention, as shown in fig. 3 and 4, the image collector 11 may be implemented as CMOS image sensors, and each two adjacent CMOS image sensors are aligned in the horizontal direction to avoid the deviation of the obtained image data during the simultaneous scanning process. For example, the image capturing unit 10 includes four CMOS image sensors, which are disposed above the object to be detected and connected in parallel along a transverse direction (perpendicular to the moving direction of the cloth) to obtain a horizontal resolution as high as or even higher than that of a conventional line CCD camera, and four full high-definition CMOS image sensors (having a resolution of 1920 × 1080) can obtain a detection resolution of about 7680 × 1080. On the other hand, the image collector 11 of the image collecting unit 10 can utilize the high-speed collecting capability of the CMOS image sensor (usually with a lower resolution), so that the collecting and detecting speed reaches 120 frames per second (one frame usually contains about 1K horizontal lines), and the images collected by the CMOS image sensors are combined into one image by the fusion processing unit 20 at the later stage, so that the resolution similar to that of the CCD in the horizontal direction is reached, meanwhile, the detecting speed of the image collecting unit 10 can reach 10 meters per second, compared with the conventional CCD line camera detecting system which is limited by itself and can only reach the detecting speed within 1 meter per second, the detecting efficiency of the automatic cloth inspecting system is greatly improved, and the detecting speed can be nearly improved by 10 times.
In addition, the image data collected by the image collecting unit 10 of the automatic cloth inspecting system of the present invention are combined to obtain an image, and the detection and analysis unit 30 of the automatic cloth inspecting system only needs to detect and analyze the combined image to obtain the corresponding defect, so that the total cost of the automatic cloth inspecting system does not increase greatly with the increase of the number of the image collecting units 10 (such as CMOS image sensors). For example, the cost of a conventional single-camera automatic cloth inspection system is about 3 ten thousand yuan, if a cloth with the width of 2 meters is inspected, 4 sets of systems are required to work in parallel, and the total cost is about 12 ten thousand yuan, and after the method is adopted, 3 CMOS image sensors and sensor interface circuits are added for about 4 ten thousand yuan in total, namely, the total cost is 7 ten thousand yuan, so that the cost is saved by 40%, and the total cost of an ultra-wide and high-speed detection system can be greatly reduced.
Of course, in other embodiments of the present invention, the image capturing unit 10 may include a CMOS image sensor and a ccd sensor, in other words, the image capturing unit 10 may be composed of a part of the CMOS image sensor and a part of the ccd sensor, for example, there are three CMOS image sensors and 1 ccd sensor in the image capturing unit 10.
In the present invention, the inspection and analysis unit 30 is used to inspect whether a defect exists in one image of the fabric to be inspected formed and to inspect the position where the defect exists, and can analyze the type of the defect existing, and the like. Defects referred to herein include, but are not limited to, broken picks, open and closed paths in a direction perpendicular to the direction of movement of the fabric to be tested; and stains or defects such as holes and fuzz. It is worth mentioning that, after the fusion processing unit 20 merges a plurality of image data into a complete image of the fabric to be detected, the automatic cloth inspecting system of the present invention can improve the detection precision of the vertical direction (perpendicular to the moving direction of the fabric to be detected), especially the defect of the woven fabric part. The defects of broken picks, thin paths, dense paths and the like of the woven fabric in the vertical direction penetrating through the whole cloth cover obviously improve the integral resolution in the fused image.
As shown in fig. 1 and 4, the automatic perching system further comprises a display control unit 40, wherein the display control unit 40 is used for marking and displaying the defects detected by the defect detection unit 30, and a user can judge and evaluate whether the to-be-detected fabric has defects, types of the defects and positions of the defects according to the marked and displayed contents. In addition, the display control circuit 40 may mark and display the result of defect detection to the user, and may also accept user settings for parameters of the detection system, such as position calibration, detection sensitivity, and the like.
As shown in fig. 2, the fusion processing unit 20 includes a receiving conversion module 21, a correction module 22, a frame buffer storage module 23, an image splicing module 24 and a transmission module 25, where the receiving conversion module 21, the correction module 22, the frame buffer storage module 23, the image splicing module 24 and the transmission module 25 are communicably connected, where the receiving conversion module 21 is configured to receive image data of each of the image collectors 11 and convert each of the received image data 11 into a consistent data format, and specifically, the receiving conversion module 21 may be replaced according to the type of the image collector 11 to adapt to different signal formats such as HDMI, SDI or MIPI, and may also restore the image data to a unified video data format according to the type of the camera sensor such as CMOS or CCD. The data of a plurality of image collectors 11 are unified into a uniform data format by the receiving and converting circuit 21, and then sent to the correcting module 22 for correcting the image data of each image collector 11. The frame buffer module 23 is formed by a memory capable of putting down the image size after the image capturing units 11 are spliced, and is usually a high-capacity dynamic memory such as DDR2, DDR3, and the like, and according to the requirements of some detection methods, the frame buffer memory module 23 can be designed to store the size of multiple frames, not limited to 1 frame of image. Preferably, the frame buffer storage module 23 may store a plurality of frames of images before and after the detection for improving the detection accuracy. The image splicing module 24 is configured to splice each image data into a complete image of the fabric to be detected according to the corresponding physical address of the image collector 11; and the sending module 25 is configured to send the stitched images of the image stitching module 24 to the detection and analysis module.
As shown in fig. 2, the correcting module 22 includes a horizontal position correcting module 221, where the horizontal position correcting module 221 is configured to correct at least two of the image collectors 11 to be located at the same horizontal position; and an overlap region correction module 222, wherein the overlap region correction module 222 is configured to obtain the calibrated image data by taking an average value of the image data of the partially overlapped region 12 or deleting one of the same data of the partially overlapped region 12. After being processed by the correction module 22 and the image splicing module 24, the whole image spliced by a plurality of image collectors 11 can be formed in the frame buffer storage module 23, and the subsequent detection analysis module 30 can detect defects in the image without increasing repeated structures in the system due to the increase of the number of the image collector modules 11, thereby greatly saving the complexity of the system.
In addition, for horizontal position correction, the horizontal position correction module 221 may be arranged to realize that the multiple image capturing units 11 are at the same horizontal position, so as to avoid the position deviation of the captured images caused by the fact that the multiple image capturing units 11 are not at the same horizontal position, so-called position deviation may be manually set, or may be obtained by shooting a special image (for example, a test grid drawing) and automatically calculated by the system.
In correspondence with the above-mentioned embodiment of the automatic cloth inspecting system, the present application further provides an automatic cloth inspecting method, as shown in fig. 5, the automatic cloth inspecting method for detecting a defect of a fabric to be detected may include the steps of:
s100, acquiring at least two image data of the fabric to be detected, which are acquired by at least two image collectors arranged at intervals;
s200, receiving at least two image data, and carrying out fusion processing on the at least two image data to obtain a complete image of the fabric to be detected; and
and S300, detecting and analyzing the defects in the image.
In the present application, at least two image collectors 11 are arranged at intervals to widen the width of the fabric to be detected, wherein each image collector 11 can collect the image data of the fabric to be detected corresponding to the corresponding detection range thereof. In order to reduce the omission ratio of the automatic cloth inspecting method, particularly the image data of the fabric to be inspected corresponding to the space between every two adjacent image collectors 11, partial overlapping data exists between the image data corresponding to every two adjacent image collectors 11.
Of course, it should be understood by those skilled in the relevant art that in step S100, in order to satisfy that the data acquired between every two adjacent image collectors 11 has partially overlapped data, the detection missing between every two adjacent image collectors 11 can be avoided by partially overlapping the detection ranges between every two adjacent image collectors 11. Here, the partially overlapped data is two identical image data acquired by two adjacent image acquiring devices 11 in the overlapping area of the detection range.
In the present application, the image data corresponding to all the image collectors 11 is received, where the image data includes partial overlapping data corresponding to every two adjacent image collectors 11, where the fusion processing is performed on all the image data, including the splicing processing on all the image data, so as to splice all the image data into a complete image according to the position relationship set by the image collectors 11, and the calibration processing is also performed on partial overlapping data corresponding to every two adjacent image collectors 11, so as to avoid that repeated data affects an image of a finally generated fabric to be detected in the splicing process, so as to improve the detection accuracy and reduce the omission ratio.
In the application, a complete image of the fabric to be detected, which is obtained through fusion processing, is subjected to detection analysis, and is used for detecting whether a defect exists in the image of the fabric to be detected, the position where the defect exists and analyzing the type of the defect. Defects referred to herein include, but are not limited to, broken picks, open and closed paths in a direction perpendicular to the direction of movement of the fabric to be tested; and stains or defects such as holes and fuzz.
As shown in fig. 5, in an embodiment of the present invention, the automatic perching method further includes the steps of:
and S400, marking and displaying the defects.
Here, the defect in the image after the detection and analysis is marked, and then the result of marking the defect is fed back to the user, where the defect in the marked image may include the type of the defect and the location of the defect. Alternatively, labeling may be performed in different ways according to different defect types. For example, defects of the types such as holes can be marked through a rectangular frame, defects of the type of fluffing can be marked through a circular frame so as to be distinguished from other defect types, and users can observe the defect types conveniently and visually.
As shown in fig. 6, which is a specific illustration of the automatic perching method of the present application, in step S200, the method may include the steps of:
s201, receiving at least two image data of a fabric to be detected, and converting each received image data into a consistent data format;
s202, calibrating the image data;
s203, splicing at least two image data into a complete image of the fabric to be detected according to the physical positions of at least two corresponding image collectors;
s204, storing the image; and
s205, sending the image for detection and analysis.
In the application, received image data is converted into a consistent data format, so that subsequent processing can be facilitated to adapt to different signal formats such as HDMI, SDI or MIPI, and the received image data can be restored into a uniform video data format according to the type of the image collector 11 such as CMOS and CCD.
In step S202 in the present application, as shown in fig. 7, calibrating the image data may include the steps of:
s2021, calibrating each image collector to be located at the same horizontal position; and
s2022, obtaining an average value of the image data of the partial overlapping data or deleting one of the image data of the partial overlapping data to obtain calibrated image data.
In the application, splicing according to the object position of the image collector 11 refers to splicing according to the installation sequence of the image collector 11, so that the spliced image is a real image of the fabric to be detected, and is used for subsequent detection and analysis.
In addition, the implementation process of the functions and actions of each step in the automatic cloth inspection method is specifically detailed in the implementation process of the corresponding module in the automatic cloth inspection system, and is not described herein again.
It will be appreciated by persons skilled in the art that the embodiments of the invention described above and shown in the drawings are given by way of example only and are not limiting of the invention. The objects of the invention have been fully and effectively accomplished. The functional and structural principles of the present invention have been shown and described in the examples, and any variations or modifications of the embodiments of the present invention may be made without departing from the principles.
Claims (10)
1. An automatic perching system for detecting defects in fabrics to be inspected, comprising:
the device comprises an image acquisition unit and a data processing unit, wherein the image acquisition unit comprises at least two image collectors which are arranged at intervals and used for acquiring each image data of the fabric to be detected, which is acquired by each image collector;
the fusion processing unit is used for receiving the image data of the image acquisition unit and carrying out fusion processing on at least two image data to obtain a complete image of the fabric to be detected; and
and the defect detection unit is used for detecting and analyzing the defects in the images sent by the fusion processing unit.
2. An automatic perching system as in claim 1,
the detection range of every two adjacent image collectors has a partial overlapping area, and the image data collected by every two adjacent image collectors in the partial overlapping area are the same.
3. An automatic perching system as in claim 1,
the automatic cloth inspecting system further comprises a display control unit, and the display control unit is used for marking and displaying the defects detected by the defect detecting unit.
4. An automatic perching system as in claim 2,
the fusion processing unit comprises a receiving and converting module used for receiving the image data of each image collector and converting the received image data into a consistent data format;
the correction module is used for calibrating the image data of each image collector;
the image splicing module is used for splicing each image data into a complete image of the fabric to be detected according to the corresponding physical address of the image collector;
the frame cache storage module is used for storing the spliced image data of the image splicing module; and
and the sending module is used for sending the spliced images of the image splicing module to the detection and analysis module.
5. An automatic perching system as in claim 4,
the correction module comprises a horizontal position correction module, and the horizontal position correction module is used for correcting each image collector to be positioned at the same horizontal position; and
an overlap region correction module for obtaining calibrated image data by taking one of an average value of image data of the partially overlapped region or deleting the same data of the partially overlapped region.
6. An automatic perching system as in claim 1,
at least two image collectors are CMOS image sensors; or
At least two of the image collectors include a CMOS image sensor and a charge coupled device sensor.
7. An automatic cloth inspecting method for detecting defects of a fabric to be detected is characterized by comprising the following steps:
acquiring at least two image data of a fabric to be detected, which are acquired by at least two image collectors arranged at intervals;
receiving at least two image data, and carrying out fusion processing on the at least two image data to obtain a complete image of the fabric to be detected; and
detecting and analyzing defects in the image.
8. The automatic perching method of claim 7, further comprising the steps of:
the defect is marked and displayed.
9. The method of claim 8, wherein the step of receiving at least two image data and fusing the at least two image data to obtain a complete image of the fabric to be inspected comprises:
receiving at least two image data of a fabric to be detected, and converting each received image data into a consistent data format;
calibrating the image data;
splicing at least two image data into a complete image of the fabric to be detected according to the physical positions of at least two corresponding image collectors;
storing the image; and
the image is transmitted for detection analysis.
10. The automatic perching method of claim 9, wherein the step of acquiring at least two image data of the fabric to be inspected, which are acquired by at least two image acquiring devices, comprises:
partial overlapping data exists between the image data corresponding to every two adjacent image collectors;
in calibrating the image data, comprising the steps of:
calibrating each image collector to be located at the same horizontal position; and
and acquiring an average value of the image data of the partial overlapping data or deleting one of the image data of the partial overlapping data to obtain calibrated image data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910835013.3A CN110632089A (en) | 2019-09-05 | 2019-09-05 | Automatic cloth inspecting system and cloth inspecting method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910835013.3A CN110632089A (en) | 2019-09-05 | 2019-09-05 | Automatic cloth inspecting system and cloth inspecting method thereof |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110632089A true CN110632089A (en) | 2019-12-31 |
Family
ID=68970133
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910835013.3A Pending CN110632089A (en) | 2019-09-05 | 2019-09-05 | Automatic cloth inspecting system and cloth inspecting method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110632089A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111650208A (en) * | 2020-06-01 | 2020-09-11 | 东华大学 | Tour type woven fabric defect on-line detector |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923059A (en) * | 2010-04-15 | 2010-12-22 | 北京经纬纺机新技术有限公司 | Automatic cloth inspection method and system |
| CN202103745U (en) * | 2011-04-29 | 2012-01-04 | 东莞市思能电子科技有限公司 | Large-breadth high-speed scanner |
| CN104104827A (en) * | 2014-07-09 | 2014-10-15 | 宁波摩视光电科技有限公司 | High-precision large-format scanner photoelectric image processing system and implementation method thereof |
| CN107643295A (en) * | 2017-08-24 | 2018-01-30 | 中国地质大学（武汉） | A kind of method and system of the cloth defect on-line checking based on machine vision |
| WO2018214661A1 (en) * | 2017-05-24 | 2018-11-29 | 香港纺织及成衣研发中心 | Method and system for automatic detection of fabric defect, and computer readable storage medium |
-
2019
- 2019-09-05 CN CN201910835013.3A patent/CN110632089A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101923059A (en) * | 2010-04-15 | 2010-12-22 | 北京经纬纺机新技术有限公司 | Automatic cloth inspection method and system |
| CN202103745U (en) * | 2011-04-29 | 2012-01-04 | 东莞市思能电子科技有限公司 | Large-breadth high-speed scanner |
| CN104104827A (en) * | 2014-07-09 | 2014-10-15 | 宁波摩视光电科技有限公司 | High-precision large-format scanner photoelectric image processing system and implementation method thereof |
| WO2018214661A1 (en) * | 2017-05-24 | 2018-11-29 | 香港纺织及成衣研发中心 | Method and system for automatic detection of fabric defect, and computer readable storage medium |
| CN107643295A (en) * | 2017-08-24 | 2018-01-30 | 中国地质大学（武汉） | A kind of method and system of the cloth defect on-line checking based on machine vision |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111650208A (en) * | 2020-06-01 | 2020-09-11 | 东华大学 | Tour type woven fabric defect on-line detector |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101103246B (en) | Automatic judging system | |
| CN106468668A (en) | Industrial camera cylinder detection method | |
| CN110428762B (en) | OLED panel aging test luminescence characteristic detection method based on pixel brightness | |
| CN111604916B (en) | Machine room IT equipment fault cabinet U-position positioning system and method | |
| CN101673784B (en) | Method and device for generating digital still pictures of wafer-shaped elements during a production process | |
| US8094922B2 (en) | Crack measuring method and apparatus | |
| CN106526917A (en) | Liquid crystal screen dot matrix detection device achieving scanning by means of line-scan digital camera | |
| KR20120052595A (en) | Inspecting apparatus for camera module | |
| CN104992446A (en) | Nonlinear illumination adaptive image splicing method and implementing system thereof | |
| CN110632089A (en) | Automatic cloth inspecting system and cloth inspecting method thereof | |
| JP2008041749A (en) | Device for inspecting image defect | |
| CN111458345A (en) | Visual detection mechanism for defects of mask | |
| KR102286470B1 (en) | LED Digital Signage Defect Detection system through Similarity Analysis of Original Image Information and Displayed Image Information | |
| KR101380803B1 (en) | Apparatus For Detecting Welding Part | |
| CN108511356A (en) | A kind of positioning of battery string welding machine and battery appearance detecting method | |
| CN217112128U (en) | Micro LED display panel defect detection device | |
| CN111458344A (en) | Mask defect visual detection method, equipment and storage medium | |
| CN118225799A (en) | Automatic cloth inspection system and cloth inspection method thereof | |
| JP4094399B2 (en) | Steel plate wrinkle inspection method and apparatus | |
| CN205879813U (en) | On -line detector | |
| KR101218637B1 (en) | Diagonal scan method for fast edge detection | |
| CN114878585A (en) | Large-breadth silk screen defect detection device | |
| CN115112675A (en) | Micro LED display panel defect detection device and method | |
| TWI468672B (en) | Optical detection device | |
| CN115993360A (en) | Visual inspection device and detection assembly line |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20191231 |