CN112213330A - High-dynamic imaging detection method and system for textile fabric flaws - Google Patents
High-dynamic imaging detection method and system for textile fabric flaws Download PDFInfo
- Publication number
- CN112213330A CN112213330A CN202011172594.6A CN202011172594A CN112213330A CN 112213330 A CN112213330 A CN 112213330A CN 202011172594 A CN202011172594 A CN 202011172594A CN 112213330 A CN112213330 A CN 112213330A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- high dynamic
- textile fabric
- flaw
- 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
- 239000004744 fabric Substances 0.000 title claims abstract description 157
- 239000004753 textile Substances 0.000 title claims abstract description 82
- 238000003384 imaging method Methods 0.000 title claims abstract description 80
- 238000001514 detection method Methods 0.000 title claims abstract description 50
- 230000007547 defect Effects 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 15
- 230000008569 process Effects 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims description 96
- 238000004140 cleaning Methods 0.000 claims description 21
- 230000002093 peripheral effect Effects 0.000 claims description 21
- 230000005540 biological transmission Effects 0.000 claims description 20
- 238000003892 spreading Methods 0.000 claims description 12
- 230000007480 spreading Effects 0.000 claims description 12
- 230000003287 optical effect Effects 0.000 claims description 10
- 238000003860 storage Methods 0.000 claims description 10
- 230000015572 biosynthetic process Effects 0.000 claims description 8
- 230000005611 electricity Effects 0.000 claims description 8
- 230000003068 static effect Effects 0.000 claims description 8
- 238000003786 synthesis reaction Methods 0.000 claims description 8
- 238000006243 chemical reaction Methods 0.000 claims description 6
- 239000012535 impurity Substances 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 230000004907 flux Effects 0.000 claims description 3
- ATHVAWFAEPLPPQ-VRDBWYNSSA-N 1-stearoyl-2-oleoyl-sn-glycero-3-phosphocholine Chemical compound CCCCCCCCCCCCCCCCCC(=O)OC[C@H](COP([O-])(=O)OCC[N+](C)(C)C)OC(=O)CCCCCCC\C=C/CCCCCCCC ATHVAWFAEPLPPQ-VRDBWYNSSA-N 0.000 claims 2
- 238000007689 inspection Methods 0.000 abstract description 11
- 230000008859 change Effects 0.000 abstract description 4
- 238000003672 processing method Methods 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003203 everyday effect Effects 0.000 description 2
- 229910052749 magnesium Inorganic materials 0.000 description 2
- 239000011777 magnesium Substances 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 206010063385 Intellectualisation Diseases 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 239000000428 dust Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000014759 maintenance of location Effects 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 230000008520 organization Effects 0.000 description 1
- 238000012827 research and development Methods 0.000 description 1
- 238000009987 spinning Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
- 238000009941 weaving Methods 0.000 description 1
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be 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
- H04N23/70—Circuitry for compensating brightness variation in the scene
- H04N23/741—Circuitry for compensating brightness variation in the scene by increasing the dynamic range of the image compared to the dynamic range of the electronic image sensors
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
Abstract
The invention discloses a high dynamic imaging detection method and a system for textile fabric flaws, wherein the detection system is combined with a high dynamic processing method, a low-cost CMOS image sensor is matched with an FPGA control logic circuit, a high dynamic range image (HDR) can be collected in the textile fabric motion process, the defects of scene change and the like caused by camera shake during exposure time and long sequence image shooting interval during fabric inspection (flaw detection) are effectively overcome, the flaw detection structure is inaccurate, in addition, the dynamic imaging system is carried with the low-cost CMOS image sensor, the high dynamic image acquisition is met, the fabric inspection cost is effectively reduced, and the accuracy is improved.
Description
Technical Field
The invention relates to the technical field of textile fabric detection equipment, in particular to a high-dynamic imaging detection method and system for textile fabric flaws.
Background
The textile industry has stringent requirements for the quality of textiles. The defects on the surface of the textile directly influence the price of a final finished product, and the detection of the surface defects has great significance on quality management and cost control of enterprises and improvement of product competitiveness.
In recent years, the manual cloth inspection mode is still the main mode of most textile enterprises, and as the cloth inspector needs to work on a production line for 12 hours every day, the visual system can be greatly damaged when watching cloth moving at high speed every day for a long time.
The manual cloth inspection is limited by the physiological characteristics of people, the detection result is greatly influenced by human factors, and the correct defect detection rate is determined by the skill of a cloth inspector. Different cloth inspectors have certain differences in the criteria for defect judgment. Therefore, it is difficult to ensure the consistency and objectivity of the test results. In addition, in the face of boring cloth inspection work, the cloth inspection worker needs to keep high concentration, and the influence of the surrounding environment, such as colleague chatting in the working process, can also greatly influence the detection result.
The time for which a person maintains his attention is limited, and is maintained for at most about 1 hour. However, the cloth inspecting worker needs to work continuously for more than ten hours and is in a cloth inspecting state, and the textile is in a moving state in the detection process, so that the cloth inspecting worker is easy to generate visual fatigue, and the leak detection rate is greatly increased. In terms of inspection speed, this greatly limits the efficiency of the cloth inspection, since the speed acceptable to the human eye is very limited.
The flaw automatic detection system based on the machine vision is a product of artificial intelligence and the development of computer science and artificial intelligence, has natural advantages, and provides a feasible alternative scheme for artificial cloth inspection. The system conforms to the development trend of automation and intellectualization of spinning, and has the advantages of objectivity, stability and high efficiency compared with manual cloth inspection.
The flaw detection systems that have been introduced on the market to date are foreign, or are upgraded on this basis, however, these defect detection systems all have a serious defect in imaging, i.e. dynamic imaging is not clear, which results in inaccurate defect detection structure, and in order to improve the defect detection accuracy, the application provides a high dynamic imaging detection method and a system for textile fabric flaws, the low-cost high dynamic imaging system is combined with an image synthesis algorithm edited by an SOPC (sequence of programmable computer), the defects of scene change and the like caused by camera shake during exposure time and long sequence image shooting interval during textile fabric detection are effectively overcome, and realizes the purpose of on-line high dynamic image on-line transmission and watching on-line long distance, is convenient for monitoring, therefore, the research and development of the domestic automatic cloth inspection system with the independent intellectual property rights have great significance for breaking foreign monopoly and technical innovation.
Disclosure of Invention
The invention aims to provide a high dynamic imaging detection method and a high dynamic imaging detection system for textile fabric flaws, and aims to solve the problem that a flaw detection structure is inaccurate due to the defects of scene change and the like caused by camera shake during exposure time and long sequence image shooting interval during textile fabric detection.
In order to solve the technical problems, the invention adopts the following technical scheme:
the utility model provides a high dynamic imaging detection method for textile fabric flaw, includes mechanical granny rag and net cloth module, image acquisition module, data processing and imaging module, flaw image database module, online contrast and record module, flaw mark module and control module, wherein: the central processing unit of the control module controls and coordinates the other modules according to the following steps to complete high dynamic imaging, cloth defect point-to-point comparison detection and defect point mechanical marking;
s1, the mechanical cloth pulling and cleaning module: flatly paving a textile fabric roll by a cloth spreading machine, and cleaning impurities on the surface of the fabric by static electricity removing and cleaning equipment in the fabric conveying process to obtain the fabric with a clean surface;
s2, the image acquisition module: collecting an image of the clean cloth on the surface through an optical camera, and forming and outputting an image digital signal to a lower stage;
s3, the data processing and imaging module: receiving the digital signal, processing the data, forming a high dynamic image by combining a high dynamic image synthesis algorithm, and forming and outputting the high dynamic image to the upper and lower levels;
s4, the defect image database module: calling out flaw images of corresponding textile fabric types in the database after receiving the high dynamic images of the textile fabrics;
s5, the online comparison and recording module: comparing the detected textile fabric combined flaw images, and recording and storing the type and the position of the detected textile fabric flaw points on line;
s6, the flaw marking module: and mechanically marking the detected flaw points of the textile fabric by using a erasable or washable color.
The further technical scheme is as follows: the image acquisition module is an optical camera composed of a CMOS image sensor and a conventional lens.
The further technical scheme is as follows: the data processing and imaging module is composed of an image processor, an SDRAM controller, a Nios II soft-core processor, a sensor configurator, an SDRAM-, an SDRAM, a VGA display, a PIO, a network transmission interface and an SOPC high dynamic imaging system, wherein:
the CMOS image sensor is matched with a conventional lens to acquire images, acquired collection data are transmitted to the image processor, the image processor acquires digital signals after processing, and the SDRAM controller transmits the digital signals to the Nios II soft-core processor;
in addition, the SDRAM controller is coupled with the SDRAM and the VGA display and used for storing and transmitting digital signals;
the Nios II soft core processor is coupled with the SDRAM, the PIO, the network transmission interface and the SOPC high dynamic imaging system, and is used for remote transmission, storage, high dynamic imaging processing and online high dynamic image watching.
The further technical scheme is as follows: the image processor of the data processing and imaging module consists of a peripheral processing circuit, an off-chip controller and an ISP image signal processor which are concentrated in the CMOS image sensor, and the off-chip controller and the ISP image signal processor are concentrated in the same chip.
The further technical scheme is as follows: the peripheral processing circuit is composed of a time sequence generating and controlling circuit, an analog signal processing circuit, an A/D converter, an exposure controlling circuit, a black and white balance circuit, a gain controlling circuit and a control register, wherein:
the timing generation and control circuit receives data of the photosensitive cell array of the CMOS image sensor to perform row reset and then reads data of each row in sequence, the analog signal processing circuit performs offset correction on the data of each row, the gain control circuit performs gain processing on the offset-corrected data, the exposure control circuit receives the data after the gain processing, and then carries out exposure processing according to the time gap from the adjustment of the time sequence generation and control circuit to the reset to the reading of the row, the A/D converter performs A/D conversion processing on the data after the exposure processing, the black-white balance circuit performs black-white balance processing on the data after A/D conversion, the gain control circuit performs gain processing on the data after black-white balance processing again, and the data processing steps are controlled by the control register.
The further technical scheme is as follows: the control module is coupled with the peripheral image control and signal processing module through the digital image transmission interface, wherein:
the peripheral image control and signal processing module configures the control module, controls the electronic shutter of the CMOS image sensor to further control the luminous flux, obtains corresponding exposure, and collects, processes and stores digital signals of output images.
The further technical scheme is as follows: the utility model provides a high dynamic imaging detecting system for textile fabric flaw, includes mechanical granny rag and clean cloth module, image acquisition module, data processing and imaging module, flaw image database module, online contrast and record module, flaw mark module and control module, wherein: the central processing unit of the control module controls each module and coordinates the work of each module to complete high dynamic imaging, cloth defect point-to-point comparison detection and defect point mechanical marking;
the mechanical cloth pulling and cleaning module comprises: flatly paving a textile fabric roll by a cloth spreading machine, and cleaning impurities on the surface of the fabric by static electricity removing and cleaning equipment in the fabric conveying process to obtain the fabric with a clean surface;
the image acquisition module: collecting an image of the clean cloth on the surface through an optical camera, and forming and outputting an image digital signal to a lower stage;
the data processing and imaging module: receiving the digital signal, processing the data, forming a high dynamic image by combining a high dynamic image synthesis algorithm, and forming and outputting the high dynamic image to the upper and lower levels;
the defect image database module: calling out flaw images of corresponding textile fabric types in the database after receiving the high dynamic images of the textile fabrics;
the online comparison and recording module: comparing the detected textile fabric combined flaw images, and recording and storing the type and the position of the detected textile fabric flaw points on line;
the flaw marking module: and mechanically marking the detected flaw points of the textile fabric by using a erasable or washable color.
The further technical scheme is as follows: the control module is coupled with the peripheral image control and signal processing module through a digital image transmission interface.
The further technical scheme is as follows: the data processing and imaging module consists of an FPGA control logic circuit and a Nios II soft-core processor embedded in the FPGA control logic circuit.
The further technical scheme is as follows: the flaw image database module 4 comprises a flaw point textile fabric image database, a normal fabric image database and a new fabric image storage database.
Compared with the prior art, the invention can at least achieve one of the following beneficial effects:
1. the invention provides a high dynamic imaging detection method and a high dynamic imaging detection system for textile fabric flaws, wherein the detection system is combined with a high dynamic processing method, a low-cost CMOS image sensor is matched with an FPGA control logic circuit, a high dynamic range image (HDR) can be collected in the movement process of the textile fabric, flaws are detected when the textile fabric is inspected, and the flaws are detected inaccurately due to the defects of scene change and the like caused by camera shake during exposure time and long sequence image shooting interval.
2. The configuration of a CMOS image sensor is realized by configuring and editing a high-dynamic imaging program for a Nios II soft-core processor embedded in an FPGA control logic circuit, the functions of exposure control, image acquisition SDRAM image caching, VGA image display and the like are achieved, image sequences of the same scene and different exposure quantities acquired by an image acquisition module are transmitted to a high-dynamic imaging support software system, an SOPC technology and a high-dynamic imaging algorithm are used for imaging, automatic time domain multiple exposure image sequence acquisition is realized, a defective image database is stored and uploaded, detection and marking are carried out, imaging is clear, comparison is accurate, defects are mechanically marked, and rechecking and finishing are facilitated.
Drawings
Fig. 1 is a flow chart of a high dynamic imaging detection method for textile fabric defects according to the present invention.
Fig. 2 is a schematic structural diagram of a high dynamic imaging detection system for detecting defects of textile fabrics according to the present invention.
Fig. 3 is a schematic structural diagram of the image acquisition module and the data processing and imaging module in fig. 2 according to the present invention.
FIG. 4 is a schematic diagram of the peripheral processing circuit of FIG. 2 according to the present invention.
Description of the drawings: 1. a mechanical cloth pulling and cleaning module; 2. an image acquisition module; 21. a conventional lens; 22. a CMOS image sensor; 221. a peripheral processing circuit; 2211. a timing generation and control circuit; 2212. an analog signal processing circuit; 2213. an A/D converter; 2214. an exposure control circuit; 2215. a black-and-white balancing circuit; 2216. a gain control circuit; 2217. a control register; 3. a data processing and imaging module; 31. an image processor; 32. an SDRAM controller; 33. a Nios II soft core processor; 34. a sensor configurator; 35. SDRAM-0; 36. SDRAM 1; 37. a VGA display; 38. PIO; 39. a network transmission interface; 40. a SOPC high dynamic imaging system; 4. a defect image database module; 5. an online comparison and recording module; 6. a flaw marking module; 7. a control module; 8. an FPGA control logic circuit; 9. a digital image transmission interface; 10. and the peripheral image control and signal processing module.
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.
Example 1:
s1, the mechanical spreading and cleaning module 1: flatly paving a textile fabric roll by a cloth spreading machine, and cleaning impurities on the surface of the fabric by static electricity removing and cleaning equipment in the fabric conveying process to obtain the fabric with a clean surface;
s2, the image acquisition module 2: collecting an image of the clean cloth on the surface through an optical camera, and forming and outputting an image digital signal to a lower stage;
s3, the data processing and imaging module 3: the digital signal is received and then data processing is carried out, a high dynamic image is formed by combining a high dynamic image synthesis algorithm, and high dynamic images are formed and output to the upper level and the lower level;
s4, the defect image database module 4: calling out flaw images of corresponding textile fabric types in the database after receiving the high dynamic images of the textile fabrics;
s5, the online comparison and recording module 5: comparing the detected textile fabric combined flaw images, and recording and storing the type and the position of the detected textile fabric flaw points on line;
s6, the flaw marking module 6: and mechanically marking the detected flaw points of the textile fabric by using a erasable or washable color.
The working principle and the steps of the high dynamic imaging detection method for the textile fabric flaws are as follows: 1. mechanical granny rag and clean cloth module 1 is controlled by control module 7, and the weaving cloth material that will detect is rolled up and is installed in the feed end department of granny rag machine, is opened through the batching cloth tiling by the granny rag machine, and the standard of tiling: the surface of the cloth is not wrinkled, then the cloth is cleaned, the dust on the surface of the tiled cloth is cleaned through a cloth cleaner and static electricity removing equipment, and static electricity is eliminated; 2. the image acquisition module 2 is controlled by the control module 7, the cloth processed cleanly enters the module, the image of the clean cloth on the surface is acquired through the optical camera, and an image digital signal is formed and output to the next stage; 3. the data processing and imaging module 3 is controlled by the control module 7, receives the digital signal, performs data processing, combines a high dynamic image synthesis algorithm (HDR) to form a high dynamic image, and forms and outputs the high dynamic image to the upper and lower levels; 4. the flaw image database module 4 is controlled by the control module 7, and calls out flaw images of corresponding textile fabric types in the database after receiving high dynamic images of the textile fabric; 5. the online comparison and recording module 5 is controlled by the control module 7, compares the detected textile fabric with the flaw image database, and records and stores the type and position of the flaw point of the detected textile fabric online; 6. the flaw marking module 6 and the flaw marking module 6 are controlled by the control module 7, and the detected flaw point of the textile fabric is marked or circled by a mechanical arm through a erasable or washable color.
Example 2:
on the basis of the above embodiment 1, embodiment 2 refers to an embodiment shown in fig. 2 and fig. 3: the image acquisition module 2 is an optical camera composed of a CMOS image sensor 22 and a conventional lens 21, and a magnesium light MT9N001 type COMS image sensor + ABF-F121212MP megapixel high-definition infrared monitoring lens is used for forming digital signals through dynamic images and sending the digital signals to the data processing and imaging module 3.
The data processing and imaging module 3 is composed of an image processor 31, an SDRAM controller 32, a Nios II soft core processor 33, a sensor configurator 34, SDRAM-035, SDRAM-136, a VGA display 37, a PIO38, a network transmission interface 39 and an SOPC high dynamic imaging system 40, wherein:
the image processor 31, the SDRAM controller 32 and the sensor configurator 34 form an FPGA control logic circuit 8, a Nios II soft-core processor 33 is embedded into the FPGA control logic circuit 8 and works according to the following steps, the CMOS image sensor 22 is matched with a conventional lens 21 for image acquisition, acquired collection data is transmitted to the image processor 31, the image processor 31 obtains digital signals after processing, the digital signals are transmitted to the SDRAM controller 32, and the SDRAM controller 32 transmits the digital signals to the Nios II soft-core processor 33;
further said SDRAM controller 32 is coupled to said SDRAM-035 and said VGA display 37 for storing and transmitting digital signals;
the Nios II soft core processor 33 is coupled with the SDRAM 136, the PIO38, the network transmission interface 39 and the SOPC high dynamic imaging system 40, and is used for remote transmission, storage, high dynamic imaging processing and online high dynamic image viewing.
The FPGA control logic circuit 8 is embedded into the Nios II soft core processor 33 to complete image acquisition, equipment control and image processing.
A data interface: the cmos image sensor 22 adopts an IO interface, and a data path between the upper layer high dynamic imaging program system adopts an ethernet control chip DM9000A as a transmission interface.
Image storage: the data bit money of the MT9N001 type COMS image sensor 22 is 12 bits, namely each pixel point is 12 bits, one RGB pixel should occupy 36 bits, therefore, the data cache adopts a magnesium light MT48LC8M32B2 type SDRAM, the word length is 32 bits, the lower 2 bits output by the MT9N001 type COMS image sensor 22 are abandoned, RGB three channels are written into the lower 30 bits of one word of the SDRAM, and the image storage adopts a Micro SD card to match with a FatFS file system to realize DIB bitmap storage.
Previewing a real-time picture: the VCG display 37 is used for previewing the real-time picture, and the A/D converter 2213 used in the VCG display 37 is A/DV7123 which is an A/D converter comprising 3 high-speed A/D conversion channels with the resolution of 10 bits and accords with the data organization form of SDRAM.
A sensor control circuit: the sensor control usually reads and writes to its internal status and control registers, using a simple 2-wire interface compatible I2C bus protocol. The method mainly realizes the writing configuration to the COMS image sensor 22 and the reading of the working state of the COMS image sensor 22, and for the application, the method mainly realizes the configuration of the exposure control register 2217 of the COMS image sensor 22, and realizes the writing of corresponding exposure data to the exposure control register 2217 under the condition that the whole system is not reset.
The DM9000A is controlled by NiosII software programming to transmit the image sequence of different exposure of the same scene acquired by the image acquisition module 2 to a high dynamic imaging support software system (SOPC technology and high dynamic imaging algorithm integration). The image acquisition module 2 realizes automatic time domain multiple exposure, stores and uploads a flaw image database, detects and marks, has clear imaging and accurate comparison, mechanically marks flaw points, and is convenient for rechecking and finishing.
The NiosII soft core processor 33 embedded in the FPGA control logic circuit 8 is used as a control core, and is combined with the CMOS image sensor 22, an external memory SDRAM-035, SDRAM-136, a DM9000A Ethernet control chip, a peripheral control circuit and the like. CMOS sensor pass I2The serial bus carries out register configuration, the obtained image data is input into the image acquisition module 2 through a general interface, and the image data is converted into RGB three-channel image data and written into SDRAM-136; the Nios II soft-core processor 33 reads image data through an Avalon bus to perform digital image processing; and UDP communication is carried out with the upper computer through DM9000A, so that data transmission and control parameter receiving are realized. The design of the whole system can be divided into an FPGA control logic circuit 8 design and an SOPC high dynamic imaging system 40. The FPGA control logic circuit 8 is designed to realize CMOS sensor control, data acquisition, data format conversion, SDRAM controller 32 cache read-write control, VGA display control and other functions by using Verilog HDL language programming, and is combined with a Nios II soft core processor and corresponding peripheral equipment to be compiled and then configured into an FPGA to form the FPGA control logic circuit. The SOPC high dynamic imaging system 40 produces the Nios II soft core processor 33 according to the SOPC Builder and simultaneously generates a corresponding user Software Development Kit (SDK),forming the basis for software development. Software interacting with the hardware module on the bottom layer is compiled based on the SDK, and functions of processing, transmitting, storing, converting upper control information and the like of image data collected by the FPGA control logic circuit 8 are achieved. Then compiling, linking and downloading to the FPGA for running.
Preferably: the image processor 31 of the data processing and imaging module 3 is composed of a peripheral processing circuit 221, an off-chip controller and an ISP image signal processor, which are integrated inside the CMOS image sensor 22, and the off-chip controller and the ISP image signal processor are integrated in the same chip.
The collected data is processed by the peripheral processing circuit 221, the off-chip controller and the ISP image signal processor, and an image signal is formed and transmitted to the next stage.
The peripheral processing circuit 221 is composed of a timing generation and control circuit 2211, an analog signal processing circuit 2212, an a/D converter 2213, an exposure control circuit 2214, a black-and-white balance circuit 2215, a gain control circuit 2216, and a control register 2217, in which: the timing generation and control circuit 2211 receives the data of the light sensing unit array 222 of the CMOS image sensor 22 to perform row reset and then sequentially reads the data of each row, the analog signal processing circuit 2212 performs offset correction on data of each row, the gain control circuit 2216 performs gain processing on the offset-corrected data, the exposure control circuit 2214 receives the data after the gain processing, performs exposure processing according to a time gap from the adjustment of the timing generation and control circuit 2211 to the reset to the reading of the row, the a/D converter 2213 subjects the data after the exposure processing to a/D conversion processing, the black-and-white balance circuit 2215 performs black-and-white balance processing on the a/D converted data, the gain control circuit 2216 performs gain processing on the data after black-white balance processing again, and the data processing steps are controlled by the control register 2217.
Further preferably, the control module 7 is coupled with a peripheral image control and signal processing module 10 through the digital image transmission interface 9, wherein:
the peripheral image control and signal processing module 10 configures the control module 7, controls the electronic shutter of the CMOS image sensor 22 to further control the luminous flux, obtains the corresponding exposure, and performs the operations of collecting, processing, and storing the digital signal of the output image.
Example 5:
mechanical spreading and cleaning module 1: flatly paving a textile fabric roll by a cloth spreading machine, and cleaning impurities on the surface of the fabric by static electricity removing and cleaning equipment in the fabric conveying process to obtain the fabric with a clean surface;
the image acquisition module 2: collecting an image of the clean cloth on the surface through an optical camera, and forming and outputting an image digital signal to a lower stage;
the data processing and imaging module 3: receiving the digital signal, processing the data, forming a high dynamic image by combining a high dynamic image synthesis algorithm, and forming and outputting the high dynamic image to the upper and lower levels;
the defect image database module 4: calling out flaw images of corresponding textile fabric types in the database after receiving the high dynamic images of the textile fabrics;
the online comparing and recording module 5: comparing the detected textile fabric combined flaw images, and recording and storing the type and the position of the detected textile fabric flaw points on line;
the flaw marking module 6: and mechanically marking the detected flaw points of the textile fabric by using a erasable or washable color.
Preferably: the control module 7 is coupled with a peripheral image control and signal processing module 10 through a digital image transmission interface 9.
Preferably: the data processing and imaging module 3 is composed of an FPGA control logic circuit 9 and a Nios II soft core processor 33 embedded in the FPGA control logic circuit 8.
Example 6:
on the basis of the above embodiment, embodiment 6 shows an embodiment in which the defect image database module 4 includes a defect point textile fabric image database, a normal fabric image database, and a new fabric image storage database.
The flaw point textile fabric image database is used for collecting a plurality of types of flaw point textile fabric data, the normal fabric image database is used for collecting a plurality of types of normal textile fabric data, when the detected fabric is compared and detected without a result, the fabric image is stored in the new fabric image storage database, and manual recheck and gear retention are carried out.
Reference throughout this specification to "one embodiment," "another embodiment," "an embodiment," "a preferred embodiment," or the like, means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment described generally in this application. The appearances of the same phrase in various places in the specification are not necessarily all referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with any embodiment, it is submitted that it is within the scope of the invention to effect such feature, structure, or characteristic in connection with other embodiments.
Although the invention has been described herein with reference to a number of illustrative embodiments thereof, it should be understood that numerous other modifications and embodiments can be devised by those skilled in the art that will fall within the spirit and scope of the principles of this disclosure. More specifically, various variations and modifications are possible in the component parts and/or arrangements of the subject combination arrangement within the scope of the disclosure, the drawings and the appended claims. In addition to variations and modifications in the component parts and/or arrangements, other uses will also be apparent to those skilled in the art.
Claims (10)
1. A high dynamic imaging detection method for textile fabric flaws is characterized by comprising the following steps: including mechanical granny rag and net cloth module (1), image acquisition module (2), data processing and imaging module (3), flaw image database module (4), online contrast and record module (5), flaw mark module (6) and control module (7), wherein: the central processing unit of the control module (7) controls and coordinates the rest modules in sequence according to the following steps to complete high dynamic imaging, cloth defect point comparison detection and defect point mechanical marking;
s1, the mechanical spreading and cleaning module (1): flatly paving a textile fabric roll by a cloth spreading machine, and cleaning impurities on the surface of the fabric by static electricity removing and cleaning equipment in the fabric conveying process to obtain the fabric with a clean surface;
s2, the image acquisition module (2): collecting an image of the clean cloth on the surface through an optical camera, and forming and outputting an image digital signal to a lower stage;
s3, the data processing and imaging module (3): the digital signal is received and then data processing is carried out, a high dynamic image is formed by combining a high dynamic image synthesis algorithm, and high dynamic images are formed and output to the upper level and the lower level;
s4, the defect image database module (4): calling out flaw images of corresponding textile fabric types in the database after receiving the high dynamic images of the textile fabrics;
s5, the online comparison and recording module (5): comparing the detected textile fabric combined flaw images, and recording and storing the type and the position of the detected textile fabric flaw points on line;
s6, the defect marking module (6): and mechanically marking the detected flaw points of the textile fabric by using a erasable or washable color.
2. The high dynamic imaging detection method for textile fabric defects according to claim 1, characterized in that: the image acquisition module (2) is an optical camera composed of a CMOS image sensor (22) and a conventional lens (21).
3. The high dynamic imaging detection method for textile fabric defects according to claim 2, characterized in that: the data processing and imaging module (3) is composed of an image processor (31), an SDRAM controller (32), a Nios II soft core processor (33), a sensor configurator (34), an SDRAM 0 (35), an SDRAM 1 (36), a VGA displayer (37), a PIO (38), a network transmission interface (39) and an SOPC high dynamic imaging system (40), wherein:
the image processor (31), the SDRAM controller (32) and the sensor configurator (34) form an FPGA control logic circuit (8), a Nios II soft-core processor (33) is embedded into the FPGA control logic circuit (8), and the FPGA control logic circuit works according to the following steps, the CMOS image sensor (22) is matched with a conventional lens (21) to acquire images, acquired collection data are transmitted to the image processor (31), the image processor (31) processes the collection data to obtain digital signals, the digital signals are transmitted to the SDRAM controller (32), and the SDRAM controller (32) transmits the digital signals to the Nios II soft-core processor (33);
the SDRAM controller (32) is coupled with the SDRAM 0 (35) and the VGA display (37) for storing and transmitting digital signals;
the Nios II soft core processor (33) is coupled with the SDRAM 1 (36), the PIO (38), the network transmission interface (39) and an SOPC high dynamic imaging system (40) and is used for remote transmission, storage, high dynamic imaging processing and online high dynamic image watching.
4. The high dynamic imaging detection method for textile fabric defects according to claim 3, characterized in that: the image processor (31) of the data processing and imaging module (3) is composed of a peripheral processing circuit (221), an off-chip controller and an ISP image signal processor which are concentrated inside the CMOS image sensor (22), and the off-chip controller and the ISP image signal processor are concentrated in the same chip.
5. The high dynamic imaging detection method for textile fabric defects according to claim 4, characterized in that: the peripheral processing circuit (221) is composed of a timing generation and control circuit (2211), an analog signal processing circuit (2212), an a/D converter (2213), an exposure control circuit (2214), a black-and-white balance circuit (2215), a gain control circuit (2216), and a control register (2217), in which:
the timing generation and control circuit 2211 receives data of a photosensitive cell array 222 of the CMOS image sensor 22, performs line reset and then sequentially reads data of each line, the analog signal processing circuit 2212 performs offset correction on the data of each line, the gain control circuit 2216 performs gain processing on the offset-corrected data, the exposure control circuit 2214 receives the gain-processed data and performs exposure processing according to a time interval from the adjustment of the timing generation and control circuit 2211 to the reading of the line, the a/D converter 2213 performs a/D conversion on the exposure-processed data, the black and white balance circuit 2215 performs black and white balance processing on the a/D-converted data, and the gain control circuit 2216 performs gain processing on the black and white-balanced-processed data again, the data processing steps are controlled and completed by the control register (2217).
6. The high dynamic imaging detection method for textile fabric defects according to claim 5, characterized in that: the control module (7) is coupled with a peripheral image control and signal processing module (10) through the digital image transmission interface (9), wherein:
the peripheral image control and signal processing module (10) configures the control module (7), controls the luminous flux by controlling an electronic shutter of the CMOS image sensor (22), obtains corresponding exposure, and collects, processes and stores digital signals of output images.
7. The utility model provides a high dynamic imaging detecting system for textile fabric flaw which characterized in that: including mechanical granny rag and net cloth module (1), image acquisition module (2), data processing and imaging module (3), flaw image database module (4), online contrast and record module (5), flaw mark module (6) and control module (7), wherein: the central processing unit of the control module (7) controls each module and coordinates the work of each module to complete high dynamic imaging, cloth defect point comparison detection and defect point mechanical marking;
the mechanical spreading and cleaning module (1): flatly paving a textile fabric roll by a cloth spreading machine, and cleaning impurities on the surface of the fabric by static electricity removing and cleaning equipment in the fabric conveying process to obtain the fabric with a clean surface;
the image acquisition module (2): collecting an image of the clean cloth on the surface through an optical camera, and forming and outputting an image digital signal to a lower stage;
the data processing and imaging module (3): receiving the digital signal, processing the data, forming a high dynamic image by combining a high dynamic image synthesis algorithm, and forming and outputting the high dynamic image to the upper and lower levels;
the defect image database module (4): calling out flaw images of corresponding textile fabric types in the database after receiving the high dynamic images of the textile fabrics;
the online comparison and recording module (5): comparing the detected textile fabric combined flaw images, and recording and storing the type and the position of the detected textile fabric flaw points on line;
said defect marking module (6): and mechanically marking the detected flaw points of the textile fabric by using a erasable or washable color.
8. The high dynamic imaging detection system for textile fabric defects of claim 7, wherein: the control module (7) is coupled with a peripheral image control and signal processing module (10) through a digital image transmission interface (9).
9. A high dynamic imaging detection system for textile fabric defects according to any one of claims 7-8, characterized in that: the data processing and imaging module (3) is composed of an FPGA control logic circuit (9) and a Nios II soft core processor (33) embedded into the FPGA control logic circuit (8).
10. A high dynamic imaging detection system for textile fabric imperfections according to claim 9, wherein: the flaw image database module (4) comprises a flaw point textile fabric image database, a normal fabric image database and a new fabric image storage database.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011172594.6A CN112213330A (en) | 2020-10-28 | 2020-10-28 | High-dynamic imaging detection method and system for textile fabric flaws |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011172594.6A CN112213330A (en) | 2020-10-28 | 2020-10-28 | High-dynamic imaging detection method and system for textile fabric flaws |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112213330A true CN112213330A (en) | 2021-01-12 |
Family
ID=74057282
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011172594.6A Pending CN112213330A (en) | 2020-10-28 | 2020-10-28 | High-dynamic imaging detection method and system for textile fabric flaws |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112213330A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113674231A (en) * | 2021-08-11 | 2021-11-19 | 宿迁林讯新材料有限公司 | Method and system for detecting iron scale in rolling process based on image enhancement |
| TWI792255B (en) * | 2021-04-07 | 2023-02-11 | 財團法人中華民國紡織業拓展會 | Defect inspecting apparatus, system, and method for stitching line trace |
| CN117147808A (en) * | 2023-10-31 | 2023-12-01 | 江苏启宸新材料有限公司 | Water thorn non-woven fabrics technique progress direction monitored control system based on big data |
| CN117270477A (en) * | 2023-11-17 | 2023-12-22 | 江苏启宸新材料有限公司 | Intelligent control system of spunlaced non-woven fabric production equipment |
-
2020
- 2020-10-28 CN CN202011172594.6A patent/CN112213330A/en active Pending
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI792255B (en) * | 2021-04-07 | 2023-02-11 | 財團法人中華民國紡織業拓展會 | Defect inspecting apparatus, system, and method for stitching line trace |
| CN113674231A (en) * | 2021-08-11 | 2021-11-19 | 宿迁林讯新材料有限公司 | Method and system for detecting iron scale in rolling process based on image enhancement |
| CN113674231B (en) * | 2021-08-11 | 2022-06-07 | 宿迁林讯新材料有限公司 | Method and system for detecting iron scale in rolling process based on image enhancement |
| CN117147808A (en) * | 2023-10-31 | 2023-12-01 | 江苏启宸新材料有限公司 | Water thorn non-woven fabrics technique progress direction monitored control system based on big data |
| CN117147808B (en) * | 2023-10-31 | 2023-12-22 | 江苏启宸新材料有限公司 | Water thorn non-woven fabrics technique progress direction monitored control system based on big data |
| CN117270477A (en) * | 2023-11-17 | 2023-12-22 | 江苏启宸新材料有限公司 | Intelligent control system of spunlaced non-woven fabric production equipment |
| CN117270477B (en) * | 2023-11-17 | 2024-02-23 | 江苏启宸新材料有限公司 | Intelligent control system of spunlaced non-woven fabric production equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112213330A (en) | High-dynamic imaging detection method and system for textile fabric flaws | |
| US8026956B2 (en) | Image sensor, image taking apparatus, and state inspection system | |
| CN100490506C (en) | Image sensor for implementing broad dynamic range by multiple sampling and time-indexing method | |
| JP5469811B2 (en) | Machine vision detector setting and testing methods and equipment | |
| CN105144699B (en) | The imaging sensor and its operating method of the resetting of having ready conditions of threshold monitor | |
| CN101482518A (en) | On-line quality detection system for movable band-shaped material | |
| CN103109523A (en) | Imaging device and imaging method | |
| CN113000413B (en) | System, method and terminal for detecting surface defects of synchronizer gear sleeve based on machine vision | |
| WO2022017197A1 (en) | Intelligent product quality inspection method and apparatus | |
| CN107310795A (en) | Product external packaging detector and detecting system based on machine vision technique | |
| CN102625056A (en) | FPGA (Field-Programmable Gate Array)-based CIS (Contact Image Sensor) image acquisition system and acquisition method thereof | |
| CN105991997B (en) | A kind of method that condenser type imaging sensor bad point positions in real time | |
| CN102572245A (en) | Method and device for extending image dynamic ranges | |
| CN109474781A (en) | Photographic device, the control method of photographic device, recording medium | |
| CN107238727A (en) | Photoelectric tachometric transducer and detection method based on dynamic visual sensor chip | |
| CN101995325A (en) | Appearance detection method and system of image sensor | |
| CN114445330A (en) | Method and system for detecting appearance defects of components | |
| CN110286131A (en) | A kind of textile flaw automatic detection analysis prompt system and method | |
| CN107454388B (en) | Image processing method and apparatus using the same | |
| CN109274896A (en) | A kind of image-pickup method and imaging sensor | |
| CN108184080B (en) | High-speed CMOS linear array camera for machine vision | |
| CN105738376B (en) | A kind of automatic cloth inspecting machine using contact-type image sensor | |
| Yang et al. | An image-based method for soiling quantification | |
| CN102547125A (en) | Tremble eliminating device and method thereof for image acquisition | |
| JPH08254499A (en) | Displaying/appearance inspection device |
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: 20210112 |