Device for automatically adjusting cloth edge image acquisition on automatic cloth inspecting machine

By designing a vertically installed image acquisition device on the automatic cloth inspection machine, using the central processor and motor control, the problem of inaccurate cloth edge detection is solved, and clear acquisition and automatic adjustment of cloth edges is realized to prevent detection loss and improve Test quality.

CN119086577APending Publication Date: 2024-12-06HANGZHOU HUIJU VISION TECH CO LTD
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202311228704.X
Authority / Receiving Office
CN · China
Patent Type
Applications(China)
Current Assignee / Owner
Filing Date
2023-09-22
Publication Date
2024-12-06

Smart Images

  • Figure CN119086577A_ABST
    Figure CN119086577A_ABST
Patent Text Reader

Abstract

The invention discloses a cloth edge image acquisition and automatic adjustment device for an automatic cloth inspecting machine, which comprises a cloth inspecting machine and a motor arranged on the cloth inspecting machine, the motor is provided with a bracket, the bracket is provided with an image acquisition device for inspecting the cloth edge on the cloth inspecting machine, and the image acquisition device is connected with the cloth inspecting machine. The image acquisition device is perpendicular to cloth on the cloth inspecting machine; the image acquisition device comprises a fixed rack body arranged on the bracket, and a camera, a central processing unit and a defect detector are arranged on the fixed rack body. The cloth edge detection device is combined on the automatic cloth inspecting machine to detect the part where the edge of the cloth is located, and the defect that detection is not accurate enough due to loss of detection defects caused by abandoning is overcome.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of equipment related to automatic cloth inspection machines, and in particular to an automatic adjustment device for collecting cloth edge images on an automatic cloth inspection machine. Background Art

[0002] As we all know, in the weaving process of the textile industry, "cloth inspection" is the inspection process of the grey cloth. "Cloth inspection" is mainly divided into manual observation and automatic inspection.

[0003] The first method is to inspect the cloth by manual observation. In the process of sampling the moving grey cloth, if it is manual observation, the influence of the edge of the cloth can be ignored, but its efficiency is too low to meet the production needs.

[0004] The second method is automatic cloth inspection, such as the Chinese utility model patent with authorization announcement number CN213804532U, which discloses an automatic cloth inspection machine based on camera inspection for defects. In the existing automatic cloth inspection, the edges of the cloth are irregular and the position is constantly changing, which often causes great interference to the inspection. For example, the irregular edges will overlap with some defect features, resulting in false alarms in the inspection, and the position of the inspection platform where the edge is located will cause a part of the exposure plate to be directly exposed to the inspection camera (camera), which will produce strong light noise. The light noise will cause the image outside the edge of the cloth to cause great interference to the inspection of the cloth, and the position of the edge is constantly changing during the inspection process, which ultimately brings a great deal of uncertainty to the determination of the edge. The existing means are usually to directly obtain the width of the cloth from an external device, and then return to the fixed inspection range of the inspection device or directly discard the image of the edge. In this way, the image of the edge can only be lost if the defect is discarded, which ultimately affects the inspection quality, and therefore cannot meet the needs of the automatic cloth inspection machine to detect defective cloth. Summary of the invention

[0005] 1. Technical issues that need to be resolved

[0006] In view of the deficiencies in the prior art, the present invention provides an automatic adjustment device for capturing images of cloth edges on an automatic cloth inspection machine. When combined with the automatic cloth inspection machine, the device can detect the portion where the cloth edge is located, thereby preventing the loss of detection defects due to abandonment, resulting in inaccurate detection defects.

[0007] (II) Technical solutions that need to be adopted

[0008] In order to achieve the above object, the technical solution adopted by the present invention is:

[0009] An automatic adjustment device for collecting images of cloth edges on an automatic cloth inspection machine, comprising a cloth inspection machine and a motor arranged on the cloth inspection machine, wherein the motor is provided with a bracket, and an image acquisition device for inspecting the edges of cloth on the cloth inspection machine is arranged on the bracket, and the image acquisition device and the cloth on the cloth inspection machine are arranged perpendicular to each other;

[0010] The image acquisition device comprises a fixed frame body arranged on the bracket, and a camera, a central processing unit and a defect detector are arranged on the fixed frame body;

[0011] The camera is used to collect images of the edges of the fabric on the fabric inspection machine;

[0012] The central processor is used to process the image of the edge of the cloth captured by the camera to obtain a clear image containing the edge of the cloth, and the central processor controls the operation of the motor;

[0013] The defect detector is used to receive the clear image of the edge of the cloth output by the central processor for defect detection.

[0014] In a further embodiment, the bracket adopts an L-shaped frame, which includes a fixing rod fixed on the motor, a connecting rod integrally formed on the fixing rod, the connecting rod and the fixing rod are vertically distributed, the connecting rod and the fabric on the fabric inspection machine are parallelly distributed, and the camera is located on the connecting rod.

[0015] In a further embodiment, the camera is located 20 to 30 cm above the fabric of the fabric inspection machine.

[0016] A further embodiment further includes an exposure plate arranged below the cloth carrying material on the cloth inspection machine.

[0017] In a further embodiment, the central processing unit includes a calculation and analysis module, an image processing module and a motor control module;

[0018] The calculation and analysis module is used to initialize the cloth image captured by the camera, extract edge features, and calculate and obtain the initial edge position;

[0019] The image processing module is used to analyze the position information of the data from the calculation and analysis module, and perform image processing and position tracking, eliminate external interference at the edge, complete image edge adjustment, and the data finally flows to the defect detector;

[0020] The motor control module is used to receive the data from the calculation and analysis module and then control the motor through the motor control module.

[0021] In a further embodiment, the central processing unit contains an FPGA chip.

[0022] In a further embodiment, the defect detector adopts an FPGA controller.

[0023] (III) Technical effects to be achieved

[0024] Compared with the prior art, the present invention has the following beneficial effects:

[0025] Firstly, the motor in the present invention is provided with a bracket, on which is provided an image acquisition device for inspecting the edge of the cloth on the cloth inspection machine. The image acquisition device and the cloth on the cloth inspection machine are vertically distributed to each other. This makes the image acquisition device easy to install and convenient for subsequent adjustment and maintenance on the one hand, and also makes it easy for the image acquisition device to capture images of cloth containing edges, thereby meeting the detection requirements.

[0026] Secondly, the image acquisition device of the present invention includes a fixed frame body arranged on a bracket, and a camera, a central processing unit and a defect detector are arranged on the fixed frame body; the camera is used to acquire the image of the edge of the cloth on the cloth inspection machine; the central processing unit is used to process the image of the edge of the cloth acquired by the camera to obtain a clear image containing the edge of the cloth, and the central processing unit controls the operation of the motor; the defect detector is used to receive the clear image of the edge of the cloth output by the central processing unit for defect detection, and the defect detector can realize the detection of the part where the edge of the cloth is located in combination with the automatic cloth inspection machine, so as to prevent the loss of detection defects due to abandonment and cause inaccurate detection defects. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] Figure 1 It is a schematic diagram of the structure of the present invention.

[0028] Figure 2 It is a block diagram of the image acquisition device of the present invention.

[0029] Figure 3 The figure is a block diagram of the processing process of the image acquisition device of the present invention.

[0030] In the figure: 1, motor; 2, bracket; 3, image acquisition device; 4, cloth; 21, fixing rod; 22, connecting rod; 31, fixing frame body; 32, camera; 33, central processing unit; 34, defect detector; 331, calculation and analysis module; 332, image processing module; 333, motor control module. DETAILED DESCRIPTION

[0031] In the description of the present invention, it should be noted that when an element is referred to as being "fixed to" or "disposed on" another element, it may be directly on the other element or indirectly on the other element. When an element is referred to as being "connected to" another element, it may be directly connected to the other element or indirectly connected to the other element.

[0032] In the description of the present invention, it should be noted that the terms "center", "length", "width", "thickness", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside", "outside" and the like indicate positions or positional relationships based on the positions or positional relationships shown in the accompanying drawings, or the positions or positional relationships in which the invention product is usually placed when in use, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore cannot be understood as limiting the present invention. In addition, the terms "first", "second", "third" and the like are only used to distinguish descriptions, and cannot be understood as indicating or implying relative importance. Thus, the features defined as "first" and "second" may explicitly or implicitly include one or more of the features. In the description of the present invention, "multiple" means two or more, unless otherwise clearly and specifically defined. "Several" means one or more, unless otherwise clearly and specifically defined.

[0033] In the description of the present invention, it is also necessary to explain that, unless otherwise clearly specified and limited, the terms "set", "install", "connect", and "connect" should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two elements. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0034] In order to make the purpose, technical scheme and advantages of the present invention clearer, the present invention is further described in detail below through the accompanying drawings and embodiments. However, it should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the scope of the present invention. In addition, in the following description, the description of known structures and technologies is omitted to avoid unnecessary confusion of the concept of the present invention.

[0035] Example 1: See Figure 1A device for automatically adjusting the image acquisition of the edge of a cloth on an automatic cloth inspection machine includes a cloth inspection machine and a motor 1 arranged on the cloth inspection machine. The cloth inspection machine used is an automatic cloth inspection machine known to the technicians, so there is no need to explain the automatic cloth inspection machine in detail. The motor 1 is provided with a bracket 2, on which an image acquisition device 3 for inspecting the edge of the cloth 4 on the cloth inspection machine is provided. The image acquisition device 3 is perpendicular to the cloth 4 on the cloth inspection machine to ensure that the cloth 4 (cloth or grey cloth) to be tested has no wrinkles, and the tension of the cloth 4 is uniform and basically consistent with the tension when the cloth inspection machine is turned on; the image acquisition device 3 includes a fixed frame body 31 arranged on the bracket 2, on which a camera 32, a central processing unit 33 and a defect detector 34 are provided, the camera 32 is used to collect the image of the edge of the cloth 4 on the cloth inspection machine; the central processing unit 33 is used to process the image of the edge of the cloth 4 collected by the camera 32 to obtain a clear image containing the edge of the cloth 4, wherein the central processing unit 33 stably tracks the edge of the cloth 4 in the image collected and automatically eliminates interference outside the edge to obtain a clear image of the edge of the cloth 4; the defect detector 34 is used to receive the clear image of the edge of the cloth 4 output by the central processing unit 33 for defect detection, and the central processing unit 33 controls the operation of the motor 1. In this embodiment, the central processing unit 33 contains an FPGA (field programmable gate array) chip. This external structure is simple, easy to implement, and has a relatively low cost.

[0036] Embodiment 2: Figure 1 As shown, it can be further said on the basis of embodiment 1 that the bracket 2 adopts an L-shaped frame, and the L-shaped frame includes a fixed rod 21 fixed on the motor 1, and a connecting rod 22 is integrally formed on the fixed rod 21, and the connecting rod 22 is vertically distributed with the fixed rod 21, and the connecting rod 22 and the cloth 4 on the cloth inspection machine are parallelly distributed, and the camera 32 is located on the connecting rod 22. This arrangement is conducive to the adjustment of the angle of the L-shaped frame by the motor 1, and then the position of the image acquisition device 3 can be automatically adjusted to meet the needs of different angles.

[0037] Embodiment 3: Figure 1 As shown, it is also desired to explain on the basis of Example 1 or Example 2 that the camera 32 is located 20 to 30 cm above the fabric 4 of the fabric inspection machine. This not only enables the camera 32 to capture images containing the edge of the fabric 4 on the fabric inspection machine, but also does not affect the normal operation of the fabric inspection machine.

[0038] Embodiment 4: It can be further said on the basis of embodiment 1 or embodiment 2 or embodiment 3 that it also includes an exposure plate arranged below the cloth 4 supported on the cloth inspection machine. This arrangement is beneficial to improving the image clarity of the cloth 4 and the edge of the cloth 4 captured by the camera 32.

[0039] Embodiment 5: Figure 2As shown, it can be further said on the basis of the first embodiment or the second embodiment or the third embodiment or the fourth embodiment that the central processing unit 33 includes a calculation and analysis module 331, an image processing module 332 and a motor control module 333. The calculation and analysis module 331 is used to initialize the image of the cloth 4 collected by the camera 32, extract edge features, and calculate and obtain the initial edge position; the image processing module 332 is used to analyze the position information of the data from the calculation and analysis module 331, and perform image processing and position tracking, eliminate external interference on the edge, complete the image edge adjustment, and the data finally flows to the defect detector 34; the motor control module 333 is used to receive the data from the calculation and analysis module 331 and then control the motor 1 through the motor control module 333. Figure 3As shown, specifically, the calculation method of the central processor 33 is as follows: the processing process of the calculation and analysis module 331 is as follows: the image containing the edge of the cloth 4 to be detected → image preprocessing → canny operator extracts edge features after filtering → calculates the radial pixel points of the image and returns the maximum position coordinates to determine the edge of the cloth and calibrates the edge position → when detecting the image, only the image within the calibrated edge position range is detected, that is, the position coordinate is compared with the position threshold value, if it is greater than the coordinate threshold value, the motor control module 333 will be notified, and the motor control module 333 will control the motor 1 to control the motor 1 to move left and right, drive the camera 32 to move, and keep the edge of the cloth at the set threshold position, and then perform image preprocessing, and then image filtering processing After processing, edge features are extracted, and finally the radial pixel points of the image are calculated and the maximum position coordinates are returned. In this way, image processing and position tracking can be repeated and continuously performed to eliminate external interference on the edge. Finally, a clear image of the fabric 4 containing the edge image can be transmitted to the defect detector 34, so that the defects of the fabric 4 on the fabric inspection machine can be detected more accurately. For example: assuming that edge detection is set to be performed only on the range of 30% (edge ​​position range) on both sides of the image, and the position threshold is set to 15%, and the current left motor position is 15% on the left side of the image. At this time, if the edge is detected to be 20% on the left side of the image, that is, greater than 15%, it is necessary to control the motor 1 to move to the right, drive the camera 32 to move to the right, and keep the edge position at 15%.The processing process of the image processing module 332 is as follows: when detecting an image, only the image within the calibrated edge position range is detected, that is, the position coordinate is compared with the position threshold (for example: assuming that only 30% (edge ​​position range) of the left and right sides of the image are set to be edge detected, and the position threshold is set to 15%, the current left motor position is 15% of the left side of the image. At this time, if the edge is detected to be 20% of the left side of the image, that is, greater than 15%, it is necessary to control the motor 1 to move to the right, drive the camera 32 to move to the right, and keep the edge position at 15%). If it is less than the coordinate threshold (for example: assuming that only 30% (edge ​​position range) of the left and right sides of the image are set to be edge detected, and the position threshold is set to 15%, the current left motor position is 15% of the left side of the image. The position range is used for edge detection, and the position threshold is set to 15%. The current left motor position is 15% of the left side of the image. At this time, if the edge is detected to be 10% of the left side of the image, that is, less than 15%, it is necessary to control the motor 1 to move to the left, drive the camera 32 to move to the left, and keep the edge position at 15%), it will be determined whether it is the first frame. If it is (YES), the image edge position calibration calculates the size and position information of the part outside the edge, and then generates an image mask. For the part outside the edge, in order to remove its interference with the detection, the proportion of the part outside the edge is automatically determined according to the edge calibration position, and a covering mask of the same size is automatically generated. The mask is used It is shielded to form an image synthesis, and the processed image is returned to the defect detector 34. If it is not (NO), it is compared with the position of the maximum value of the edge pixel count in the previous frame. In this way, the edge position can be updated in real time during the real-time detection of the cloth to remove interference. When the position difference is less than the threshold value, the edge position remains unchanged, and then it will be consistent with the size and position information of the outer part of the edge calculated by the image edge position calibration. When the position difference is greater than the threshold value, for example: assuming that the detected edge position is 10% of the left side of the image, which is less than the position threshold of 15%, because it is the first frame, the position is not updated immediately at this time, but the frame number of the new position is recorded. When a certain number of frames are continuous, such as 10 frames, the detected edge If the positions are all less than 15%, the new cloth position is updated to 10%. At this time, the motor 1 is controlled to move to the left, driving the camera 32 to move to the left, so that the cloth edge returns to the position threshold of 15%, and the edge position is updated. Then, it will be consistent with the size and position information of the outer part of the edge calculated by the image edge position calibration. This setting has high robustness (also refers to the characteristics of the control system maintaining certain other performances under certain structural and size parameter perturbations). In the edge detection, each frame of the edge image will automatically be compared with the edge position of the previous frame image, so that real-time tracking can be achieved when the edge position of the cloth 4 is relatively stable, and adjustment tracking can be quickly achieved when the edge position suddenly changes. The position threshold and difference threshold in this embodiment are preset values, and can also be manually input. The entire edge position detection will use this value as a reference.

[0040] In the present invention, after the cloth inspection machine is started, the camera 32 is used to collect the image to be detected containing the edge of the cloth 4 on the cloth inspection machine, and then the calculation and analysis module 331 in the central processing unit 33 performs initialization processing on the detected image, extracts edge features, calculates and obtains the initial edge position and analyzes the position information, and then the image processing module 332 in the central processing unit 33 performs image processing and position tracking to eliminate external interference on the edge. Finally, after the edge detection is completed, the processed image is output to the defect detector 34 for defect detection.

[0041] The present invention can automatically adjust the position of the image acquisition device 3 according to the edge position of the cloth 4 on the platform of the automatic cloth inspection machine, wherein the motor 1 is controlled to rotate the screw rod so that the slide on the screw rod (the camera 32 is installed on the slide rod) produces a left and right displacement, so that the position of the camera 32 is always aligned with the edge of the cloth, and the edge position in the image is automatically calibrated, and stable tracking of the edge of the cloth is achieved, and interference outside the edge is automatically eliminated. The edge position in the image is automatically calibrated by inputting the image captured by the camera 32 that shoots the edge of the cloth into the processor 33, and the calibration is performed through software recognition.

[0042] Embodiment 6: It can be further stated on the basis of Embodiment 1 or Embodiment 2 or Embodiment 3 or Embodiment 4 or Embodiment 5 that the defect detector 34 adopts an FPGA controller, which is known to those skilled in the art and does not need to be described in detail here.

[0043] The standard parts used in this application document can all be purchased from the market, and the specific connection methods of each part adopt conventional means such as mature motors in the existing technology. The internal components of the camera all adopt conventional models in the existing technology, and its internal structure belongs to the existing technology structure. Workers can complete normal operation of it according to the existing technical manual. In addition, the circuit connection adopts the conventional connection method in the existing technology, and no specific description is given here.

[0044] It should be noted that, although the above embodiments have been described in this article, the scope of patent protection of the present invention is not limited thereby. Therefore, based on the innovative concept of the present invention, changes and modifications made to the embodiments described herein, or equivalent structures or equivalent process changes made using the contents of the present specification and drawings, directly or indirectly applying the above technical solutions to other related technical fields are all included in the scope of protection of the patent of the present invention.

Claims

1. A device for automatically adjusting the image acquisition of cloth edges on an automatic cloth inspection machine, comprising a cloth inspection machine and a motor (1) arranged on the cloth inspection machine, characterized in that: The motor (1) is provided with a bracket (2), and the bracket (2) is provided with an image acquisition device (3) for inspecting the edge of the cloth (4) on the cloth inspection machine, and the image acquisition device (3) and the cloth (4) on the cloth inspection machine are arranged perpendicular to each other; The image acquisition device (3) comprises a fixed frame body (31) arranged on the bracket (2), and a camera (32), a central processing unit (33) and a defect detector (34) are arranged on the fixed frame body (31); The camera (32) is used to collect images of the edge of the cloth (4) on the cloth inspection machine; The central processor (33) is used to process the image of the edge of the cloth (4) captured by the camera (32) to obtain a clear image containing the edge of the cloth (4), and the central processor (33) controls the operation of the motor (1); The defect detector (34) is used to receive the clear image of the edge of the cloth (4) output by the central processor (33) to perform defect detection.

2. The automatic adjustment device for collecting and adjusting cloth edge images on an automatic cloth inspection machine according to claim 1, characterized in that: The bracket (2) is an L-shaped frame, and the L-shaped frame comprises a fixing rod (21) fixed on the motor (1), a connecting rod (22) is integrally formed on the fixing rod (21), the connecting rod (22) and the fixing rod (21) are vertically distributed, the connecting rod (22) and the cloth (4) on the cloth inspection machine are parallelly distributed, and the camera (32) is located on the connecting rod (22).

3. The automatic adjustment device for collecting and adjusting cloth edge images on an automatic cloth inspection machine according to claim 1 or 2, characterized in that: The camera (32) is located 20 to 30 cm above the cloth (4) of the cloth inspection machine.

4. The automatic adjustment device for collecting and adjusting cloth edge images on an automatic cloth inspection machine as claimed in claim 1 or 2, characterized in that: It also comprises an exposure plate arranged below the cloth (4) carried on the cloth inspection machine.

5. The automatic adjustment device for collecting and adjusting cloth edge images on an automatic cloth inspection machine as claimed in claim 1 or 2, characterized in that: The central processing unit (33) comprises a calculation and analysis module (331), an image processing module (332) and a motor control module (333); The calculation and analysis module (331) is used to perform initialization processing on the image of the cloth 4 collected by the camera (32), extract edge features, and calculate and obtain the initial edge position; The image processing module (332) is used to analyze the position information of the data transmitted by the calculation and analysis module (331), and perform image processing and position tracking, eliminate external interference at the edge, complete image edge adjustment, and the data finally flows to the defect detector (34); The motor control module (333) is used to receive data from the calculation and analysis module (331) and then control the motor (1) through the motor control module (333).

6. The automatic adjustment device for collecting and adjusting cloth edge images on an automatic cloth inspection machine as claimed in claim 1 or 2, characterized in that: The central processing unit (33) contains an FPGA chip.

7. The automatic adjustment device for collecting and adjusting cloth edge images on an automatic cloth inspection machine as claimed in claim 1 or 2, characterized in that: The defect detector (34) adopts an FPGA controller.