Cloth detection system

Abstract

The invention discloses a cloth detection system. The cloth detection system comprises a bowl-shaped light source, an area-array camera, an encoder, a line scanning camera, a strip-shaped light source and a controller, wherein the bowl-shaped light source provides first irradiation light for the area-array camera, the strip-shaped light source provides second irradiation light for the line scanning camera, and cloth to be detected sequentially passes through the shooting range of the area-array camera and the shooting range of the line scanning camera; the encoder is used for measuring the moving distance of the cloth to be detected; the area-array camera is used for shooting a first image of to-be-detected cloth; the line scanning camera is used for shooting a second image of the to-be-detected cloth; and the controller is used for controlling a brightness parameter of the strip-shaped light source and a gain parameter of the line scanning camera according to the first image, so that the line scanning camera shoots a second image meeting a preset requirement. According to the embodiment of the invention, the detection hysteresis can be reduced, and the detection accuracy is improved. The method can be widely applied to the field of cloth detection.

Description

Technical Field

[0001] This application relates to the field of fabric inspection technology, and in particular to a fabric inspection system. Background Technology

[0002] Under current technology, when using an intelligent fabric inspection machine to inspect a piece of fabric, the fabric needs to pass through a line-scanning camera. The light source and camera parameters are manually adjusted based on the image quality observed to ensure the image is favorable for inspection. This process introduces a lag and human error. The fabric needs to pass through the line-scanning camera first before the light source brightness and camera gain can be adjusted based on the image quality, sometimes requiring multiple adjustments. By the time the image quality is properly adjusted, the fabric that has passed through the camera on the inspection machine may have covered tens of meters. This section of fabric used for camera adjustments may have unsuitable image quality, leading to incomplete defect detection and missed detections. Furthermore, the adjustment process relies on human observation to determine the appropriateness of the light source brightness and camera gain, which introduces subjective judgment errors. Summary of the Invention

[0003] To address one of the aforementioned problems, the main objective of this application is to propose a fabric inspection system that aims to reduce inspection lag and improve inspection accuracy.

[0004] To achieve the above objectives, one aspect of this application provides a fabric inspection system, which includes a bowl-shaped light source, an area array camera, an encoder, a line scan camera, a bar light source, and a controller; wherein the bowl-shaped light source provides a first illumination light to the area array camera, and the bar light source provides a second illumination light to the line scan camera, and the fabric to be inspected sequentially passes through the shooting range of the area array camera and the line scan camera; The encoder is used to measure the distance the fabric to be tested has moved. The area array camera is used to capture a first image of the fabric to be inspected; The line scan camera is used to capture a second image of the fabric to be inspected; The controller is used to control the brightness parameters of the bar light source and the gain parameters of the line scan camera according to the first image, so that the line scan camera can capture a second image that meets preset requirements.

[0005] In some embodiments, the controller is further configured to: The type of the fabric to be detected is determined based on the brightness change of the first image. If the type of fabric to be tested changes, determine the time to adjust the brightness parameter of the bar light source and the gain parameter of the line scan camera.

[0006] In some embodiments, determining whether the type of the fabric to be detected has changed based on the brightness change of the first image includes: If the brightness difference between two adjacent first images exceeds a preset range or the brightness difference between different areas of the same first image exceeds the preset range, the type of the fabric to be detected changes. Otherwise, the type of the fabric to be tested remains unchanged.

[0007] In some embodiments, the brightness parameter of the bar light source and the gain parameter of the line scan camera are determined by the following method: The first image is input into a pre-trained preset model to obtain the brightness parameters of the bar light source and the gain parameters of the line scan camera. The preset model is trained using the following method: The image samples of the area scan camera, the brightness parameter samples of the bar light source, and the gain parameter samples of the line scan camera are obtained. The brightness parameter samples and the gain parameter samples are determined by adjusting the bar light source and the line scan camera based on the image samples of the area scan camera. An initial model is trained based on image samples from the area scan camera, brightness parameter samples, and gain parameter samples until a preset requirement is met, thus obtaining the preset model.

[0008] In some embodiments, determining the timing for adjusting the brightness parameter of the bar light source and the gain parameter of the line scan camera includes: The moment when the type of the fabric to be detected changes is taken as the initial moment, and the first displacement measured by the encoder from the initial moment is recorded. If the difference between the second distance between the area scan camera and the line scan camera and the first displacement reaches a preset threshold, the current moment is determined as the moment to adjust the brightness parameter of the bar light source and the gain parameter of the line scan camera.

[0009] In some embodiments, if the fabric to be inspected requires backlighting for inspection, the bowl-shaped light source and the area scan camera are positioned on the same side of the fabric to be inspected.

[0010] In some embodiments, if the fabric to be inspected requires front-facing illumination for inspection, the bowl-shaped light source and the area scan camera are positioned on both sides of the fabric to be inspected.

[0011] In some embodiments, the line scan camera and the strip light source are disposed on the same side of the fabric to be inspected, the line scan camera is disposed in the vertical direction of the fabric to be inspected, and the light emission direction of the strip light source and the light incident direction of the line scan camera are at a preset angle.

[0012] In some embodiments, the line scan camera and the strip light source are disposed on both sides of the fabric to be inspected, the line scan camera is disposed in the vertical direction of the fabric to be inspected, and the light emission direction of the strip light source and the light incident direction of the line scan camera are on the same straight line.

[0013] In some embodiments, the system further includes a shield with a light-blocking material disposed inside, the shield having an opening on one side and being disposed on both sides of the fabric to be tested.

[0014] The embodiments of this application include at least the following beneficial effects: This application provides a fabric inspection system, which includes a bowl-shaped light source, an area scan camera, an encoder, a line scan camera, a bar light source, and a controller; the bowl-shaped light source provides a first illumination light for the area scan camera, and the bar light source provides a second illumination light for the line scan camera. The fabric to be inspected passes through the shooting range of the area scan camera and the line scan camera in sequence; the area scan camera is used to capture a first image of the fabric to be inspected; the line scan camera is used to capture a second image of the fabric to be inspected; the controller is used to control the brightness parameters of the bar light source and the gain parameters of the line scan camera according to the first image, so that the line scan camera captures a second image that meets the preset requirements. In this embodiment, an area scan camera is added before the line scan camera, and the brightness parameters of the bar light source and the gain parameters of the line scan camera are controlled by the first image captured by the area scan camera, so that the control parameters are adjusted in time when the fabric to be inspected reaches the vicinity of the line scan camera, reducing detection lag. In addition, the control parameters are automatically determined according to the first image captured by the area scan camera, reducing the error of human subjective judgment and improving the accuracy of detection. Attached Figure Description

[0015] Figure 1 This is a schematic diagram of the structure of a fabric inspection system provided in an embodiment of this application; Figure 2 This is a schematic diagram of another fabric inspection system provided in an embodiment of this application; Figure 3 This is a schematic diagram of the installation of the protective cover in the fabric inspection system provided in this application embodiment. Detailed Implementation

[0016] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0017] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0018] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0019] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0020] Before providing a detailed description of the embodiments of this application, some of the nouns and terms involved in the embodiments of this application will be explained first. The nouns and terms involved in the embodiments of this application are subject to the following interpretations.

[0021] The intelligent fabric inspection system combines traditional manual fabric inspection machines with industrial camera light source sensors and other components to form a system that assists manual fabric inspection. Its working principle involves using an encoder sensor to convert the physical movement of the fabric into a constant pulse signal. The camera then captures images of the fabric based on the received encoder pulse signals. During image acquisition, a light source is used to illuminate the camera's shooting position. The inspection software deployed on the industrial control computer receives the fabric image data and uses model data to determine if the fabric has any defects. If defects are found, they are marked. A labeling machine can be configured to affix a label near the defective location, facilitating subsequent fabric processing.

[0022] The brightness of the camera image, and the stability of the image quality captured by the camera, directly affects the software's detection results. The optimal effect is achieved when capturing images of fabric defects, which is the image quality used to train the defect model. This image brightness is affected by several factors. One is the brightness of the light source; adjusting the light source brightness is the most common way to improve image quality. Another is adjusting the camera's analog and digital gain.

[0023] See Figure 1 One aspect of this application provides a fabric inspection system, which includes a bowl-shaped light source 1-2, an area scan camera 1-1, an encoder 1-3, a line scan camera 1-5, a strip light source 1-4, and a controller; wherein, the bowl-shaped light source 1-2 provides a first illumination light for the area scan camera 1-1, and the strip light source 1-4 provides a second illumination light for the line scan camera 1-5, and the fabric to be inspected passes through the shooting range of the area scan camera 1-1 and the line scan camera 1-5 in sequence; Encoders 1-3 are used to measure the distance the fabric to be inspected moves. Area array camera 1-1 is used to capture the first image of the fabric to be inspected; Line scan cameras 1-5 are used to capture a second image of the fabric to be inspected; The controller is used to control the brightness parameters of the bar light source and the gain parameters of the line scan camera based on the first image, so that the line scan camera can capture a second image that meets the preset requirements.

[0024] A line scan camera uses a 5cm-long linear sensor as its image sensor. Each image captured is a single line, parallel to the camera's sensor and mounted on the intelligent fabric inspection system. After attaching a lens, it can typically capture a line about 1 meter wide. As the fabric moves in one direction, each of the fine lines captured by the camera at high frequency is sequentially stitched together to form an image. Camera parameters, such as analog and digital gain, can be used to adjust the brightness of the captured image.

[0025] A bar light source is used to supplement the camera's illumination. The bar light source is long and narrow, with a long, narrow luminous surface. When the light source shines on the fabric, it creates a long, narrow strip of light. The position captured by the line scan camera coincides with this strip of light; that is, the position captured by the line scan camera is the brightest line on the fabric illuminated by the light source. The brightness of the bar light source can currently be adjusted via software.

[0026] An encoder is a device that converts physical distance into constant pulse electrical signals. The encoder's bearing is connected to a rubber wheel, which is pressed against the surface of the fabric on the intelligent fabric inspection machine. This allows the encoder to convert the distance the fabric moves into a constant pulse electrical signal. For example, if the rubber wheel used by the encoder has a circumference of 150mm, and the encoder's bearing can output 2500 pulse electrical signals in one rotation, then the encoder will output one pulse electrical signal for every 0.06mm the fabric moves.

[0027] It should be noted that the number of line scanning cameras in the fabric inspection system is determined based on the actual application, and this embodiment does not impose specific limitations, such as setting 2 or 4 line scanning cameras. The position and angle of the line scanning cameras and the bar light source are determined based on the actual application, and this embodiment does not impose specific limitations. The positions of the bowl-shaped light source and the area array camera are determined based on the actual application, and this embodiment does not impose specific limitations.

[0028] In some embodiments, the controller is further configured to: The type of the fabric to be detected has changed based on the brightness changes in the first image; If the type of fabric to be inspected changes, determine when to adjust the brightness parameters of the bar light source and the gain parameters of the line scan camera.

[0029] If the type of fabric to be detected changes, the brightness of the first image will change significantly. Therefore, the change in brightness of the first image is used to determine whether the type of fabric to be detected has changed. If the type of fabric to be detected has changed, the timing for adjusting the brightness parameters of the bar light source and the gain parameters of the line scan camera is determined to ensure timely adjustment of these parameters. If the type of fabric to be detected has not changed, the brightness parameters of the bar light source and the gain parameters of the line scan camera are kept constant.

[0030] In some embodiments, determining whether the type of the fabric to be detected has changed based on the brightness change of the first image includes: If the brightness difference between two adjacent first images exceeds the preset range or the brightness difference between different areas of the same first image exceeds the preset range, the type of fabric to be detected changes. Otherwise, the type of fabric being tested has not changed.

[0031] It should be noted that the preset range is determined based on the actual application, and this embodiment does not impose specific limitations. If the brightness difference between two adjacent first images exceeds the preset range, it indicates that the boundary between the two types of fabrics is between the two images; if the brightness difference between different areas of the same first image exceeds the preset range, it indicates that the boundary between the two types of fabrics is in the same image.

[0032] In one specific embodiment, the fabric detection system begins fabric detection by first capturing images of the fabric through an area scan camera. For example, 10 images are captured per second, meaning the fabric moves 1 meter (10 centimeters) per second, and one image is captured for each meter of movement. For higher precision, 100 images can be captured per second, with one image captured for every centimeter the fabric moves. These 100 images are compared. If none of the 100 images show significant brightness changes (i.e., the brightness change does not exceed a preset range), it indicates that the fabric type remains constant within that 1-meter distance, and no adjustment to the brightness parameters of the bar light source and the camera gain parameters of the line scan camera is necessary. If there are dividing lines among the 100 images (i.e., significant brightness changes within the same image or between consecutive images, meaning the brightness change exceeds a preset range), then the system proceeds. This allows us to determine the type of fabric within a 1-meter distance. As for the precise location, such as the exact dividing line within that 1-meter distance, the pixel coordinates of the dividing line can be determined through image analysis, combined with the image's actual horizontal and vertical resolution to calculate the physical location. In this embodiment, the distance between the shooting positions of the area scan camera and the line scan camera can be measured. Therefore, when a change in fabric is detected, the physical distance from the dividing line of change to the shooting position of the detection camera can be accurately provided. This allows the bar light source and camera gain parameters to be set one second before the new type of fabric reaches the detection camera.

[0033] In some embodiments, the brightness parameters of the bar light source and the gain parameters of the line scan camera are determined by the following method: The first image is input into the trained preset model to obtain the brightness parameters of the bar light source and the gain parameters of the line scan camera. The preset model is trained using the following method: The image samples from the area scan camera, the brightness parameter samples from the bar light source, and the gain parameter samples from the line scan camera are obtained. The brightness parameter samples and gain parameter samples are determined by adjusting the bar light source and the line scan camera based on the image samples from the area scan camera. The initial model is trained based on image samples, brightness parameter samples, and gain parameter samples from the area scan camera until the preset requirements are met, thus obtaining the preset model.

[0034] It should be noted that the preset model is determined based on the actual application, and this embodiment does not impose specific limitations, such as a large-scale artificial intelligence model. During the training process, the samples are divided into training data and validation data. The ratio of training data to validation data is determined based on the actual application, for example, a ratio of 9:1. The initial model is trained using the training data, the parameters of the initial model are adjusted, and the model after parameter adjustment is validated using the validation data until the preset requirements are met, such as a prediction accuracy of 98%. The model parameters are then fixed to obtain the preset model.

[0035] In one specific embodiment, 100 images captured by the area scan camera within one second are considered similar if there are no significant differences. This indicates that the fabric type has not changed, and the data from these 100 images can be used to train a pre-defined model for the correspondence. This involves comparing the 100 images captured by the area scan camera with 100 images captured by the line scan camera used for detection, and calculating the differences. During the pre-defined model training phase, collaboration between technical and algorithm engineers is required. The algorithm engineers primarily evaluate whether the image acquisition effect of the line scan camera is optimal. For each type of fabric, the imaging effect needs to be adjusted to its best state, and the light source brightness parameters and the gain parameters of the line scan camera at this point need to be recorded. The area scan camera in this embodiment can adjust the brightness of the light source and the gain parameter value of the camera to make the imaging effect of the area scan camera in this embodiment as close as possible to the image acquisition effect of the line scan camera used for detection. For example, the digital gain of the current area scan camera is 2, the exposure is 100us (to ensure that the moving image captured by the camera does not produce ghosting or blurring. The maximum speed of the fabric movement determines that the area scan camera has a maximum exposure value, let's say 200us. When the exposure of the area scan camera is less than 200us), and the brightness of the light source is 100 (0-255). At this time, the area scan camera can make the image data of the area scan camera close to the image effect of the line scan camera used for detection by changing the exposure, gain, light source brightness, etc. During the adjustment process, this embodiment can collect a large amount of image data from the area scan camera under different light source brightness, exposure, and gain conditions. The purpose of this image data is to assist in judging changes in the fabric. For example, the optimal image capture effect for fabric type A is a light source brightness of 120, a camera exposure of 80, and a gain of 1. The optimal image capture effect for the next roll of fabric type B corresponds to a light source brightness of 100, a camera exposure of 60, and a gain of 1. Therefore, when switching from fabric A to the next roll of fabric B, the image captured by the area scan camera will still be the image effect under the conditions of a light source brightness of 120, a camera exposure of 80, and a gain of 1. If the image effect of the next roll of fabric B under a light source brightness of 120, a camera exposure of 80, and a gain of 1 has been collected in advance, then during the actual detection process, when switching from the previous roll of fabric A to the next roll of fabric B, the parameters of the possible fabric type B can be quickly obtained through the image effect. The relevant parameters of the area scan camera can then be changed from 120, 80, 1 to 100, 60, 1, and then the data can be collected and compared. The goal is to identify the fabric type using the image quality from the area scan camera, and then provide the relevant parameters for the line scan camera based on that fabric type. Most importantly, even without prior data collection on a particular fabric type, the system can adjust the area scan camera's parameters and infer the line scan camera's parameters based on the image quality obtained from the area scan camera. The preset model needs to be analyzed and provided based on the specific fabric's imaging performance.

[0036] In some embodiments, determining the timing for adjusting the brightness parameters of the bar light source and the gain parameters of the line scan camera includes: The moment when the type of the fabric to be detected changes is taken as the initial moment, and the first displacement measured by the encoder from the initial moment is recorded. If the difference between the second distance and the first displacement between the area scan camera and the line scan camera reaches a preset threshold, the current moment is determined as the moment to adjust the brightness parameters of the bar light source and the gain parameters of the line scan camera.

[0037] It should be noted that the preset threshold is determined based on the actual application, and this embodiment does not impose specific restrictions. For example, it can be determined based on the actual acceptable hysteresis index, such as requiring a hysteresis of no more than 5 seconds. The preset threshold is calculated based on the hysteresis time and the speed of fabric movement. When the difference between the second distance and the first displacement between the area scan camera and the line scan camera reaches the preset threshold, it indicates that the boundary line between the two types of matching has reached the vicinity of the line scan camera's shooting range.

[0038] In some embodiments, if the fabric to be inspected requires backlighting, the bowl-shaped light source and the area scan camera are positioned on the same side of the fabric to be inspected.

[0039] First, determine the lighting method based on the fabric to be tested. For example, pure white woven fabric or white cotton fabric is tested using backlighting. (See also...) Figure 1 If the fabric to be inspected requires backlighting, the bowl-shaped light source and the area scan camera are set on the same side of the fabric to be inspected.

[0040] In some embodiments, if the fabric to be inspected requires front-facing illumination, a bowl-shaped light source and an area scan camera are positioned on both sides of the fabric to be inspected.

[0041] First, determine the lighting method based on the fabric to be inspected. For example, solid-color fabrics of various colors are inspected using backlighting. (See also...) Figure 2 If the fabric to be inspected requires front-facing lighting, the bowl-shaped light source and the area scan camera are set on both sides of the fabric to be inspected.

[0042] In some embodiments, the line scan camera and the strip light source are positioned on the same side of the fabric to be inspected, the line scan camera is positioned in the vertical direction of the fabric to be inspected, and the light emission direction of the strip light source and the light incident direction of the line scan camera are at a preset angle.

[0043] It should be noted that the preset angle between the light emission direction of the bar light source and the light incident direction of the line scan camera is determined according to the actual application, and this embodiment does not impose specific restrictions.

[0044] See Figure 1In one specific embodiment, the line scan camera always photographs the front of the fabric from above, perpendicularly downwards. The strip light source illuminating the line scan camera can be mounted at a 45° angle above the fabric, or it can be positioned below the fabric, perpendicular to the back of the fabric, illuminating the back of the fabric.

[0045] In some embodiments, the line scan camera and the strip light source are positioned on opposite sides of the fabric to be inspected. The line scan camera is positioned perpendicular to the fabric to be inspected, and the light emission direction of the strip light source is on the same straight line as the light incident direction of the line scan camera.

[0046] See Figure 2 In one specific embodiment, the line scan camera always photographs the front of the fabric from above, perpendicularly downwards. A strip light source illuminating the line scan camera is positioned below the fabric, perpendicular to the back of the fabric, and illuminates the back of the fabric.

[0047] In some embodiments, the system further includes a shield with a light-blocking material disposed inside, and an opening on one side of the shield and disposed on both sides of the fabric to be tested.

[0048] It should be noted that the shape of the protective cover and the light-shielding material are determined according to the actual application, and this embodiment does not impose specific limitations. The bowl-shaped light source, the area scan camera, the line scan camera, and the strip light source are all placed inside the protective cover, thereby reducing external light interference.

[0049] See Figure 3 In one specific embodiment, the bowl-shaped light source, area scan camera, line scan camera, and strip light source are covered by a cuboid-shaped shield 1-6. This is to mitigate the impact of variations in natural light on the image acquisition effect, ensuring consistent image acquisition results for the same type of fabric under different times and environments, and avoiding the influence of ambient light. The inner wall of the shield has a black frosted coating to prevent interference from light sources other than the light source. The shield consists of two parts, both cuboid in shape, with only one open side and a black interior. For example, the exterior uses an aluminum alloy cuboid frame, while the interior uses black fleece fabric for light absorption. There is a shield on both the front and back of the fabric, with the openings facing each other and aligned. The fabric to be detected by the system passes through the joint between these two shield openings, but the fabric does not touch the shield. In other words, in this embodiment, whether the lighting is from the front or the back, it appears as a cuboid shield from the outside.

[0050] The embodiments of this application include at least the following beneficial effects: This application provides a fabric inspection system, which includes a bowl-shaped light source, an area scan camera, an encoder, a line scan camera, a bar light source, and a controller; the bowl-shaped light source provides a first illumination light for the area scan camera, and the bar light source provides a second illumination light for the line scan camera. The fabric to be inspected passes through the shooting range of the area scan camera and the line scan camera in sequence; the area scan camera is used to capture a first image of the fabric to be inspected; the line scan camera is used to capture a second image of the fabric to be inspected; the controller is used to control the brightness parameters of the bar light source and the gain parameters of the line scan camera according to the first image, so that the line scan camera captures a second image that meets the preset requirements. In this embodiment, an area scan camera is added before the line scan camera, and the brightness parameters of the bar light source and the gain parameters of the line scan camera are controlled by the first image captured by the area scan camera, so that the control parameters are adjusted in time when the fabric to be inspected reaches the vicinity of the line scan camera, reducing detection lag. In addition, the control parameters are automatically determined according to the first image captured by the area scan camera, reducing the error of human subjective judgment and improving the accuracy of detection.

[0051] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0052] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0053] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0054] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0055] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0056] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0057] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. A fabric inspection system, characterized in that, The system includes a bowl-shaped light source, an area array camera, an encoder, a line scan camera, a bar light source, and a controller; wherein, the bowl-shaped light source provides a first illumination light for the area array camera, and the bar light source provides a second illumination light for the line scan camera, and the fabric to be inspected passes through the shooting range of the area array camera and the line scan camera in sequence; The encoder is used to measure the distance the fabric to be tested has moved. The area array camera is used to capture a first image of the fabric to be inspected; The line scan camera is used to capture a second image of the fabric to be inspected; The controller is used to control the brightness parameters of the bar light source and the gain parameters of the line scan camera according to the first image, so that the line scan camera can capture a second image that meets preset requirements.

2. The system according to claim 1, characterized in that, The controller is also used for: The type of the fabric to be detected is determined based on the brightness change of the first image. If the type of fabric to be tested changes, determine the time to adjust the brightness parameter of the bar light source and the gain parameter of the line scan camera.

3. The system according to claim 1, characterized in that, Determining whether the type of the fabric to be detected has changed based on the brightness change of the first image includes: If the brightness difference between two adjacent first images exceeds a preset range or the brightness difference between different areas of the same first image exceeds the preset range, the type of the fabric to be detected changes. Otherwise, the type of the fabric to be tested remains unchanged.

4. The system according to claim 1, characterized in that, The brightness parameters of the bar light source and the gain parameters of the line scan camera are determined by the following method: The first image is input into a pre-trained preset model to obtain the brightness parameters of the bar light source and the gain parameters of the line scan camera. The preset model is trained using the following method: The image samples of the area scan camera, the brightness parameter samples of the bar light source, and the gain parameter samples of the line scan camera are obtained. The brightness parameter samples and the gain parameter samples are determined by adjusting the bar light source and the line scan camera based on the image samples of the area scan camera. An initial model is trained based on image samples from the area scan camera, brightness parameter samples, and gain parameter samples until a preset requirement is met, thus obtaining the preset model.

5. The system according to claim 2, characterized in that, The determination of the timing for adjusting the brightness parameters of the bar light source and the gain parameters of the line scan camera includes: The moment when the type of the fabric to be detected changes is taken as the initial moment, and the first displacement measured by the encoder from the initial moment is recorded. If the difference between the second distance between the area scan camera and the line scan camera and the first displacement reaches a preset threshold, the current moment is determined as the moment to adjust the brightness parameter of the bar light source and the gain parameter of the line scan camera.

6. The system according to claim 1, characterized in that, If the fabric to be inspected requires backlighting for inspection, the bowl-shaped light source and the area scan camera are positioned on the same side of the fabric to be inspected.

7. The system according to claim 1, characterized in that, If the fabric to be inspected requires front-facing lighting for inspection, the bowl-shaped light source and the area scan camera are positioned on both sides of the fabric to be inspected.

8. The system according to claim 1, characterized in that, The line scan camera and the strip light source are positioned on the same side of the fabric to be inspected. The line scan camera is positioned in the vertical direction of the fabric to be inspected. The light emission direction of the strip light source and the light incident direction of the line scan camera are at a preset angle.

9. The system according to claim 1, characterized in that, The line scan camera and the strip light source are positioned on opposite sides of the fabric to be inspected. The line scan camera is positioned perpendicular to the fabric to be inspected, and the light emission direction of the strip light source is on the same straight line as the light incident direction of the line scan camera.

10. The system according to claim 1, characterized in that, The system also includes a protective cover, the inside of which is provided with a light-blocking material, and the cover has an opening on one side and is located on both sides of the fabric to be tested.

Images