Glass sheet scratch defect detection system and detection method

Abstract

The invention relates to the technical field of defect detection, and discloses a glass sheet scratch defect detection system and a detection method.The glass sheet scratch defect detection system is characterized in that fluorescent powder is added into printing ink of a glass sheet to form a printing ink composition, then the edge of the glass sheet is irradiated by a UV light source, and the printing ink composition containing the fluorescent powder generates fluorescence; the image collector is used for collecting a fluorescence image, and the processor is used for identifying and analyzing the fluorescence image, so that the accuracy of detecting the edge scratch defect of the glass sheet can be effectively improved. Compared with manual visual inspection, the method is not limited by experience, small scratches and missing inspection are avoided, the detection efficiency is high, and the large-scale production requirement is met. Compared with optical microscope detection, contact sampling is not needed, secondary damage is avoided, comprehensive detection can be achieved, and quality is ensured. Compared with conventional machine vision detection, the fluorescence image contrast is high, the misjudgment rate is low, reliable data is provided, the product quality is improved, and the strict requirement of modern electronic products for the glass sheet quality is met.

Description

Technical Field

[0001] This invention relates to the field of defect detection technology, and in particular to a glass slide scratch defect detection system and method. Background Technology

[0002] Due to its high strength, hardness, and wear resistance, glass is now widely used in everyday consumer goods, primarily in the form of glass sheets, and has become an indispensable part of electronic products such as smartphones, tablets, and AR glasses. When used in electronic products such as glass covers and eyeglass lenses, it typically requires an ink-coated area around the edges to prevent light leakage and increase the structural strength of the edges.

[0003] However, currently, there are three traditional methods for detecting edge scratches on such glass sheets:

[0004] (1) Manual visual inspection. This method relies heavily on the personal experience and subjective judgment of the inspectors. Due to the limitations of human visual perception, it is easy to miss tiny scratches at the micrometer level. Moreover, manual visual inspection requires a lot of manpower and time, and the overall inspection efficiency is relatively low, making it difficult to meet the needs of large-scale production inspection.

[0005] (2) Optical Microscope Inspection Method. Optical microscope inspection usually requires contact sampling of the glass slide. During the sampling process, interaction forces may be generated between the glass slide and the contact parts of the microscope, which may cause secondary damage to the glass slide. In addition, optical microscope inspection cannot comprehensively inspect all glass slides and can only use sampling inspection. This may result in some defective glass slides not being detected in time, thus affecting product quality.

[0006] (3) Machine vision inspection method. Under conventional light source conditions, the contrast between the ink area on the edge of the glass sheet and the scratch defect is low, which makes it difficult for the machine vision system to accurately identify the scratch defect, resulting in a high false positive rate. Because the accuracy of machine vision inspection is affected, it cannot provide reliable inspection data for the production process, thus limiting its widespread application in the detection of scratch defects on the edge of glass sheets.

[0007] In conclusion, given the numerous limitations of existing technologies, it is imperative to improve and optimize existing testing technologies to meet the stringent quality requirements of modern electronic product manufacturing for glass sheets, thereby enhancing the accuracy, efficiency, and reliability of testing.

[0008] The above information is provided as background information only to aid in understanding this disclosure and does not constitute an assertion or admission that any of the above content can be used as prior art relative to this disclosure. Summary of the Invention

[0009] This invention provides a glass slide scratch defect detection system and method to solve the problems of low detection accuracy, low efficiency, and easy secondary damage in the prior art.

[0010] To achieve the above objectives, the present invention provides the following technical solution:

[0011] In a first aspect, the present invention provides a glass slide scratch defect detection system, comprising a glass slide and a scratch defect detection device; wherein...

[0012] The glass sheet comprises a glass body and an ink composition; the ink composition is disposed at the edge of the glass body;

[0013] The ink composition includes ink and fluorescent powder;

[0014] The scratch defect detection device includes a UV light source, an image acquisition unit, and a processor;

[0015] The UV light source is used to irradiate UV light onto the edge of the glass sheet;

[0016] The image acquisition device is used to acquire fluorescence images of the edge of the glass slide;

[0017] The processor identifies whether there are scratches or defects on the edge of the glass body based on the fluorescence image.

[0018] Furthermore, in the glass slide scratch defect detection system, the phosphor is an inert phosphor.

[0019] Furthermore, in the glass slide scratch defect detection system, the phosphor is a rare earth-doped aluminate phosphor.

[0020] Furthermore, in the glass slide scratch defect detection system, the excitation wavelength of the phosphor is 365nm or 395nm;

[0021] The phosphor emits light at wavelengths of 420-550 nm.

[0022] Furthermore, in the glass slide scratch defect detection system, the wavelength of the UV light source is 365±5nm, and the power density is ≤10mW / cm².

[0023] Furthermore, in the glass slide scratch defect detection system, the scratch defect detection device also includes a filter;

[0024] The filter is located between the image acquisition unit and the glass plate.

[0025] Furthermore, in the glass slide scratch defect detection system, the cutoff wavelength of the filter is <430nm.

[0026] In a second aspect, the present invention provides a method for detecting scratch defects in glass slides, which is performed using the glass slide scratch defect detection system provided in the first aspect above, the method comprising:

[0027] The UV light source irradiates UV light onto the edge of the glass sheet;

[0028] The image acquisition device acquires fluorescence images of the edges of the glass slide;

[0029] The processor identifies whether there are scratches or defects on the edge of the glass body based on the fluorescence image.

[0030] Furthermore, in the glass scratch defect detection method, the step of the processor identifying whether there is a scratch defect on the edge of the glass body based on the fluorescence image includes:

[0031] The processor preprocesses the fluorescence image;

[0032] The processor identifies whether there are continuous non-fluorescent areas in the fluorescence image; if so, it determines that there are scratches on the edge of the glass body; if not, it determines that there are no scratches on the edge of the glass body.

[0033] Furthermore, in the method for detecting scratches on a glass slide, the method further includes:

[0034] The processor determines the severity of the scratch defect based on its characteristic parameters.

[0035] Compared with the prior art, the present invention has the following beneficial effects:

[0036] This invention provides a glass slide scratch defect detection system and method. By adding phosphor to the ink on the glass slide to form an ink composition, and then irradiating the edge of the glass slide with a UV light source, the phosphor-containing ink composition fluoresces. An image acquisition device captures the fluorescence image, which is then analyzed by a processor. This effectively improves the accuracy of detecting glass slide edge scratch defects. Compared with manual visual inspection, it is not limited by the experience and subjective judgment of the inspectors, avoiding missed detections of minor scratches, and significantly improving detection efficiency to meet the needs of large-scale production. Compared with optical microscopy, it eliminates the need for contact sampling, avoiding secondary damage to the glass slide, and enables comprehensive inspection, ensuring the reliable quality of all glass slides. Compared with conventional machine vision inspection, the fluorescence image significantly improves the contrast between scratch defects and ink, reducing the false positive rate and providing more reliable inspection data for the production process, thus helping to improve product quality and meet the stringent quality requirements of modern electronic product manufacturing for glass slides.

[0037] The present invention has other features and advantages, which will be apparent from or will be set forth in detail in the accompanying drawings and the following detailed description, which together serve to explain the particular principles of the invention. Attached Figure Description

[0038] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0039] Figure 1 This is a schematic diagram of the structure of a glass slide scratch defect detection system provided in Embodiment 1 of the present invention;

[0040] Figure 2 This is a schematic diagram of the structure of the glass sheet provided in Embodiment 1 of the present invention;

[0041] Figure 3 This is a schematic diagram of the structure of the ink composition provided in Embodiment 1 of the present invention;

[0042] Figure 4 This is one of the flowcharts of a glass slide scratch defect detection method provided in Embodiment 2 of the present invention;

[0043] Figure 5 This is the second flowchart of a glass slide scratch defect detection method provided in Embodiment 2 of the present invention.

[0044] Figure label:

[0045] Glass slide 1, scratch defect detection device 2;

[0046] Glass body 11, ink composition 12;

[0047] Ink 121, fluorescent powder 122;

[0048] UV light source 21, image acquisition unit 22, processor 23, filter 24. Detailed Implementation

[0049] To illustrate the possible application scenarios, technical principles, implementable specific solutions, and achievable objectives and effects of this application in detail, the following description, in conjunction with the listed specific embodiments and accompanying drawings, provides a detailed explanation. The embodiments described herein are merely illustrative of the technical solutions of this application and are therefore intended to limit the scope of protection of this application.

[0050] In this document, the term "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The term "embodiment" appearing in various places throughout the specification does not necessarily refer to the same embodiment, nor does it specifically limit its independence or connection with other embodiments. In principle, in this application, as long as there are no technical contradictions or conflicts, the technical features mentioned in each embodiment can be combined in any way to form corresponding implementable technical solutions.

[0051] Unless otherwise defined, the technical terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application pertains; the use of related terms herein is merely for the purpose of describing particular embodiments and is not intended to limit this application.

[0052] In the description of this application, the term "and / or" is used to describe the logical relationship between objects, indicating that three relationships can exist. For example, A and / or B means: A exists, B exists, and A and B exist simultaneously. Additionally, the character " / " in this document generally indicates that the preceding and following objects have an "or" logical relationship.

[0053] In this application, terms such as “first” and “second” are used only to distinguish one entity or operation from another, and do not necessarily require or imply any actual quantity, hierarchy or order relationship between these entities or operations.

[0054] Unless otherwise specified, the use of terms such as “comprising,” “including,” “having,” or other similar expressions in this application is intended to cover non-exclusive inclusion, which does not exclude the presence of additional elements in a process, method, or product that includes the stated elements, such that a process, method, or product that includes a list of elements may include not only those defined elements but also other elements not expressly listed, or elements inherent to such a process, method, or product.

[0055] In this application, expressions such as "greater than", "less than", and "exceeding" are understood to exclude the stated number; expressions such as "above", "below", and "within" are understood to include the stated number. Furthermore, in the description of the embodiments of this application, "multiple" means two or more (including two), and similar expressions related to "multiple" are also understood in this way, such as "multiple groups" and "multiple times", unless otherwise explicitly specified.

[0056] In the description of the embodiments of this application, the space-related expressions used, such as "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "vertical," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," and "circumferential," indicate the orientation or positional relationship based on the orientation or positional relationship shown in the specific embodiments or drawings. They are only for the purpose of describing the specific embodiments of this application or for the reader's understanding, and do not indicate or imply that the device or component referred to must have a specific position, a specific orientation, or be constructed or operated in a specific orientation. Therefore, they should not be construed as limitations on the embodiments of this application.

[0057] Unless otherwise expressly specified or limited, the terms "installation," "connection," "linking," "fixing," and "setting," as used in the description of the embodiments of this application, should be interpreted broadly. For example, "connection" can be a fixed connection, a detachable connection, or an integral setting; it can be a mechanical connection, an electrical connection, or a communication connection; it can be a direct connection or an indirect connection through an intermediate medium; it can be the internal connection of two components or the interaction between two components. For those skilled in the art to which this application pertains, the specific meaning of the above terms in the embodiments of this application can be understood according to the specific circumstances.

[0058] Example 1

[0059] Please refer to Figure 1-3 This invention provides a glass slide scratch defect detection system, including a glass slide 1 and a scratch defect detection device 2;

[0060] The glass slide 1 is further divided into two components: the glass body 11 and the ink composition 12. The ink composition 12 is disposed around the perimeter of the glass body 11, a design that plays a crucial role in subsequent detection. Specifically, the ink composition 12 is not ordinary ink, but a mixture of ink 121 and phosphor 122 in a specific ratio (depending on the specific situation). Ink 121 is a conventional printing material with adhesion and a certain degree of light-blocking properties, while the addition of phosphor 122 brings unique fluorescent characteristics to the entire detection system, which is one of the key factors for achieving efficient and accurate detection.

[0061] The scratch defect detection device 2 is a precision device integrating multiple functions, comprising three important modules: a UV light source 21, an image acquisition unit 22, and a processor 23. The UV light source 21, as the excitation source, primarily functions to irradiate the edge area of ​​the glass slide 1 with UV light (dwell time 0.5-2s). This specific wavelength of UV light excites the phosphor 122 in the ink composition 12, causing it to fluoresce, thus providing a clear fluorescent signal for subsequent image acquisition.

[0062] Image acquisition unit 22 is responsible for capturing the fluorescence image generated by the edge of glass slide 1 under UV light illumination. It possesses high resolution and fast acquisition capabilities, recording every detail of the edge of glass slide 1, including any possible scratches and defects, as well as the distribution of the ink composition 12. By digitizing the acquired fluorescence image, image acquisition unit 22 provides an accurate data foundation for subsequent identification and analysis.

[0063] The processor 23 plays a crucial role in the in-depth analysis and processing of fluorescence images. It employs specific image recognition algorithms to meticulously analyze the acquired fluorescence images, accurately identifying whether scratches or defects exist on the edges of the glass body 11. Once a scratch defect is detected, the processor 23 can also measure and record its location, providing a strong basis for subsequent quality assessment and production decisions.

[0064] The unique feature of this invention lies in the ingenious addition of phosphor 122 to the ink 121 of the glass slide 1, forming an ink composition 12 with special fluorescent properties. During the detection process, the edge of the glass slide 1 is irradiated using a UV light source 21, causing the ink composition 12 containing phosphor 122 to produce a fluorescent effect. Subsequently, the fluorescent image is acquired using an image acquisition device 22, and intelligently identified and analyzed by a processor 23. This innovative detection method can significantly improve the accuracy of detecting scratch defects on the edge of the glass slide 1, and has many advantages.

[0065] Compared with traditional inspection methods, this invention has significant advantages. Specifically, compared with manual visual inspection, this invention is not affected by the experience level and subjective judgment of the inspector. Manual visual inspection often relies on the inspector's personal experience and attention, and is prone to missing minor scratches due to fatigue or negligence. In contrast, the inspection system of this invention, based on objective fluorescence images and advanced algorithm analysis, can accurately detect minute scratch defects with a false negative rate of <0.01%, greatly improving the accuracy and reliability of inspection. At the same time, the system's inspection efficiency is also significantly improved (increasing the inspection speed to 0.8 seconds / piece, 20 times more efficient than manual inspection), meeting the needs of large-scale production, effectively shortening the production cycle, and reducing production costs.

[0066] Compared to optical microscopy, this invention eliminates the need for direct contact sampling of the glass slide 1. Optical microscopy typically requires placing the glass slide under a microscope for observation, a process that can cause secondary damage to the slide and affect product quality. The detection system of this invention employs a non-contact detection method, using UV light to excite fluorescence for detection, thus avoiding direct contact with the glass slide and effectively protecting its integrity. Furthermore, this detection system enables comprehensive inspection, meticulously examining each glass slide to ensure reliable quality and provide strong assurance for stable product quality.

[0067] Compared to conventional machine vision inspection, this invention significantly improves the contrast between scratch defects and ink 121 through fluorescence imaging. In conventional machine vision inspection, the low contrast between ink and scratch defects at the edge of the glass sheet under conventional light sources easily leads to misjudgment. However, the detection system of this invention utilizes the fluorescence effect, making scratch defects appear distinct in the fluorescence image, creating a clear contrast with the ink, thereby reducing the misjudgment rate. This provides more reliable inspection data for the production process, helping production personnel to promptly identify and resolve quality problems, improve the overall quality of products, and meet the stringent quality requirements of modern electronic product manufacturing for glass sheets 1.

[0068] In a specific and optimized embodiment of this example, there are strict requirements for the selection of the phosphor 122 used. Specifically, an inert phosphor 122 is selected, a choice made after comprehensive consideration from multiple aspects. In the production and subsequent processing of the glass sheet, the performance stability of the ink 121 is crucial, directly affecting the quality of the glass sheet and the subsequent processing effect. If a non-inert phosphor is used, it may chemically react with the components in the ink 121, leading to modification of the ink 121. Once the ink 121 is modified, its dyne value will significantly decrease. The dyne value is an important indicator for measuring the surface energy of a material. In the subsequent bonding process of the glass sheet, the dyne value directly affects the bonding strength and quality. If the dyne value decreases, the adhesion between the ink 121 surface and the bonding material will weaken, thus affecting the smooth progress of the entire bonding process, potentially leading to poor bonding, air bubbles, and other quality problems, seriously affecting the performance and reliability of the product. Therefore, using inert phosphor 122 can effectively avoid the above problems, ensure the stability of ink 121's performance, and guarantee the high-quality completion of subsequent bonding processes.

[0069] To illustrate the selection of phosphor 122 more specifically, it can be, for example, a rare-earth-doped aluminate phosphor. This phosphor possesses numerous superior properties, making it particularly suitable for use in the glass slide scratch defect detection system of this embodiment. From a microstructural perspective, the surface of the rare-earth-doped aluminate phosphor particles has organic long chains compatible with the ink resin. This special structural design offers significant advantages, as the presence of organic long chains can significantly reduce the surface energy of the particles. In materials science, surface energy is one of the important factors affecting the interaction between materials and other substances. When the surface energy of the phosphor particles is reduced, the interfacial energy between them and the ink substrate can achieve a perfect match. This perfect match allows phosphor 122 to be uniformly dispersed in ink 121 without aggregation or precipitation, thereby ensuring the uniformity and stability of the ink composition 12. Meanwhile, good interface matching also helps to improve the bonding force between phosphor 122 and ink 121, so that phosphor 122 can exist stably in ink 121 for a long time and will not fall off or fail during use, thereby ensuring the reliability and stability of the entire glass slide scratch defect detection system.

[0070] In a specific and refined implementation of this embodiment, the key parameters of phosphor 122 and UV light source 21 have been rigorously and scientifically set to ensure that the entire glass slide scratch defect detection system can operate efficiently, stably and accurately.

[0071] Specifically, the excitation wavelength of the phosphor 122 is precisely set to 365nm or 395nm. These two wavelength ranges are commonly used in the field of industrial UV LEDs, with a broad application base and mature technical support. Choosing these two wavelengths as the excitation wavelengths of the phosphor 122 allows for full utilization of the stability and efficiency of industrial UV LED light sources, ensuring sufficient and stable excitation energy for the phosphor 122 during the detection process. Furthermore, these two wavelength light sources are readily available on the market, helping to reduce the overall cost of the system and improve its practicality and scalability.

[0072] Meanwhile, the emission wavelength of the phosphor 122 is set within the range of 420-550 nm. This specific emission wavelength range was carefully selected and experimentally verified to achieve high contrast with the ink background color. During the detection of scratches on the glass slide, the high-contrast fluorescent image makes the scratches more clearly visible, facilitating accurate capture and recording by the image acquisition unit 22, thereby providing a more reliable data foundation for the processor 23's identification and analysis. This high-contrast design effectively improves the detection system's ability to identify minute scratches, reduces the false negative rate and misjudgment rate, and thus enhances the accuracy and reliability of the entire detection system.

[0073] Furthermore, the parameters of the UV light source 21 are strictly limited. Its wavelength is controlled within the range of 365±5nm. This setting matches the excitation wavelength of the phosphor 122, ensuring that the light emitted by the UV light source 21 can maximally excite the phosphor 122, causing it to emit bright fluorescence. Simultaneously, controlling the wavelength accuracy within ±5nm helps ensure the stability and consistency of the excitation process, avoiding fluorescence intensity changes caused by wavelength fluctuations, thereby improving the repeatability and reliability of the detection results.

[0074] Regarding power density, the UV light source 21 is set to ≤10mW / cm². This parameter is set for material protection. During the testing process, materials such as the glass slide 1 and the ink composition 12 are exposed to the UV light source 21 for an extended period. If the power density is too high, these materials may experience aging, discoloration, or other adverse reactions, affecting the quality of the glass slide and its subsequent performance. By controlling the power density within the range of ≤10mW / cm², material aging can be effectively avoided, ensuring that the glass slide 1 and the ink composition 12 maintain stable performance and appearance during the testing process. This also helps extend the service life of the testing equipment and reduce maintenance costs.

[0075] In a specific and optimized embodiment of this example, the scratch defect detection device 2 further adds a key component, a filter 24, to the original structure, thereby improving the performance and detection accuracy of the entire detection system.

[0076] From the perspective of component positioning, the filter 24 is precisely positioned between the image acquisition unit 22 and the glass plate 1. This layout design is not arbitrary but rather the result of rigorous optical principle analysis and extensive experimental verification. During the detection process, the ink composition 12 on the edge of the glass plate 1 fluoresces under the excitation of the UV light source 21, while the UV light source 21 itself also emits excitation light of a certain intensity. If this excitation light directly enters the image acquisition unit 22, it will interfere with the fluorescence signal, causing noise and blurring in the acquired fluorescence image, severely affecting the subsequent processor 23's identification and analysis of scratch defects. The filter 24, located between the image acquisition unit 22 and the glass plate 1, can effectively filter and screen the light entering the image acquisition unit 22, thereby solving the critical problem of excitation light interference.

[0077] Regarding the performance parameters of filter 24, its cutoff wavelength is precisely set to <430nm. This parameter setting is based on in-depth research into the fluorescence emission spectrum and excitation spectrum. As mentioned above, the emission wavelength range of phosphor 122 is 420-550nm, while the excitation wavelength is mainly concentrated around 365nm or 395nm. By setting the cutoff wavelength of filter 24 to <430nm, light with wavelengths of 430nm and below, especially excitation light, can be effectively blocked, preventing it from passing through filter 24 and entering image acquisition unit 22. Fluorescence signals with wavelengths greater than 430nm can pass smoothly through filter 22 and be accurately acquired by image acquisition unit 22. In this way, filter 24 acts like a precise "optical sieve," removing interference from excitation light and retaining only useful fluorescence signals, thereby significantly improving the clarity and signal-to-noise ratio of the fluorescence image.

[0078] In practical applications, this scratch defect detection device 2 with filter 24 exhibits superior performance. It can more accurately capture the fluorescence information at the edge of the glass slide 1, enabling the processor 23 to more clearly identify minute scratch defects, significantly reducing the missed detection rate and false positive rate. Compared to detection devices without filter 24, the detection device in this embodiment represents a qualitative improvement in detection accuracy and reliability, better meeting the stringent quality inspection requirements of modern electronic product manufacturing for glass slides 1, and providing strong technical support for improving product quality and production efficiency.

[0079] Although this application frequently uses terms such as glass slide and phosphor, the possibility of using other terms is not excluded. These terms are used merely for the convenience of describing and explaining the essence of the invention; interpreting them as any additional limitation would contradict the spirit of the invention.

[0080] Example 2

[0081] Please refer to Figure 4 This is a flowchart illustrating a method for detecting scratches on a glass slide according to Embodiment 1 of the present invention. The method is executed as described in the glass slide scratch detection system provided in Embodiment 1 above. The method specifically includes the following steps:

[0082] S101, The UV light source irradiates UV light onto the edge of the glass sheet.

[0083] It should be noted that this step is the starting point and key step in the entire glass slide scratch defect detection method. Its core purpose is to create conditions for the subsequent fluorescence reaction, so as to present the scratch defects that may exist on the edge of the glass slide in a visual fluorescence form.

[0084] In the glass slide scratch defect detection system of the present invention, the edge of the glass slide is coated with a specific ink composition, which includes phosphor. When UV light of a specific wavelength shines on the phosphor, the phosphor absorbs the energy of the UV light and undergoes an energy level transition. Subsequently, it releases energy and emits fluorescence in the process of returning to the ground state.

[0085] The UV light source needs to emit UV light of appropriate wavelength and intensity. As mentioned above, the wavelength of the UV light source is usually set within a range that matches the excitation wavelength of the phosphor, such as 365±5nm, to ensure efficient excitation of the phosphor. Simultaneously, the power density also needs to be controlled within a reasonable range, generally ≤10mW / cm², to avoid aging of the glass slide or ink composition due to excessive power, which would affect the accuracy of the detection results. Furthermore, it is essential to ensure that the UV light accurately illuminates the edge area of ​​the glass slide, ensuring that the entire edge is fully excited without any blind spots.

[0086] S102, The image acquisition device acquires a fluorescence image of the edge of the glass slide.

[0087] It should be noted that this step aims to capture and record the fluorescence information at the edge of the glass slide after UV excitation, converting it into visualized image data for subsequent analysis and processing. The fluorescence image contains the fluorescence distribution at the edge of the glass slide, and scratches can affect this distribution; therefore, the acquired fluorescence image is crucial for identifying scratches.

[0088] Image acquisition devices (such as cameras) can sense and convert light. When the edge of a glass slide emits fluorescence, the photosensitive element of the image acquisition device receives these fluorescence signals and converts them into electrical signals. By digitizing these electrical signals, a digital image reflecting the fluorescence distribution at the edge of the glass slide can be generated.

[0089] The image acquisition device needs appropriate parameter settings to ensure good quality of the acquired fluorescence images. For example, a suitable exposure time must be selected to avoid overexposure or underexposure, which would result in images that are too bright or too dark, affecting the capture of fluorescence details. Simultaneously, the image acquisition device's resolution needs to be high enough to clearly distinguish minute fluorescence changes at the glass slide edge, enabling accurate detection of potential scratches or defects. Furthermore, the position and angle of the image acquisition device also need precise adjustment to ensure complete and clear acquisition of the fluorescence image at the glass slide edge, reducing image distortion and blurring.

[0090] S103. The processor identifies whether there are scratches or defects on the edge of the glass body based on the fluorescence image.

[0091] It should be noted that this is the ultimate goal of the entire detection method: by analyzing and processing the acquired fluorescence images, it is possible to determine whether there are scratches or defects on the edges of the glass slides, providing a basis for subsequent quality control and production decisions. If scratches or defects are detected, the glass slides can be screened or processed in a timely manner, preventing unqualified products from flowing into the next process and improving product quality and production efficiency.

[0092] Because scratches alter the environment surrounding the phosphor in the ink composition at the edge of the glass slide, they affect fluorescence emission characteristics such as fluorescence intensity and distribution. By analyzing these features of the fluorescence image, the processor can establish a correspondence between the scratch and the observed scratch, thus identifying the presence of scratches. For example, a scratch may cause a significant difference in fluorescence intensity compared to normal areas due to altered phosphor distribution. The processor can detect this difference by setting appropriate thresholds or algorithms, thereby determining the presence of a scratch.

[0093] The processor needs to employ suitable image processing algorithms and defect recognition models. Common image processing algorithms include image enhancement, filtering, and segmentation. These algorithms can preprocess fluorescence images, improving image quality and highlighting fluorescence features to facilitate subsequent defect recognition. The defect recognition model can be selected based on actual needs, such as rule-based models or machine learning models. Rule-based models can determine the presence of defects based on pre-set fluorescence feature thresholds, while machine learning models can be trained on large amounts of sample data to automatically learn the complex relationship between fluorescence images and scratch defects, improving the accuracy and robustness of defect recognition. Simultaneously, the processor also needs sufficient computing power and storage capacity to quickly process large amounts of fluorescence image data and provide timely detection results.

[0094] In one embodiment of this example, step S103 can be further refined to include the following steps:

[0095] The processor preprocesses the fluorescence image.

[0096] The processor identifies whether there are continuous non-fluorescent areas in the fluorescence image; if so, it determines that there are scratches on the edge of the glass body; if not, it determines that there are no scratches on the edge of the glass body.

[0097] It should be noted that during the acquisition process, fluorescence images may suffer from noise, blurring, and insufficient contrast due to various factors such as the performance of the image acquisition device, ambient light, and reflections from the glass slide surface. Preprocessing aims to eliminate these adverse factors, improve image quality, highlight key features in the fluorescence image, and lay the foundation for accurate identification of scratches and defects.

[0098] In the specific detection principle of this invention, the ink composition on the edge of the glass slide emits fluorescence under UV light excitation. However, when there are scratches on the edge of the glass slide, the scratches disrupt the integrity of the ink composition, resulting in the absence of phosphor in that area and thus preventing fluorescence, forming a non-fluorescent region. Therefore, identifying whether there is a continuous non-fluorescent region in the fluorescence image is a key step in determining whether there are scratches on the edge of the glass slide.

[0099] Please refer to Figure 5 In one embodiment of this example, in Figure 4 Based on this, the method further includes:

[0100] S104. The processor determines the severity of the scratch defect based on the characteristic parameters of the scratch defect.

[0101] It's important to note that simply identifying scratches on the glass surface is insufficient for the glass scratch defect detection process. Scratches of varying severity have different impacts on the quality and performance of the glass. For example, minor scratches may have little impact on the appearance and basic functions of the glass, and may be acceptable in applications where quality requirements are not extremely high; however, severe scratches can lead to reduced structural strength, impaired optical performance, or even render the glass unusable. Therefore, introducing step S104, which allows the processor to determine the severity of the scratch defect based on its characteristic parameters, provides a more accurate and detailed basis for subsequent quality assessments, product grading, and production decisions, thus helping to improve product quality control and production efficiency.

[0102] The severity of scratch defects is closely related to their characteristic parameters. Generally, the larger the length, width, and depth of the scratch, the more severe the damage to the glass slide, and the higher its severity. For example, a longer scratch means a wider area of ​​damage to the edge of the glass slide, which may affect the overall structural stability of the slide; a wider scratch may destroy more phosphor, leading to an increase in the area of ​​non-fluorescent regions in the fluorescence image, thus more significantly affecting the appearance quality of the glass slide; while a deeper scratch may directly penetrate the surface coating of the glass slide, having a greater impact on the optical and mechanical properties of the slide. By quantitatively analyzing these characteristic parameters, a correspondence between them and the severity of scratch defects can be established, thereby enabling accurate classification of the severity of scratch defects.

[0103] Specifically, the processor compares the extracted scratch defect feature parameters with pre-set classification criteria. If the length and width of the scratch defect are within the threshold range of minor scratches, the scratch defect is determined to be a minor scratch; if the length and width meet the threshold range of moderate scratches, it is determined to be a moderate scratch; if the length and width exceed the threshold of severe scratches, it is determined to be a severe scratch.

[0104] Finally, it should be noted that although the above embodiments have been described in the text and drawings of this application, this should not limit the scope of patent protection of this application. Any technical solutions that are based on the essential concept of this application and utilize the content described in the text and drawings of this application, resulting in equivalent structural or procedural substitutions or modifications, as well as the direct or indirect application of the technical solutions of the above embodiments to other related technical fields, are all included within the scope of patent protection of this application.

Claims

1. A glass sheet flaw detection system, comprising: The glass sheet (1) and a scratch defect detection device (2) are included. The glass sheet (1) includes a glass body (11) and an ink composition (12); the ink composition (12) is arranged on the edge of the glass body (11). The ink composition (12) includes ink (121) and fluorescent powder (122). The scratch defect detection device (2) includes a UV light source (21), an image collector (22), and a processor (23). The UV light source (21) is used to irradiate UV light on the edge of the glass sheet (1). The image collector (22) is used to collect the fluorescent image of the edge of the glass sheet (1). The processor (23) identifies whether there is a scratch defect on the edge of the glass body (11) according to the fluorescent image.

2. The glass sheet edge damage detection system of claim 1, wherein, The fluorescent powder (122) is inert fluorescent powder.

3. The glass sheet edge damage detection system of claim 2, wherein, The fluorescent powder (122) is rare earth doped aluminate type fluorescent powder.

4. The glass sheet edge damage detection system of claim 1, wherein, The excitation wavelength of the fluorescent powder (122) is 365 nm or 395 nm. The emission wavelength of the fluorescent powder (122) is 420-550 nm.

5. The glass sheet edge damage detection system of claim 1, wherein, The wavelength of the UV light source (21) is 365±5 nm, and the power density is ≤10 mW / cm².

6. The glass sheet edge damage detection system of claim 1, wherein, The scratch defect detection device (2) further includes a filter (24). The filter (24) is located between the image collector (22) and the glass sheet (1).

7. The glass sheet edge damage detection system of claim 6, wherein, The cutoff wavelength of the filter (24) is <430 nm.

8. A method of glass sheet flaw detection, performed using the glass sheet flaw detection system of any one of claims 1-7, wherein, The method includes: The UV light source irradiates UV light on the edge of the glass sheet. The image collector collects the fluorescent image of the edge of the glass sheet. The processor identifies whether there is a scratch defect on the edge of the glass body according to the fluorescent image.

9. The glass sheet edge damage detection method of claim 8, wherein, The processor identifies whether there is a scratch defect on the edge of the glass body according to the fluorescent image. The processor pre-processes the fluorescent image. The processor identifies whether there is a continuous non-fluorescent area in the fluorescent image; if yes, it is determined that there is a scratch defect on the edge of the glass body; if not, it is determined that there is no scratch defect on the edge of the glass body.

10. The glass sheet edge damage detection method of claim 8, wherein, The method further includes: The processor determines the severity of the scratch defect according to the characteristic parameters of the scratch defect.

Images