Search

KR-102962915-B1 - Laser-based inclusion detection system and method

KR102962915B1KR 102962915 B1KR102962915 B1KR 102962915B1KR-102962915-B1

Abstract

An apparatus and method for detecting inclusions in glass are described. The apparatus and method employ a laser configured to project a laser sheet at a first angle from one side of a glass sheet, and a camera configured to capture an image at a second angle from the other side of the glass sheet. While the camera captures the image, the glass sheet is moved along the laser sheet. One or more processing devices execute an image processing algorithm to identify an area of the glass sheet containing inclusions based on the captured image. In some examples, the identified area of the glass sheet is revisited to determine whether it contains inclusions.

Inventors

  • 쇼드허리 소우마
  • 숨마 마크 앤서니
  • 양 승철
  • 장 자샹

Assignees

  • 코닝 인코포레이티드

Dates

Publication Date
20260511
Application Date
20201202
Priority Date
20191213

Claims (20)

  1. It is a device, and A laser configured to project a laser sheet onto a first surface of a glass sheet; A first camera configured to capture a plurality of images of a glass sheet from a second side of the glass sheet, wherein the first camera captures a plurality of images using dark-field illumination when the glass sheet is moved; and It includes at least one processor configured to determine a region of relatively higher light intensity in a captured image, and At least one processor, Identify the top line of higher light intensity in the first image among the captured images; In the first image, identify the bottom line of higher light intensity; In the first image, identify a first region of higher light intensity between the top line of higher light intensity and the bottom line of higher light intensity; and It is configured to determine inclusions in the first region based on the light intensity of the top line, bottom line and the first region, and At least one additional processor, Determine the first distance from the first area to the top line; For each of the first plurality of images of the captured first image, a first expected location of a first region in each image is determined based on a first distance; Determine the second distance from the first area to the bottom line; For each of the second plurality of images of the captured first image, a second expected location of the first region in each image is determined based on the second distance; Determining light intensity at each first predicted position and each second predicted position; Classify light intensity by running a machine learning algorithm; and A device configured to determine inclusions in a first region based on classified light intensity.
  2. The apparatus according to claim 1, further comprising a moving stage configured to move a glass sheet through a laser sheet.
  3. delete
  4. A device according to claim 1, wherein at least one processor is configured to identify inclusions within a glass sheet based on a region of relatively higher light intensity in a captured first image.
  5. delete
  6. In claim 1, determining the region of relatively higher light intensity in the captured first image is: Determine the first distance from the first area to the top line; A second region is determined in the second image based on a first distance, and the first region is overlaid on the top line of higher light intensity in the second image; and A device further comprising determining that the first light intensity of a first region of a first image is greater than the second light intensity of a second region of a second image.
  7. In claim 1, determining the region of relatively higher light intensity in the captured first image is: Determine the second distance from the first area to the bottom line; A third region is determined in the third image based on the second distance, and the first region is overlaid on the bottom line of the higher light intensity in the third image; and A device further comprising determining that the first light intensity of a first region of a first image is greater than the third light intensity of a third region of a third image.
  8. delete
  9. A device comprising a microscope imaging camera configured to view a glass sheet from a second side of the glass sheet, in accordance with claim 1.
  10. A device according to claim 1, comprising a second camera configured to capture a second image of a glass sheet from a first surface of the glass sheet, wherein the second camera captures the second image using brightfield illumination.
  11. A device according to claim 10, comprising a diffuse blue light-emitting diode configured to provide light to a first surface of a glass sheet, and a first camera comprising a blue light blocking filter.
  12. In paragraph 11, the device is a laser that is a red line laser.
  13. A device according to claim 11, wherein the first camera and the second camera are each configured to simultaneously capture the first image and the second image.
  14. A device according to claim 1, comprising a color confocal sensor configured to capture a second image of a reflection event of a glass sheet from a first surface of the glass sheet.
  15. It is a system, and A laser configured to project a laser sheet onto a first surface of a glass sheet; A camera configured to capture multiple images of a glass sheet from a second surface of the glass sheet, wherein the camera captures multiple images using dark-field illumination when the glass sheet is moved; A moving stage configured to move a glass sheet through a laser sheet; A backlight configured to project light onto a first surface of a glass sheet; A microscope configured to view the second side of a glass sheet; and It includes at least one processor configured to determine a region of relatively higher light intensity in a captured image, and At least one processor, Identify the top line of higher light intensity in the first image among the captured images; In the first image, identify the bottom line of higher light intensity; In the first image, identify a first region of higher light intensity between the top line of higher light intensity and the bottom line of higher light intensity; and It is configured to determine inclusions in the first region based on the light intensity of the top line, bottom line and the first region, and At least one additional processor, Determine the first distance from the first area to the top line; For each of the first plurality of images of the captured first image, a first expected location of a first region in each image is determined based on a first distance; Determine the second distance from the first area to the bottom line; For each of the second plurality of images of the captured first image, a second expected location of the first region in each image is determined based on the second distance; Determining light intensity at each first predicted position and each second predicted position; Classify light intensity by running a machine learning algorithm; and A system configured to determine inclusions in a first region based on classified light intensity.
  16. In paragraph 15, the system is configured such that the moving stage moves the glass sheet by a predetermined distance through the laser sheet.
  17. In Clause 16, the predetermined distance is less than or equal to the width of the laser sheet, in a system.
  18. delete
  19. delete
  20. delete

Description

Laser-based inclusion detection system and method Related applications This application claims the benefit of priority under 35 U.S.C. §119 of U.S. Provisional Application No. 62/947800 filed December 13, 2019, and relies on the contents of which are incorporated herein by reference. Initiation field The present disclosure relates to the detection of inclusions in glass, and more specifically to an apparatus and method for detecting inclusions in thin, textured glass. Glass sheets are used in a variety of applications. For example, glass sheets can be used in glass display panels such as mobile devices, laptops, tablets, computer monitors, and television displays. However, during production, glass sheets may contain defects such as inclusions or surface discontinuities. Some defects, when they appear on the glass surface, may be referred to as "bumps." These bumps may be convex features that protrude above the surface of the surrounding (e.g., polished) glass. In some instances, inclusions may appear within the glass sheet. Glass manufacturers inspect glass sheets in an attempt to detect these defects, for example, for quality control or classification purposes. Inclusions within the glass can cause functional (e.g., strength) defects or cosmetic (e.g., visual) defects. In some conventional examples, a human glass inspector attempts to detect inclusions in a glass sheet. In this embodiment, a highly well-trained inspector wearing a pair of magnifying glasses manually tips and tilts the glass against a black background while illuminating the glass sheet from the edges (e.g., using dark-field illumination). In a very time-consuming process, the inspector attempts to distinguish the scattering centers of the glass volume from the numerous scattering centers caused by the rough glass surface. For example, in the case of thin glass with a textured surface, light scattering due to the surface texture generates a high density of false positives. In some examples, the inclusions may be small (e.g., less than 10 µm in size), which makes detection much more difficult. Furthermore, performance among different inspectors can vary significantly due to training, experience, and visual acuity. Even for the same individual, inclusion detection may degrade over time when performing such high-intensity work. As such, there is an opportunity to improve the detection of defects in glass sheets. The above summary and the detailed description of exemplary embodiments below can be read together with the accompanying drawings. The drawings illustrate parts of the exemplary embodiments described herein. As further explained below, the claims are not limited to the exemplary embodiments. For clarity and readability, views of certain features may be omitted in the drawings. FIG. 1 schematically illustrates an exemplary glass inclusion detection device according to some examples. FIG. 2 is a block diagram of the detection of inclusions by an exemplary glass inclusion detection device according to some examples. FIG. 3 illustrates light scattering based on the position of inclusions as inclusions pass through a laser sheet, as detected by the glass inclusion detection device of FIG. 2. Figure 4 illustrates an image showing the light scattering intensity corresponding to the light scattering induced by the inclusions of Figure 3. Figure 5 illustrates a comparison of light intensity graphs when inclusions are present and when a surface texture is present on the glass. FIG. 6 is a block diagram of an exemplary glass inclusion detection device having a water bath system that reduces surface scattering according to some examples. FIGS. 7a, FIGS. 7b and FIGS. 7c are block diagrams of an exemplary glass inclusion detection device employing a laser dark-field system to further evaluate a suspected area detected in the first pass by a macro camera according to some examples. Figure 8 illustrates an image of inclusions detected by the laser dark-field system of Figure 7 according to some examples. FIG. 9 is a block diagram of an exemplary glass inclusion detection system that employs a dark-field camera and shows the light intensity profile when an inclusion crosses through a laser sheet according to some examples. FIG. 10a illustrates an image of a glass inclusion captured by the exemplary glass inclusion detection device of FIG. 9 according to some examples. FIG. 10b illustrates an image of a surface defect on glass captured by the exemplary glass inclusion detection device of FIG. 9 according to some examples. FIG. 11 is a block diagram of an exemplary glass inclusion detection device employing a dark-field camera according to some examples. FIG. 12a illustrates a dynamic tracking image captured by the exemplary glass inclusion detection device of FIG. 11 according to some examples. FIG. 12b illustrates a static trace image captured by the exemplary glass inclusion detection device of FIG. 11 according to some examples. FIG. 13 is a block dia