# US 12,007,337 B2 · System and method for detecting glass-ceramic material > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 12,007,337 B2 - Document ID: US12007337B2 - Status: Granted - Kind: B2 - Application number: 17/601,853 - Filed: 2020-04-09 - Published: 2022-06-16 - Granted: 2024-06-11 - Earliest claimed: 2019-04-19 - Assignees: Saint-Gobain Isover - Applicants: Saint-Gobain Isover; Verallia Packaging - Inventors: Hugues Chenneviere; Ezzeddine Ouerghemmi - Web page: https://patentgrep.com/patent/US12007337B2 ## CPC - G01N 21/958: Inspecting transparent materials {or objects, e.g. windscreens (for conveyed flat sheet or rod G01N21/896)} - B07C 5/3422: {using video scanning devices, e.g. TV-cameras} - G01N 21/8806: {Specially adapted optical and illumination features} - G01N 21/8851: {Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges (G01N21/8806 and G01N21/93 - G01N21/95692 take precedence; optical measurement of dimensions G01B11/00; optical scanning G02B26/10; image transformation G06T3/00; computerised image enhancement G06T5/00; image processing per se for flaw detection G06T7/0002)} - G01N 2021/8845: {Multiple wavelengths of illumination or detection} - G01N 2021/8887: {based on image processing techniques} - G01N: INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES (measuring or testing apparatus or processes other than immunoassay, involving enzymes or microorganisms C12M, C12Q) - B07C: POSTAL SORTING; SORTING INDIVIDUAL ARTICLES, OR BULK MATERIAL FIT TO BE SORTED PIECE-MEAL, e.g. BY PICKING (specially adapted for a specific purpose covered by another class, see the relevant place, e.g. A43D33/06, B23Q7/12) ## Abstract An automated system for detecting glass-ceramic materials among a cullet, includes at least one white light source and at least one monochromatic ultraviolet light source, each being oriented to emit in the same emission region. The system includes an image acquisition device configured to acquire an image of the emission region and an image processing device configured to process each of the images acquired by the image acquisition device, the image processing device including a colorimetric image processing module configured to ensure the detection of the glass-ceramic material among other types of glass. ## Claims ### Claim 1 An automated detection system for detecting materials of a glass-ceramic type among a cullet, comprising at least one white light source and at least one monochromatic ultraviolet light source, each being oriented to emit in a same emission region, an image acquisition device configured to acquire an image of said emission region and an image processing device configured to process each of the images acquired by the image acquisition device, the image processing device comprising a colorimetric image processing module configured to provide detection of glass-ceramic materials among other types of glass. ### Claim 2 (depends on 1) The automated detection system according to claim 1, wherein the colorimetric image processing module processes the images obtained by the image acquisition device by considering only one datum of a three-data colorimetric processing model. ### Claim 3 (depends on 2) The automated detection system according to claim 2, wherein the colorimetric image processing module comprises an HSV (Hue Saturation Value) model and processes the images obtained by the image acquisition device only by considering the hue data H of the HSV model. ### Claim 4 (depends on 1) The automated detection system according to claim 1, wherein the emission region comprises a cullet arranged on a reflective surface, illuminated by the at least one white light source and at least one monochromatic ultraviolet light source simultaneously, the light rays of which are picked up by the image acquisition device arranged on a same side of the reflective surface as the at least one white and at least one monochromatic ultraviolet light sources. ### Claim 5 (depends on 1) The automated detection system according to claim 1, wherein the radiation from the at least one monochromatic ultraviolet light source passes through a band-pass filter centered at 365 nm. ### Claim 6 (depends on 1) The automated detection system according to claim 1, wherein the light waves emitted by at least the at least one white light source are processed by a crossed polarizer and analyzer device before being picked up by the image acquisition device. ### Claim 7 (depends on 1) The automated detection system according to claim 1, further comprising a conveyor intended to make the cullet pass through the emission region of the light sources. ### Claim 8 (depends on 1) The automated detection system according to claim 1, further comprising a calculation module configured to determine a position of the various fragments of the cullet during its movement, the calculation module being configured to record the position of the fragments of the cullet detected as being fragments of glass-ceramic material at each instant t at the emission region, and to estimate their position downstream at an instant t+Δt by taking into account the movement speed of the cullet on the conveyor. ### Claim 9 (depends on 1) The automated detection system according to claim 1, wherein the image processing device further comprises a colorimetric image processing module according to an RGB model, said colorimetric image processing module according to an RGB model being configured to check results of the colorimetric image processing module configured to provide detection of glass-ceramic materials among other types of glass. ### Claim 10 (depends on 1) A facility for manufacturing glass fibers, hollow glass or flat glass comprising at least one glass furnace and forming stations, in which cullet is poured into the glass furnace to obtain molten glass intended to supply the forming stations, said facility comprising a system for automated detection according to claim 1, said automated detected system being positioned on a path of the cullet toward the at least one glass furnace. ### Claim 11 (depends on 1) A method for implementing an automated detection system for colorimetrically detecting materials of the glass-ceramic type among a cullet according to claim 1, comprising: a step of simultaneous lighting a cullet by at least one source of white light and at least one monochromatic ultraviolet light source, a step of acquiring light rays reflected by an image acquisition device, a step of colorimetric processing by a colorimetric image processing module of the image obtained by the image acquisition device making it possible to identify a glass-ceramic material among other types of glass. ### Claim 12 (depends on 11) The method according to claim 11, wherein the colorimetric processing is carried out by determining a single datum per pixel or group of pixels of the analyzed image, then by comparison with a range of data. ### Claim 13 (depends on 11) The method according to claim 11, wherein the colorimetric processing is colorimetric processing according to an HSV (Hue Saturation Value) model and is thresholded around an HSV datum of H of between 50° and 70° with S=1 and V=0.5. ### Claim 14 (depends on 11) The method according to claim 11, wherein representations obtained by the image acquisition device of the fragments of cullet identified as being fragments of glass-ceramic material by the colorimetric processing according to an HSV (Hue Saturation Value) model are rechecked by calculating the ratio of blue color to red color after a second colorimetric processing by the colorimetric image processing module according to an RGB model of these same fragment representations. ### Claim 15 (depends on 14) The method according to claim 14, wherein the fragments of cullet identified as being fragments of glass-ceramic material by the colorimetric processing according to the HSV model are confirmed as being fragments of glass-ceramic material if a calculation of a ratio of blue color to red color is greater than 0.5 after colorimetric processing according to the RGB model.