# US 6,448,549 B1 · Bottle thread inspection system and method of operating the same > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 6,448,549 B1 - Document ID: US6448549B1 - Status: Granted - Kind: B1 - Application number: 09/011,510 - Filed: 1998-02-03 - Granted: 2002-09-10 - Earliest claimed: 1995-08-04 - Assignees: Image Processing Systems, Inc. - Inventors: Reza Safaee-Rad - Web page: https://patentgrep.com/patent/US6448549B1 ## CPC - B07C 5/3408: {for bottles, jars or other glassware (according to size B07C5/122)} - G01N 21/9054: {Inspection of sealing surface and container finish} - 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) - 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) ## Abstract A method of inspecting a bottle (14) having a threaded section (104) for thread defects as the bottle moves along a production line (10) requires video images (100) of the bottle to be taken as the bottle moves into the fields of view of video cameras (22). Each video image encompasses a general region of interest (108) which contains at least a portion of the threaded section of the bottle. The position of the bottle (14) within the video image is then determined based on the location of the top rim (110) of the bottle within the video image. A portion of the general region of interest which encompasses at least a portion of the threaded section of the bottle is segmented into a plurality of specific regions of interest (120, 122). Pixels of the video image within the specific regions of interest are then examined to detect thread defects. ## Claims ### Claim 1 A method of inspecting bottles having a threaded section for thread defects as said bottles move along a high speed production line without requiring handling or manipulation of said bottles during thread defect inspection, said method comprising the steps of: capturing video images of each bottle with video cameras as each said bottle moves into the fields of view of said video cameras irrespective of the position of each said bottle within said fields of view, each video image encompassing a general region of interest containing a different portion of the threaded section of each said bottle; for each video image, processing pixels of said video image to highlight pixels corresponding to defects in said threaded section and corresponding to a reference feature of said bottle; determining for each video image, the location of said reference feature based on highlighted pixels; determining for each video image, the position of said threaded section of said bottle within said general region of interest based on the location of said reference feature; for each video image, segmenting a portion of said general region of interest, which encompasses said portion of said threaded section into at least one specific region of interest; and for each video image, examining the pixels of the video image in said at least one specific region of interest to detect thread defects generally about the circumference of said bottle. ### Claim 2 (depends on 1) The method of claim 1 wherein said feature is the top rim of said bottle. ### Claim 3 (depends on 2) The method of claim 2 wherein highlighted pixels corresponding to said top rim define a torus and wherein the portion of said general region of interest and the position of said at least one specific region of interest are determined based on the position of said torus. ### Claim 4 (depends on 3) The method of claim 3 wherein said general region of interest is segmented into a plurality of specific regions of interest including a central specific region of interest the position of the central specific region of interest being determined relative to said torus and wherein the positions of other specific regions of interest on opposite sides of said central specific region of interest are determined relative to the position of said central specific region of interest. ### Claim 5 (depends on 4) The method of claim 4 wherein said other specific regions of interest are increasingly offset in a Y-direction the further they are from said central specific region of interest to follow the threaded section of said bottle in said video image. ### Claim 6 (depends on 5) The method of claim 5 wherein said specific regions of interest decrease in an X-direction the further they are from said central specific region of interest to compensate for perspective effects. ### Claim 7 (depends on 6) The method of claim 6 wherein said specific regions of interest are positioned side-by-side. ### Claim 8 (depends on 6) The method of claim 6 wherein said specific regions of interest overlap adjacent specific regions of interest. ### Claim 9 (depends on 3) The method of claim 3 wherein said step of examining said pixels includes the steps of: determining a black/white pixel threshold value for said specific regions of interest; comparing said pixels with said threshold value and binarizng said pixels as white or black depending on the results of said comparison; and determining groups of contiguous white pixels larger than a threshold value thereby to detect thread defects. ### Claim 10 (depends on 9) The method of claim 9 wherein during the step of determining groups of contiguous white pixels, the groups of contiguous white pixels are filtered to reduce false detection of bottle thread defects. ### Claim 11 (depends on 1) The method of claim 1 wherein steps (i) to (iv) are performed at a plurality of circumferentially spaced locations about said bottle to detect thread defects in the entire threaded section of said bottle. ### Claim 12 (depends on 1) The method of claim 1 wherein during pixel processing of each said video image, said highlighted pixels are white and remaining pixels are black. ### Claim 13 (depends on 12) The method of claim 12 wherein said reference feature is the top rim of said bottle and wherein said corresponding highlighted pixels take the form of a torus. ### Claim 14 (depends on 13) The method of claim 13 wherein said examining step includes the step of determining groups of contiguous white pixels larger than a threshold value thereby to detect thread defects. ### Claim 15 (depends on 13) The method of claim 13 wherein blob detection is performed on pixels of each said video image to locate the highlighted pixels resembling said torus. ### Claim 16 (depends on 14) The method of claim 14 wherein blob detection is used to determine said groups of contiguous white pixels. ### Claim 17 A system for inspecting bottles having a threaded section for thread defects as said bottles are moved along a production line without requiring handling or manipulation of said bottles during thread defect inspection, said system comprising: a plurality of video imaging sections disposed along said production line at spaced locations, each video imaging section being oriented with respect to said production line to take a video image of each bottle at a different circumferential region thereof as each bottle moves into the field of view of said video imaging section irrespective of the position of each said bottle within said field of view, each video image encompassing a general region of interest containing a different portion of the threaded section of each bottle; and processing means in communication with said video imaging section and receiving the video images taken thereby, said processing means processing in real-time each video image to: highlight pixels of each video image corresponding to defects in said threaded section and corresponding to a reference feature of said bottle; determine the location of said reference feature based on highlighted pixels; determine the position of the threaded section of said bottle within said general region of interest based on the location of said reference feature; segment a portion of said general region of interest, which encompasses said portion of said threaded section into at least one specific region of interest; and examine the pixels in said at least one specific region of interest to detect thread defects generally about the circumference of said bottle. ### Claim 18 (depends on 17) A system for inspecting bottles as defined in claim 17 wherein each video imaging section includes a video imaging camera and a light source, said light source and said video imaging camera being located on opposite sides of said production line, the video imaging cameras and light sources in said video imaging sections being oriented so that video images of the entire circumference of each bottle are taken by said video imaging sections. ### Claim 19 (depends on 18) A system for inspecting bottles as defined in claim 18 further comprising at least one bottle detection sensor for detecting the presence of a bottle, said processing means being responsive to said at least one bottle detection sensor and triggering said video imaging sections to take video images of said bottle. ### Claim 20 (depends on 19) A system for inspecting bottles as defined in claim 19 wherein said light sources remain illuminated and wherein said processing means triggers the video imaging camera to take an image of said bottle in response to the associated bottle detection sensor. ### Claim 21 (depends on 20) A system for inspecting bottles as defined in claim 20 wherein said processing means signals a bottle reject mechanism along said production line upon detection of a bottle having a thread defect. ### Claim 22 (depends on 18) A system for inspecting bottles as defined in claim 18 wherein said video imaging sections are arranged in interlocking pairs to reduce spacing and optical interference therebetween. ### Claim 23 A system for inspecting bottles each having a threaded section for thread defects as said bottles are moved along a high speed production line without requiring handling or manipulation of said bottles during thread defect inspection, said system comprising: a plurality of video imaging sections disposed along said production line at spaced locations, each video imaging section being positioned with respect to said production line to take a video image of each bottle neck at a different circumferential region thereof as each bottle moves into the field of view of said video imaging section irrespective of the position of said bottle within said field of view, said video imaging sections being arranged in pairs oriented to reduce spacing and optical interference therebetween; and processing means in communication with said video imaging sections and receiving the video images taken thereby, said processing means processing each said video image to: highlight pixels corresponding to defects in said threaded section and corresponding to the top rim of said bottle; determine for each video image the location of said top rim based on highlighted pixels; determine the position of threads of said bottle neck within said general region of interest based on the location of said top rim; segment at least a portion of each video image, which encompasses said threads into a plurality of specific regions of interest based on the location of said top rim; and process each specific region of interest independently to determine defects in each of said specific regions of interest based on the existence of areas of white pixels larger than a prescribed threshold area size within said specific regions of interest. ### Claim 24 (depends on 23) A system for inspecting bottles as defined in claim 23 wherein each video imaging section includes a video imaging camera and a fight source, the video imaging camera and light source being positioned on opposite sides of said production line and being laterally offset so that the optical axis of each video imaging section forms an oblique angle with respect to said production line. ### Claim 25 (depends on 24) A system for inspecting bottles as defined in claim 24 wherein said system includes four video imaging sections arranged in an upstream pair and a downstream pair, the video imaging cameras and light sources in said upstream pair forming an obtuse angle with respect to said production line and the video imaging cameras and light sources in said downstream pair forming acute angles with respect to said production line. ### Claim 26 (depends on 25) A system for inspecting bottles defined in claim 25 wherein the positions of said video imaging cameras and light sources with respect to said production line alternate in successive video imaging sections. ### Claim 27 A method for detecting thread defects in a bottle having threads about a neck of said bottle comprising the steps of: capturing video images of said bottle about the circumference of said neck to image said neck; processing pixels of each video image to highlight pixels corresponding to defects in said threads and corresponding to the top rim of said bottle; determining for each video image the location of said top rim based on highlighted pixels; determining the position of the threads of said bottle within said general region of interest based on the location of said top rim; segmenting at least a portion of each video image, which encompasses said threads into a plurality of specific regions of interest based on the location of said top rim; and video processing each specific region of interest independently to determine defects in each of said specific regions of interest based on the existence of areas of white pixels larger than a prescribed threshold area size within said specific regions of interest. ### Claim 28 A system for detecting thread defects in a bottle having threads about a neck of said bottle, comprising: means for capturing video images of said bottle about the circumference of said neck; means for processing pixels of each video image to highlight pixels corresponding to defects in said threads and corresponding to the top rim of said bottle; means for determining for each video image the location of said top rim based on highlighted pixels; means for determining the position of the threads of said bottle neck within said general region of interest based on the location of said top rim; means for segmenting at least a portion of each video image into a plurality of specific regions of interest based on the location of said top rim; and means for video processing each specific region of interest independently to determine defects in each of said specific regions of interested based on the existence of white areas of white pixels larger than a prescribed threshold area size within said specific region of interest. ### Claim 29 A method of inspecting bottles having a threaded section for thread defects as said bottles move along a high speed production line without requiring handling or manipulation of said bottles during thread defect inspection, said method comprising the steps of: capturing video images of each bottle with video cameras as each said bottle moves into the fields of view of said video cameras irrespective of the position of each said bottle within said fields of view, each video image encompassing a general region of interest containing a different portion of the threaded section of said bottle; determining for each video image, the location of a rim of said bottle within said video image; determining for each video image the position of said threaded section of said bottle within said general region of interest based on the location of the rim of said bottle; for each video image segmenting a portion of said general region of interest, which encompasses said portion of said threaded section into a plurality of specific regions of interest, said specific regions of interest including a central specific region of interest and other specific regions on opposite sides of said central specific region of interest, the position of said central specific region of interest being determined based on the location of said rim; and for each video image examining pixels of the video image in said specific regions of interest to detect thread defects generally about the circumference of said bottle. ### Claim 30 (depends on 29) The method of claim 29 wherein said other specific regions of interest are increasingly offset in a Y-direction the further they are from said central specific region of interest to follow the threaded section of said bottle in said video image. ### Claim 31 (depends on 30) The method of claim 30 wherein said specific regions of interest decrease in a X-direction the further they are from said central specific region of interest to compensate for perspective effects. ### Claim 32 (depends on 31) The method of claim 31 wherein said specific regions of interest are positioned side-by-side. ### Claim 33 (depends on 31) The method of claim 31 wherein said specific regions of interest overlap adjacent specific regions of interest.