# US 11,443,400 B2 · Methods and arrangements for configuring industrial inspection systems > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 11,443,400 B2 - Document ID: US11443400B2 - Status: Granted - Kind: B2 - Application number: 16/819,510 - Filed: 2020-03-16 - Published: 2020-10-01 - Granted: 2022-09-13 - Earliest claimed: 2015-06-11 - Assignees: Digimarc Corporation - Applicants: Digimarc Corporation - Inventors: Eric D. Evans; Christopher M. Haverkate - Web page: https://patentgrep.com/patent/US11443400B2 ## CPC - H04N 17/002: {for television cameras} - G06F 18/22: Matching criteria, e.g. proximity measures - G06T 1/0028: {Adaptive watermarking, e.g. Human Visual System [HVS]-based watermarking} - G06T 5/40: using histogram techniques - G06V 10/22: by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition - G06V 10/462: {Salient features, e.g. scale invariant feature transforms [SIFT]} - H04N 19/44: Decoders specially adapted therefor, e.g. video decoders which are asymmetric with respect to the encoder - H04N 19/91: Entropy coding, e.g. variable length coding [VLC] or arithmetic coding - G01N 2021/8887: {based on image processing techniques} - G06T 2201/0052: Embedding of the watermark in the frequency domain - H04N: PICTORIAL COMMUNICATION, e.g. TELEVISION - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING - 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 In computer vision systems that need to decode machine-readable indicia from captured imagery, it is critical to select imaging parameters (e.g., exposure interval, exposure aperture, camera gain, intensity and duration of supplemental illumination) that best allow detection of subtle features from imagery. In illustrative embodiments, a Shannon entropy metric or a KL divergence metric is used to guide selection of an optimal set of imaging parameters. In accordance with other aspects of the technology, different strategies identify which spatial locations within captured imagery should be successively examined for machine readable indicia, in order to have a greatest likelihood of success, within a smallest interval of time. A great variety of other features and arrangements are also detailed. ## Claims ### Claim 1 A method comprising the acts: receiving a first set of images, each image comprising a frame of P rows and Q columns of pixels, each image in said set depicting an item in front of a camera, each item having a printed indicia formed thereon; establishing a first group of N spatial regions {1, 2, . . . N} within said frame of pixels; for each image in the first set, identifying which 0, 1, or more, of the N spatial regions within said frame, depicts an indicia from which an identifier can be read; identifying, from across said first set of images, one of said N spatial regions, termed region A, that most commonly depicts an indicia from which an identifier can be read; thinning the first set of images to produce a smaller second set of images, by removing images that depict, in region A, an indicia from which an identifier can be read; and identifying, from across said second set of images, one of said N spatial regions, termed region B, that most commonly depicts an indicia from which an identifier can be read. ### Claim 2 (depends on 1) The method of claim 1 that further includes acting to ensure that an origin of region B is spaced from an origin of region A by more than a threshold spatial distance. ### Claim 3 (depends on 2) The method of claim 2 in which each of said N spatial regions is a square area having a height of J pixels and a width of J pixels, and wherein the threshold distance is greater than or equal to J/2 pixels. ### Claim 4 (depends on 2) The method of claim 2 in which each of said N spatial regions is a square area having a height of J pixels and a width of J pixels, and wherein the threshold distance is greater than or equal to 3J/4 pixels. ### Claim 5 (depends on 2) The method of claim 2 in which each of said N spatial regions is a square area having a height of 128 pixels and a width of 128 pixels, and wherein the threshold distance is 96 pixels. ### Claim 6 (depends on 2) The method of claim 2 that further includes: after thinning the first set of images to produce the smaller second set of images, thinning the first group of N spatial regions to produce a smaller second group of M spatial regions {1, 2, . . . M}, wherein said thinning of the first group of regions comprises omitting, from the second group of regions those regions having origins that are within said spatial distance of region A; and wherein region B is identified from said second group of M spatial regions. ### Claim 7 (depends on 1) The method of claim 1 that further includes: receiving a further image depicting an item passing in front of a camera; attempting to read an indicia from region A of said further image; attempting to read an indicia from region B of said further image; and taking an action based on an indicia read from one of said regions A or B. ### Claim 8 (depends on 7) The method of claim 7 that includes reading indicia from both regions A and B of said further image, and comparing the two read indicia for consistency. ### Claim 9 (depends on 1) The method of claim 1 that further includes: thinning the second set of images to produce a smaller third set of images, by removing images that depict, in region B, an indicia from which an identifier can be read; and identifying, from across said third set of images, one of said N spatial regions, termed region C, that most commonly depicts an indicia from which an identifier can be read. ### Claim 10 (depends on 9) The method of claim 9 that further includes: receiving a further image depicting an item passing in front of a camera; attempting to read an indicia from region A of said further image; attempting to read an indicia from region B of said further image; attempting to read an indicia from region C of said further image; and taking an action based on an indicia read from one of said regions A, B or C. ### Claim 11 (depends on 10) The method of claim 10 that includes reading indicia from two or more of said regions A, B and C, and comparing the read indicia for consistency. ### Claim 12 A method comprising the acts: receiving a set of images, each image comprising a frame of P rows and Q columns of pixels, each image in said set depicting an item in front of a camera, each item having a printed indicia formed thereon; establishing a first group of N spatial regions {1, 2, . . . N} within said frame of pixels; for each image in the set, identifying which 0, 1, or more, of the N spatial regions within said frame, depicts an indicia from which an identifier can be read; identifying, from across said set of images, one of said N spatial regions, termed region A, that most commonly depicts an indicia from which an identifier can be read; thinning the first group of N spatial regions to produce a smaller second group of M spatial regions; and identifying, from across said set of images, one of said M spatial regions, termed region B, that most commonly depicts an indicia from which an identifier can be read; wherein the thinning comprises removing from the first group of spatial regions: (a) region A, and (b) those regions that are within a threshold distance of region A. ### Claim 13 A system including one or more processors and one or more memories, the one or more memories containing software instructions operative to configure the one or more processors to cause the system to perform the following acts: receiving a first set of images, each image comprising a frame of P rows and Q columns of pixels, each image in said set depicting an item in front of a camera, each item having a printed indicia formed thereon; establishing a first group of N spatial regions {1, 2, . . . N} within said frame of pixels; for each image in the first set, identifying which 0, 1, or more, of the N spatial regions within said frame, depicts an indicia from which an identifier can be read; identifying, from across said first set of images, one of said N spatial regions, here termed region A, that most commonly depicts an indicia from which an identifier can be read; thinning the first set of images to produce a smaller second set of images, by removing images that depict, in region A, an indicia from which an identifier can be read; and identifying, from across said second set of images, one of said N spatial regions, here termed region B, that most commonly depicts an indicia from which an identifier can be read. ### Claim 14 (depends on 13) The system of claim 13 in which said instructions are further operative to cause the system to ensure that an origin of region B is spaced from an origin of region A by more than a threshold spatial distance. ### Claim 15 (depends on 14) The system of claim 14 in which each of said N spatial regions is a square area having a height of J pixels and a width of J pixels, and wherein the threshold distance is greater than or equal to J/2 pixels. ### Claim 16 (depends on 14) The system of claim 14 in which said instructions are further operative to cause the system to perform the acts: after thinning the first set of images to produce the smaller second set of images, thinning the first group of N spatial regions to produce a smaller second group of M spatial regions {1, 2, . . . M}, wherein said thinning of the first group of regions comprises omitting, from the second group of regions those regions having origins that are within said spatial distance of region A; and wherein region B is identified from said second group of M spatial regions. ### Claim 17 (depends on 13) The system of claim 13 in which said instructions are further operative to cause the system to perform the acts: receiving a further image depicting an item passing in front of a camera; attempting to read an indicia from region A of said further image; attempting to read an indicia from region B of said further image; and taking an action based on an indicia read from one of said regions A or B. ### Claim 18 (depends on 17) The system of claim 17 in which said instructions are further operative to cause the system to perform the acts of reading indicia from both regions A and B of said further image, and comparing the two read indicia for consistency. ### Claim 19 (depends on 13) The system of claim 13 in which said instructions are further operative to cause the system to perform the acts: thinning the second set of images to produce a smaller third set of images, by removing images that depict, in region B, an indicia from which an identifier can be read; and identifying, from across said third set of images, one of said N spatial regions, here termed region C, that most commonly depicts an indicia from which an identifier can be read. ### Claim 20 (depends on 19) The system of claim 19 in which said instructions are further operative to cause the system to perform the acts: receiving a further image depicting an item passing in front of a camera; attempting to read an indicia from region A of said further image; attempting to read an indicia from region B of said further image; attempting to read an indicia from region C of said further image; and taking an action based on an indicia read from one of said regions A, B or C.