# US 10,121,232 B1 · Visual quality of photographs with handwritten content > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,121,232 B1 - Document ID: US10121232B1 - Status: Granted - Kind: B1 - Application number: 15/384,956 - Filed: 2016-12-20 - Granted: 2018-11-06 - Earliest claimed: 2015-12-23 - Assignees: Evernote Corporation - Applicants: Evernote Corporation - Inventors: Boris Gorbatov; Eugene Livshitz; Alexander Pashintsev; Ilia Buriak; Natalia Galaktionova - Web page: https://patentgrep.com/patent/US10121232B1 ## CPC - G06V 10/993: {Evaluation of the quality of the acquired pattern} - G06V 10/26: Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion - G06V 10/426: Graphical representations - G06V 10/457: {by analysing connectivity, e.g. edge linking, connected component analysis or slices} - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract Improving visual quality of a raster image includes detecting connectivity components, detecting defects in each of the connectivity components based on a characteristic line width thereof, detecting segments in each of the connectivity components, detecting joints based on geometry of the connectivity components, creating a structural graph based on the segments and joints, and correcting the raster image according to the structural graph and detected ones of the defects. The joints may correspond to linear joints, T-joints, or X-joints. Detecting types of joints may include determining a configuration of adjacent segments in a proximity of each of the joints. A characteristic line width may be determined by determining co-boundaries on opposite sides of each of the segments and determining average distances between the co-boundaries. The raster image may be a binary black-and-white image of a line drawing obtained from a photograph or a scan of a handwritten document. ## Claims ### Claim 1 A method of improving visual quality of a raster image, comprising: detecting connectivity components; detecting defects in each of the connectivity components; detecting segments in each of the connectivity components; detecting joints based on geometry of the connectivity components; creating a structural graph based on the segments and joints; and correcting the raster image according to the structural graph and detected ones of the defects. ### Claim 2 (depends on 1) A method, according to claim 1, wherein the joints correspond to one of: linear joints, T-joints, and X-joints. ### Claim 3 (depends on 2) A method, according to claim 2, wherein detecting types of joints includes determining a configuration of adjacent segments in a proximity of each of the joints. ### Claim 4 (depends on 2) A method, according to claim 2, wherein a linear joint is detected by determining that an angle between axes of two segments in a proximity of a joint is approximately 180 degrees. ### Claim 5 (depends on 4) A method, according to claim 4, wherein the two segments are joined to correct the linear joint. ### Claim 6 (depends on 2) A method, according to claim 2, wherein a T-joint is detected by determining that an angle between axes of a first segment and a second segment in a proximity of a joint is approximately 180 degrees, an angle between the axis of the first segment and an axis of a third segment in a proximity of a joint is approximately 90 degrees and an angle between axes of the second segment and the third segment in a proximity of a joint is approximately 90 degrees. ### Claim 7 (depends on 6) A method, according to claim 6, wherein uneven angles between the first, second, and third segments are sharpened to correct the T-joint. ### Claim 8 (depends on 2) A method, according to claim 2, wherein an X-joint is detected by determining that an angle between axes of a first segment and a second segment in a proximity of a joint is approximately 90 degrees, an angle between the axis of the second segment and an axis of a third segment in a proximity of a joint is approximately 90 degrees, an angle between the axis of the third segment and an axis of a fourth segment in a proximity of a joint is approximately 90 degrees, and an angle between axes of the fourth segment and the first segment in a proximity of a joint is approximately 90 degrees. ### Claim 9 (depends on 8) A method, according to claim 8, wherein uneven angles between the first, second, third, and fourth segments are sharpened to correct the X-joint. ### Claim 10 (depends on 1) A method, according to claim 1, wherein the defects include holes and minor deviations from the characteristic line width. ### Claim 11 (depends on 10) A method, according to claim 10, wherein the defects are a result of artifact noise. ### Claim 12 (depends on 1) A method, according to claim 1, wherein the characteristic line width is determined by determining co-boundaries on opposite sides of each of the segments and determining average distances between the co-boundaries. ### Claim 13 (depends on 1) A method, according to claim 1, wherein the raster image is a binary black-and-white image of a line drawing obtained from one of: a photograph or a scan of a handwritten document. ### Claim 14 A non-transitory computer readable medium containing software that improves visual quality of a raster image, the software comprising: executable code that detects connectivity components; executable code that detects defects in each of the connectivity components; executable code that detects segments in each of the connectivity components; executable code that detects joints based on geometry of the connectivity components; executable code that creates a structural graph based on the segments and joints; and executable code that corrects the raster image according to the structural graph and detected ones of the defects. ### Claim 15 (depends on 14) A non-transitory computer-readable medium, according to claim 14, wherein the joints correspond to one of: linear joints, T-joints, and X-joints. ### Claim 16 (depends on 15) A non-transitory computer-readable medium, according to claim 15, wherein detecting types of joints includes determining a configuration of adjacent segments in a proximity of each of the joints. ### Claim 17 (depends on 15) A non-transitory computer-readable medium, according to claim 15, wherein a linear joint is detected by determining that an angle between axes of two segments in a proximity of a joint is approximately 180 degrees. ### Claim 18 (depends on 17) A non-transitory computer-readable medium, according to claim 17, wherein the two segments are joined to correct the linear joint. ### Claim 19 (depends on 15) A non-transitory computer-readable medium, according to claim 15, wherein a T-joint is detected by determining that an angle between axes of a first segment and a second segment in a proximity of a joint is approximately 180 degrees, an angle between the axis of the first segment and an axis of a third segment in a proximity of a joint is approximately 90 degrees and an angle between axes of the second segment and the third segment in a proximity of a joint is approximately 90 degrees. ### Claim 20 (depends on 19) A non-transitory computer-readable medium, according to claim 19, wherein uneven angles between the first, second, and third segments are sharpened to correct the T-joint. ### Claim 21 (depends on 15) A non-transitory computer-readable medium, according to claim 15, wherein an X-joint is detected by determining that an angle between axes of a first segment and a second segment in a proximity of a joint is approximately 90 degrees, an angle between the axis of the second segment and an axis of a third segment in a proximity of a joint is approximately 90 degrees, an angle between the axis of the third segment and an axis of a fourth segment in a proximity of a joint is approximately 90 degrees, and an angle between axes of the fourth segment and the first segment in a proximity of a joint is approximately 90 degrees. ### Claim 22 (depends on 21) A non-transitory computer-readable medium, according to claim 21, wherein uneven angles between the first, second, third, and fourth segments are sharpened to correct the X-joint. ### Claim 23 (depends on 14) A non-transitory computer-readable medium, according to claim 14, wherein the defects include holes and minor deviations from the characteristic line width. ### Claim 24 (depends on 23) A non-transitory computer-readable medium, according to claim 23, wherein the defects are a result of artifact noise. ### Claim 25 (depends on 14) A non-transitory computer-readable medium, according to claim 14, wherein the characteristic line width is determined by determining co-boundaries on opposite sides of each of the segments and determining average distances between the co-boundaries. ### Claim 26 (depends on 14) A non-transitory computer-readable medium, according to claim 14, wherein the raster image is a binary black-and-white image of a line drawing obtained from one of: a photograph or a scan of a handwritten document.