# US 10,311,576 B2 · Image processing device and image processing method > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 10,311,576 B2 - Document ID: US10311576B2 - Status: Granted - Kind: B2 - Application number: 15/681,095 - Filed: 2017-08-18 - Published: 2018-03-29 - Granted: 2019-06-04 - Earliest claimed: 2016-09-26 - Assignees: Fujitsu Limited - Applicants: Fujitsu Limited - Inventors: Nobuyasu Yamaguchi; Yojiro Numata; Hiroshi Kuwabara - Web page: https://patentgrep.com/patent/US10311576B2 ## CPC - G06T 7/344: {involving models} - G06T 7/13: Edge detection - G06T 7/181: involving edge growing; involving edge linking - G06T 7/251: {involving models} - G06T 7/564: from contours - G06T 7/75: {involving models} - G06V 10/44: Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components - G06V 20/20: in augmented reality scenes - G06V 20/64: Three-dimensional [3D] objects - G06T 15/02: Non-photorealistic rendering - G06T 2200/24: involving graphical user interfaces [GUIs] - G06T 2207/20104: Interactive definition of region of interest [ROI] - G06T 2207/20116: Active contour; Active surface; Snakes - G06T 2207/30244: Camera pose - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract A computer extracts a plurality of candidate lines that are observed from a position of an imaging device that captures an image of an object from among a plurality of candidate lines included in shape information of the object. The computer generates plural pieces of association information indicating a prescribed number of combinations obtained by respectively associating the prescribed number of candidate lines of the observed plurality of candidate lines with the prescribed number of feature lines of a plurality of feature lines detected from the image. The computer determines an association result according to respective errors of the plural pieces of association information. ## Claims ### Claim 1 A non-transitory computer-readable recording medium having stored therein an image processing program causing a computer to execute a process comprising: extracting a plurality of candidate lines that are observed from a position of an imaging device that captures an image of an object from among a plurality of candidate lines included in shape information of the object; generating plural pieces of association information indicating a prescribed number of combinations obtained by respectively associating the prescribed number of candidate lines of the observed plurality of candidate lines with the prescribed number of feature lines of a plurality of feature lines detected from the image; generating the prescribed number of projection lines by projecting the prescribed number of candidate lines onto the image; and determining an association result according to respective errors of the plural pieces of association information, each of the respective errors indicating a deviation between a position of each of the prescribed number of projection lines and a position of each of the prescribed number of feature lines. ### Claim 2 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein the extracting the observed plurality of candidate lines removes one or more hidden lines from the plurality of candidate lines included in the shape information by using a prescribed position in a space as the position of the imaging device, and extracts remaining candidate lines as the observed plurality of candidate lines. ### Claim 3 (depends on 2) The non-transitory computer-readable recording medium according to claim 2, wherein the extracting the observed plurality of candidate lines extracts candidate lines indicating an outline edge of the object from among the remaining candidate lines, as the observed plurality of candidate lines. ### Claim 4 (depends on 3) The non-transitory computer-readable recording medium according to claim 3, wherein the extracting the observed plurality of candidate lines extracts candidate lines indicating an outer periphery of the object from among the candidate lines indicating the outline edge, as the observed plurality of candidate lines. ### Claim 5 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein two candidate lines of the prescribed number of candidate lines are not parallel to each other. ### Claim 6 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein no two candidate lines of the prescribed number of candidate lines exist on a straight line. ### Claim 7 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein the generating the plural pieces of association information extracts a plurality of feature lines that each include a portion included in a specified region within the image from among the plurality of feature lines detected from the image, and selects the prescribed number of feature lines from the extracted plurality of feature lines. ### Claim 8 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein the generating the plural pieces of association information extracts a plurality of feature lines that exist within a range of a prescribed distance from a reference position in the image from among the plurality of feature lines detected from the image, and selects the prescribed number of feature lines from the extracted plurality of feature lines. ### Claim 9 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein two feature lines of the prescribed number of feature lines are not parallel to each other. ### Claim 10 (depends on 1) The non-transitory computer-readable recording medium according to claim 1, wherein no two feature lines of the prescribed number of feature lines exist on a straight line. ### Claim 11 An image processing device comprising: a memory that stores shape information of an object; and a processor coupled to the memory and configured to extract a plurality of candidate lines that are observed from a position of an imaging device that captures an image of the object from among a plurality of candidate lines included in the shape information, to generate plural pieces of association information indicating a prescribed number of combinations obtained by respectively associating the prescribed number of candidate lines of the observed plurality of candidate lines with the prescribed number of feature lines of a plurality of feature lines detected from the image, to generate the prescribed number of projection lines by projecting the prescribed number of candidate lines onto the image, and to determine an association result according to respective errors of the plural pieces of association information, each of the respective errors indicating a deviation between a position of each of the prescribed number of projection lines and a position of each of the prescribed number of feature lines. ### Claim 12 (depends on 11) The image processing device according to claim 11, wherein the processor removes one or more hidden lines from the plurality of candidate lines included in the shape information by using a prescribed position in a space as the position of the imaging device, and extracts remaining candidate lines as the observed plurality of candidate lines. ### Claim 13 An image processing method comprising: extracting, by a processor, a plurality of candidate lines that are observed from a position of an imaging device that captures an image of an object from among a plurality of candidate lines included in shape information of the object; generating, by the processor, plural pieces of association information indicating a prescribed number of combinations obtained by respectively associating the prescribed number of candidate lines of the observed plurality of candidate lines with the prescribed number of feature lines of a plurality of feature lines detected from the image; generating, by the processor, the prescribed number of projection lines by projecting the prescribed number of candidate lines onto the image; and determining, by the processor, an association result according to respective errors of the plural pieces of association information, each of the respective errors indicating a deviation between a position of each of the prescribed number of projection lines and a position of each of the prescribed number of feature lines. ### Claim 14 (depends on 13) The image processing method according to claim 13, wherein the extracting the observed plurality of candidate lines removes one or more hidden lines from the plurality of candidate lines included in the shape information by using a prescribed position in a space as the position of the imaging device, and extracts remaining candidate lines as the observed plurality of candidate lines.