# US 2018/0025250 A1 · Image processing apparatus, image processing system, image processing method, and storage medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 2018/0025250 A1 - Document ID: US20180025250A1 - Status: Published application - Kind: A1 - Application number: 15/649,720 - Filed: 2017-07-14 - Published: 2018-01-25 - Earliest claimed: 2016-07-22 - Assignees: Canon Kabushiki Kaisha - Applicants: Canon Kabushiki Kaisha - Inventors: Bin Chen; Daisuke Furukawa - Web page: https://patentgrep.com/patent/US20180025250A1 ## CPC - G06T 7/149: involving deformable models, e.g. active contour models - G06F 16/583: using metadata automatically derived from the content - G06T 7/12: Edge-based segmentation - G06V 10/267: {by performing operations on regions, e.g. growing, shrinking or watersheds} - G06V 10/754: {involving a deformation of the sample pattern or of the reference pattern; Elastic matching} - G06T 2207/20076: Probabilistic image processing - G06T 2207/20101: Interactive definition of point of interest, landmark or seed - G06T 2207/30064: Lung nodule - G06V 2201/032: of protuberances, polyps nodules, etc. - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G06F: ELECTRIC DIGITAL DATA PROCESSING (computer systems based on specific computational models G06N) - G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING ## Abstract An image processing apparatus is configured to extract an object region from an image. The image processing apparatus includes: a setting unit configured to set a plurality of reference points in the image; an obtaining unit configured to obtain a contour of the object region corresponding to each of the plurality of reference points as an initial extraction result based on a characteristic of the object region; and an extraction unit configured to extract the object region from the image based on an integration result obtained by integrating values of pixels in a plurality of initial extraction results. ## Claims ### Claim 1 An image processing apparatus configured to extract an object region from an image, comprising: a setting unit configured to set a plurality of reference points in the image; an obtaining unit configured to obtain a contour of the object region corresponding to each of the plurality of reference points as an initial extraction result based on a characteristic of the object region; and an extraction unit configured to extract the object region from the image based on an integration result obtained by integrating values of pixels in a plurality of initial extraction results. ### Claim 2 (depends on 1) The apparatus according to claim 1, wherein the extraction unit generates a likelihood map representing a likelihood that each pixel in the integration result is included in the object region, and extracts the object region from the image based on the likelihood map. ### Claim 3 (depends on 2) The apparatus according to claim 2, wherein the extraction unit extracts the object region from the image based on the likelihood of each pixel in the likelihood map and the characteristic of the object region. ### Claim 4 (depends on 2) The apparatus according to claim 2, wherein the characteristic of the object region includes a characteristic of an intensity value change representing that an intensity value changes between an inside and an outside of the object region, and a characteristic of a contour shape of the object region. ### Claim 5 (depends on 4) The apparatus according to claim 4, wherein the extraction unit extracts the object region from the image based on an evaluation result of the characteristic of the intensity value change, an evaluation result of the characteristic of the contour shape, and an evaluation result of the likelihood of each pixel in the likelihood map. ### Claim 6 (depends on 1) The apparatus according to claim 1, wherein the extraction unit extracts the object region from the image based on a result obtained by adding the values of the pixels in the plurality of initial extraction results at the same pixel position. ### Claim 7 (depends on 1) The apparatus according to claim 1, wherein the setting unit sets, as the plurality of reference points, a plurality of pixels each having an image feature similar to an image feature of an initial reference point set based on input information from an operation unit. ### Claim 8 (depends on 7) The apparatus according to claim 7, wherein the setting unit sets, as the plurality of reference points, the initial reference point set based on the input information from the operation unit and the plurality of pixels each having the image feature similar to the image feature of the initial reference point. ### Claim 9 (depends on 7) The apparatus according to claim 7, wherein the setting unit uses a LoG (Laplacian of Gaussian) kernel as an evaluation function used to obtain an image size, and decides the image size of an image region including the object region based on a distribution of output values of the evaluation function. ### Claim 10 (depends on 9) The apparatus according to claim 9, wherein the setting unit decides the image size of the image region including the object region based on a parameter representing a scale of the evaluation function corresponding to a maximum value of the output value of the evaluation function. ### Claim 11 (depends on 10) The apparatus according to claim 10, wherein the setting unit sets the plurality of reference points based on the output value of the evaluation function. ### Claim 12 (depends on 11) The apparatus according to claim 11, wherein the obtaining unit obtains a centroid of the plurality of reference points, thereby setting a position of the image region including the object region, and the obtaining unit obtains the image region from the image using the image size and the position. ### Claim 13 (depends on 9) The apparatus according to claim 9, wherein the image feature includes one of the pixel value of each pixel that constitutes the image and the output value of the evaluation function. ### Claim 14 (depends on 1) The apparatus according to claim 1, wherein the setting unit additionally sets a plurality of reference points in a repetitive operation, the obtaining unit obtains, as the initial extraction result, the contour of the object region corresponding to each of a plurality of set first reference points and a plurality of additionally set second reference points, and the extraction unit extracts the object region from the image based on an integration result obtained by integrating the values of pixels in a plurality of initial extraction results obtained based on the plurality of first reference points and the plurality of additionally set second reference points. ### Claim 15 (depends on 14) The apparatus according to claim 14, further comprising a determination unit configured to obtain a variation of feature information representing a feature of the object region extracted by the extraction unit as the plurality of additionally set reference points increase, and determine, based on a comparison between the variation and a threshold, whether to continue the repetitive operation. ### Claim 16 (depends on 1) The apparatus according to claim 1, further comprising a display control unit configured to perform display control to cause a display unit to display a result of region extraction by the extraction unit, wherein the display control unit causes the display unit to display an image composited by superimposing the extracted object region on the image. ### Claim 17 An image processing system comprising an image processing apparatus configured to extract an object region from an image, the image processing apparatus comprising: a setting unit configured to set a plurality of reference points in the image; an obtaining unit configured to obtain a contour of the object region corresponding to each of the plurality of reference points as an initial extraction result based on a characteristic of the object region; and an extraction unit configured to extract the object region from the image based on an integration result obtained by integrating values of pixels in a plurality of initial extraction results. ### Claim 18 An image processing method of an image processing apparatus configured to extract an object region from an image, comprising: setting a plurality of reference points in the image; obtaining a contour of the object region corresponding to each of the plurality of reference points as an initial extraction result based on a characteristic of the object region; and extracting the object region from the image based on an integration result obtained by integrating values of pixels in a plurality of initial extraction results. ### Claim 19 A storage medium storing a program configured to cause a computer to execute each step of an image processing method of an image processing apparatus configured to extract an object region from an image, the image processing method comprising: setting a plurality of reference points in the image; obtaining a contour of the object region corresponding to each of the plurality of reference points as an initial extraction result based on a characteristic of the object region; and extracting the object region from the image based on an integration result obtained by integrating values of pixels in a plurality of initial extraction results.