# US 9,517,029 B2 · Image processing device, image processing method, image processing system, program, and recording medium > Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt - Number: US 9,517,029 B2 - Document ID: US9517029B2 - Status: Granted - Kind: B2 - Application number: 13/483,446 - Filed: 2012-05-30 - Published: 2012-12-06 - Granted: 2016-12-13 - Earliest claimed: 2011-06-06 - Assignees: Sony Corporation - Applicants: Shinichiro Gomi; Masaru Suzuki; Yusuke Nakamura; Hideo Sato; Kazuo Omori; Mitsuharu Ohki - Inventors: Shinichiro Gomi; Masaru Suzuki; Yusuke Nakamura; Hideo Sato; Kazuo Omori; Mitsuharu Ohki - Web page: https://patentgrep.com/patent/US9517029B2 ## CPC - A61B 5/441: {Skin evaluation, e.g. for skin disorder diagnosis} - A61B 5/0077: {Devices for viewing the surface of the body, e.g. camera, magnifying lens} - A61B 5/103: Measuring devices for testing the shape, pattern, {colour,} size or movement of the body or parts thereof, for diagnostic purposes (measuring instruments specially adapted for dentistry A61C19/04) - G06T 7/44: using image operators, e.g. filters, edge density metrics or local histograms - G06T 2207/10148: Varying focus - G06T 2207/10152: Varying illumination - G06T 2207/20081: Training; Learning - G06T 2207/30088: Skin; Dermal - G06T 2207/30201: Face - G16H 30/20: for handling medical images, e.g. DICOM, HL7 or PACS - A61B: DIAGNOSIS; SURGERY; IDENTIFICATION (usefulness limited to only animals A61D) - G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL - G16H: HEALTHCARE INFORMATICS, i.e. INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR THE HANDLING OR PROCESSING OF MEDICAL OR HEALTHCARE DATA ## Abstract Provided is an image processing device including a specifying unit configured to specify a part of a living body within a first image on the basis of a characteristic amount of the first image capturing skin of the living body, and a setting unit configured to set a capturing condition under which a second image indicating a state of the skin of the part is captured in response to the specified part. ## Claims ### Claim 1 An image processing device comprising: a central processing unit (CPU) configured to execute a program, in which upon execution of the program the CPU is caused to operate as: a characteristic analysis unit configured to extract a characteristic amount of a first image; a learning unit configured to accumulate learning data, to determine when a predetermined amount of learning data has been accumulated, and when a determination result thereof indicates that the predetermined amount of learning data has been accumulated to generate a discriminator based on the accumulated learning data, said discriminator being identification information for identifying a part of a living body on the basis of the characteristic amount; a specifying unit configured to specify the part of the living body within the first image on the basis of the characteristic amount of the first image capturing skin of the living body extracted by the characteristic analysis unit and the identification information learned by the learning unit; and a setting unit configured to set a number of capturing conditions under which a second image indicating a state of the skin of the part is captured in response to the specified part, in which one of the capturing conditions set by the setting unit is a depth of a focus location from a surface of the part based on a measurement depth value indicative of how deep a measurement is to be performed from a surface of the skin part and another one of the capturing conditions set by the setting unit is a set polarization direction which indicates a relationship between a polarization direction of illumination light and a polarization direction of incident light incident on an image sensor, in which the set polarization direction has a value selected from one of a parallel value, an orthogonal value, or a no value, and in which the parallel value indicates that the polarization direction of illumination light is parallel to the polarization direction of incident light, the orthogonal value indicates that the polarization direction of the illumination light is orthogonal to the polarization direction of incident light, and the no value indicates that there is no polarization between the illumination light and the incident light. ### Claim 2 (depends on 1) The image processing device according to claim 1, in which upon execution of the program the CPU is further caused to operate as: a measurement unit configured to measure the state of the skin of the specified part on the basis of the second image captured under the set capturing conditions. ### Claim 3 (depends on 2) The image processing device according to claim 2, wherein the measurement unit measures at least one of texture, a wrinkle, a spot, and a keratin plug of the skin in the specified part. ### Claim 4 (depends on 2) The image processing device according to claim 2, further comprising: a display control unit configured to control display of a measurement result of the part. ### Claim 5 (depends on 1) The image processing device according to claim 1, wherein the setting unit in addition to the depth and the set polarization direction sets at least one of a wavelength of light used to capture the second image and a capturing magnification on the basis of at least one of the part and measurement items in the part. ### Claim 6 (depends on 1) The image processing device according to claim 1, further comprising: a capturing unit configured to capture the living body. ### Claim 7 An image processing method comprising: by an image processing device, extracting a characteristic amount of a first image; accumulating learning data, determining when a predetermined amount of learning data has been accumulated, and when a determination result thereof indicates that the predetermined amount of learning data has been accumulated generating a discriminator based on the accumulated learning data, said discriminator being identification information for identifying a part of a living body on the basis of the characteristic amount; specifying the part of the living body within the first image on the basis of the extracted characteristic amount of the first image capturing skin of the living body and the learned identification information; and setting a number of capturing conditions under which a second image indicating a state of the skin of the part is captured in response to the specified part, in which one of the set capturing conditions is a depth of a focus location from a surface of the part based on a measurement depth value indicative of how deep a measurement is to be performed from a surface of the skin part and another one of the set capturing conditions is a set polarization direction which indicates a relationship between a polarization direction of illumination light and a polarization direction of incident light incident on an image sensor, in which the set polarization direction has a value selected from one of a parallel value, an orthogonal value, or a no value, and in which the parallel value indicates that the polarization direction of illumination light is parallel to the polarization direction of incident light, the orthogonal value indicates that the polarization direction of the illumination light is orthogonal to the polarization direction of incident light, and the no value indicates that there is no polarization between the illumination light and the incident light. ### Claim 8 A non-transitory computer-readable recording medium having recorded thereon a program for causing a computer to execute processes including: extracting a characteristic amount of a first image; accumulating learning data, determining when a predetermined amount of learning data has been accumulated, and when a determination result thereof indicates that the predetermined amount of learning data has been accumulated generating a discriminator based on the accumulated learning data, said discriminator being identification information for identifying a part of a living body on the basis of the characteristic amount; specifying the part of the living body within the first image on the basis of the extracted characteristic amount of the first image capturing skin of the living body and the learned identification information; and setting a number of capturing conditions under which a second image indicating a state of the skin of the part is captured in response to the specified part, in which one of the set capturing conditions is a depth of a focus location from a surface of the part based on a measurement depth value indicative of how deep a measurement is to be performed from a surface of the skin part and another one of the set capturing conditions is a set polarization direction which indicates a relationship between a polarization direction of illumination light and a polarization direction of incident light incident on an image sensor, in which the set polarization direction has a value selected from one of a parallel value, an orthogonal value, or a no value, and in which the parallel value indicates that the polarization direction of illumination light is parallel to the polarization direction of incident light, the orthogonal value indicates that the polarization direction of the illumination light is orthogonal to the polarization direction of incident light, and the no value indicates that there is no polarization between the illumination light and the incident light. ### Claim 9 An image processing system comprising: a capturing device; and an image processing device, wherein the image processing device is configured to operate as: a characteristic analysis unit configured to extract a characteristic amount of a first image; a learning unit configured to accumulate learning data, to determine when a predetermined amount of learning data has been accumulated, and when a determination result thereof indicates that the predetermined amount of learning data has been accumulated to generate a discriminator based on the accumulated learning data, said discriminator being identification information for identifying a part of a living body on the basis of the characteristic amount; a specifying unit configured to specify the part of the living body within the first image on the basis of the characteristic amount of the first image of skin of the living body captured by the capturing device extracted by the characteristic analysis unit and the identification information learned by the learning unit; and a setting unit configured to set, on the capturing device, a number of capturing conditions under which a second image indicating a state of the skin of the part is captured in response to the specified part, in which one of the capturing conditions set by the setting unit is a depth of a focus location from a surface of the part based on a measurement depth value indicative of how deep a measurement is to be performed from a surface of the skin part and another one of the capturing conditions set by the setting unit is a set polarization direction which indicates a relationship between a polarization direction of illumination light and a polarization direction of incident light incident on an image sensor, in which the set polarization direction has a value selected from one of a parallel value, an orthogonal value, or a no value, and in which the parallel value indicates that the polarization direction of illumination light is parallel to the polarization direction of incident light, the orthogonal value indicates that the polarization direction of the illumination light is orthogonal to the polarization direction of incident light, and the no value indicates that there is no polarization between the illumination light and the incident light.