Information processing device, operation method of information processing device, and program of information processing device

Abstract

To determine an impression of a surface state of the skin with a higher degree of precision.SOLUTION: An information processing device includes: a storage unit for storing a captured image obtained by imaging a skin texture; and a control unit for deriving a distribution pattern of a gradation value pair by which a feature image in the captured image is maintained when the captured image is subjected to filtering with a plurality of gradation values, deriving an extended pattern of a plurality of linear regions having gradation values different from those of the other regions in the captured image, and generating a model for deriving a score indicating the skin texture regularity in a second captured image based on the second captured image by learning correspondence between the score indicating the skin texture regularity in a first captured image and a combination of the distribution pattern of the gradation value pair derived from the first captured image and an extended pattern of the plurality of linear regions.SELECTED DRAWING: Figure 2

Description

[Technical Field]

[0001] The present disclosure relates to an information processing device, an operation method of the information processing device, and a program for the information processing device. [Background technology]

[0002] The surface condition of a person's facial skin affects the impression of the observer and changes depending on various factors. Changes in surface condition are manifested, for example, as roughness of the skin texture, and are a cosmetic concern. Various techniques for evaluating such skin surface condition have been proposed (e.g., Patent Documents 1 to 4). [Prior art documents] [Patent documents]

[0003] [Patent Document 1] Japanese Patent Application Laid-Open No. 2016-104124 [Patent Document 2] Japanese Patent Application Publication No. 2019-092694 [Patent Document 3] Japanese Patent Publication No. 2023-166041 [Patent Document 4] International Publication No. 2020 / 189754 Summary of the Invention [Problem to be solved by the invention]

[0004] The observer's impression of the surface condition of the facial skin is subjective, and the criteria for judgment are unclear and variable. Therefore, it is desirable to accurately judge the impression that the surface condition may give to the observer using more uniform criteria.

[0005] In view of the above, the following discloses an information processing device and the like that can determine the impression of the skin surface condition with higher accuracy. [Means for solving the problem]

[0006] In order to solve the above problem, the information processing device of the present disclosure has a memory unit that stores captured images obtained by capturing skin texture, and a control unit that derives a distribution pattern of gradation value pairs such that a characteristic image in the captured image is maintained when the captured image is filtered with a plurality of gradation values, derives an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image, and generates a model for deriving the score indicating the regularity of the skin texture in a first captured image based on a second captured image by learning the correspondence between the score indicating the regularity of the skin texture in the first captured image and a combination of the distribution pattern of the gradation value pairs and the extension pattern of the plurality of linear regions derived from the first captured image.

[0007] Another information processing device according to the present disclosure includes a memory unit that stores captured images obtained by capturing skin texture, and a control unit that derives a distribution pattern of gradation value pairs that maintains a characteristic image in the captured image when the captured image is filtered with a plurality of gradation values, derives an extension pattern of a plurality of linear regions that have gradation values ​​different from other regions in the captured image, and derives a score that indicates the regularity of the skin texture in a first captured image based on a second captured image using a model generated by learning a correspondence between the score and a combination of the distribution pattern of gradation value pairs derived from the first captured image and the extension pattern of the plurality of linear regions.

[0008] An operating method of an information processing device in the present disclosure includes the steps of: acquiring an image obtained by capturing an image of skin texture; deriving a distribution pattern of gradation value pairs such that a characteristic image in the captured image is maintained when the captured image is filtered with a plurality of gradation values; deriving an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image; and generating a model for deriving the score indicating the regularity of the skin texture in a first captured image based on a second captured image by learning the correspondence between a score indicating the regularity of the skin texture in the first captured image and a combination of the distribution pattern of the gradation value pairs derived from the first captured image and the extension pattern of the plurality of linear regions.

[0009] Another operating method of an information processing device according to the present disclosure includes the steps of: acquiring an image obtained by capturing an image of skin texture; deriving a distribution pattern of gradation value pairs such that a characteristic image in the captured image is maintained when the captured image is filtered with a plurality of gradation values; deriving an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image; and deriving the score indicating the regularity of the skin texture in a first captured image based on a second captured image using a model generated by learning the correspondence between a score indicating the regularity of the skin texture in the first captured image and a combination of the distribution pattern of the gradation value pairs derived from the first captured image and the extension pattern of the plurality of linear regions.

[0010] A program for an information processing device in the present disclosure is executed by an information processing device, causing the information processing device to perform the following steps: acquiring an image obtained by capturing an image of skin texture; deriving a distribution pattern of gradation value pairs such that a characteristic image in the captured image is maintained when the captured image is filtered with a plurality of gradation values; deriving an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image; and generating a model for deriving the score indicating the regularity of the skin texture in a first captured image based on a second captured image by learning the correspondence between a score indicating the regularity of the skin texture in the first captured image and a combination of the distribution pattern of the gradation value pairs and the extension patterns of the plurality of linear regions derived from the first captured image.

[0011] Another information processing device program in the present disclosure is executed by an information processing device, causing the information processing device to perform the following steps: acquiring an image obtained by capturing an image of skin texture; deriving a distribution pattern of gradation value pairs such that a characteristic image in the captured image is maintained when the captured image is filtered with a plurality of gradation values; deriving an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image; and deriving the score indicating the regularity of the skin texture in a first captured image based on a second captured image using a model generated by learning the correspondence between a score indicating the regularity of the skin texture in the first captured image and a combination of the distribution pattern of the gradation value pairs derived from the first captured image and the extension pattern of the plurality of linear regions. [Effects of the Invention]

[0012] According to the information processing device and the like of the present disclosure, it is possible to determine the impression of the skin surface condition with higher accuracy. [Brief explanation of the drawings]

[0013] [Figure 1] FIG. 1 is a diagram illustrating an example of a configuration including an information processing device. [Figure 2] FIG. 10 is a flowchart illustrating an example of an operation procedure of the information processing device. [Figure 3] FIG. 10 is a flowchart illustrating an example of an operation procedure of the information processing device. [Figure 4] FIG. 10 is a diagram illustrating an example of a corrected image. [Figure 5] FIG. 10 is a diagram illustrating filtering. [Figure 6] FIG. 10 is a diagram illustrating a feature image. [Figure 7] FIG. 10 is a diagram illustrating aggregate information of surviving tone value pairs. [Figure 8] FIG. 10 is a flowchart illustrating an example of an operation procedure of the information processing device. [Figure 9A] FIG. 10 is a diagram illustrating a linear region. [Figure 9B] FIG. 10 is a diagram illustrating the direction of a linear region. [Figure 10] FIG. 10 is a flowchart illustrating an example of an operation procedure of the information processing device. [Figure 11] FIG. 10 is a diagram showing an example of a display on a terminal device. DETAILED DESCRIPTION OF THE INVENTION

[0014] Hereinafter, an embodiment of the present invention will be described.

[0015] [System Configuration] FIG. 1 is a diagram showing an example of the configuration of an embodiment of the present invention. The information processing system 1 includes a server device 10 and a terminal device 12 that are connected to each other via a network 11 so that they can communicate with each other. In the information processing system 1, the server device 10 performs information processing using various information sent from the terminal device 12. The terminal device 12 is, for example, one or more personal computers. The personal computer may include a tablet terminal device, a smartphone, etc. The server device 10 corresponds to the "information processing device" in this embodiment. The server device 10 is, for example, one or more server computers. The server device 10 may be a single server computer or multiple server computers that cooperate to execute the operations in this embodiment. The network 11 is, for example, a local area network (LAN), the Internet, an ad hoc network, a metropolitan area network (MAN), a mobile communication network, or other networks, or any combination thereof.

[0016] In this embodiment, the server device 10 receives various information from the terminal device 12 and performs information processing to determine the regularity of the skin texture in a captured image (hereinafter referred to as a skin texture image) obtained by capturing an image of a person's skin, for example, the skin texture of the face. Generally, the higher the regularity of the skin texture, the better the impression the observer will have. The regularity of the skin texture depends on the state of the skin grooves extending on the surface of the skin. Specifically, the higher the index, such as the uniformity of the area of ​​the skin ridges between the skin grooves, the clarity of the skin grooves, or the anisotropy of the skin grooves (dissimilarity in the extension directions of multiple skin grooves), the higher the regularity of the skin texture is determined to be. When the observer subjectively evaluates the skin texture captured in the skin texture image and assigns a score indicating the regularity (hereinafter referred to as a regularity score), the server device 10 performs information processing to derive a regularity score for a new skin texture image based on the correspondence between the state of the skin grooves and the regularity score.

[0017] In the server device 10, the storage unit 102 stores captured images obtained by capturing skin texture, i.e., texture images. The control unit 103 derives a distribution pattern of gradation value pairs that maintains a characteristic image in the texture image when filtering the texture image with multiple gradation values ​​(hereinafter, this process is referred to as a distribution pattern derivation process). The control unit 103 also derives an extended pattern of multiple linear regions that have different gradation values ​​from other regions in the texture image (hereinafter, this process is referred to as an extended pattern derivation process). The control unit 103 also learns the correspondence between the regularity score assigned to the regularity of the skin texture in the texture image and the combination of the distribution pattern of gradation value pairs and the extended pattern of the multiple linear regions, thereby generating a model (hereinafter, referred to as a regularity assessment model) that derives a regularity score indicating the regularity of the skin texture in a new texture image based on the new texture image. The control unit 103 also uses the regularity assessment model to derive a regularity score indicating the regularity of the skin texture in the new texture image based on the new texture image. The server device 10 derives the regularity score using the regularity assessment model that reflects the observer's assessment results, enabling a uniform evaluation of regularity that is closer to the observer's assessment without relying on the observer's subjectivity. This allows for a more accurate assessment of the impression of the skin surface condition.

[0018] [Configuration example of server device 10] The server device 10 includes a communication unit 101, a storage unit 102, and a control unit 103. When the server device 10 is configured with two or more server computers, these components are appropriately arranged in the two or more server computers.

[0019] The communication unit 101 includes one or more communication interfaces. The communication interface is, for example, a LAN interface. The communication unit 101 receives information used in the operation of the server device 10 and transmits information obtained by the operation of the server device 10. The server device 10 is connected to a network 11 by the communication unit 101 and communicates information with a terminal device 12 via the network 11.

[0020] The storage unit 102 includes, for example, one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these, that function as a main storage device, an auxiliary storage device, or a cache memory. The semiconductor memories are, for example, RAM (Random Access Memory) or ROM (Read Only Memory). The RAM is, for example, SRAM (Static RAM) or DRAM (Dynamic RAM). The ROM is, for example, EEPROM (Electrically Erasable Programmable ROM). The storage unit 102 stores information used in the operation of the control unit 103 and information obtained by the operation of the control unit 103.

[0021] The control unit 103 includes one or more processors, one or more dedicated circuits, or a combination thereof. The processor is, for example, a general-purpose processor such as a CPU (Central Processing Unit), or a dedicated processor such as a GPU (Graphics Processing Unit) specialized for a specific process. The dedicated circuit is, for example, an FPGA (Field-Programmable Gate Array), an ASIC (Application Specific Integrated Circuit), etc. The control unit 103 executes information processing related to the operation of the server device 10 while controlling each unit of the server device 10.

[0022] The functions of the server device 10 are realized by a processor included in the control unit 103 executing a control program. The control program is a program for causing the processor to function as the control unit 103. Alternatively, some or all of the functions of the server device 10 may be realized by a dedicated circuit included in the control unit 103. Alternatively, the control program may be stored in a non-transitory recording / storage medium readable by the control unit 103, and read by the control unit 103 from the medium.

[0023] [Configuration example of terminal device 12] The terminal device 12 includes a communication unit 121 , a storage unit 122 , a control unit 123 , an input unit 125 , and an output unit 126 .

[0024] The communication unit 121 includes a communication module compatible with wired or wireless LAN standards, a module compatible with mobile communication standards such as LTE (Long Term Evolution), 4G (4th Generation), or 5G (5th Generation), etc. The terminal device 12 is connected to the network 11 by the communication unit 121 via a nearby router device or a mobile communication base station, and performs information communication with the server device 10, etc. via the network 11.

[0025] The storage unit 122 includes one or more semiconductor memories, one or more magnetic memories, one or more optical memories, or a combination of at least two of these. The semiconductor memories are, for example, RAM or ROM. The RAM is, for example, SRAM or DRAM. The ROM is, for example, EEPROM. The storage unit 122 functions as, for example, a main storage device, an auxiliary storage device, or a cache memory. The storage unit 122 stores information used in the operation of the control unit 123 and information obtained by the operation of the control unit 123.

[0026] The control unit 123 has, for example, one or more general-purpose processors such as a CPU, an MPU (Micro Processing Unit), etc., or one or more dedicated processors such as a GPU specialized for a specific process. Alternatively, the control unit 123 may have one or more dedicated circuits such as an FPGA, an ASIC, etc. The control unit 123 performs overall control of the operation of the terminal device 12 by operating according to a control / processing program or operating according to an operating procedure implemented as a circuit. The control unit 123 then transmits and receives various information to and from the server device 10, etc. via the communication unit 121, and performs the operation according to this embodiment.

[0027] The functions of the terminal device 12 are realized by a processor included in the control unit 123 executing a control program. The control program is a program for causing the processor to function as the control unit 123. Alternatively, some or all of the functions of the terminal device 12 may be realized by a dedicated circuit included in the control unit 123. Alternatively, the control program may be stored in a non-transitory recording / storage medium readable by the control unit 123, and read by the control unit 123 from the medium.

[0028] The input unit 125 includes one or more input interfaces. The input interfaces include, for example, physical keys, capacitive keys, a pointing device, and a touch screen integrated with a display. The input interface may also include a microphone for receiving voice input, and a camera or microscope for capturing texture images. The input unit 125 receives an operation for inputting information used in the operation of the control unit 123, and sends the input information to the control unit 123. The input unit 125 also sends images captured by a camera or the like to the control unit 123.

[0029] The output unit 126 includes one or more output interfaces. The output interface is, for example, a display or a speaker. The display is, for example, an LCD (Liquid Crystal Display) or an organic EL (Electro-Luminescence) display. The output unit 126 outputs information obtained by the operation of the control unit 123.

[0030] [Operation procedure of server device 10] Fig. 2 is a flowchart illustrating an example of an operation procedure of the server device 10. The procedure in Fig. 2 is a procedure for generating an orderliness assessment model, which is executed by the control unit 103. For example, a user operates the terminal device 12 to send an instruction to the server device 10 to operate the server device 10, and in response to the instruction, the control unit 103 executes the procedure in Fig. 2.

[0031] In step S20, the control unit 103 acquires a texture image and a neatness score. The texture image is generated by capturing an image of a part of a person's face, such as a cheek or eyelid. Alternatively, the texture image may be generated by capturing an image of a part of a person's arm. The image of a person's face, arm, or other part is captured, for example, by a camera on the terminal device 12 or a microscope connected to the terminal device 12. The control unit 103 receives and acquires the texture image of the person sent from the terminal device 12 via the communication unit 101. The control unit 103 may also acquire the texture image from an open source. The neatness score is a score assigned in response to an evaluator's visual evaluation of the neatness of the texture of each texture image, and may be, for example, a score with a multi-level value representing the degree of neatness. The neatness score is, for example, entered into the terminal device 12 by the evaluator who visually inspects the texture image displayed on the terminal device 12, linked to the texture image, and sent to the server device 10, where it is acquired by the control unit 103. The acquired texture image and neatness score are stored in the storage unit 102 in association with each other.

[0032] In step S21, the control unit 103 executes a distribution pattern derivation process. The detailed operation procedure of step S21 is shown in FIG.

[0033] In step S30 of Fig. 3, the control unit 103 generates a corrected image by performing brightness correction processing on the skin texture image. Fig. 4 is a schematic diagram showing an example of the corrected image. The control unit 103 uses, for example, wavelet transform to generate a corrected image 40 that contains only information in a predetermined frequency domain. In the corrected image 40, noise components unrelated to the unevenness of the skin surface in the skin texture image have been removed.

[0034] In step S31 of FIG. 3, the control unit 103 performs filtering on the texture image to detect a feature image.

[0035] FIG. 5 is a diagram illustrating filtering. The control unit 103 sequentially binarizes the corrected image 40 using multiple thresholds to generate binarized images corresponding to each threshold. In graph 50, the horizontal axis represents the one-dimensional position of a pixel in the corrected image 40, and the vertical axis represents the gradation value of each pixel. The control unit 103 gradually changes the binarization threshold from thresholds t1 to t6, assigning white to pixels having gradation values ​​above each threshold and black to pixels having gradation values ​​below each threshold. In this way, filtered images 51-1, 51-2, 51-3, 51-4, 51-5, and 51-6 are obtained by filtering using thresholds t1, t2, t3, t4, t5, and t6, respectively. For example, in filtered image 51-1, all pixels have gradation values ​​below the threshold, so black is assigned to all pixels. In filtered image 51-6, all pixels have gradation values ​​above the threshold, so white is assigned to all pixels. In the filtered images 51-2, 51-3, 51-4 and 51-5, black regions having areas corresponding to the number of pixels with gradation values ​​above the threshold are formed, and white regions having areas corresponding to the number of pixels with gradation values ​​equal to or less than the threshold are formed.

[0036] FIG. 6 is a diagram illustrating a feature image. Filtered images 60-1, 60-2, and 60-3 schematically show the transition of white and black pixel regions when the control unit 103 filters the corrected image 40 using multiple thresholds. In the filtered images 60-1, 60-2, and 60-3, white pixel regions (hereinafter referred to as white regions) are represented by dots or hatching, and black pixel regions (hereinafter referred to as black regions) are represented by outlined regions. As the control unit 103 gradually lowers the threshold, the white region 61 expands in the order of the filtered images 60-1, 60-2, and 60-3. As the white region 61 expands, adjacent white regions 61 connect with each other, as shown in the filtered image 60-2. Then, a gap-like black region 62-1 appears within the connected white regions 61. The control unit 103 detects this gap-like black region 62-1 as a feature image. As the white region 61 expands further, the black region 62-1 is eroded by the white region 61 and disappears, as shown in the filtered image 60-3. Meanwhile, another black region 62-2 appears and is detected as another feature image. As filtering continues, the black region 62-2 disappears. In this way, the control unit 103 detects feature images that appear in the filtered image when filtering is performed, and stores in the storage unit 102 the threshold value at which each feature image appears (hereinafter referred to as the appearance gradation value) and the threshold value at which each feature image disappears (hereinafter referred to as the disappearance gradation value) as a survival gradation value pair. In this way, a feature image is an area having a black gradation value outside the range of the survival gradation value pair, surrounded by an area of ​​pixels having a white gradation value within the range of the survival gradation value pair.

[0037] In step S32 of Fig. 3, the control unit 103 determines a surviving gradation value pair. When performing filtering to detect feature images in step S31, the control unit 103 determines a surviving gradation value pair including an appearance gradation value and a disappearance gradation value for each feature image. In the example of Fig. 6, a surviving gradation value pair corresponding to black region 62-1 and a surviving gradation value pair corresponding to black region 62-2 are determined. The determined surviving gradation value pairs are stored in the storage unit 102.

[0038] 3, the control unit 103 stores the filtered images generated while performing filtering using all thresholds in the storage unit 102 together with information about the thresholds, and determines the appearance and disappearance of a feature image in the stored series of filtered images one after another, and can determine a survival gradation value pair by reading out the appearance gradation value and disappearance gradation value from the storage unit 102. Alternatively, the control unit 103 may determine the appearance or disappearance of a feature image in the generated filtered images each time the threshold is switched during the filtering process, store the thresholds used for determining appearance and disappearance as the appearance gradation value and disappearance gradation value in the storage unit 102, and determine a survival gradation value pair by reading out the appearance gradation value and disappearance gradation value from the storage unit 102.

[0039] In step S33, the control unit 103 generates aggregated information of the surviving gradation value pairs. The control unit 103 generates aggregated information that aggregates one or more surviving gradation value pairs for one corrected image. An example of the aggregated information is shown in FIG. 7. FIG. 7 shows a persistence map 70 in which the horizontal axis indicates the appearance gradation value and the vertical axis indicates the disappearance gradation value. Here, an example is shown in which five surviving gradation value pairs 71-1 to 71-5 obtained by filtering one corrected image are mapped. For example, the surviving gradation value pairs 71-1 and 71-2 correspond to the surviving gradation value pairs of the feature images 62-1 and 62-2 in FIG. 6, respectively. This aggregated information corresponds to a distribution pattern. Alternatively, the control unit 103 may perform a regression analysis on the surviving gradation value pairs mapped to the persistence map 70 to derive a linear expression corresponding to the distribution of the surviving gradation value pairs as a distribution pattern.

[0040] The control unit 103 derives a distribution pattern by executing steps S30 to S33, and then ends step S21 in FIG.

[0041] 2, the control unit 103 executes an extended pattern derivation step. The detailed operation procedure of step S22 is shown in FIG.

[0042] In step S80, the control unit 103 extracts linear regions from the texture image acquired in step S20. The linear regions are, for example, skin grooves, which are elongated regions having different color gradation values ​​from other regions in the texture image. The elongated regions are, for example, rectangular regions with any aspect ratio. For example, as schematically shown in FIG. 9A , six linear regions 91-1, 91-2, 91-3, 91-4, 91-5, and 91-6 corresponding to skin grooves 91 are detected in the texture image 90. The control unit 103 extracts the skin grooves 91 using any image processing method, such as a Frangi vessel enhancement filter. Before extracting the skin grooves 91, the control unit 103 may apply image processing, such as an average filter, to the texture image to remove information other than the skin grooves 91, such as moles and blemishes.

[0043] In step S81, the control unit 103 derives the direction of each linear region. The direction of a linear region can be derived by any method. In one example, the direction is derived as the angle of a straight line along the longitudinal direction of the linear region in any rotation direction relative to a reference line. For example, as schematically shown in FIG. 9B , the control unit 103 derives the directions of the linear regions 91-1, 91-2, 91-3, 91-4, 91-5, and 91-6 as the angles θ1, θ2, θ3, θ4, θ5, and θ6 formed counterclockwise by the straight lines along the longitudinal directions of the linear regions 91-1, 91-2, 91-3, 91-4, 91-5, and 91-6, respectively, relative to a horizontal line 92 in the texture image 90.

[0044] In step S82, the control unit 103 derives the directional similarity of each linear region. The directional similarity of the linear regions can be derived by any method, but in one example, it is derived using cosine similarity. For example, the control unit 103 derives the mutual cosine similarity of angles θ1, θ2, θ3, θ4, θ5, and θ6 of linear regions 91-1, 91-2, 91-3, 91-4, 91-5, and 91-6 shown in FIG. 9B. Such similarity information corresponds to the extension pattern.

[0045] The control unit 103 derives the extension pattern by executing steps S80 to S82, and then ends step S22 in FIG.

[0046] In a modified example of the extended pattern derivation, the control unit 103 may tally up the area values ​​of the linear regions at any angle, for example, at 30 degrees, 60 degrees, 90 degrees, 120 degrees, and 150 degrees counterclockwise from the horizontal line in the texture image 90, and calculate the variance value for each angle to define the extended pattern.

[0047] In step S23 of FIG. 2, the control unit 103 generates an orderliness assessment model. The control unit 103 generates training data that associates the orderliness scores obtained in step S20 associated with each texture image with combinations of distribution patterns and extension patterns derived from each texture image. The control unit 103 then performs machine learning using any method using the generated training data to generate an orderliness assessment model. Machine learning includes any supervised learning method, such as linear regression. The orderliness assessment model is a model for deriving an orderliness score corresponding to a new combination of distribution patterns and extension patterns derived from a texture image when the combination is input. This orderliness assessment model enables orderliness assessment taking into account the uniformity of the area of ​​the skin ridges between skin furrows, the clarity of the skin furrows, and the anisotropy of the skin furrows. Information for implementing the orderliness assessment model generated in this way is stored in the storage unit 102.

[0048] Fig. 10 is a flowchart illustrating another example of the operation procedure of the server device 10. The procedure in Fig. 10 is executed by the control unit 103 to derive the regularity of the texture in a new texture image using a regularity determination model. For example, a user operates the terminal device 12 to send an instruction to the server device 10 to operate the server device 10, and in response to the instruction, the control unit 103 executes the procedure in Fig. 10.

[0049] In step S100, the control unit 103 acquires a texture image to be determined. The server device 10 acquires, from the terminal device 12, a texture image obtained by the terminal device 12 capturing an image of a person's face or a texture image acquired by the terminal device 12 from an open source. The acquired texture image is stored in the storage unit 102.

[0050] In step S101, the control unit 103 executes a distribution pattern derivation process for the texture image to be determined. The detailed operation procedure of step S101 is the same as the operation procedure shown in FIG.

[0051] In step S102, the control unit 103 executes an extended pattern derivation process for the texture image to be determined. The detailed operation procedure of step S102 is the same as the operation procedure shown in FIG.

[0052] In step S103, the control unit 103 determines the orderliness based on the combination of the distribution pattern derived in step S101 and the extension pattern derived in step S102. For example, the control unit 103 derives an orderliness score corresponding to the combination of the distribution pattern and the extension pattern using an orderliness determination model. The orderliness score thus derived is sent to the terminal device 12 and output to the evaluator on the terminal device 12 by display or the like.

[0053] FIG. 11 shows an example of a display on the terminal device 12. In step S102, the terminal device 12 displays an output screen 1100. The output screen 1100 displays a texture image 1101, a persistence diagram 1102 as aggregate information of the persistence gradation value pairs corresponding to the texture image 1101, an average appearance / disappearance gradation value 1103, linear region information 1104, and an orderliness score 1105 derived from the texture image 1101. The linear region information 1104 includes corrected images obtained by filtering the linear regions in the texture image 1101 in the 0-degree, 60-degree, and 120-degree directions, the area values ​​of the linear regions in each direction, and a variance score. By checking the output screen 1100, the evaluator can evaluate orderliness based on more objective and uniform criteria. This allows for a more accurate assessment of the impression of the skin surface condition.

[0054] 10 is preferably executed by a terminal device 12 installed in a cosmetics store or the like to determine the neatness of the skin texture of a user visiting the store. When a counselor at the store acquires a skin texture image of the user using the terminal device 12 and sends it to the server device 10, the neatness score derived by the server device 10 is sent to the terminal device 12 and output.

[0055] According to the above-described embodiment, by deriving an orderliness score using an orderliness judgment model that reflects the observer's judgment results from the distribution pattern of gradation value pairs that indicate the state of the skin grooves in the new skin texture image and the extension pattern of the linear region, it is possible to make a uniform orderliness evaluation that is closer to the observer's evaluation without relying on the observer's subjectivity, thereby making it possible to more accurately judge the impression of the skin surface condition.

[0056] In the above, the operation procedure has been described assuming that the server device 10 corresponds to an "information processing device." However, the terminal device 12 may execute some or more of the operations of the server device 10, and the server device 10 and the terminal device 12 may cooperate to configure an "information processing device," or the terminal device 12 may independently correspond to an "information processing device."

[0057] In the above-described embodiment, the processing / control program that defines the operation of the terminal device 12 may be stored in the memory unit 102 of the server device 10 or in the memory unit of another server device, and may be downloaded to the terminal device 12 via the network 11, or may be stored in a computer-readable non-transitory recording / storage medium and read by the terminal device 12 from the medium.

[0058] Although the embodiments have been described above based on the drawings and examples, it should be noted that those skilled in the art can easily make various modifications and alterations based on the present disclosure. Therefore, it should be noted that these modifications and alterations are included in the scope of the present disclosure. For example, the functions included in each means, step, etc. can be rearranged so as not to be logically inconsistent, and multiple means, steps, etc. can be combined or divided into one. [Explanation of symbols]

[0059] 10: Server device 11: Network 12: Terminal device 101, 121: Communications Department 102, 122: Storage section 103, 123: control unit 125: Input section 126: Output section

Claims

1. a storage unit for storing captured images obtained by capturing images of skin texture; a control unit that derives a distribution pattern of gradation value pairs such that a characteristic image in the captured image is maintained when the captured image is filtered with a plurality of gradation values, derives an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image, and learns a correspondence between a score indicating the regularity of the skin texture in a first captured image and a combination of the distribution pattern of the gradation value pairs and the extension pattern of the plurality of linear regions derived from the first captured image, thereby generating a model for deriving the score indicating the regularity of the skin texture in the second captured image based on the second captured image. Information processing device.

2. a storage unit for storing captured images obtained by capturing images of skin texture; a control unit that derives a distribution pattern of gradation value pairs such that a characteristic image in the captured image persists when the captured image is filtered with a plurality of gradation values, derives an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image, and derives the score indicating the regularity of the skin texture in the first captured image based on the second captured image using a model generated by learning a correspondence between the score indicating the regularity of the skin texture in the first captured image and a combination of the distribution pattern of the gradation value pairs and the extension pattern of the plurality of linear regions derived from the first captured image. Information processing device.

3. In claim 1 or 2, The pair of gradation values ​​is a gradation value when the characteristic image appears and a gradation value when the characteristic image disappears. Information processing device.

4. In claim 3, the characteristic image is a region having a second gradation value outside the range of the gradation value pair, surrounded by a region of pixels having a first gradation value within the range of the gradation value pair; Information processing device.

5. In claim 1 or 2, the extension pattern of the linear regions includes a similarity between the directions of the plurality of linear regions; Information processing device.

6. acquiring an image obtained by imaging the texture of the skin; a step of deriving a distribution pattern of gradation value pairs such that a characteristic image in the captured image persists when the captured image is filtered with a plurality of gradation values; deriving an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image; generating a model for deriving the score indicating the regularity of the skin texture in the second captured image based on the second captured image by learning a correspondence between the score indicating the regularity of the skin texture in the first captured image and a combination of a distribution pattern of the gradation value pairs and an extension pattern of the plurality of linear regions derived from the first captured image; A method for operating an information processing device.

7. acquiring an image obtained by imaging the texture of the skin; a step of deriving a distribution pattern of gradation value pairs such that a characteristic image in the captured image persists when the captured image is filtered with a plurality of gradation values; deriving an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image; deriving a score indicating the regularity of the skin texture in the second captured image based on the second captured image using a model generated by learning a correspondence between a score indicating the regularity of the skin texture in the first captured image and a combination of a distribution pattern of the gradation value pairs and an extension pattern of the plurality of linear regions derived from the first captured image, A method for operating an information processing device.

8. In claim 6 or 7, The pair of gradation values ​​is a gradation value when the characteristic image appears and a gradation value when the characteristic image disappears. A method for operating an information processing device.

9. In claim 8, the characteristic image is a region having a second gradation value outside the range of the gradation value pair, surrounded by a region of pixels having a first gradation value within the range of the gradation value pair; A method for operating an information processing device.

10. In claim 6 or 7, the extension pattern of the linear regions includes a similarity between the directions of the plurality of linear regions; A method for operating an information processing device.

11. When executed by an information processing device, the information processing device acquiring an image obtained by imaging the texture of the skin; a step of deriving a distribution pattern of gradation value pairs such that a characteristic image in the captured image persists when the captured image is filtered with a plurality of gradation values; deriving an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image; and generating a model for deriving the score indicating the regularity of the skin texture in the second captured image based on the second captured image by learning the correspondence between the score indicating the regularity of the skin texture in the first captured image and the combination of the distribution pattern of the gradation value pairs and the extension pattern of the plurality of linear regions derived from the first captured image. A program for an information processing device.

12. When executed by an information processing device, the information processing device acquiring an image obtained by imaging the texture of the skin; a step of deriving a distribution pattern of gradation value pairs such that a characteristic image in the captured image persists when the captured image is filtered with a plurality of gradation values; deriving an extension pattern of a plurality of linear regions having gradation values ​​different from other regions in the captured image; deriving a score indicating the regularity of the skin texture in the second captured image based on the second captured image using a model generated by learning the correspondence between a score indicating the regularity of the skin texture in the first captured image and a combination of a distribution pattern of the gradation value pairs and an extension pattern of the plurality of linear regions derived from the first captured image; A program for an information processing device.

13. In claim 11 or 12, The pair of gradation values ​​is a gradation value when the characteristic image appears and a gradation value when the characteristic image disappears. A program for an information processing device.

14. In claim 13, the characteristic image is a region having a second gradation value outside the range of the gradation value pair, surrounded by a region of pixels having a first gradation value within the range of the gradation value pair; A program for an information processing device.

15. In claim 11 or 12, the extension pattern of the linear regions includes a similarity between the directions of the plurality of linear regions; A program for an information processing device.

Images