WO2014027522A1 - 画像処理装置、画像処理方法、プログラムおよび画像処理システム - Google Patents
画像処理装置、画像処理方法、プログラムおよび画像処理システム Download PDFInfo
- Publication number
- WO2014027522A1 WO2014027522A1 PCT/JP2013/068140 JP2013068140W WO2014027522A1 WO 2014027522 A1 WO2014027522 A1 WO 2014027522A1 JP 2013068140 W JP2013068140 W JP 2013068140W WO 2014027522 A1 WO2014027522 A1 WO 2014027522A1
- Authority
- WO
- WIPO (PCT)
- Prior art keywords
- feature
- image
- skin
- feature amount
- image processing
- Prior art date
Links
- 238000012545 processing Methods 0.000 title claims abstract description 138
- 238000003672 processing method Methods 0.000 title description 5
- 239000011148 porous material Substances 0.000 claims abstract description 108
- 238000000605 extraction Methods 0.000 claims abstract description 92
- 238000004364 calculation method Methods 0.000 claims abstract description 84
- 238000000926 separation method Methods 0.000 claims abstract description 26
- 239000000284 extract Substances 0.000 claims abstract description 23
- XUMBMVFBXHLACL-UHFFFAOYSA-N Melanin Chemical compound O=C1C(=O)C(C2=CNC3=C(C(C(=O)C4=C32)=O)C)=C2C4=CNC2=C1C XUMBMVFBXHLACL-UHFFFAOYSA-N 0.000 claims description 112
- 238000003384 imaging method Methods 0.000 claims description 54
- 238000004458 analytical method Methods 0.000 claims description 40
- 238000000034 method Methods 0.000 claims description 25
- 230000010365 information processing Effects 0.000 claims description 13
- 230000008859 change Effects 0.000 claims description 8
- 206010000496 acne Diseases 0.000 abstract description 6
- -1 as feature sections Substances 0.000 abstract 1
- 238000007781 pre-processing Methods 0.000 description 17
- 238000005516 engineering process Methods 0.000 description 15
- 239000011159 matrix material Substances 0.000 description 14
- 230000008569 process Effects 0.000 description 13
- 230000006870 function Effects 0.000 description 10
- 230000010287 polarization Effects 0.000 description 8
- 239000000203 mixture Substances 0.000 description 7
- 238000001514 detection method Methods 0.000 description 5
- 230000001678 irradiating effect Effects 0.000 description 5
- 238000005286 illumination Methods 0.000 description 4
- 238000003705 background correction Methods 0.000 description 3
- 238000004891 communication Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000009466 transformation Effects 0.000 description 3
- 208000002874 Acne Vulgaris Diseases 0.000 description 2
- 238000006243 chemical reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000004065 semiconductor Substances 0.000 description 2
- NAWXUBYGYWOOIX-SFHVURJKSA-N (2s)-2-[[4-[2-(2,4-diaminoquinazolin-6-yl)ethyl]benzoyl]amino]-4-methylidenepentanedioic acid Chemical compound C1=CC2=NC(N)=NC(N)=C2C=C1CCC1=CC=C(C(=O)N[C@@H](CC(=C)C(O)=O)C(O)=O)C=C1 NAWXUBYGYWOOIX-SFHVURJKSA-N 0.000 description 1
- 241000894006 Bacteria Species 0.000 description 1
- 230000002730 additional effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000002537 cosmetic Substances 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000414 obstructive effect Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 210000002374 sebum Anatomy 0.000 description 1
- 230000003595 spectral effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000001629 suppression Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
- G06T7/0014—Biomedical image inspection using an image reference approach
- G06T7/0016—Biomedical image inspection using an image reference approach involving temporal comparison
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/0059—Measuring for diagnostic purposes; Identification of persons using light, e.g. diagnosis by transillumination, diascopy, fluorescence
- A61B5/0077—Devices for viewing the surface of the body, e.g. camera, magnifying lens
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/44—Detecting, measuring or recording for evaluating the integumentary system, e.g. skin, hair or nails
- A61B5/441—Skin evaluation, e.g. for skin disorder diagnosis
- A61B5/444—Evaluating skin marks, e.g. mole, nevi, tumour, scar
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10024—Color image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10141—Special mode during image acquisition
- G06T2207/10152—Varying illumination
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
- G06T2207/20028—Bilateral filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20172—Image enhancement details
- G06T2207/20192—Edge enhancement; Edge preservation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
- G06T2207/30088—Skin; Dermal
Definitions
- This technology relates to an image processing apparatus, an image processing method, a program, and an image processing system, and enables a feature portion to be detected from a skin image with high accuracy.
- the pore is measured by subtracting the smooth image from the original image and binarizing the image after subtraction to divide the pore into an area indicating the pore and another area. The number and size of the area to be shown are measured.
- an image obtained by subtracting the smoothed image from the original image includes an edge component and a texture component that are obstructive factors in detecting pores. Therefore, when binarization is performed on an image after subtraction, it is not possible to distinguish between a region showing pores and a region showing edge components or texture components, and it is possible to accurately detect pores that are characteristic portions of the skin. It may not be possible.
- an object of this technique is to provide an image processing apparatus, an image processing method, a program, and an image processing system that can accurately detect a characteristic portion from a skin image.
- a feature amount calculating unit that calculates a polarity indicating a tone of a skin image and a scale indicating an image region having a similar pixel value different from the surroundings as the feature amount, and the feature amount calculating unit
- the image processing apparatus includes a feature portion extraction unit that extracts a feature portion of the skin image based on the feature amount calculated in step (1).
- luminance information separation processing is performed on a skin image in which reflection of the surface of the skin is excluded by making the polarizing filter provided for the light source and the imaging unit orthogonal to each other.
- Global luminance information indicating the structural component is acquired.
- the feature amount is calculated using the global luminance information.
- the feature amount for example, a polarity indicating the polarity of the tone of the skin image and a scale indicating an image region having similar pixel values different from the surroundings are calculated.
- the intensity indicating the signal difference between the image area having similar pixel values and the surrounding area may be further calculated as the feature amount.
- at least one of feature portions of the skin image for example, pores, balloons, spots, pores, is extracted.
- the statistic is calculated based on the extraction result of the feature portion that is the feature amount satisfying the preset extraction condition, and information on the number and size of the feature portions and / or the color density is generated.
- a melanin analysis unit for analyzing melanin is provided, and feature portions are extracted using the feature amount calculated based on the skin image and the melanin analysis result of the skin image. For example, using features calculated based on skin images captured using white light and melanin analysis results such as skin images captured using red light and near infrared light, or ultraviolet light Part extraction is performed.
- an image alignment unit that aligns the past skin image and the current skin image is provided so that the feature parts match, and matching of the feature parts using the second feature amount indicating the polarity of the intensity change is performed. As a result, the skin image is aligned so that the corresponding feature portions in the past skin image and the current skin image match.
- the imaging range is moved so that the position of the corresponding feature portion in the current skin image becomes the position of the corresponding feature portion in the past skin image. Advice is presented.
- a second aspect of this technique is a step of calculating, as a feature amount, a polarity relating to a tone of a skin image and a scale indicating an image region having a similar pixel value different from the surroundings, and based on the calculated feature amount. And a step of extracting a characteristic part of the skin image.
- a third aspect of the present technology is a program that causes a computer to execute skin image processing, and includes a polarity indicating the tone of the skin image and a scale indicating an image region having similar pixel values different from the surroundings, and a feature amount And a program for causing the computer to execute a procedure for extracting a feature portion of the skin image based on the calculated feature value.
- the program of the present technology is, for example, a storage medium or a communication medium provided in a computer-readable format to a general-purpose computer that can execute various program codes, such as an optical disk, a magnetic disk, or a semiconductor memory. It is a program that can be provided by a medium or a communication medium such as a network. By providing such a program in a computer-readable format, processing corresponding to the program is realized on the computer.
- the imaging device is provided with an imaging unit that generates a skin image.
- the feature amount calculation unit that calculates the polarity relating to the gradation of the skin image and the scale indicating the image region of the similar pixel value different from the surroundings as the feature amount, and the feature amount calculation unit
- the image processing system includes a feature part extraction unit that extracts a feature part of the skin image based on a feature amount and a presentation unit that presents the feature part.
- the polarity indicating the tone of the skin image and the scale indicating the image area having similar pixel values different from the surroundings are calculated as the feature amount, and the feature portion of the skin image is extracted based on the feature amount. Is done. Accordingly, it becomes possible to accurately detect skin pores, blowouts, and the like as characteristic portions, and it is possible to more accurately perform various advices according to the state of the skin. Note that the effects described in the present specification are merely examples and are not limited, and may have additional effects.
- Blend ratio BR s is a diagram illustrating a BR M. It is a figure which shows the structure of a characteristic part analysis part. It is a flowchart which shows the extraction operation
- Image processing system First embodiment 2-1. Configuration of first embodiment 2-2. Operation of the first embodiment Second embodiment 3-1. Configuration of second embodiment 3-2. Operation of second embodiment 4. Third embodiment 4-1. Configuration of third embodiment 4-2. Operation of the third embodiment
- FIG. 1 illustrates a configuration of an image processing system according to the present technology.
- the image processing system 10 is configured using a device 11 having an imaging function (hereinafter referred to as “imaging device”), information processing devices 15 and 16, and the like.
- imaging device for example, a personal computer device
- the imaging device 11 and the information processing device (for example, a personal computer device) 15 can be directly connected via a wired or wireless transmission path.
- the imaging device 11 and the information processing device (for example, a server device) 16 can be connected via a public communication network or the like.
- the imaging device 11 includes an imaging unit 112 that generates a captured image of the skin.
- One of the imaging device 11 and the information processing devices 15 and 16 is provided with an image processing device 20 that detects a characteristic portion of the skin.
- the image processing apparatus 20 includes a feature amount calculation unit and a feature part extraction unit.
- the feature amount calculation unit calculates, as a feature amount, a scale representing a polarity related to gradation from a captured image of skin (hereinafter referred to as “skin image”) and a pixel region having similar pixel values different from the surroundings.
- the feature portion extraction unit extracts a feature portion of the skin based on the calculated feature amount.
- the imaging unit 11 or the information processing devices 15 and 16 is provided with a presentation unit 50 that presents the extraction result of the skin feature.
- the skin image used for detection of the skin characteristic portion by the image processing apparatus 20 is not limited to the skin image output from the imaging unit 112 but may be a skin image generated by the imaging unit 112 and stored in a recording medium
- FIG. 2 shows a simplified configuration of an imaging apparatus that images skin.
- 2A is a front view of the imaging apparatus 11, and
- FIG. 2B is a side view of the imaging apparatus 11.
- An attachment device 12 is provided at the tip of the lens barrel 111 of the imaging device 11.
- the attachment device 12 may be configured integrally with the lens barrel 111 or may be configured to be detachable from the lens barrel 111.
- the attachment device 12 has a plurality of light sources 121 (for example, LEDs (Light-Emitting-Diode) 1 to LEDn) arranged in a ring shape.
- a white LED is preferred as the light source.
- a white LED 121-1 provided with a polarization filter having a predetermined polarization plane, and a predetermined polarization plane
- a white LED 121-2 provided with a polarizing filter whose polarization planes are orthogonal to each other is provided.
- the clogging of pores may be detected as a characteristic part by using a near-ultraviolet LED 121-v as a light source as shown in FIG.
- the imaging device 11 provided with the accessory device 12 captures a skin image while being in close contact with the skin, for example, as shown in FIG.
- a polarization filter 113 whose polarization plane is orthogonal to a predetermined polarization plane is provided on the optical path to the imaging unit 112.
- FIG. 5 shows the configuration of the first embodiment of the image processing apparatus.
- the image processing apparatus 20 includes a preprocessing unit 21, a luminance information separation unit 22, and a feature portion analysis unit 24.
- the pre-processing unit 21 acquires a skin image and performs pre-processing.
- the pre-processing unit 21 applies contrast enhancement processing to make the shadow information stand out more with respect to the luminance information of the acquired skin image.
- contrast enhancement processing method for example, histogram equalization processing is used. When noise is conspicuous, noise removal may be performed before contrast enhancement, and when shading is conspicuous, shading correction may be performed before contrast enhancement.
- the luminance information separation unit 22 separates the luminance information obtained by the preprocessing unit 21 into global luminance information and local luminance information.
- the global luminance information is information indicating the illumination component included in the image and the structural component of the skin.
- the local luminance information is information indicating a fine skin pattern such as texture.
- the luminance information may be separated by performing low-pass processing on the input luminance information to separate the global luminance information, or a separation method disclosed in Japanese Patent Application Laid-Open No. 2009-98925 may be used.
- this separation method low-pass filter processing is performed on the acquired luminance information (input luminance information) f in W to generate luminance information f G ′ (see Expression (1)).
- the small amplitude component in the difference between the input luminance information f in W and the luminance information f G ′ is set as the local luminance information f L W.
- simple low-pass filter processing is performed in a portion where the edge strength is high, a strong edge is included in the local luminance information.
- the local luminance information f L W is generated by extracting only the small amplitude component using the function C that suppresses the high amplitude component (see Expression (2)). Further, the difference between the input luminance information f in W and the local luminance information f L W is calculated to generate global luminance information f G W (see Expression (3)).
- FIG. 6 illustrates function C.
- a process for suppressing the amplitude is performed on a signal whose amplitude is not included in the range of “i_min to i_max”.
- 6A to 6D illustrate functions C having different amplitude suppression characteristics.
- a plurality of low-pass filters having different pass frequency bands are used, and the function C is used to limit the amplitude between the input luminance information and each luminance information after filtering. I do.
- Global luminance information can also be generated using local luminance information obtained by integrating luminance information after amplitude limitation.
- the low-pass filter processing of the input luminance information f in W is performed using three low-pass filters having different pass frequency bands to generate luminance information f G ′ (see Expression (4)).
- S, M, and L indicate the number of taps of the low-pass filter, and the band of the low-pass filter becomes a narrow band in this order.
- difference between the input luminance information f in W and luminance information f Gj W by extracting only the small-amplitude components to generate a luminance information f Lj W (Equation (5) see).
- Blend ratio BR s corresponding to the further edge strength, performs the integration of luminance information f Lj W with BR M, to generate the local luminance information f L W (see equation (6)). Such may generate global luminance information f G W from equation (3) using the local luminance information f L W generated in the.
- Figure 7 illustrates blending ratio BR s, the BR M.
- edge strength is strong, the ratio of both the blend ratio BR s and the blend ratio BR M is high.
- edge strength is intermediate, the ratio of the blend ratio BR M is higher than the blend ratio BR s .
- edge strength is weak, the ratio of both the blend ratio BR s and the blend ratio BR M is low.
- the separation of luminance information is not limited to the above method, and a known edge-preserving smoothing filter such as a bilateral filter may be applied as the low-pass filter.
- the feature portion analysis unit 24 calculates a feature amount from the skin image, and analyzes the feature portion of the skin based on the calculated feature amount.
- FIG. 8 shows a configuration of the feature portion analysis unit 24.
- the feature portion analysis unit 24 includes a feature amount calculation unit 241, a feature portion extraction unit 243, and a statistic calculation unit 244.
- the feature amount calculation unit 241 calculates a feature amount.
- the feature amount calculation unit 241 calculates the feature amount using, for example, global luminance information generated by the luminance information separation unit 22.
- the feature amount calculation unit 241 calculates a scale representing a polarity related to the tone of the skin image as a feature amount and a pixel region having similar pixel values different from the surroundings. Further, the feature amount calculation unit 241 may further calculate an intensity indicating a signal difference between an image region having similar pixel values as a feature amount and the surrounding area.
- the feature points are calculated using an image feature extraction method.
- image feature extraction methods include SURF (Speeded Up Up Robust Feature) and SIFT (Scale Invariant Feature Up Transform).
- SURF Speeded Up Robust Feature
- feature points white circles, black circles
- the feature point in the image is detected by searching for a point where the matrix value of the Hessian matrix becomes maximum while changing the standard deviation ⁇ of the Gaussian function.
- the calculation of Expression (7) using an approximate filter is performed for speeding up.
- D xx , D yy , and D xy indicate image convolution using a Gaussian second derivative that is a component of a Hessian matrix calculated using a box filter.
- the filter size corresponds to a Gaussian standard deviation.
- the feature amount calculation unit 241 calculates, as the feature amount, a scale representing a pixel region having similar pixel values different from the surroundings, that is, a scale at which the matrix value calculated by Expression (7) is maximized. Also, the feature amount calculation unit 241 uses the Laplacian value of the feature point at which the polarity relating to the tone of the skin image, that is, the feature amount is calculated, as the feature amount. Further, the feature amount calculation unit 241 may include an intensity indicating a signal difference between an image region having a similar pixel value and the surroundings, for example, the maximum value of the matrix value calculated by Expression (7), in the feature amount. Note that the feature amount calculation unit 241 may calculate the feature amount using the other feature extraction method described above.
- the feature portion extraction unit 243 extracts a feature portion based on the feature amount obtained by the feature amount calculation unit 241. For example, when extracting the pore portion as the feature portion, the feature portion extraction unit 243 sets the Laplacian to “1” as an extraction condition. This is because Laplacian indicates the polarity relating to the gradation of the skin image, and when Laplacian is “1”, it indicates a feature in which black pixels are surrounded by white pixels and matches the feature of pores. In addition, the feature portion extraction unit 243 limits a scale representing a pixel region having a similar pixel value different from the surroundings. It is known that the pore size is about 0.1 mm to 0.3 mm. Therefore, the feature portion extraction unit 243 uses the feature amount scale obtained by the feature amount calculation unit 241 as an extraction condition that corresponds to the pore size.
- the feature portion extraction unit 243 may limit the strength. For example, a feature that appears to be a conspicuous pore region requires some signal strength (contrast difference) relative to other regions. Therefore, the feature portion extraction unit 243 uses the strength (matrix value) that can extract conspicuous pores as an extraction condition.
- the feature portion extraction unit 243 can extract only the pore region from the skin image by extracting the feature points that satisfy all the extraction conditions set as described above as the skin feature portions. As will be described later, the extraction condition may be changed to extract the blowout or the like as a skin feature.
- the statistic calculation unit 244 calculates a statistic for the feature portion extracted by the feature portion extraction unit 243. For example, when pores are extracted as feature portions, the statistic calculation unit 244 calculates the number of pores by measuring the number of extracted feature portions. In addition, the statistic calculation unit 244 calculates an average value of the scales of the extracted feature portions, and obtains a statistic of the pore size from the average value. Further, the statistic calculation unit 244 calculates the average value of the strengths (for example, Hessian values) of the extracted feature parts to obtain the density of the pores. Further, the statistic calculator 244 may calculate not only the average value but also the maximum value, variance, and the like. In addition, classification of pore sizes and colors may be performed, and a class value may be calculated for each class. Further, the statistic calculation unit 244 may calculate the statistic in the same manner not only for pores but also for blowouts and the like. Further, the statistic calculation unit 244 may obtain a ratio of a region having a high melanin index.
- the analysis result of the feature portion analysis unit 24 is presented to the user.
- the presentation unit 50 displays the statistics calculated by the feature portion analysis unit 24 on the screen.
- FIG. 9 is a flowchart showing the feature portion extraction operation.
- the image processing apparatus 20 acquires a feature amount.
- the image processing apparatus 20 uses the feature amount calculated using the global luminance information, for example, the polarity relating to the tone of the skin image, the scale representing the pixel region having similar pixel values different from the surroundings, and the intensity (contrast difference).
- the feature quantity shown is acquired, and the process proceeds to step ST2.
- step ST2 the image processing apparatus 20 determines whether the polarity is a predetermined polarity.
- the image processing device 20 proceeds to step ST3.
- the image processing apparatus 20 proceeds to step ST7 when the feature amount does not indicate the polarity of the feature portion.
- step ST3 the image processing apparatus 20 determines whether the scale is a predetermined scale.
- the process proceeds to step ST4.
- the image processing apparatus 20 proceeds to step ST7 when the feature amount does not indicate a predetermined scale.
- step ST4 the image processing apparatus 20 determines whether the intensity is a predetermined intensity.
- the image processing device 20 proceeds to step ST5.
- the image processing apparatus 20 proceeds to step ST7 when the feature amount does not indicate the predetermined intensity, for example, when the strength indicated by the feature amount is smaller than the contrast difference between the pore portion and the skin portion.
- step ST5 the image processing apparatus 20 determines that the feature portion. For example, when the pore extraction condition is satisfied in steps ST2 to ST4, the image processing apparatus 20 determines that the feature portion indicates a pore and proceeds to step ST6.
- step ST6 the image processing apparatus 20 determines whether the feature portion extraction processing has been completed.
- the image processing apparatus 20 proceeds to step ST7 if a feature amount region that has not been determined whether or not it is a feature portion remains, and ends the feature portion extraction operation if it does not remain.
- step ST7 the image processing apparatus 20 acquires a new feature amount.
- the image processing apparatus 20 acquires a feature amount that has not been determined whether or not it is a feature portion, and returns to step ST2.
- the order of determination of polarity, scale, and intensity is not limited to the order shown in FIG. 9, but may be another order. It is also possible to extract feature parts without determining the strength.
- the image processing apparatus 20 performs such processing to accurately extract the pore portion from the skin image. Further, when presenting the extraction result of the characteristic part to the presentation unit 50, it is presented in a form that is easy for the user to understand.
- FIG. 10 shows the relationship between the feature part to be extracted, the light source, and the extraction condition.
- a white light source is used as the extraction condition.
- the polarity indicating the characteristics surrounded by the pixels with high luminance and the range of the scale are set to about 0.1 to 0.3 mm.
- the extraction condition the polarity indicating the characteristics surrounded by the low-luminance pixels and the range of the scale are set to about 0.5 to 1.0 mm.
- a near ultraviolet light source When detecting clogging of pores, a near ultraviolet light source is used. It is known that the sebum portion emits green light by near-ultraviolet light, and the porferrin portion produced by acne bacteria emits orange light by near-ultraviolet light. Therefore, in the extraction condition, when the skin image is grayscale, the polarity indicating the characteristics surrounded by the low luminance pixels, the polarity indicating green or orange by near ultraviolet light, and the range of the scale is about 0.2 to Set to about 0.5 mm.
- FIG. 11 illustrates the operation of the presentation unit.
- FIG. 11A shows a state in which pores are plotted according to size, for example, with respect to a skin image
- FIG. 11B displays pore size distribution (histogram) by size.
- pore size distribution histogram
- C shows a state where pores are plotted with respect to density on the captured image
- FIG. 11D shows pore density distribution (histogram) for each density.
- the presentation unit 50 presents the feature portion extraction result in a form that is easy for the user to understand.
- Second Embodiment> By the way, when the scale and brightness of the stain and the pore are similar, it is difficult to distinguish the stain and the pore. Therefore, in the second embodiment, a case will be described in which melanin that is present in many spots is analyzed, and spots and pores are discriminated using the analysis results.
- the imaging device 11 When analyzing melanin, the imaging device 11 performs imaging by switching the wavelength of the light source so that melanin can be easily analyzed. For example, as shown in FIG. 12, a red LED 121 -r and a near-infrared LED 121 -ir are further provided in the attachment device 12, and the imaging device 11 switches the light source used for illumination and images the skin.
- melanin may be analyzed using an image captured by irradiating ultraviolet rays, or melanin may be analyzed using spectral reflectance of the skin.
- melanin may be analyzed using an image obtained by switching between red light and near infrared light.
- FIG. 13 shows the configuration of the second embodiment of the image processing apparatus.
- the image processing apparatus 20 includes a preprocessing unit 21, a luminance information separation unit 22, a melanin analysis unit 23, and a feature portion analysis unit 24.
- the preprocessing unit 21 acquires a skin image captured using a white light source and performs preprocessing. As in the first embodiment, the preprocessing unit 21 applies contrast enhancement processing to the luminance information of the acquired skin image in order to make a shadow stand out. When noise is conspicuous, noise removal may be performed before contrast enhancement, and when shading is conspicuous, shading correction may be performed before contrast enhancement.
- the brightness information includes a B (blue) channel signal for a skin image using a white light source, and an R (red) channel signal for a skin image using a red light source and a skin image using a near infrared light source. It is desirable to use it.
- the luminance information separation unit 22 separates the luminance information obtained by the preprocessing unit 21 into global luminance information and local luminance information.
- the luminance information separation unit 22 is configured to display global luminance information that is information indicating illumination components and skin structural components included in an image, and local information that indicates a fine pattern of skin such as texture. Separation of luminance information.
- the melanin analysis unit 23 acquires a skin image captured using a red light source and a skin image captured using a near-infrared light source, and analyzes melanin based on the acquired skin image.
- FIG. 14 shows the configuration of the melanin analysis unit 23.
- the melanin analysis unit 23 includes a melanin distribution calculation unit 231 and a melanin index calculation unit 232.
- the melanin distribution calculating unit 231 calculates an average value Avg std R of luminance information (red component) f std R from a captured image obtained by irradiating a standard diffuse reflector used for calibration with red light. (See equation (8)). Similarly, to calculate the near-infrared intensity information light from the captured image obtained by irradiating the near-infrared region (near-infrared component) f std IR average value Avg std IR standard diffuse reflector (see equation (9)).
- the melanin distribution Mx is calculated from the luminance information (near infrared component) f in IR and the average values Avg std R and Avg std IR when using a standard diffuse reflector (see formula (10)).
- Equation (10) “k” is a parameter representing the slope of the equation, and “q” is a parameter representing the intercept of the equation.
- the melanin index calculation unit 232 normalizes the melanin distribution calculated by the melanin distribution calculation unit 231 and calculates the melanin index.
- Melanin index calculating unit 232 calculates an input luminance information (red component) f in the average value Avg in R and the input luminance information (near-infrared component) of R f in IR average value Avg in IR (formula (11) , (12)).
- the average value Avg in R of the input luminance information (red component) f in R the average value Avg in IR of the input luminance information (near infrared component) f in IR , and the average when using a standard diffuse reflector
- An average melanin amount Mx avg is calculated using the values Avg std R and Avg std IR (formula (13)).
- Equation (13) “k” is a parameter representing the slope of the equation, and “q” is a parameter representing the intercept of the equation.
- threshold values Mx_th1 and Mx_th2 are set using the average melanin amount Mx avg (Equations (14) and (15)).
- “e” is a parameter that defines the melanin distribution Mx with the melanin index in the range of “0” to “1”.
- the threshold setting method is not limited to the above method, and may be set to a fixed value, for example.
- the melanin index calculation unit 232 sets threshold values Mx_th1 and Mx_th2, and converts the melanin distribution Mx into the melanin index ID Mx with the conversion characteristics shown in FIG.
- the feature portion analysis unit 24 calculates a feature amount from the skin image, and extracts a feature portion of the skin based on the calculated feature amount.
- the feature portion analysis unit 24 includes a feature amount calculation unit 241, a feature portion extraction unit 243, and a statistic calculation unit 244, as in the first embodiment.
- the feature amount calculation unit 241 calculates a feature amount.
- the feature amount calculation unit 241 calculates the feature amount using, for example, global luminance information generated by the luminance information separation unit 22.
- the feature amount calculation unit 241 calculates a scale representing a polarity related to the tone of the skin image as a feature amount and a pixel region having similar pixel values different from the surroundings. Further, the feature amount calculation unit 241 may further calculate an intensity indicating a signal difference between an image region having similar pixel values as a feature amount and the surrounding area.
- the feature portion extraction unit 243 extracts a feature portion based on the feature amount obtained by the feature amount calculation unit 241. For example, when extracting the pore portion as the feature portion, the feature portion extraction unit 243 sets the Laplacian to “1” as an extraction condition. This is because Laplacian indicates the polarity relating to the gradation of the skin image, and when Laplacian is “1”, it indicates a feature in which black pixels are surrounded by white pixels and matches the feature of pores. In addition, the feature portion extraction unit 243 limits a scale representing a pixel region having a similar pixel value different from the surroundings. It is known that the pore size is about 0.1 mm to 0.3 mm. Therefore, the feature portion extraction unit 243 uses the feature amount scale obtained by the feature amount calculation unit 241 as an extraction condition that corresponds to the pore size.
- the feature portion extraction unit 243 may limit the strength. For example, a feature that appears to be a conspicuous pore region requires some signal strength (contrast difference) relative to other regions. Therefore, the feature portion extraction unit 243 uses the strength (matrix value) that can extract conspicuous pores as an extraction condition.
- the feature portion extraction unit 243 determines whether the region is a pore region or a stain region based on the melanin index ID Mx for the extracted feature portion. For example, when the melanin index ID Mx is larger than a predetermined value, it is determined as a spot region, and when it is equal to or smaller than the predetermined value, it is determined as a pore region.
- the statistic calculation unit 244 calculates a statistic for the feature portion extracted by the feature portion extraction unit 243. For example, when pores are extracted as feature portions by distinguishing them from spots, the statistic calculation unit 244 calculates the number of pores by measuring the number of extracted feature portions. Further, the statistic calculation unit 244 calculates an average value of the scales of the feature portions of the pores, and obtains a statistic of the size of the pores from the average value. Further, the statistic calculation unit 244 calculates the average value of the strengths (for example, Hessian values) of the extracted feature parts to obtain the density of the pores. Further, the statistic calculation unit 244 may obtain a ratio of a region having a high melanin index.
- the analysis result of the feature portion analysis unit 24 is presented to the user.
- the presentation unit 50 displays the statistics calculated by the feature portion analysis unit 24 on the screen.
- FIG. 16 is a flowchart showing the feature portion extraction operation.
- the image processing apparatus 20 acquires a feature amount.
- the image processing apparatus 20 indicates a feature amount calculated using luminance information, for example, a polarity related to the tone of a skin image, a scale representing a pixel region having similar pixel values different from the surroundings, and intensity (contrast difference).
- luminance information for example, a polarity related to the tone of a skin image, a scale representing a pixel region having similar pixel values different from the surroundings, and intensity (contrast difference).
- luminance information for example, a polarity related to the tone of a skin image, a scale representing a pixel region having similar pixel values different from the surroundings, and intensity (contrast difference).
- luminance information for example, a polarity related to the tone of a skin image, a scale representing a pixel region having similar pixel values different from the surroundings, and intensity (contrast difference).
- luminance information for example, a
- step ST12 the image processing apparatus 20 determines whether the polarity is a predetermined polarity.
- the image processing device 20 proceeds to step ST13.
- the image processing apparatus 20 proceeds to step ST18 when the feature amount does not indicate the polarity of the feature portion.
- step ST13 the image processing apparatus 20 determines whether the scale is a predetermined scale.
- the image processing apparatus 20 proceeds to step ST14.
- the image processing apparatus 20 proceeds to step ST18 when the feature amount does not indicate a predetermined scale.
- step ST14 the image processing apparatus 20 determines whether the intensity is a predetermined intensity.
- the image processing device 20 proceeds to step ST15.
- the image processing apparatus 20 proceeds to step ST18 when the feature amount does not indicate the predetermined intensity, for example, when the strength indicated by the feature amount is smaller than the contrast difference between the pore portion and the skin portion.
- step ST15 the image processing apparatus 20 determines whether the melanin index is equal to or less than a predetermined value.
- the image processing device 20 proceeds to step ST16 when the melanin index of the characteristic portion is equal to or smaller than the predetermined value, and proceeds to step ST18 when the melanin index is larger than the predetermined value.
- step ST16 the image processing apparatus 20 determines that it is a characteristic part.
- the image processing apparatus 20 satisfies the pore extraction condition in, for example, step ST12 to step ST14. If the melanin index is less than or equal to a predetermined value in step ST15, the image processing apparatus 20 determines that the feature portion indicates a pore and step ST17. Proceed to If the melanin index is larger than a predetermined value, it may be determined as a feature portion showing a spot and the process may proceed to step ST18.
- step ST17 the image processing apparatus 20 determines whether the feature portion extraction processing has been completed.
- the image processing apparatus 20 proceeds to step ST18 if a feature amount region that has not been determined whether or not it is a feature portion remains, and ends the feature portion extraction operation if it does not remain.
- step ST18 the image processing apparatus 20 acquires a new feature amount.
- the image processing apparatus 20 acquires a feature amount that has not been determined whether or not it is a feature portion, and returns to step ST12.
- the order of determination of polarity, scale, and intensity is not limited to the order shown in FIG. 16, but may be another order. It is also possible to extract feature parts without determining the strength.
- the image processing apparatus 20 can distinguish pores and spots by performing such processing, and accurately extract pores.
- the region having a high melanin index may be displayed in a different color, and the statistic calculation unit 244 You may show the ratio of the area
- pores and spots can be distinguished using melanin analysis results, and pores can be extracted with high accuracy. Further, since pores and spots can be distinguished, the state of pores and spots can be presented with high accuracy.
- FIG. 17 shows the configuration of the third embodiment of the image processing apparatus.
- the image processing apparatus 20 includes a preprocessing unit 21, a luminance information separation unit 22, and a feature portion analysis unit 24.
- the pre-processing unit 21 acquires a skin image and performs pre-processing. As in the first embodiment, the preprocessing unit 21 applies contrast enhancement processing to the luminance information of the acquired skin image in order to make a shadow stand out. When noise is conspicuous, noise removal may be performed before contrast enhancement, and when shading is conspicuous, shading correction may be performed before contrast enhancement.
- the luminance information separation unit 22 separates the luminance information obtained by the preprocessing unit 21 into global luminance information and local luminance information.
- the luminance information separation unit 22 is configured to display global luminance information that is information indicating illumination components and skin structural components included in an image, and local information that indicates a fine pattern of skin such as texture. Separation of luminance information.
- the feature portion analysis unit 24 calculates a feature amount from the skin image, and analyzes the feature portion of the skin based on the calculated feature amount. As shown in FIG. 18, the feature portion analysis unit 24 includes a feature amount calculation unit 241, a position alignment unit 242, a feature portion extraction unit 243, and a statistic calculation unit 244.
- the feature amount calculation unit 241 calculates a feature amount.
- the feature amount calculation unit 241 calculates the feature amount using, for example, global luminance information generated by the luminance information separation unit 22.
- the feature amount calculation unit 241 calculates a scale representing a polarity related to the tone of the skin image as a feature amount and a pixel region having similar pixel values different from the surroundings. Further, the feature amount calculation unit 241 may further calculate an intensity indicating a signal difference between an image region having similar pixel values as a feature amount and the surrounding area.
- the feature amount calculation unit 241 calculates a second feature amount used for feature portion matching in order to align the past skin image and the current skin image.
- the feature quantity calculation unit 241 calculates, for example, a feature quantity indicating the polarity of intensity change as the second feature quantity.
- a square area centered on the characteristic part for example, a “20s ⁇ 20s” area is divided into “4 ⁇ 4” sub-areas and rotated by an orientation angle.
- the gradient vector is obtained by dividing the sub-region into four and creating HaarWavelets (2s) of the same size.
- a four-dimensional vector ( ⁇ dx, ⁇ dy, ⁇
- This four-dimensional vector has a positive gradient direction when the gradient in the x direction is large and the absolute value thereof is also large.
- the gradient in the x direction is small and its absolute value is large.
- the four-dimensional vector is information indicating the polarity of the intensity change. Accordingly, a four-dimensional vector is obtained from the 16 sub-regions, and 64 feature amounts are used as the second feature amount.
- the feature amount calculation unit 241 stores global luminance information and the second feature amount calculated from this information so that alignment with a subsequently captured skin image can be performed.
- the information storage unit 25 stores global luminance information and a second feature amount calculated from this information.
- the information storage unit 25 stores a skin image, a pre-processed skin image, or global luminance information, and performs the above-described processing by the feature amount calculation unit 241 or the like to calculate a second feature amount. May be output to the alignment unit 242.
- Alignment unit 242 performs matching of the feature portions of the past skin image and the current skin image, and detects a pair of feature portions corresponding to each other.
- a matching method for example, a method such as the nearest linear search may be used.
- the registration unit 242 performs projective transformation or the like and performs registration between a new skin image and a past skin image. For example, a new skin image is matched with the position of a past skin image by obtaining a homography matrix from a pair of feature parts and performing projective transformation.
- the alignment unit 242 moves the imaging range in a direction in which more pairs of feature portions are found based on the positions of feature point portions that are paired when the number of feature portion pairs found by matching is equal to or less than a predetermined number. Present advice as you do.
- the position of the corresponding feature portion in the new skin image is biased to the left of the screen relative to the position in the past skin image
- the position of the corresponding feature portion is the past skin image and the current skin image.
- the feature portion extraction unit 243 extracts a feature portion based on the feature amount obtained by the feature amount calculation unit 241. For example, when extracting the pore portion as the feature portion, the feature portion extraction unit 243 sets the Laplacian to “1” as an extraction condition. This is because Laplacian indicates the polarity relating to the gradation of the skin image, and when Laplacian is “1”, it indicates a feature in which black pixels are surrounded by white pixels and matches the feature of pores. In addition, the feature portion extraction unit 243 limits a scale representing a pixel region having a similar pixel value different from the surroundings. It is known that the pore size is about 0.1 mm to 0.3 mm. Therefore, the feature portion extraction unit 243 uses the feature amount scale obtained by the feature amount calculation unit 241 as an extraction condition that corresponds to the pore size.
- the feature portion extraction unit 243 may limit the strength. For example, a feature that appears to be a conspicuous pore region requires some signal strength (contrast difference) relative to other regions. Therefore, the feature portion extraction unit 243 uses the strength (matrix value) that can extract conspicuous pores as an extraction condition.
- the feature portion extraction unit 243 can extract only the pore region from the skin image by extracting the feature points that satisfy all the extraction conditions set as described above as the skin feature portions. As will be described later, the extraction condition may be changed to extract the blowout or the like as a skin feature.
- the feature portion extraction unit 243 extracts feature points such as skin pores and pimples by extracting feature points with the polarity and scale related to the gradation of the skin image.
- the statistic calculation unit 244 calculates a statistic for the feature portion extracted by the feature portion extraction unit 243. For example, when pores are extracted as feature portions, the statistic calculation unit 244 calculates the number of pores by measuring the number of extracted feature portions. In addition, the statistic calculation unit 244 calculates an average value of the scales of the extracted feature portions, and obtains a statistic of the pore size from the average value. Further, the statistic calculation unit 244 calculates the average value of the strengths (for example, Hessian values) of the extracted feature parts to obtain the density of the pores.
- the strengths for example, Hessian values
- the analysis result of the feature portion analysis unit 24 is presented to the user.
- the presentation unit 50 displays the statistics calculated by the feature portion analysis unit 24 on the screen.
- FIG. 19 is a flowchart showing the operation of the third embodiment.
- the image processing apparatus 20 acquires a skin image.
- the image processing device 20 acquires the skin image generated by the imaging device 11, and proceeds to step ST22.
- step ST22 the image processing apparatus 20 performs preprocessing.
- the image processing apparatus 20 performs a contrast enhancement process or the like to make the shade information more prominent with respect to the luminance information of the acquired skin image, and proceeds to step ST23.
- step ST23 the image processing apparatus 20 separates the luminance information.
- the image processing apparatus 20 separates the luminance information that has been preprocessed into global luminance information and local luminance information, and proceeds to step ST24.
- step ST24 the image processing apparatus 20 calculates a feature amount.
- the image processing apparatus 20 uses the global luminance information to calculate, as a feature amount, a scale representing a polarity related to the tone of the skin image and a pixel region having similar pixel values different from the surroundings, and proceeds to step ST25. Further, the image processing apparatus 20 may further calculate an intensity indicating a signal difference between an image region having a similar pixel value and the periphery.
- step ST25 the image processing apparatus 20 determines whether or not the number of feature pairs exceeds a predetermined number.
- the image processing device 20 determines whether or not the number of pairs of feature portions detected from the past skin image and the corresponding feature portions in the current skin image is greater than a predetermined number. If the number is less than the predetermined number, the process proceeds to step ST26. If the number is larger than the predetermined number, the process proceeds to step ST27.
- step ST26 the image processing apparatus 20 presents advice.
- the image processing device 20 presents, for example, advice on the moving direction of the imaging range on the presentation unit 50 so that the position of the pair of feature portions is approximately the same in the past skin image and the skin image generated by the imaging device 11. And return to step ST21.
- step ST27 the image processing apparatus 20 calculates a homography matrix. Since the image processing device 20 matches the position of the past skin image and the skin image generated by the imaging device 11, the image processing device 20 is a homolog indicating the correspondence relationship between the past skin image and the skin image generated by the imaging device 11. The graphic matrix is calculated and the process proceeds to step ST28.
- step ST28 the image processing apparatus 20 performs alignment.
- the image processing device 20 performs projective transformation using the calculated homography matrix, matches the position of the past skin image and the skin image generated by the imaging device 11, and ends the processing.
- the image processing apparatus 20 performs such a process, aligns the images so that the corresponding feature portions can be easily compared between the past skin image and the skin image generated by the imaging device 11, and the detection result. Present.
- FIG. 20 illustrates the operation of the presentation unit.
- 20A shows a state in which, for example, pores are plotted according to size with respect to a past skin image
- FIG. 20B shows a pore size distribution (histogram) in the past skin image.
- FIG. 20C shows a state in which pores are plotted by size, for example, on the skin image newly generated by the imaging apparatus 11, and
- FIG. 20D shows the newly generated skin.
- the pore size distribution (histogram) in the image is displayed by size.
- size of a pore you may compare by the number of pores, the density of a pore, and may compare by all of them.
- FIG. 21 exemplifies advice when the number of feature part pairs is a predetermined number or less.
- the detection result of the past skin image and the detection result of the new skin image are displayed, and further, the advice of the moving direction of the imaging range is performed so that the skin image is substantially in the same position. Therefore, the past skin image and the current skin image can be easily aligned.
- the past skin condition and the current skin condition can be easily compared, and how the various advices and the like are obtained. Can be easily and accurately confirmed.
- the series of processes described in the specification can be executed by hardware, software, or a combined configuration of both.
- a program in which a processing sequence is recorded is installed and executed in a memory in a computer incorporated in dedicated hardware.
- the program can be installed and executed on a general-purpose computer capable of executing various processes.
- the program can be recorded in advance on a hard disk or ROM (Read Only Memory) as a recording medium.
- the program can be temporarily or permanently stored on a removable recording medium such as a flexible disk, CD-ROM (Compact Disc Read Only Memory), MO (Magneto optical disc), DVD (Digital Versatile Disc), magnetic disk, semiconductor memory card, etc. Can be stored (recorded).
- a removable recording medium can be provided as so-called package software.
- the program may be transferred from the download site to the computer wirelessly or by wire via a network such as a LAN (Local Area Network) or the Internet.
- the computer can receive the program transferred in this way and install it on a recording medium such as a built-in hard disk.
- the image processing apparatus may have the following configuration.
- a feature amount calculating unit that calculates, as a feature amount, a polarity relating to the gradation of a skin image and a scale indicating an image region having a similar pixel value different from the surroundings;
- An image processing apparatus comprising: a feature portion extraction unit that extracts a feature portion of the skin image based on the feature amount calculated by the feature amount calculation unit.
- a luminance information separation unit that performs luminance information separation processing on the skin image and acquires global luminance information, The image processing apparatus according to (1), wherein the feature amount calculation unit calculates the feature amount using the global luminance information acquired by the luminance information separation unit.
- the image processing device calculates, as the feature amount, an intensity indicating a signal difference between the image region having the similar pixel value and the periphery.
- the feature portion extraction unit performs feature portion extraction using the feature amount calculated by the feature amount calculation unit and the analysis result obtained by the melanin analysis unit.
- the feature amount calculation unit calculates a second feature amount indicating the polarity of intensity change,
- the image alignment unit performs feature part matching using the second feature amount, and aligns the skin image so that corresponding feature parts match in the first and second skin images ( The image processing apparatus according to any one of 1) to (4).
- (6) Using a past image as the first skin image and a current image as the second skin image, When the number of corresponding feature portions is equal to or less than a predetermined number, the image alignment unit is configured such that the position of the corresponding feature portion in the second skin image corresponds to the position of the corresponding feature portion in the first skin image.
- the image processing apparatus which presents an advice for moving the imaging range so that (7)
- the image processing apparatus according to any one of (1) to (6), wherein the feature part extraction unit extracts at least one of pores, blowouts, spots, and pores as the feature parts.
- the feature portion extraction unit extracts at least one of pores, blowouts, and spots from a skin image captured using white light based on the feature amount calculated by the feature amount calculation unit,
- the image processing apparatus according to (7), wherein clogging of pores is extracted from a skin image captured using light based on the feature amount calculated by the feature amount calculation unit.
- the image processing apparatus according to any one of (1) to (8), further including an amount calculation unit.
- the skin image is an image in which surface reflection of the skin is excluded by making the polarizing filter provided for the light source and the imaging unit orthogonal to each other. The image processing apparatus described.
- the polarity indicating the tone of the skin image and the scale indicating the image area of the similar pixel value different from the surroundings are calculated as the feature amount, A feature portion of the skin image is extracted based on the feature amount. For this reason, it becomes possible to accurately detect skin pores, blowouts, and the like as characteristic portions, and it is possible to perform various advices and the like more accurately according to the state of the skin. Therefore, it is suitable for an electronic device having a skin imaging function, for example, a digital camera, a portable terminal device, an information processing device that provides various services via a network, and the like.
- DESCRIPTION OF SYMBOLS 10 ... Image processing system 11 ... Imaging device 12 ... Attached device 15, 16 ... Information processing device 20 ; Image processing device 21 ... Pre-processing part 22 ... Luminance information separation part DESCRIPTION OF SYMBOLS 23 ... Melanin analysis part 24 ... Feature part analysis part 25 ... Information storage part 50 ... Presentation part 111 ... Lens barrel 112 ... Imaging part 113 ... Polarizing filter 121 ... Light source 231 ... Melanin distribution calculation unit 232 ... Melanin index calculation unit 241 ... Feature amount calculation unit 242 ... Positioning unit 243 ... Feature part extraction unit 244 ... Statistics amount calculation unit
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Heart & Thoracic Surgery (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Dermatology (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Measuring And Recording Apparatus For Diagnosis (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
Description
1.画像処理システム
2.第1の実施の形態
2-1.第1の実施の形態の構成
2-2.第1の実施の形態の動作
3.第2の実施の形態
3-1.第2の実施の形態の構成
3-2.第2の実施の形態の動作
4.第3の実施の形態
4-1.第3の実施の形態の構成
4-2.第3の実施の形態の動作
図1は、本技術の画像処理システムの構成を例示している。画像処理システム10は、撮像機能を有する機器(以下「撮像装置」という)11や情報処理装置15,16等を用いて構成されている。撮像装置11と情報処理装置(例えばパーソナルコンピュータ装置等)15は、有線または無線の伝送路を介して直接接続可能とされている。また、撮像装置11と情報処理装置(例えばサーバ装置等)16は、公衆通信網のネットワーク等を介して接続可能とされている。
第1の実施の形態では、画像処理装置20によって肌画像から毛穴等の特徴部分を検出する場合について説明する。
図5は、画像処理装置の第1の実施の形態の構成を示している。画像処理装置20は、前処理部21、輝度情報分離部22、特徴部分解析部24を有している。
次に、画像処理装置の第1の実施の形態の動作について説明する。図9は、特徴部分の抽出動作を示すフローチャートである。ステップST1で画像処理装置20は特徴量を取得する。画像処理装置20は、グローバル輝度情報を用いて算出された特徴量、例えば肌画像の階調に関する極性、周辺とは異なる類似した画素値をもつ画素領域を表すスケール、および強度(コントラスト差分)を示す特徴量を取得してステップST2に進む。
ところで、シミと毛穴のスケールや輝度が類似していると、シミと毛穴を区別することが困難である。そこで、第2の実施の形態では、シミの部分に多く存在するメラニンについての解析を行い、この解析結果を利用してシミと毛穴の判別を行う場合について説明する。メラニンの解析を行う場合、撮像装置11では、メラニンの解析を容易に行うことができるように、光源の波長を切り替えて撮像を行う。例えば図12に示すように、付属装置12に赤色LED121-rと近赤外LED121-irをさらに設けて、撮像装置11は、照明に用いる光源を切り替えて肌の撮像を行う。また、メラニンの解析では、紫外線を照射して撮像された撮像画像を用いてメラニンの解析を行ってもよく、肌の分光反射率を用いてメラニンの解析を行うようにしてもよい。以下、赤色光と近赤外光を切り替えて撮像を行うことにより得られた画像を用いてメラニンの解析を行う場合について説明する。
図13は、画像処理装置の第2の実施の形態の構成を示している。画像処理装置20は、前処理部21、輝度情報分離部22、メラニン解析部23、特徴部分解析部24を有している。
次に、画像処理装置の第2の実施の形態の動作について説明する。図16は、特徴部分の抽出動作を示すフローチャートである。ステップST11で画像処理装置20は特徴量を取得する。画像処理装置20は、輝度情報を用いて算出された特徴量、例えば肌画像の階調に関する極性、周辺とは異なる類似した画素値をもつ画素領域を表すスケール、および強度(コントラスト差分)を示す特徴量を取得してステップST12に進む。
第1の実施の形態と第2の実施の形態では、肌の特徴部分を検出する処理について説明したが、肌の観察では、時間の経過と共に肌の特徴部分がどのように変化したか判別できることが望ましい。例えば、毛穴を小さくする治療や吹出物等を無くする治療等が行われた場合、毛穴や吹出物等がどのように変化しているか比較できることが望ましい。そこで、第3の実施の形態では、時間の異なる複数の肌画像間で、対応する特徴部分が同じ位置となるように画像の位置合わせを容易に行うことができる画像処理装置について説明する。
図17は、画像処理装置の第3の実施の形態の構成を示している。画像処理装置20は、前処理部21、輝度情報分離部22、特徴部分解析部24を有している。
次に、画像処理装置の第3の実施の形態の動作について説明する。図19は、第3の実施の形態の動作を示すフローチャートである。ステップST21で画像処理装置20は肌画像を取得する。画像処理装置20は、撮像装置11で生成された肌画像を取得してステップST22に進む。
(1) 肌画像の階調に関する極性と、周辺とは異なる類似した画素値の画像領域を示すスケールを、特徴量として算出する特徴量算出部と、
前記特徴量算出部で算出された特徴量に基づき、前記肌画像の特徴部分を抽出する特徴部分抽出部と
を備える画像処理装置。
(2) 前記肌画像に対して輝度情報分離処理を行い、グローバル輝度情報を取得する輝度情報分離部を備え、
前記特徴量算出部は、前記輝度情報分離部で取得した前記グローバル輝度情報を用いて前記特徴量の算出を行う(1)に記載の画像処理装置。
(3) 前記特徴量算出部は、前記類似した画素値の画像領域と周辺との信号差を示す強度を、前記特徴量として算出する(1)または(2)に記載の画像処理装置。
(4) メラニンの解析を行うメラニン解析部をさらに備え、
前記特徴部分抽出部は、前記特徴量算出部で算出された特徴量と前記メラニン解析部で得られた解析結果を用いて特徴部分の抽出を行う(1)乃至(3)の何れかに記載の画像処理装置。
(5) 特徴部分が一致するように第1と第2の肌画像の位置合わせを行う画像位置合わせ部をさらに備え、
前記特徴量算出部は、強度変化の極性を示す第2特徴量の算出を行い、
前記画像位置合わせ部は、前記第2特徴量を用いて特徴部分のマッチングを行い、前記第1と第2の肌画像において対応する特徴部分が一致するように前記肌画像の位置合わせを行う(1)乃至(4)の何れかに記載の画像処理装置。
(6) 前記第1の肌画像として過去画像、前記第2の肌画像として現在画像を用い、
前記画像位置合わせ部は、対応する特徴部分の数が所定数以下である場合、前記第2の肌画像において前記対応する特徴部分の位置が、前記第1の肌画像において対応する特徴部分の位置となるように撮像範囲の移動アドバイスを提示する(5)に記載の画像処理装置。
(7) 前記特徴部分抽出部は、前記特徴部分として毛穴、吹出物、シミ、毛穴のつまりの少なくとも何れかを抽出する(1)乃至(6)の何れかに記載の画像処理装置。
(8) 前記特徴部分抽出部は、白色光を用いて撮像された肌画像から前記特徴量算出部で算出された特徴量に基づき、毛穴、吹出物、シミの少なくとも何れかを抽出し、近紫外光を用いて撮像された肌画像から前記特徴量算出部で算出された特徴量に基づき、毛穴のつまりを抽出する(7)に記載の画像処理装置。
(9) 予め設定された抽出条件を満たす特徴量である特徴部分の抽出結果に基づき統計量の算出を行い、特徴部分の数と大きさと色の濃さの少なくとも何れかに関する情報を生成する統計量算出部を有する(1)乃至(8)の何れかに記載の画像処理装置。
(10) 前記肌画像は、光源と撮像部に対して設けられた偏光フィルタを直交関係とすることで肌の表面反射が除外されている画像である(1)乃至(9)の何れかに記載の画像処理装置。
11・・・撮像装置
12・・・付属装置
15,16・・・情報処理装置
20・・・画像処理装置
21・・・前処理部
22・・・輝度情報分離部
23・・・メラニン解析部
24・・・特徴部分解析部
25・・・情報記憶部
50・・・提示部
111・・・鏡胴
112・・・撮像部
113・・・偏光フィルタ
121・・・光源
231・・・メラニン分布算出部
232・・・メラニン指数算出部
241・・・特徴量算出部
242・・・位置合わせ部
243・・・特徴部分抽出部
244・・・統計量算出部
Claims (13)
- 肌画像の階調に関する極性と、周辺とは異なる類似した画素値の画像領域を示すスケールを、特徴量として算出する特徴量算出部と、
前記特徴量算出部で算出された特徴量に基づき、前記肌画像の特徴部分を抽出する特徴部分抽出部と
を備える画像処理装置。 - 前記肌画像に対して輝度情報分離処理を行い、グローバル輝度情報を取得する輝度情報分離部を備え、
前記特徴量算出部は、前記輝度情報分離部で取得した前記グローバル輝度情報を用いて前記特徴量の算出を行う
請求項1記載の画像処理装置。 - 前記特徴量算出部は、前記類似した画素値の画像領域と周辺との信号差を示す強度を、前記特徴量として算出する
請求項1記載の画像処理装置。 - メラニンの解析を行うメラニン解析部をさらに備え、
前記特徴部分抽出部は、前記特徴量算出部で算出された特徴量と前記メラニン解析部で得られた解析結果を用いて特徴部分の抽出を行う
請求項1記載の画像処理装置。 - 特徴部分が一致するように第1と第2の肌画像の位置合わせを行う画像位置合わせ部をさらに備え、
前記特徴量算出部は、強度変化の極性を示す第2特徴量の算出を行い、
前記画像位置合わせ部は、前記第2特徴量を用いて特徴部分のマッチングを行い、前記第1と第2の肌画像において対応する特徴部分が一致するように前記肌画像の位置合わせを行う
請求項1記載の画像処理装置。 - 前記第1の肌画像として過去画像、前記第2の肌画像として現在画像を用い、
前記画像位置合わせ部は、対応する特徴部分の数が所定数以下である場合、前記第2の肌画像において前記対応する特徴部分の位置が、前記第1の肌画像において対応する特徴部分の位置となるように撮像範囲の移動アドバイスを提示する
請求項5記載の画像処理装置。 - 前記特徴部分抽出部は、前記特徴部分として毛穴、吹出物、シミ、毛穴のつまり少なくとも何れかを抽出する
請求項1記載の画像処理装置。 - 前記特徴部分抽出部は、白色光を用いて撮像された肌画像から前記特徴量算出部で算出された特徴量に基づき、毛穴、吹出物、シミの少なくとも何れかを抽出し、近紫外光を用いて撮像された肌画像から前記特徴量算出部で算出された特徴量に基づき、毛穴のつまりを抽出する
請求項7記載の画像処理装置。 - 予め設定された抽出条件を満たす特徴量である特徴部分の抽出結果に基づき統計量の算出を行い、特徴部分の数と大きさと色の濃さの少なくとも何れかに関する情報を生成する統計量算出部を有する
請求項1記載の画像処理装置。 - 前記肌画像は、光源と撮像部に対して設けられた偏光フィルタを直交関係とすることで肌の表面反射が除外されている画像である
請求項1記載の画像処理装置。 - 肌画像の階調に関する極性と、周辺とは異なる類似した画素値の画像領域を示すスケールを、特徴量として算出する工程と、
前記算出された特徴量に基づき、前記肌画像の特徴部分を抽出する工程と
を含む画像処理方法。 - 肌画像の処理をコンピュータで実行させるプログラムであって、
肌画像の階調に関する極性と、周辺とは異なる類似した画素値の画像領域を示すスケールを、特徴量として算出する手順と、
前記算出された特徴量に基づき、前記肌画像の特徴部分を抽出する手順と
を前記コンピュータで実行させるプログラム。 - 撮像装置と情報処理装置を用いて構成される画像処理システムにおいて、
前記撮像装置には、肌画像を生成する撮像部を設け、
前記撮像装置または情報処理装置の何れかに、
前記肌画像の階調に関する極性と、周辺とは異なる類似した画素値の画像領域を示すスケールを、特徴量として算出する特徴量算出部と、
前記特徴量算出部で算出された特徴量に基づき、前記肌画像の特徴部分を抽出するに特徴部分抽出部と
前記特徴部分の抽出結果を提示する提示部と
を設けた画像処理システム。
Priority Applications (3)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US14/420,522 US9697618B2 (en) | 2012-08-17 | 2013-07-02 | Image processing apparatus, image processing method, program, and image processing system |
CN201380042484.XA CN104540445B (zh) | 2012-08-17 | 2013-07-02 | 图像处理装置、图像处理方法和图像处理*** |
JP2014530497A JP6299594B2 (ja) | 2012-08-17 | 2013-07-02 | 画像処理装置、画像処理方法、プログラムおよび画像処理システム |
Applications Claiming Priority (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
JP2012-180861 | 2012-08-17 | ||
JP2012180861 | 2012-08-17 |
Publications (1)
Publication Number | Publication Date |
---|---|
WO2014027522A1 true WO2014027522A1 (ja) | 2014-02-20 |
Family
ID=50685532
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
PCT/JP2013/068140 WO2014027522A1 (ja) | 2012-08-17 | 2013-07-02 | 画像処理装置、画像処理方法、プログラムおよび画像処理システム |
Country Status (4)
Country | Link |
---|---|
US (1) | US9697618B2 (ja) |
JP (1) | JP6299594B2 (ja) |
CN (1) | CN104540445B (ja) |
WO (1) | WO2014027522A1 (ja) |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015159767A1 (ja) * | 2014-04-18 | 2015-10-22 | ソニー株式会社 | 情報処理装置、情報処理方法、及び、プログラム |
EP3029629A1 (en) * | 2014-11-07 | 2016-06-08 | Casio Computer Co., Ltd. | Diagnostic apparatus and image processing method in the same apparatus |
WO2016121518A1 (ja) * | 2015-01-29 | 2016-08-04 | ソニー株式会社 | 情報処理装置、情報処理方法、およびプログラム |
JP2016539964A (ja) * | 2013-12-09 | 2016-12-22 | ユーシービー バイオファルマ エスピーアールエル | Tnf活性のモジュレーターとしてのテトラヒドロイミダゾピリジン誘導体 |
JP2017009598A (ja) * | 2015-06-16 | 2017-01-12 | 株式会社シーボン | 美容施術効果の解析方法 |
CN107079110A (zh) * | 2014-11-12 | 2017-08-18 | 索尼公司 | 信息处理装置、信息处理方法和程序 |
US9818183B2 (en) | 2014-11-07 | 2017-11-14 | Casio Computer Co., Ltd. | Disease diagnostic apparatus, image processing method in the same apparatus, and medium storing program associated with the same method |
US9836836B2 (en) | 2014-11-07 | 2017-12-05 | Casio Computer Co., Ltd. | Disease diagnostic apparatus, image processing method in the same apparatus, and medium storing program associated with the same method |
JP2018196426A (ja) * | 2017-05-23 | 2018-12-13 | 花王株式会社 | 毛穴検出方法及び毛穴検出装置 |
WO2020218180A1 (ja) * | 2019-04-24 | 2020-10-29 | ソニー株式会社 | 画像処理装置、方法及び電子機器 |
JP2021532915A (ja) * | 2018-08-21 | 2021-12-02 | ザ プロクター アンド ギャンブル カンパニーThe Procter & Gamble Company | 毛穴の色を特定する方法 |
Families Citing this family (19)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2014027523A1 (ja) * | 2012-08-17 | 2014-02-20 | ソニー株式会社 | 画像処理装置、画像処理方法、プログラムおよび画像処理システム |
US20160366316A1 (en) * | 2015-06-12 | 2016-12-15 | Htc Corporation | Skin analysis device and image capturing module thereof |
CN105787929B (zh) * | 2016-02-15 | 2018-11-27 | 天津大学 | 基于斑点检测的皮肤疹点提取方法 |
JP6650819B2 (ja) | 2016-04-15 | 2020-02-19 | 株式会社 資生堂 | 色ムラ部位の評価方法、色ムラ部位評価装置及び色ムラ部位評価プログラム |
CN106264463A (zh) * | 2016-08-05 | 2017-01-04 | 深圳美立知科技有限公司 | 一种皮肤敏感度分析方法及装置 |
TWI657799B (zh) * | 2016-09-29 | 2019-05-01 | 麗寶大數據股份有限公司 | 電子裝置與其提供膚質檢測資訊的方法 |
CN110177486B (zh) * | 2016-12-20 | 2022-04-08 | 株式会社资生堂 | 涂布控制装置、涂布控制方法、程序以及记录介质 |
EP3384829A1 (en) * | 2017-04-05 | 2018-10-10 | Koninklijke Philips N.V. | Skin gloss measurement for quantitative estimation of skin gloss |
CN108784647B (zh) * | 2017-04-27 | 2021-07-27 | 立特克科技股份有限公司 | 皮肤检测装置与其检测方法 |
CN109064438A (zh) | 2017-06-09 | 2018-12-21 | 丽宝大数据股份有限公司 | 皮肤状态检测方法、电子装置与皮肤状态检测*** |
CN110013102B (zh) * | 2017-12-22 | 2021-12-10 | 卡西欧计算机株式会社 | 图像处理装置、图像处理方法以及记录介质 |
CN109978810B (zh) * | 2017-12-26 | 2024-03-12 | 南通罗伯特医疗科技有限公司 | 痣的检测方法、***、设备及存储介质 |
WO2020189754A1 (ja) * | 2019-03-20 | 2020-09-24 | 学校法人慶應義塾 | 推定方法、推定モデルの生成方法、プログラム、及び推定装置 |
CN110298815B (zh) * | 2019-03-27 | 2023-04-14 | 天津财经大学 | 一种皮肤毛孔检测与评价的方法 |
US11961608B2 (en) * | 2019-11-11 | 2024-04-16 | Healthy.Io Ltd. | Image processing systems and methods for caring for skin features |
US20210196186A1 (en) * | 2019-12-30 | 2021-07-01 | L'oreal | Acne detection using image analysis |
JP7436708B2 (ja) | 2020-05-08 | 2024-02-22 | ザ プロクター アンド ギャンブル カンパニー | 樹状毛穴を識別するための方法 |
CN112274110B (zh) * | 2020-10-10 | 2023-06-16 | 苏州万微光电科技有限公司 | 一种基于皮肤荧光图像的毛孔检测***、装置及方法 |
CN115358930B (zh) * | 2022-10-19 | 2023-02-03 | 成都菁蓉联创科技有限公司 | 一种基于多无人机实时图像拼接方法及目标检测方法 |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1176173A (ja) * | 1997-09-12 | 1999-03-23 | Kenji Hashimoto | 肌診断器具 |
JP2006305184A (ja) * | 2005-04-28 | 2006-11-09 | Shiseido Co Ltd | 肌状態解析方法、肌状態解析装置、肌状態解析プログラム、及び該プログラムが記録された記録媒体 |
JP2007130329A (ja) * | 2005-11-11 | 2007-05-31 | Matsushita Electric Works Ltd | 画像による外観検査方法 |
JP2008293325A (ja) * | 2007-05-25 | 2008-12-04 | Noritsu Koki Co Ltd | 顔画像解析システム |
JP2010119431A (ja) * | 2008-11-17 | 2010-06-03 | Shiseido Co Ltd | シワ評価方法、シワ評価装置、シワ評価プログラム、及び該プログラムが記録された記録媒体 |
JP2011118671A (ja) * | 2009-12-03 | 2011-06-16 | Kao Corp | 画像処理装置、画像処理方法、画像処理システム、肌評価方法 |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP3219550B2 (ja) * | 1993-06-30 | 2001-10-15 | 株式会社資生堂 | 肌の表面状態の解析システム |
IL124616A0 (en) * | 1998-05-24 | 1998-12-06 | Romedix Ltd | Apparatus and method for measurement and temporal comparison of skin surface images |
JP2003070749A (ja) * | 2001-09-07 | 2003-03-11 | Scalar Corp | 診断システム、肌の診断方法、及びそれに用いられる情報処理装置、並びにプログラム、記録媒体 |
JP3919722B2 (ja) * | 2003-09-11 | 2007-05-30 | 花王株式会社 | 肌形状計測方法及び肌形状計測装置 |
JP4548076B2 (ja) * | 2003-10-02 | 2010-09-22 | パナソニック電工株式会社 | 光式生体情報測定装置 |
WO2006118060A1 (ja) | 2005-04-28 | 2006-11-09 | Shiseido Company, Ltd. | 肌状態解析方法、肌状態解析装置、及び肌状態解析プログラムを記録した記録媒体 |
JP2007061307A (ja) * | 2005-08-30 | 2007-03-15 | Shiseido Co Ltd | シミの分類方法 |
JP5080060B2 (ja) * | 2005-11-08 | 2012-11-21 | 株式会社 資生堂 | 肌状態解析方法、肌状態解析装置、肌状態解析プログラム、及び該プログラムが記録された記録媒体 |
SG177951A1 (en) * | 2007-01-05 | 2012-02-28 | Myskin Inc | System, device and method for dermal imaging |
JP2009098925A (ja) | 2007-10-17 | 2009-05-07 | Sony Corp | 画像処理装置、画像処理方法、および、プログラム |
JP5426475B2 (ja) * | 2010-05-21 | 2014-02-26 | 株式会社 資生堂 | 肌の色ムラ解析装置、肌の色ムラ解析方法、及び肌の色ムラ解析プログラム |
WO2012012576A1 (en) * | 2010-07-20 | 2012-01-26 | Lockheed Martin Corporation | Image analysis systems using non-linear data processing techniques and methods using same |
-
2013
- 2013-07-02 CN CN201380042484.XA patent/CN104540445B/zh not_active Expired - Fee Related
- 2013-07-02 JP JP2014530497A patent/JP6299594B2/ja active Active
- 2013-07-02 WO PCT/JP2013/068140 patent/WO2014027522A1/ja active Application Filing
- 2013-07-02 US US14/420,522 patent/US9697618B2/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JPH1176173A (ja) * | 1997-09-12 | 1999-03-23 | Kenji Hashimoto | 肌診断器具 |
JP2006305184A (ja) * | 2005-04-28 | 2006-11-09 | Shiseido Co Ltd | 肌状態解析方法、肌状態解析装置、肌状態解析プログラム、及び該プログラムが記録された記録媒体 |
JP2007130329A (ja) * | 2005-11-11 | 2007-05-31 | Matsushita Electric Works Ltd | 画像による外観検査方法 |
JP2008293325A (ja) * | 2007-05-25 | 2008-12-04 | Noritsu Koki Co Ltd | 顔画像解析システム |
JP2010119431A (ja) * | 2008-11-17 | 2010-06-03 | Shiseido Co Ltd | シワ評価方法、シワ評価装置、シワ評価プログラム、及び該プログラムが記録された記録媒体 |
JP2011118671A (ja) * | 2009-12-03 | 2011-06-16 | Kao Corp | 画像処理装置、画像処理方法、画像処理システム、肌評価方法 |
Cited By (22)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2016539964A (ja) * | 2013-12-09 | 2016-12-22 | ユーシービー バイオファルマ エスピーアールエル | Tnf活性のモジュレーターとしてのテトラヒドロイミダゾピリジン誘導体 |
JPWO2015159767A1 (ja) * | 2014-04-18 | 2017-04-13 | ソニー株式会社 | 情報処理装置、情報処理方法、及び、プログラム |
US11324438B2 (en) | 2014-04-18 | 2022-05-10 | Sony Corporation | Information processing apparatus, information processing method, and non-transitory computer-readable medium for acquiring and displaying a skin condition analysis result based on an epidermis image |
WO2015159767A1 (ja) * | 2014-04-18 | 2015-10-22 | ソニー株式会社 | 情報処理装置、情報処理方法、及び、プログラム |
US9836836B2 (en) | 2014-11-07 | 2017-12-05 | Casio Computer Co., Ltd. | Disease diagnostic apparatus, image processing method in the same apparatus, and medium storing program associated with the same method |
US10055844B2 (en) | 2014-11-07 | 2018-08-21 | Casio Computer Co., Ltd. | Disease diagnostic apparatus, image processing method in the same apparatus, and medium storing program associated with the same method |
EP3029629A1 (en) * | 2014-11-07 | 2016-06-08 | Casio Computer Co., Ltd. | Diagnostic apparatus and image processing method in the same apparatus |
US9996928B2 (en) | 2014-11-07 | 2018-06-12 | Casio Computer Co., Ltd. | Disease diagnostic apparatus, image processing method in the same apparatus, and medium storing program associated with the same method |
US9881368B2 (en) | 2014-11-07 | 2018-01-30 | Casio Computer Co., Ltd. | Disease diagnostic apparatus, image processing method in the same apparatus, and medium storing program associated with the same method |
US9818183B2 (en) | 2014-11-07 | 2017-11-14 | Casio Computer Co., Ltd. | Disease diagnostic apparatus, image processing method in the same apparatus, and medium storing program associated with the same method |
US20170316554A1 (en) * | 2014-11-12 | 2017-11-02 | Sony Corporation | Information processing apparatus, information processing method, and program |
US10229485B2 (en) * | 2014-11-12 | 2019-03-12 | Sony Corporation | Information processing apparatus and information processing method |
CN107079110B (zh) * | 2014-11-12 | 2020-04-14 | 索尼公司 | 信息处理装置、信息处理方法和计算机可读记录介质 |
CN107079110A (zh) * | 2014-11-12 | 2017-08-18 | 索尼公司 | 信息处理装置、信息处理方法和程序 |
WO2016121518A1 (ja) * | 2015-01-29 | 2016-08-04 | ソニー株式会社 | 情報処理装置、情報処理方法、およびプログラム |
JPWO2016121518A1 (ja) * | 2015-01-29 | 2017-11-09 | ソニー株式会社 | 情報処理装置、情報処理方法、およびプログラム |
US10682089B2 (en) | 2015-01-29 | 2020-06-16 | Sony Corporation | Information processing apparatus, information processing method, and program |
JP2017009598A (ja) * | 2015-06-16 | 2017-01-12 | 株式会社シーボン | 美容施術効果の解析方法 |
JP2018196426A (ja) * | 2017-05-23 | 2018-12-13 | 花王株式会社 | 毛穴検出方法及び毛穴検出装置 |
JP2021532915A (ja) * | 2018-08-21 | 2021-12-02 | ザ プロクター アンド ギャンブル カンパニーThe Procter & Gamble Company | 毛穴の色を特定する方法 |
JP7108127B2 (ja) | 2018-08-21 | 2022-07-27 | ザ プロクター アンド ギャンブル カンパニー | 毛穴の色を特定する方法 |
WO2020218180A1 (ja) * | 2019-04-24 | 2020-10-29 | ソニー株式会社 | 画像処理装置、方法及び電子機器 |
Also Published As
Publication number | Publication date |
---|---|
CN104540445A (zh) | 2015-04-22 |
US20150213619A1 (en) | 2015-07-30 |
JPWO2014027522A1 (ja) | 2016-07-25 |
US9697618B2 (en) | 2017-07-04 |
CN104540445B (zh) | 2017-05-17 |
JP6299594B2 (ja) | 2018-03-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
JP6299594B2 (ja) | 画像処理装置、画像処理方法、プログラムおよび画像処理システム | |
JP6483826B2 (ja) | 画像解析装置、画像解析方法、画像解析システム、画像解析プログラム、および記録媒体 | |
JP6045417B2 (ja) | 画像処理装置、電子機器、内視鏡装置、プログラム及び画像処理装置の作動方法 | |
TWI669660B (zh) | 斑點評估裝置、斑點評估方法及程式 | |
WO2023103467A1 (zh) | 图像处理方法、装置及设备 | |
CN107958453B (zh) | 乳腺图像病变区域的检测方法、装置及计算机存储介质 | |
US9053537B2 (en) | Classifier for use in generating a diffuse image | |
Zhou et al. | Feature-preserving artifact removal from dermoscopy images | |
JP5914688B2 (ja) | デジタル画像に関する色解析 | |
Raffei et al. | A low lighting or contrast ratio visible iris recognition using iso-contrast limited adaptive histogram equalization | |
CN107529963B (zh) | 图像处理装置、图像处理方法和存储介质 | |
KR101612188B1 (ko) | 흑색종의 병변 판단 장치 및 방법 | |
Paulsen et al. | Introduction to medical image analysis | |
GB2541864A (en) | Automatic detection of cutaneous lesions | |
CN117764994B (zh) | 基于人工智能的胆胰成像***及方法 | |
JP2006227973A (ja) | 物体追跡方法および物体追跡装置ならびにプログラム | |
WO2014083743A1 (ja) | 画像計測装置および画像計測方法 | |
JP2006061170A (ja) | 皮膚の鑑別法 | |
JP5860970B2 (ja) | 固有画像の生成を改良するための後処理 | |
Reza et al. | Automatic detection of optic disc in fundus images by curve operator | |
JP2017023474A (ja) | 皮膚毛穴解析装置,皮膚毛穴解析方法および該装置に用いるプログラム | |
EP3023936B1 (en) | Diagnostic apparatus and image processing method in the same apparatus | |
CN107832763A (zh) | 图形图像处理方法和设备 | |
CN113128372A (zh) | 基于图像处理的黑头识别方法、黑头识别装置及终端设备 | |
Breneman | Towards early-stage malignant melanoma detection using consumer mobile devices |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
121 | Ep: the epo has been informed by wipo that ep was designated in this application |
Ref document number: 13879479 Country of ref document: EP Kind code of ref document: A1 |
|
ENP | Entry into the national phase |
Ref document number: 2014530497 Country of ref document: JP Kind code of ref document: A |
|
WWE | Wipo information: entry into national phase |
Ref document number: 14420522 Country of ref document: US |
|
NENP | Non-entry into the national phase |
Ref country code: DE |
|
122 | Ep: pct application non-entry in european phase |
Ref document number: 13879479 Country of ref document: EP Kind code of ref document: A1 |