KR20170100717A

KR20170100717A - Apparatus and method for analyzing skin condition using spectral reflectance estimation

Info

Publication number: KR20170100717A
Application number: KR1020160022765A
Authority: KR
Inventors: 장인수; 남승우; 최윤석; 정순철; 김진서
Original assignee: 한국전자통신연구원
Priority date: 2016-02-25
Filing date: 2016-02-25
Publication date: 2017-09-05

Abstract

Disclosed are an apparatus and a method for analyzing a skin condition using spectral reflectance estimation. The method includes: photographing and measuring a predetermined color chart by a digital camera in skin analysis; generating a plurality of skin color samples according to the result of the measurement; obtaining an image of the skin to be measured photographed by the digital camera; estimating a transformation matrix using skin color samples according to spectrum-based input and output characteristics of the digital camera; and applying the transformation matrix to the image to estimate analysis data of the skin to be measured, wherein the analysis data includes at least one of a melanin index and a hemoglobin index. Accordingly, the present invention can improve the performance of skin analysis through a simple work.

Description

[0001] APPARATUS AND METHOD FOR ANALYZING SKIN CONDITION USING SPECTRAL REFLECTANCE ESTIMATION [0002]

The present invention relates to a skin analysis apparatus and method for processing skin condition analysis using a digital camera-based face scanner.

Generally, the skin analysis is performed by photographing the skin with a camera using a general light, a polarized light, an ultraviolet (UV) light source, and estimating information on skin tone (or color), pore, do. Since most of the images used in the image analysis are images that are corrected through the image processing chip of the camera, there is a problem that the accuracy of the analysis data is lowered.

On the other hand, in order to estimate the melanin and hemoglobin index which determine the skin tone among the skin conditions, reflectance information for a light source of a specific wavelength band is required. In this case, even if raw data that does not pass through the image processing chip of the camera is used, the estimation is limited because the raw data is already the data through the red, green, and blue color filters of the camera. Therefore, in order to obtain optimal data for analyzing the skin condition, it is necessary to use an expensive camera using the filter of the corresponding wavelength band.

In the conventional skin analyzer, a single item analysis filter was attached to a CCD (Charge Coupled Device) camera, and a specific point of the skin was photographed. In this case, not only is the price of the imaging equipment high, but also it is difficult to analyze the entire face since only one item of data can be obtained by measuring a specific point of the skin.

On the other hand, by analyzing the image of the entire face taken by a general digital camera, it is possible to analyze various skin conditions such as wrinkles and pores with one device. However, the skin analysis method using such a digital camera has a limitation in that the accuracy with respect to specific skin analysis indexes such as melanin and hemoglobin is low. Therefore, there is a need for a method for improving the skin analysis accuracy of a face scanner using a digital camera.

In this regard, Korean Patent Laid-Open No. 10-2001-0110850 (entitled " scan data registration system and scan data registration method using the same ") discloses a technique for acquiring skin images obtained through a skin scanner equipped with an optical system and an imaging device And a skin condition analysis server for receiving skin image data transmitted from a remote skin image acquisition device through a data communication network and analyzing the skin condition through a communication network, The skin condition analyzing server stores standard skin information data composed of a plurality of digitized skin information each having a value suitable for each taxon, the plurality of skin information being converted into numerical values, and each taxon classified according to a predetermined classification Wherein the skin condition analysis unit includes a skin information database, A plurality of pieces of skin information for skin condition determination are measured and converted into numerical values, and the skin condition is analyzed by comparing the converted values with standard skin information data, and the result is transmitted to a skin image acquisition device through a data communication network A skin condition analyzing system.

An embodiment of the present invention is to provide a skin analysis apparatus and method for acquiring skin reflectance information of a specific wavelength band in a skin photographing step using a digital camera to process skin condition analysis.

It should be understood, however, that the technical scope of the present invention is not limited to the above-described technical problems, and other technical problems may exist.

According to one aspect of the present invention, there is provided a skin analysis apparatus comprising: a digital camera for photographing and measuring a predetermined color chart; a plurality of skin color samples corresponding to a result of the measurement; A skin color sample generating unit for generating a skin color sample; A skin photographing unit for acquiring an image of the measurement subject skin taken by the digital camera; A spectral characteristic estimator for estimating a transform matrix using the skin color samples according to an input / output characteristic of a spectrum of the digital camera; And a skin analysis data estimating unit for estimating analysis data of the measurement target skin by applying the transformation matrix to the image, wherein the analysis data includes at least one of a melanin index and a hemoglobin index.

According to any one of the above-mentioned objects of the present invention, the performance of the skin analysis can be improved through a simple operation in a generally used skin scanner. In addition, it can be applied to various analysis items such as melanin and hemoglobin index by using spectral reflectance analysis data instead of skin analysis of simple image processing.

According to any one of the tasks of the present invention, since the data reflecting the input / output characteristics of the camera is used as the spectral-based skin analysis technique, the accuracy of the skin analysis method using the RGB data of the general camera is higher than that of the conventional analysis method, It is possible to process results faster than skin analysis system using expensive equipment.

1 is a block diagram showing a configuration of a skin analysis apparatus according to an embodiment of the present invention.
2 is a flowchart illustrating a method of optimizing a transform matrix in a reflectivity estimation process according to an exemplary embodiment of the present invention.
3 is a flowchart illustrating a skin analysis method according to an embodiment of the present invention.

Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings, which will be readily apparent to those skilled in the art. The present invention may, however, be embodied in many different forms and should not be construed as limited to the embodiments set forth herein. In order to clearly explain the present invention in the drawings, parts not related to the description are omitted.

Throughout the specification, when an element is referred to as "including" an element, it does not exclude other elements unless specifically stated to the contrary, But do not preclude the presence or addition of one or more of the other features, numbers, steps, operations, elements, parts, or combinations thereof.

In this specification, the term " part " means a unit realized by hardware or software, a unit realized by using both, and one unit may be realized by using two or more hardware, The above units may be realized by one hardware.

Hereinafter, a skin analysis apparatus and an analysis method thereof according to an embodiment of the present invention will be described in detail with reference to the drawings.

1 is a block diagram showing a configuration of a skin analysis apparatus according to an embodiment of the present invention

1, the skin analysis apparatus 100 according to an embodiment of the present invention includes a skin color sample generation unit 110, a spectrum characteristic estimation unit 120, a skin photographing unit 130, And an estimating unit 140.

At this time, the skin analysis apparatus 100 is a device including a function as a scanner for scanning the skin using a digital camera. That is, the color sample generation unit 110 and the skin photographing unit 130 of the skin analysis apparatus 100 may be a scanner using a digital camera, or may acquire and process data photographed from a digital camera in cooperation with the scanner . On the other hand, the skin analysis apparatus 100 estimates a transformation matrix related to input / output characteristics based on a spectrum of a camera used in a scanner using a color chart. Then, the skin analysis apparatus 100 performs skin analysis by converting the RGB data of the skin image taken by the scanner into skin analysis data using the estimated conversion matrix.

The skin color sample generation unit 110 photographs and measures a skin color sample to be used as reference data of skin analysis.

The skin color sample generation unit 110 measures data obtained by photographing the predetermined color chart through the digital camera of the scanner and extracts reference data (i.e., skin color sample) for estimating the input / output characteristics of the digital camera . For reference, the selection of skin color samples and skin imaging preferences have a significant impact on the end result of the skin analysis process.

The skin color sample generation unit 110 can use a skin color chart composed of only skin color, not a color chart including various commonly used colors as a skin color sample. For reference, the types and the number of skin color samples can be adjusted in the optimization process of the spectral characteristic estimating unit 120.

The environment for photographing the skin color sample can be performed in the same environment as the environment for photographing the skin to be measured, such as a face, in order to perform actual skin analysis. For example, a color chart as a skin color sample can be positioned and photographed at a portion of the scanner where the face will be located (e.g., "center portion"). For reference, when shooting a skin color sample, the camera's output file format can be selected and saved in the RAW file format. This is because, in the case of a file format such as general JPEG or TIFF, color is distorted due to the image processing process of the camera itself. Therefore, in one embodiment of the present invention, a RAW file format without a color correction process is used as a file format of an image.

In addition, the skin color sample generation unit 110 acquires the average RGB value of the skin color sample portion in the photographed image as photographic data.

At this time, the spectral reflectance can be measured for the same skin color sample as the skin color sample obtained with the average RGB value, and the measured spectral reflectance can be used to estimate the input / output characteristics of the camera.

The spectral characteristic estimating unit 120 estimates the relationship between digital RGB data, which is an output signal for spectral reflectance data, which is an input signal of a camera used in a scanner. At this time, the spectral characteristic estimator 120 estimates a transform matrix according to the input / output characteristics based on the spectral reflectance data of the camera and the RGB data.

In general, the spectral reflectance data can utilize 62 or 31 data sampled at 5 nm or 10 nm for a wavelength range of 400 to 700 nm. For example, as shown in the following Equation 1, the output digital RGB signal D of the camera can be estimated for n input reflection information R ?. At this time, since the input / output characteristics of the camera have linearity, a conversion matrix can be obtained through linear conversion as shown in Equation (1) below.

For reference, when using the entire data as in Equation (1), since the relationship of the output signals to the input signals is corresponded several-for-one, it is difficult to obtain an optimal single solution.

On the other hand, melanin and hemoglobin indicators can be used in the analysis of skin color and condition in skin analysis. These melanin and hemoglobin indicators are estimated using the spectral reflectance model of the skin. At this time, as shown in the following equation (2), the absorptivity (A) of the skin and the reflectance (R) are in inverse proportion, and the reflectance can be estimated through the reflectance model for this absorptivity.

Where M is the absorption coefficient of melanin, H is the absorption coefficient of hemoglobin, and C _m and C _h indicate amounts of hemoglobin and melanin, respectively. D is the absorption rate of other skin constituents. To obtain C representing the amount of melanin and hemoglobin, a difference between two absorbances for two specific wavelength ranges is used as shown in Equation 3 below.

At this time, as the wavelength band, the absorption rate of melanin is greatly different, and the absorption rate of hemoglobin is not substantially different (

) The amount of melanin can be obtained using the wavelength band. In addition, as the wavelength band, the absorption rate of hemoglobin differs greatly, and the absorption rate of melanin is little different (

) The amount of hemoglobin can be determined using the wavelength band. In other words, it can be calculated using the absorption rate of at least two wavelengths to estimate the amount of melanin and hemoglobin.

Accordingly, the spectral characteristic estimating unit 120 can correct Equation (1) for estimating the input / output characteristics of the camera used in the scanner as shown in Equations (4) and (5) below by applying a specific wavelength band.

That is, spectral characteristics are estimated by separating each conversion matrix corresponding to melanin and hemoglobin. To do this, we use the data obtained by taking and measuring skin color samples. At this time, the conversion matrix is estimated using n or more skin color sample data as shown in Equations (6) and (7) below.

In estimating the transform matrix, an inverse matrix of the digital RGB matrix D, which is the right term for each of Equations (6) and (7), can be obtained and estimated as shown in Equation (8) below.

On the other hand, in order to optimize the reflectance estimation process, it is possible to process the correction of the transformation matrix using a combination of skin color samples. Hereinafter, a method of optimizing the reflectance estimation process will be described with reference to FIG.

2 is a flowchart illustrating a method of optimizing a transform matrix in a reflectivity estimation process according to an exemplary embodiment of the present invention.

First, a transform matrix is estimated using skin color samples (S210).

At this time, the transformation matrix is estimated using the entire skin color sample and Equation (8).

Next, an estimation error for the entire skin color sample is calculated (S220).

At this time, the spectral reflectance estimated through Equation (6) or (7) is calculated using the transform matrix estimated through the step (S210), and the difference between the estimated spectral reflectance and the actually measured data is calculated.

Then, it is determined whether the calculated estimation error is minimum (S230). If the estimation error is not minimum, the number and combination of sample skin colors are changed (S240), and the process returns to the step S210, . An error is calculated with respect to the number of all possible combinations to finally determine the minimum combination (S250).

The spectrum characteristic estimating unit 120 transmits the transformation matrix obtained through the above steps to the skin analysis data estimating unit 140. [

Referring back to FIG. 1, the skin photographing unit 130 acquires the result of photographing the actual skin to be measured, in an environment identical to the environment in which the camera used in the scanner photographs the skin color sample. At this time, the image (i.e., image) of the skin image is stored as a RAW file and the digital RGB data of the skin area is used.

The skin analysis data estimating unit 140 uses the digital RGB data of the skin image acquired through the skin photographing unit 130 to estimate the melanin and hemoglobin indexes, which are the target skin analysis data.

At this time, the skin analysis data estimating unit 140 uses the spectral reflectance data for melanin estimation and the spectral reflectance data for hemoglobin estimation obtained through the spectral characteristic estimator 120. [ That is, the spectral reflectance data for melanin and hemoglobin estimation can be obtained from the images of the skin to be measured, using Equations 4 and 5 above.

The skin analysis data estimating unit 140 finally estimates the melanin and hemoglobin index using the respective spectral reflectance data. At this time, the skin analysis data estimation unit 140 can derive the final melanin and hemoglobin index using Equation (3).

Meanwhile, the skin analysis apparatus 100 according to an embodiment of the present invention may include a scanner (not shown), a memory (not shown), and a processor (not shown).

That is, the memory (not shown) stores a program including a series of operations and algorithms for processing the skin condition analysis based on the spectral reflectance described above. At this time, the program stored in the memory (not shown) may be a program in which all the operations processed by the respective components of the skin analysis apparatus 100 are implemented as one, or a plurality of programs for separately processing the operations of the components of the skin analysis apparatus 100 May be interlinked with each other. A processor (not shown) executes a program stored in a memory (not shown). As the processor (not shown) executes the program, the operations and algorithms processed by the respective components of the skin analysis apparatus 100 described above can be performed. For reference, the components of the skin analysis apparatus 100 may be implemented in hardware such as software or an FPGA (Field Programmable Gate Array) or ASIC (Application Specific Integrated Circuit), and may perform predetermined roles. However, 'components' are not meant to be limited to software or hardware, and each component may be configured to reside on an addressable storage medium and configured to play one or more processors. Thus, by way of example, an element may comprise components such as software components, object-oriented software components, class components and task components, processes, functions, attributes, procedures, Routines, segments of program code, drivers, firmware, microcode, circuitry, data, databases, data structures, tables, arrays, and variables. The components and functions provided within those components may be combined into a smaller number of components or further separated into additional components.

Hereinafter, a skin condition analysis method using the skin analysis apparatus 100 according to an embodiment of the present invention will be described with reference to FIG.

3 is a flowchart illustrating a skin analysis method according to an embodiment of the present invention.

First, the predetermined color chart is photographed through the digital camera of the scanner, and the photographed result is measured to generate skin color samples (S310).

Digital RGB data is obtained from these skin color samples.

Next, a transformation matrix is generated according to input / output characteristics of the digital camera, and a transformation matrix is generated using digital RGB data and spectral reflectance for the skin color sample (S320).

At this time, the input signal of the camera is the spectral reflectance of the skin color sample, and the output signal is the digital RGB data of the skin color sample.

In addition, in one embodiment of the present invention, the spectral characteristics of a digital camera with respect to skin color indexes such as melanin and hemoglobin index can be estimated using skin color samples. Such melanin and hemoglobin indices can be estimated through a spectral reflectance model that is inversely proportional to skin absorption and reflectance. At this time, spectral reflectance modeling is performed for a specific wavelength band specialized for the melanin and hemoglobin index, so that a conversion matrix can be generated more efficiently.

Then, in a similar environment to the environment in which the skin color sample is photographed, the actual skin to be measured is photographed to acquire skin image data (S330).

And obtains digital RGB data from this skin image.

Next, the skin analysis data of a predetermined type is estimated by applying the transformation matrix to the obtained skin image (S340).

At this time, the kind of the skin analysis data is not limited, but in one embodiment of the present invention, it has been shown that the skin color (or tone) characteristic includes melanin and hemoglobin index.

That is, in one embodiment of the present invention, a process for optimizing the transformation matrix may be performed to estimate skin color index for actually measured skin.

Specifically, the step S320 includes estimating a transformation matrix using the entire skin color sample, calculating an estimation error for the estimated entire skin color sample, and estimating a transformation matrix until the estimation error becomes minimum And determining a final transformation matrix by applying a combination and a number of skin color samples that minimize the estimation error after repeating the process.

The skin analysis method using the skin analysis apparatus 100 according to an embodiment of the present invention described above may be performed in the form of a computer program stored in a medium executed by a computer or a recording medium including instructions executable by the computer Can be implemented. Computer readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. In addition, the computer-readable medium may include both computer storage media and communication media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Communication media typically includes any information delivery media, including computer readable instructions, data structures, program modules, or other data in a modulated data signal such as a carrier wave, or other transport mechanism.

While the methods and systems of the present invention have been described in connection with specific embodiments, some or all of those elements or operations may be implemented using a computer system having a general purpose hardware architecture.

It will be understood by those skilled in the art that the foregoing description of the present invention is for illustrative purposes only and that those of ordinary skill in the art can readily understand that various changes and modifications may be made without departing from the spirit or essential characteristics of the present invention. will be. It is therefore to be understood that the above-described embodiments are illustrative in all aspects and not restrictive. For example, each component described as a single entity may be distributed and implemented, and components described as being distributed may also be implemented in a combined form.

The scope of the present invention is defined by the appended claims rather than the detailed description and all changes or modifications derived from the meaning and scope of the claims and their equivalents are to be construed as being included within the scope of the present invention do.

100: Skin analysis device
110: skin color sample generation unit
120: spectral characteristic estimating unit
130:
140: skin analysis data estimation unit

Claims

In a skin analyzer,
A skin color sample generation unit that takes a predetermined color chart with a digital camera and generates a plurality of skin color samples according to a result of measuring the photographed data;
A skin photographing unit for acquiring an image of the measurement subject skin taken by the digital camera;
A spectral characteristic estimator for generating a transform matrix according to input / output characteristics of a spectrum of the digital camera, the spectral characteristic estimator estimating the transform matrix using the skin color samples; And
And a skin analysis data estimating unit for estimating analysis data of the measurement target skin by applying the transformation matrix to the captured image,
The analysis data includes:
A melanin index, and a hemoglobin index.