Skin detection method and system based on FPI image acquisition system

Abstract

The invention discloses a skin detection method and system based on an FPI image acquisition system, and the method comprises the steps: S1, employing an adjustable FPI image acquisition system, selecting a corresponding characteristic wavelength according to a to-be-detected substance, and carrying out the collection of a human face image, and obtaining a characteristic wavelength image; s2, acquiring a to-be-detected human face skin area on the characteristic wavelength image through a human face recognition algorithm, and aligning the characteristic wavelength image to obtain spectral data of each pixel of the to-be-detected human face skin area; s3, performing correlation analysis on the spectral data of each pixel of the to-be-detected human face skin area and the reference spectral data of the to-be-detected substance; and S4, obtaining distribution of the to-be-detected substance on the to-be-detected human face skin area based on a correlation analysis result, and performing visual output.

Description

Technical Field

[0001] The present invention relates to the field of skin detection and analysis, and in particular to a skin detection method and system based on an FPI image acquisition system. Background Art

[0002] Current skin detection systems generally use different light source spectra (such as UVA, parallel polarized light, cross-polarized light, Wood's light, ultraviolet light, blue light, etc.) to collect images, obtain different spectral images, analyze surface features and structural features, and provide quantitative measurement and evaluation functions such as severity assessment before treatment and efficacy evaluation after treatment for beauty care, and medical diagnosis.

[0003] Such skin detection systems have complex structures, cannot be miniaturized, and are inconvenient to use. The number of spectral images provided is limited, and spectral dimension analysis cannot be achieved, resulting in poor accuracy of detection results.

[0004] The adjustable Fabry-Perot filter (FPI) is a narrow-band adjustable filter, which consists of a pair of high-reflectivity mirrors that are parallel to each other and at a certain distance, and a power device to adjust the distance between the two. According to the principle of interference, a group of plane mirrors with different spacing can filter different lengths, so the output wave can be controlled by adjusting the spacing between the parallel mirrors of the cavity. Due to the small size and low cost of the adjustable FPI, by replacing the current transmission grating for spectroscopy, it can greatly simplify the structure of the hyperspectral imaging system and realize the miniaturization of the hyperspectral system.

[0005] Therefore, compared with the traditional multi-light source skin detection system, the FPI image acquisition system can output a smaller half-wave peak width and a larger number of band images, thereby providing detection and analysis of more skin parameters and more accurate detection. Summary of the invention

[0006] In view of the technical problems in the prior art, the present application proposes a skin detection method and system based on an FPI image acquisition system.

[0007] According to one aspect of the present invention, a skin detection method based on an FPI image acquisition system is proposed, comprising the following steps:

[0008] S1. Use an adjustable FPI image acquisition system to select the corresponding characteristic wavelength according to the substance to be detected to collect the face image and obtain the characteristic wavelength image;

[0009] S2. Obtain the facial skin area to be detected on the characteristic wavelength image by using a face recognition algorithm, align the characteristic wavelength image, and obtain spectral data of each pixel of the facial skin area to be detected;

[0010] S3, performing correlation analysis on the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected;

[0011] S4. Based on the result of the correlation analysis, the distribution of the substance to be detected on the skin area of ​​the face to be detected is obtained and output visually.

[0012] The substance to be detected is a skin component of the facial skin area to be detected, optionally including porphyrin, blood oxygen, eumelanin, pheomelanin, melanin, carotene, bilirubin, water, lipid or hemoglobin. The method of the present invention can select different skin components for analysis according to actual needs to obtain corresponding content and distribution.

[0013] Preferably, selecting the corresponding characteristic wavelength according to the substance to be detected in S1 specifically includes: for substances to be detected with known characteristic wavelengths, selecting the corresponding characteristic wavelength by adjusting the adjustable FPI image acquisition system; extracting features of substances to be detected with unknown characteristic wavelengths to determine the characteristic wavelength, and then selecting the corresponding characteristic wavelength by adjusting the adjustable FPI image acquisition system. Compared with ordinary skin detection systems, the adjustable FPI image acquisition system is used to collect facial images of corresponding characteristic wavelengths, which is more targeted, has less data processing volume, and has high detection efficiency.

[0014] Preferably, the acquisition of the reference spectral data of the substance to be detected in S3 includes: pre-collecting skin data containing the substance to be detected by a hyperspectral camera, thereby obtaining a reference spectral curve of the substance to be detected on the skin as the reference spectral data of the substance to be detected. The reference spectral data of the substance to be detected can be pre-collected before detecting the skin and stored in a corresponding storage unit. When comparative analysis is required, the pre-stored reference spectral data is called. By using the spectral curve of the substance on the skin as the reference spectrum, rather than the spectral curve of the substance itself, the similarity with the spectral curve detected by the actual skin is better, and the analysis result is more accurate.

[0015] Preferably, the acquisition of the reference spectrum data of the substance to be detected in S3 includes: searching for the enriched area of ​​the substance to be detected in the skin area of ​​the face to be detected, taking the average spectrum of the enriched area as the reference spectrum curve of the substance to be detected on the skin, and obtaining the reference spectrum data of the substance to be detected. By using the spectrum of the substance enriched area in the skin area of ​​the face to be detected as the reference spectrum, the spectrum differences caused by individual skin differences and light source differences can be eliminated, and the detection result is more accurate.

[0016] Further preferably, the correlation analysis is performed by calculating the distance function, correlation coefficient, spectral information divergence or spectral angle between the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected. The correlation analysis method can achieve relative quantitative analysis and has a fast detection and analysis speed.

[0017] Preferably, S4 specifically includes: mapping the correlation analysis result of each pixel of the facial skin area to be detected to a colormap, so that different values ​​correspond to different colors, and outputting a visualized effect diagram. Outputting a visualized effect diagram through a colormap can intuitively quantify the distribution state of the substance to be detected on the skin, which is conducive to observing the state of the skin and reducing the difficulty of treatment.

[0018] According to one aspect of the present invention, a skin detection system based on an FPI image acquisition system is proposed, comprising the following modules:

[0019] Characteristic wavelength image acquisition module: using an adjustable FPI image acquisition system, select the corresponding characteristic wavelength according to the substance to be detected to collect facial images and obtain characteristic wavelength images;

[0020] Spectral data acquisition module: acquires the facial skin area to be detected on the characteristic wavelength image through a face recognition algorithm, aligns the characteristic wavelength image, and obtains spectral data of each pixel of the facial skin area to be detected; and

[0021] Correlation analysis module: performing correlation analysis on the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected;

[0022] Visualization output module: based on the results of correlation analysis, the distribution of the substance to be detected on the skin area of ​​the face to be detected is obtained and visualized.

[0023] According to one aspect of the present invention, a computer program product is provided, on which a computer program is stored. When the computer program is executed by a processor, the method according to any one of the first aspects is implemented.

[0024] According to one aspect of the present invention, a computing system is provided, including a processor and a memory, wherein the processor is configured to execute the method as described in any one of the first aspects.

[0025] The present invention is beneficial in that:

[0026] 1. Through the FPI image acquisition system, the target band images can be collected in a targeted manner, which greatly reduces the amount of spectral imaging data and improves the detection speed.

[0027] 2. Using spectral correlation analysis and relative quantitative analysis, the detection and analysis speed is fast.

[0028] 3. Using the spectral curve of the substance on the skin as the pre-stored reference spectrum can be closer to the actual test results; using the spectrum of the substance-enriched area in the facial skin area to be tested as the reference spectrum to eliminate the spectral differences caused by individual skin differences and light source differences, the test results are more accurate. BRIEF DESCRIPTION OF THE DRAWINGS

[0029] The accompanying drawings are included to provide a further understanding of the embodiments and are incorporated into and constitute a part of this specification. The accompanying drawings illustrate the embodiments and are used together with the description to explain the principles of the present invention. It will be easy to recognize other embodiments and many expected advantages of the embodiments because they become better understood by reference to the following detailed description. The elements of the drawings are not necessarily to scale with each other. The same reference numerals refer to corresponding similar parts.

[0030] Figure 1 A flowchart of a skin detection method based on an FPI image acquisition system according to the present invention is shown;

[0031] Figure 2 A diagram showing the effect of detecting hemoglobin according to the skin detection method based on the FPI image acquisition system of the present invention;

[0032] Figure 3 A structural diagram of a skin detection system based on an FPI image acquisition system according to the present invention is shown.

[0033] Figure 4 It is a schematic diagram of the structure of a computer device suitable for implementing an electronic device of an embodiment of the present invention. DETAILED DESCRIPTION

[0034] The present application will be further described in detail below in conjunction with the accompanying drawings and embodiments. It is to be understood that the specific embodiments described herein are only used to explain the relevant invention, rather than to limit the invention. It should also be noted that, for ease of description, only the parts related to the relevant invention are shown in the accompanying drawings.

[0035] It should be noted that, in the absence of conflict, the embodiments and features in the embodiments of the present application can be combined with each other. The present application will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0036] Figure 1 A flow chart of a skin detection method based on an FPI image acquisition system according to the present invention is shown, comprising the following steps:

[0037] S1. Use an adjustable FPI image acquisition system to select the corresponding characteristic wavelength according to the substance to be detected to collect the face image and obtain the characteristic wavelength image;

[0038] S2. Obtain the facial skin area to be detected on the characteristic wavelength image by using a face recognition algorithm, align the characteristic wavelength image, and obtain spectral data of each pixel of the facial skin area to be detected;

[0039] S3, performing correlation analysis on the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected;

[0040] S4. Based on the result of the correlation analysis, the distribution of the substance to be detected on the skin area of ​​the face to be detected is obtained and output visually.

[0041] The substance to be detected is a skin component of the human facial skin area to be detected, and optionally includes porphyrin, blood oxygen, eumelanin, pheomelanin, melanin, carotene, bilirubin, water, lipid or hemoglobin.

[0042] The wavelength band of the acquired skin image is determined according to the substance to be analyzed. When the substance to be detected is hemoglobin, the characteristic wavelength is between 500-700nm; when the substance to be detected is porphyrin, the characteristic wavelength is mainly between 600-660nm; blood oxygen detection is in the near-infrared 600-900nm band.

[0043] If the characteristic wavelength of the substance to be tested is uncertain, the characteristic wavelength data with a strong correlation with the test substance can be extracted from the image data through a feature extraction method.

[0044] In one embodiment, an interval variable iterative space shrinkage method is used for feature extraction. This method is based on the idea of ​​model cluster analysis (MPA) and uses a weighted binary sampling method to construct a variable subspace. Each iterative process meets the two criteria of gradual shrinkage of the variable space and gradual optimization of the increment space. The global and local processes are used alternately to optimize the interval position until the best feature variable is selected.

[0045] In one embodiment, a competitive adaptive reweighting algorithm is used for feature extraction. This method is based on the "survival of the fittest" principle in Darwin's theory. The absolute value of the regression coefficient in the partial least squares (PLS) model is used as an evaluation index of the importance of the band. Each time, adaptive reweighted sampling (ARS) is used to retain the bands with larger absolute value weights of the regression coefficient in the PLS model as new subsets, and the bands with smaller weights are removed. Then, a PLS model is established based on the new subset. After multiple calculations, the wavelength in the subset with the smallest root mean square error of interactive verification (RMSECV) of the PLS model is selected as the characteristic wavelength.

[0046] In one embodiment, the iterative information variable retention method is used for feature extraction. IRIV randomly combines the variables multiple times and establishes a PLS model. The change of the prediction error is interactively verified when each variable exists in the model. According to the idea of ​​model cluster analysis MPA, the variables are divided into strong information variables, weak information variables, no information variables and interference variables. After analyzing each variable one by one, the no information variables and interference variables are removed, and multiple iterative analyses are performed until the remaining variables are all strong information variables and weak information variables. The variables finally retained are the required characteristic wavelengths.

[0047] In one embodiment, the interval random frog leaping algorithm is used for feature extraction. The interval random frog leaping algorithm is a post-heuristic population evolution algorithm. In order to obtain all possible continuous intervals, the spectrum is first divided into multiple intervals by moving a fixed-width window across the entire spectrum. The random frog leaping algorithm and the PLS model are used to sort these overlapping intervals and select the optimal overlapping interval. The interval random frog leaping algorithm combines the advantages of the memetic algorithm based on memetic evolution and the particle swarm algorithm based on group behavior, with fast calculation speed and strong global search and optimization capabilities.

[0048] In one embodiment, a continuous projection algorithm is used for feature extraction. This is a forward variable selection algorithm that can minimize collinearity in vector space. This method first arbitrarily selects one wavelength to project onto other wavelengths, then introduces the wavelength corresponding to the largest projection vector into the variable combination, and uses the variable combination to establish a multivariate linear regression analysis (MLR) model. Finally, the variable combination with the smallest root mean square error in the interactive verification in the MLR model is selected as the characteristic wavelength.

[0049] It can be understood that the feature extraction methods listed above are only preferred embodiments, and the feature extraction methods that can be selected include but are not limited to the above methods.

[0050] After obtaining the characteristic wavelength data of the substance to be detected, the output wavelength can be controlled by adjusting the parallel mirror spacing of the cavity through the adjustable FPI image acquisition system to acquire characteristic wavelength images of a single or several substances to be detected at the characteristic wavelength.

[0051] After obtaining the characteristic wavelength image, the facial skin area on the characteristic wavelength image can be detected through the face recognition algorithm, and the spectral data of each pixel can be obtained by aligning the images under the characteristic wavelength.

[0052] Optionally, the face recognition algorithm includes a Haar cascade classifier, a face key point detection algorithm, threshold separation and semantic segmentation, and the face key point detection algorithm includes a DLIB algorithm, a Media Pipe algorithm, etc.

[0053] In a specific embodiment, aligning the characteristic wavelength image includes adopting a rigid alignment method and a non-rigid alignment method, the rigid alignment method includes a phase alignment method and an image similarity alignment method; the non-rigid alignment method includes: a registration algorithm based on feature points + thin plate spline (Thin Plate Spline, TPS) transformation, a registration algorithm based on feature points + free transformation (Free-Form-Deformation, FFD), a registration algorithm based on partial differential equations (Partial Differential Equation, PDE), and a Demons registration algorithm.

[0054] In a specific embodiment, the acquisition of the reference spectrum data of the substance to be detected in S3 includes: collecting skin data containing the substance to be detected by a hyperspectral camera in advance, thereby obtaining a reference spectrum curve of the substance to be detected on the skin as the reference spectrum data of the substance to be detected. The reference spectrum data is stored in a storage unit before the skin is detected. The pre-stored reference spectrum data is called when comparative analysis is required.

[0055] In a specific embodiment, the acquisition of the reference spectral data of the substance to be detected in S3 also includes: searching for an enriched area of ​​the substance to be detected in the skin area of ​​the face to be detected, using the average spectrum of the enriched area as a reference spectral curve of the substance to be detected on the skin, and obtaining the reference spectral data of the substance to be detected.

[0056] Finding the enriched area of ​​the substance to be detected can be achieved by semantic segmentation, instance segmentation or threshold segmentation.

[0057] For example, when the substance to be detected is hemoglobin, the average spectrum of hemoglobin-enriched areas such as acne areas, lip areas, and inflamed areas can be used as the reference spectrum of hemoglobin; when the substance to be detected is melanin, the average spectrum of melanin-enriched areas such as eyebrows, eyelashes, and mole areas can be used as the reference spectrum of melanin.

[0058] In a specific embodiment, the correlation analysis is performed by calculating a distance function between the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected.

[0059] In one embodiment, the distance function selected is a Euclidean distance function.

[0060] In one embodiment, the distance function selected is the Manhattan distance function.

[0061] In one embodiment, the distance function selected is the Fréchet distance function.

[0062] It can be understood that the distance functions listed above are only preferred embodiments, and the distance functions that can be selected include but are not limited to the above methods.

[0063] In one embodiment, the correlation analysis is performed by calculating the correlation coefficient between the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected.

[0064] In one embodiment, the correlation analysis is performed by calculating the spectral information divergence (SID) between the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected. The spectral vector is taken as a random variable and the similarity of the two random vectors is analyzed based on probability statistics theory. The smaller the value of the spectral information divergence, the more similar the two groups of spectra are.

[0065] In one embodiment, the correlation analysis is performed by calculating the spectral angle of the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected, i.e., spectral angle matching (SAM). The spectral data of each pixel of the facial skin area to be detected is regarded as a high-dimensional vector, and the similarity between the two spectral data is measured by calculating the angle between the spectral vector of the facial skin area to be detected and the spectral vector of the substance to be detected based on the angle of the vector space. A smaller angle means a higher similarity.

[0066] like Figure 2 As shown, Figure 2The visualization result of detecting hemoglobin on human face skin using the method proposed in the present invention is shown. In a specific embodiment, the correlation analysis result of each pixel of the human face skin area to be detected is mapped to a colormap, so that values ​​of different sizes correspond to different colors, and a visualization effect diagram is output.

[0067] At the same time, different colors can be used to represent multiple substances. In addition, before the visualization conversion, the correlation results can be differentially enhanced by contrast enhancement methods, such as curve enhancement.

[0068] According to one aspect of the present invention, a skin detection system based on an FPI image acquisition system is proposed, comprising the following modules:

[0069] Characteristic wavelength image acquisition module 301: adopts an adjustable FPI image acquisition system, selects the corresponding characteristic wavelength according to the substance to be detected to perform face image acquisition, and obtains a characteristic wavelength image.

[0070] Spectral data acquisition module 302: acquires the facial skin area to be detected on the characteristic wavelength image through a face recognition algorithm, aligns the characteristic wavelength image, and obtains spectral data of each pixel of the facial skin area to be detected.

[0071] Correlation analysis module 303: performing correlation analysis on the spectral data of each pixel of the face skin area to be detected and the reference spectral data of the substance to be detected;

[0072] Visualization output module 304: based on the result of correlation analysis, the distribution of the substance to be detected on the skin area of ​​the face to be detected is obtained and visualized and outputted.

[0073] Reference below Figure 4 , which shows a schematic diagram of the structure of a computer system 400 suitable for implementing an electronic device of an embodiment of the present application. Figure 4 The electronic device shown is merely an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0074] like Figure 4 As shown, the computer system 400 includes a central processing unit (CPU) 401, which performs various appropriate actions and processes according to a program stored in a read-only memory (ROM) 402 or a program loaded from a storage part 409 into a random access memory (RAM) 404. In the RAM 404, various programs and data required for the operation of the system 400 are also stored. The CPU 401, the ROM 402, and the RAM 404 are connected to each other via a bus 405. An input / output (I / O) interface 406 is also connected to the bus 405.

[0075] The following components are connected to the I / O interface 406: an input section 407 including a keyboard, a mouse, etc.; an output section 408 including a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 409 including a hard disk, etc.; and a communication section 410 including a network interface card such as a LAN card, a modem, etc. The communication section 410 performs communication processing via a network such as the Internet. A drive 411 is also connected to the I / O interface 406 as needed. A removable medium 412, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is installed on the drive 411 as needed so that a computer program read therefrom is installed into the storage section 409 as needed.

[0076] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart is implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable storage medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program is downloaded and installed from the network through the communication part 410, and / or installed from the removable medium 412. When the computer program is executed by the central processing unit (CPU) 401, the above-mentioned functions defined in the method of the present application are executed.

[0077] It should be noted that the computer-readable storage medium of the present application is a computer-readable signal medium or a computer-readable storage medium or any combination of the above two. The computer-readable storage medium is, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples of computer-readable storage media include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present application, a computer-readable storage medium is any tangible medium containing or storing a program that is used by or in combination with an instruction execution system, device or device. In the present application, a computer-readable signal medium includes a data signal propagated in a baseband or as part of a carrier wave, which carries a computer-readable program code. This propagated data signal takes a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium is any computer-readable storage medium other than a computer-readable storage medium that sends, propagates or transmits a program for use by or in conjunction with an instruction execution system, apparatus or device. The program code contained on the computer-readable storage medium is transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0078] Computer program code for performing the operations of the present application is written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code is executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer is connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or is connected to an external computer (e.g., via the Internet using an Internet service provider).

[0079] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each box in the flow chart or block diagram represents a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some implementations as replacements, the functions marked in the box also occur in a sequence different from that marked in the accompanying drawings. For example, two boxes represented in succession are actually executed substantially in parallel, and they are sometimes also executed in the opposite order, depending on the functions involved. It should also be noted that each box in the block diagram and / or flow chart, and the combination of the boxes in the block diagram and / or flow chart, are implemented by a dedicated hardware-based system that performs the specified function or operation, or are implemented by a combination of dedicated hardware and computer instructions.

[0080] The modules involved in the embodiments of the present application are implemented by software and hardware.

[0081] As another aspect, the present application also provides a computer-readable storage medium, which is included in the electronic device described in the above embodiment; it also exists independently and is not assembled into the electronic device. The above computer-readable storage medium carries one or more programs. When the above one or more programs are executed by the electronic device, the electronic device: adopts an adjustable FPI image acquisition system to select the corresponding characteristic wavelength according to the substance to be detected for face image acquisition, and obtains a characteristic wavelength image; through a face recognition algorithm, obtains the face skin area to be detected on the characteristic wavelength image, aligns the characteristic wavelength image, and obtains the spectral data of each pixel of the face skin area to be detected; performs correlation analysis on the spectral data of each pixel of the face skin area to be detected and the reference spectral data of the substance to be detected; based on the result of the correlation analysis, obtains the distribution of the substance to be detected on the face skin area to be detected, and performs visual output.

[0082] The above description is only a preferred embodiment of the present application and an explanation of the technical principles used. Those skilled in the art should understand that the scope of the invention involved in the present application is not limited to the technical solution formed by a specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the above invention concept. For example, the above features are replaced with the technical features with similar functions disclosed in this application (but not limited to) by each other to form a technical solution.

Claims

1. A skin detection method based on an FPI image acquisition system, comprising the following steps: S1. Use an adjustable FPI image acquisition system to select the corresponding characteristic wavelength according to the substance to be detected to collect the face image and obtain the characteristic wavelength image; S2. Obtain the facial skin area to be detected on the characteristic wavelength image by using a face recognition algorithm, align the characteristic wavelength image, and obtain spectral data of each pixel of the facial skin area to be detected; S3, performing correlation analysis on the spectral data of each pixel of the facial skin area to be detected and the reference spectral data of the substance to be detected; S4. Based on the result of the correlation analysis, the distribution of the substance to be detected on the skin area of ​​the face to be detected is obtained and output visually.

2. A skin detection method based on FPI image acquisition system according to claim 1, characterized in that: The substances to be detected are skin components of the facial skin area to be detected, including porphyrin, blood oxygen, eumelanin, pheomelanin, melanin, carotene, bilirubin, water, lipid or hemoglobin.

3. The skin detection method based on the FPI image acquisition system according to claim 1, characterized in that: The selecting of the corresponding characteristic wavelength according to the substance to be detected in S1 specifically includes: for the substance to be detected with a known characteristic wavelength, selecting the corresponding characteristic wavelength by adjusting the adjustable FPI image acquisition system; for the substance to be detected with an unknown characteristic wavelength, feature extraction is performed to determine the characteristic wavelength, and then the corresponding characteristic wavelength is selected by adjusting the adjustable FPI image acquisition system.

4. The skin detection method based on the FPI image acquisition system according to claim 1, characterized in that: The acquisition of the reference spectral data of the substance to be detected in S3 includes: collecting skin data containing the substance to be detected by a hyperspectral camera in advance, thereby obtaining a reference spectral curve of the substance to be detected on the skin as the reference spectral data of the substance to be detected.

5. The skin detection method based on the FPI image acquisition system according to claim 1, characterized in that: The acquisition of the reference spectral data of the substance to be detected in S3 includes: searching for an enriched area of ​​the substance to be detected in the skin area of ​​the face to be detected, using the average spectrum of the enriched area as a reference spectral curve of the substance to be detected on the skin, and obtaining the reference spectral data of the substance to be detected.

6. A skin detection method based on FPI image acquisition system according to claim 4 or 5, characterized in that: The correlation analysis is performed by calculating the distance function, correlation coefficient, spectral information divergence or spectral angle between the spectral data of each pixel in the facial skin area to be detected and the reference spectral data of the substance to be detected.

7. The skin detection method based on the FPI image acquisition system according to claim 1, characterized in that: S4 specifically includes: mapping the correlation analysis result of each pixel of the facial skin area to be detected to a colormap, so that values ​​of different sizes correspond to different colors, obtaining the distribution of the substance to be detected on the facial skin area to be detected, and outputting a visual effect diagram.

8. A skin detection system based on an FPI image acquisition system, characterized in that: Includes the following modules: Characteristic wavelength image acquisition module: using an adjustable FPI image acquisition system, select the corresponding characteristic wavelength according to the substance to be detected to collect facial images and obtain characteristic wavelength images; Spectral data acquisition module: acquires the facial skin area to be detected on the characteristic wavelength image through a face recognition algorithm, aligns the characteristic wavelength image, and obtains spectral data of each pixel of the facial skin area to be detected; Correlation analysis module: performing correlation analysis on the spectral data of each pixel of the face skin area to be detected and the reference spectral data of the substance to be detected; Visualization output module: based on the results of correlation analysis, the distribution of the substance to be detected on the skin area of ​​the face to be detected is obtained and visualized.

9. A computer program product having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the method according to any one of claims 1 to 7.

10. A computing system comprising a processor and a memory, wherein the processor is configured to execute the method according to any one of claims 1 to 7.

Images