Collection device for hyperspectral and structured light images of traditional Chinese medicine lingual face diagnosis

Abstract

The embodiment of the utility model provides an acquisition device for hyperspectral and structured light images of traditional Chinese medicine lingual face diagnosis, and belongs to the technical field of image acquisition equipment. The acquisition device comprises a multispectral camera module for acquiring a biomarker image in a tongue or a face, the hyperspectral camera is used for receiving reflected light with different wavelengths to form biomarker images of the same tongue or the same face under different spectral bands when the light with different wavelengths emitted by the light source part irradiates the tongue or the face and is reflected; the light source part and the hyperspectral camera are integrated together, and the hyperspectral camera is arranged on the backlight side of the light source part; the structured light camera module is used for acquiring a three-dimensional contour image of the tongue or face surface; and the visible light camera module is used for acquiring color images of tongue or face surface features. According to the utility model, the hyperspectral camera, the structured light camera and the visible light camera are integrated to obtain multi-dimensional image information at one time, so that the inspection efficiency and accuracy of traditional Chinese medicine are improved.

Description

Technical Field

[0001] This utility model belongs to the technical field of image acquisition equipment, and specifically relates to a device for acquiring hyperspectral and structured light images for tongue diagnosis in traditional Chinese medicine. Background Technology

[0002] Traditional Chinese medicine diagnosis relies primarily on the doctor's direct observation of the patient and their clinical experience to assess the patient's health or illness. During this process, the doctor mainly infers the functional state of the internal organs and pathological changes by observing subtle changes in the patient's overall face, local sensory organs, tongue, and other areas. These subtle changes typically include, for example, the skin tone and texture of the face or tongue, the state of blood circulation under the skin, and the distribution of skin pigmentation.

[0003] However, this traditional Chinese medicine method of observation relies heavily on the doctor's experience and diagnostic skills. Furthermore, environmental conditions during the observation process, such as lighting and temperature changes, are also significant factors influencing the doctor's assessment of the patient's condition. This results in a clear subjectivity and limitation in traditional Chinese medicine observation methods.

[0004] Currently, with the development of optical imaging technology and its widespread application in the medical field, traditional Chinese medicine diagnostic techniques are gradually evolving towards digitalization and intelligence through integration with optical imaging technology. For example, high-resolution images obtained through visible light technology can replace the doctor's subjective observation, and image data can accurately capture the surface features of the target skin, such as tone and texture.

[0005] However, research on the intelligent and digital aspects of TCM visual diagnosis is still in its early stages of basic research. In particular, there is a lack of feasible technical solutions and in-depth research on how to combine optical imaging technology and equipment with TCM visual diagnosis in a diversified manner to obtain multi-dimensional biological information about the patient's facial and tongue skin.

[0006] In view of this, there is a need to propose a new type of acquisition device for hyperspectral and structured light images of the tongue surface in traditional Chinese medicine to solve all or part of the above problems. Utility Model Content

[0007] To address at least one of the aforementioned problems and deficiencies in the existing technology, embodiments of this utility model provide a device for acquiring hyperspectral and structured light images of the tongue surface in Traditional Chinese Medicine (TCM). By integrating a hyperspectral camera, a structured light camera, and a visible light camera into a single acquisition device, it simultaneously acquires images of the subject's face and tongue, obtaining multispectral biomarker images, three-dimensional contour images, and color images. This provides objective, detailed, and multidimensional tongue surface image data for TCM visual diagnosis, thereby improving the accuracy and efficiency of TCM visual diagnosis. The technical solution is as follows:

[0008] According to one aspect of the present invention, a device for acquiring hyperspectral and structured light images for tongue and facial diagnosis in Traditional Chinese Medicine is provided. The device includes: a multispectral camera module for acquiring biomarker images of the interior of the tongue or face; the multispectral camera module includes a light source and a hyperspectral camera for receiving reflected light of different wavelengths when the light source emits light of different wavelengths onto the tongue or face and reflection occurs, forming biomarker images of the same tongue or face in different spectral bands; the light source and the hyperspectral camera are integrated together, and the hyperspectral camera is disposed on the backlight side of the light source; a structured light camera module for acquiring three-dimensional contour images of the surface of the tongue or face; and a visible light camera module for acquiring color images of the surface features of the tongue or face.

[0009] In some embodiments, the light source unit specifically includes a ring-shaped light source plate and at least one group of LED beads disposed on the ring-shaped light source plate. Each group of LED beads includes a first group of LED beads for providing white light and a second group of LED beads for providing different wavelengths. The LED beads in each group are arranged in a ring around the center of the ring-shaped light source plate.

[0010] In some embodiments, the first LED group further includes at least one LED for providing white light. The second LED group has at least one preset wavelength value, and at least one LED with a preset wavelength is provided for each of these preset wavelength values. The preset wavelength value ranges from 390 nm to 940 nm. The LEDs in each LED group are arranged uniformly in ascending order of preset wavelength value, starting with the LED providing white light and proceeding counterclockwise or clockwise.

[0011] In some embodiments, preferably, the number of LEDs in the first LED group is equal to the number of LEDs in each preset wavelength value in the second LED group.

[0012] In some embodiments, preferably, at least one group of LED beads is at least two groups of LED beads. Each of the at least two groups of LED beads is arranged after the previous group of LED beads is arranged on the side of the previous group of LED beads away from the center of the annular light source plate.

[0013] In some embodiments, specifically, the lens of the hyperspectral camera is coaxially arranged with the ring light source plate. The lens direction of the hyperspectral camera is the same as the light emission direction of the light source.

[0014] In some embodiments, the light source unit further includes a control circuit board integrated with at least one group of LED beads and a hyperspectral camera. The control circuit board has a control switch for switching the LED beads in the at least one group of LED beads to illuminate or extinguish.

[0015] In some embodiments, the light source may alternatively include an annular reflector disposed on the annular light source plate. The annular reflector is disposed on the side of the annular light source plate on which the LEDs are disposed, and a coating film for improving the diffuse reflectivity of the light source is disposed on the surface of the annular reflector.

[0016] In some embodiments, specifically, the structured light camera module includes a projector and at least one industrial camera integrated with the projector. The structured light camera module is positioned on the backlight side of the light source. The lens direction of each of the at least one industrial camera is aligned with the light emission direction of the light source.

[0017] In some embodiments, the acquisition device further includes a housing for fixing and mounting the multispectral camera module, the structured light camera module, and the visible light camera module. Further, the housing has an opening at one end in the light emission direction of the light source section, and a head bracket for fixing the position of the tongue or face is provided on the opening.

[0018] The embodiments of this utility model provide a device for acquiring hyperspectral and structured light images for tongue diagnosis in traditional Chinese medicine, which has at least one or a portion of the following advantages:

[0019] (1) By integrating a hyperspectral camera, a structured light camera and a visible light camera into the same acquisition device, the face and tongue of the subject can be acquired at the same time, and biomarker images of multispectral imaging, three-dimensional contour images of structured light imaging and color images can be obtained simultaneously, providing objective, detailed and multi-dimensional tongue image data for TCM observation diagnosis to improve the efficiency and accuracy of TCM observation diagnosis.

[0020] (2) By combining hyperspectral cameras, structured light cameras and visible light cameras, the shortcomings of visible light cameras in capturing surface image information of the tongue and / or face of the subject can be effectively overcome, and the physiological changes of the tongue can be deeply captured based on the surface image information of the tongue, thereby obtaining multi-dimensional tongue image information data.

[0021] (3) By integrating a hyperspectral camera and a multi-wavelength light source, the biomarker images corresponding to different spectral bands of the same tongue or the same face can be obtained within a large wavelength range by adjusting the emission wavelength of the light source. This enables in-depth exploration of physiological characteristics such as blood vessels and lymph nodes under the skin of the face and tongue, which has significant guiding value for the discovery of potential diseases and early judgment of diseases.

[0022] (4) By setting and adjusting the wavelength of the lamp beads and arranging the lamp bead group in the light source section, the light source can be adapted to various tongue diagnosis requirements and multi-dimensional tongue image data can be obtained in the same acquisition device, thereby improving the imaging stability and image acquisition efficiency of the acquisition device.

[0023] (5) By adjusting the number of LED beads and the arrangement of LED bead groups, it can be adapted to most TCM observation diagnosis scenarios and tongue diagnosis requirements. While obtaining more objective and comprehensive tongue image information, it also reduces the difficulty of acquisition and equipment investment costs, and has broad application prospects.

[0024] (6) By using a structured light camera to perform three-dimensional contour imaging of the face and tongue, the face and tongue of the subject can be accurately modeled in three dimensions, providing rich information on subtle physiological changes from a structural information level, thereby improving the image acquisition sensitivity and accuracy of the acquisition device.

[0025] (7) By using the image data processing modules configured inside hyperspectral cameras, structured light cameras and visible light cameras to process the collected image information and image data, the diagnosis time of traditional Chinese medicine observation and the acquisition time of image data can be effectively shortened, greatly improving the efficiency of consultation, shortening the consultation time of the subject, and improving the quality of medical services. Attached Figure Description

[0026] These and / or other aspects and advantages of this invention will become apparent and readily understood from the following description of preferred embodiments taken in conjunction with the accompanying drawings, in which:

[0027] Figure 1 This is a schematic diagram of the data acquisition device according to an embodiment of the present invention;

[0028] Figure 2 for Figure 1 An exploded view of the structure of the data acquisition device shown;

[0029] Figure 3 This is a schematic diagram of a lamp bead arrangement in the light source section of the acquisition device according to the present invention;

[0030] Figure 4This is a schematic diagram illustrating the working process of a hyperspectral camera according to the acquisition device of this utility model;

[0031] Figure 5 This is a schematic diagram of the structure of a structured light camera module according to the acquisition device of this utility model;

[0032] Figure 6 A schematic diagram of a biomarker image of a subject's face obtained using a multispectral camera module with an acquisition device according to various embodiments of the present invention;

[0033] Figure 7 This is a schematic diagram of a three-dimensional contour image of the tongue of a subject obtained by using the acquisition device according to various embodiments of the present invention via a structured light camera module. Detailed Implementation

[0034] The technical solution of this utility model will be further described in detail below through embodiments and in conjunction with the accompanying drawings. In this specification, the same or similar reference numerals indicate the same or similar components. The following description of the embodiments of this utility model with reference to the accompanying drawings is intended to explain the overall inventive concept of this utility model and should not be construed as a limitation thereof.

[0035] See Figure 1 The diagram illustrates the structure of a data acquisition device 100 according to an embodiment of the present invention. The acquisition device 100 comprises four main parts: a multispectral camera module 10, a structured light camera module 20, a visible light camera module 30, and a housing 40. The housing 40 has an open end, and the multispectral camera module 10, structured light camera module 20, and visible light camera module 30 are integrated inside the housing 40. When the subject places their head on the headrest 41 at the open end of the housing 40, the multispectral camera module 10, structured light camera module 20, and visible light camera module 30 sequentially capture images and record the captured pictures and image data, thus obtaining tongue surface image data containing multidimensional information in a single operation.

[0036] Specifically, the multispectral camera module 10 is used to acquire images of the interior of the tongue or face, particularly biomarkers under the skin of the tongue or face. The multispectral camera module 10 includes a light source unit 11 and a hyperspectral camera 12. When the light source unit 11 emits light of different wavelengths to illuminate the tongue or face and causes reflection, the hyperspectral camera 12 receives the reflected light of different wavelengths, forming biomarker images of the same tongue or face in different spectral bands. The light source unit 11 and the hyperspectral camera 12 are integrated together, with the hyperspectral camera 12 positioned on the backlight side of the light source unit 11. The structured light camera module 20 is used to acquire three-dimensional contour images of the surface of the tongue or face. The visible light camera module 30 is used to acquire color images of the surface features of the tongue or face.

[0037] See Figure 2 This shows, as Figure 1 An exploded view of the structure of the data acquisition device 100 shown. Combined with... Figure 1 and Figure 2 As shown, the specific structures of the multispectral camera module 10, the structured light camera module 20, and the visible light camera module 30 will be described in more detail below.

[0038] Multispectral imaging is an optoelectronic imaging technology capable of simultaneously acquiring multi-band spectral features and spatial image information. Its spectral feature acquisition range covers a wider spectrum beyond the visible light range of the human eye. Therefore, by combining these extensive multi-band spectral features with the comprehensive spectral information formed by the spatial image, it is possible to conduct in-depth analysis of biomarker information such as blood circulation, pigment distribution, and texture changes under the skin of the subject's face and / or tongue.

[0039] In one example, such as Figure 2 As shown, the multispectral camera module 10 comprises three main parts: a light source 11, a hyperspectral camera 12, and a control circuit board 13. The light source 11 emits light of different wavelengths towards the tongue or face (including both whole and partial facial areas) of the subject. The hyperspectral camera 12 is positioned behind the light source 11 and receives the light reflected from the subject's tongue or face (including both whole and partial facial areas) using this reflected light to acquire spectral characteristic information and spatial spectral images. The control circuit board 13 is integrated with the light source 11 and the hyperspectral camera 12, and through circuit and / or signal connections, adjusts the light emitted by the light source 11 to different wavelengths, controls the on / off operation of the light source 11, and the interval between each emission.

[0040] In one example, specifically, the light source unit 11 includes a ring-shaped light source plate 111 and at least one group of lamp beads 112 disposed on the ring-shaped light source plate 111. See also Figure 3The diagram illustrates the structure of one embodiment where a light source plate 111 and at least one set of LED bead groups 112 are assembled together. Each of the at least one set of LED bead groups 112 includes a first LED bead group 1121 for providing white light (i.e., mixed visible light with a wavelength range of 390 nm to 780 nm) and a second LED bead group 1122 for providing different wavelengths. The LEDs in each LED bead group are arranged in a ring around the center of the annular light source plate 111.

[0041] In one example, the first LED group 1121 further includes at least one LED for providing white light. The second LED group 1122 is configured with at least one preset wavelength value, and at least one LED of that preset wavelength is provided for each preset wavelength value. The preset wavelength value ranges from 390nm to 940nm. The LEDs in each group are evenly arranged in ascending order of preset wavelength value, starting with the LED providing white light and proceeding counter-clockwise or clockwise. The specific number of LEDs in any given LED group can be customized according to the specific requirements of tongue diagnosis; one, two, three, or more LEDs can be set in any given group. Typically, at least two LEDs are set. This effectively prevents the acquisition device 100 from failing during use due to the lack of a replacement of the same wavelength. Furthermore, the simultaneous operation of multiple LEDs of the same wavelength during post-processing of the acquired image data ensures the reliability of the acquired data and facilitates image data analysis. The settings for the number of LED beads are provided here only as illustrative examples and should not be construed as a limitation of this utility model by those skilled in the art.

[0042] In one example, preferably, the number of LEDs in the first LED group 1121 is equal to the number of LEDs in each preset wavelength value in the second LED group 1122. That is, if the first LED group 1121 contains N LEDs (N is an integer greater than or equal to 1), then the number of LEDs in each corresponding wavelength value group in the second LED group 1122 is also N. The purpose of this arrangement is to evenly distribute all LEDs on the ring light source plate 111, so that when the LEDs of each wavelength are lit sequentially, the number of LEDs emitting light each time is the same, and therefore the uniformity, intensity, and other parameters of each emission are the same.

[0043] In one example, preferably, the number of at least two groups of LED beads 112 is at least two. Each group of LED beads 112 in the at least two groups is arranged after the previous group of LED beads is arranged in the annular light source plate 111, and then on the side of the previous group of LED beads away from the center of the annular light source plate 111.

[0044] In one example, specifically, such as Figure 3The diagram illustrates an exemplary embodiment of an arrangement of LED beads. The LED beads can be, for example, LED beads. A first group of LED beads 1121 provides white light. A second group of LED beads 1122 has 14 preset wavelength values ​​set according to a range of preset wavelength values, and a group of LED beads is set for each of these 14 preset wavelength values, sequentially including a 390nm LED bead group a, a 420nm LED bead group b, a 450nm LED bead group c, a 525nm LED bead group d, a 570nm LED bead group e, a 630nm LED bead group f, a 660nm LED bead group g, a 730nm LED bead group h, a 780nm LED bead group i, an 850nm LED bead group j, an 870nm LED bead group k, an 890nm LED bead group l, a 910nm LED bead group m, and a 940nm LED bead group n.

[0045] In one example, two sets of LED groups 112, namely a first LED group 112a and a second LED group 112b, are further arranged on the ring light source plate 111. The first LED group 112a is arranged first, and then the second LED group 112b is arranged around the first LED group 112a.

[0046] Specifically, taking the first LED group 112a as an example, starting from point A of the annular light source plate 111, the following LED groups from the first LED group 1121 and the second LED group 1122 are arranged clockwise: 390nm LED group a, 420nm LED group b, 450nm LED group c, 525nm LED group d, 570nm LED group e, 630nm LED group f, 660nm LED group g, 730nm LED group h, 780nm LED group i, 850nm LED group j, 870nm LED group k, 890nm LED group l, 910nm LED group m, and 940nm LED group n. Each of these groups contains 12 LEDs, meaning a total of 180 LEDs are used to complete one complete circle. The arrangement of the second LED group 112b follows the same arrangement as the first LED group 112a, arranged sequentially around its outer perimeter; details will not be repeated here.

[0047] When arranging each LED, it is necessary to ensure that there is a certain gap between each LED, and also to ensure that the overall arrangement of the LEDs in the first LED group 112a is staggered from the overall arrangement of the LEDs in the second LED group 112b. In other words, the LEDs need to avoid blocking each other, which can ensure that the emission state is uniform each time, thereby improving the accuracy and reliability of image information data acquisition.

[0048] Those skilled in the art will understand that the specific number of LEDs in each group within the same LED group, the number of preset wavelength values, and the number of cycles of the LED groups set on the same annular light source plate 111 can all be set according to the actual requirements of tongue diagnosis and image data processing. The embodiments of this utility model only provide some illustrative examples, and therefore should not be construed as a limitation of this utility model.

[0049] In one example, specifically, the lens of the hyperspectral camera 12 is coaxially arranged with the ring light source plate 111. The lens direction of the hyperspectral camera 12 is the same as the light emission direction of the light source 11. The working principle of the hyperspectral camera 12 is based on spectral decomposition and spectral reconstruction. That is, the hyperspectral camera 12 divides the light signals of each band (generally a wide band) of the incident light reflected after the light source 11 illuminates the face and / or tongue of the subject into several narrow band beams, and then images these beams onto their respective detectors to obtain images of different spectral bands. Therefore, by switching the light emission of the lamp group of the light source 11 to illuminate the face and / or tongue of the subject, and then providing incident light of different wavelengths after reflection, different wavelengths of incident light can be provided to the hyperspectral camera 12. Furthermore, after the hyperspectral camera 12 obtains spectral images of different wavelengths, it can also combine a group of spectral images of different wavelengths through image fusion processing to form a multispectral image corresponding to the same face (or the same tongue).

[0050] In one example, alternatively, see Figure 4 This document exemplifies the working principle of a hyperspectral camera 12 and an embodiment of its main parameter settings. The hyperspectral camera 12 can use common spectroscopic camera products; the higher the spectral resolution of its detector system, the higher the accuracy of the images obtained in different spectral bands. Furthermore, the hyperspectral camera 12 can also set shooting parameters through its data acquisition module, such as the width, height, and magnification of the target, as well as the horizontal and vertical viewing angles and working distance of the lens. These are merely illustrative examples and should not be construed as limiting the scope of this invention.

[0051] In one example, alternatively, the hyperspectral camera 12 receives image data via an image sensor, processes the image data using, for example, an ISP image processing algorithm, and finally transmits the data via a USB interface 50 (see [link]). Figure 2 (As shown) to complete the high-speed transmission of image data.

[0052] In one example, furthermore, in order to control and adjust the light emission of each group of LED beads within the light source section 11, combined with Figure 1 and Figure 2As shown, a control circuit board 13 is also provided in the light source section 11. This control circuit board 13 is integrated with at least one set of LED beads 112 and the hyperspectral camera 12. The control circuit board 13 is provided with a control switch (not shown) for switching the LEDs in the at least one set of LED beads 112 to light up or turn off.

[0053] Combination Figure 3 and Figure 4 As shown, when the acquisition device 100 is used to photograph the face and / or tongue of the subject, the working process of the light source 11, especially the several sets of LED beads thereon, is as follows:

[0054] After the acquisition device 100 is started, the control switch on the control circuit board 13 first turns on the first group of 24 LED beads (group 1121) for two weeks. Simultaneously, the hyperspectral camera 12 receives the reflected light after it illuminates the tongue or face, forming a spectral image corresponding to the first group of LED beads 1121. Next, the control switch turns off all the first group of LED beads 1121. When the next LED bead illumination instruction is issued, the 390nm LED bead group a in the second group of 24 LED beads 1122 for two weeks is turned on. Simultaneously, the hyperspectral camera 12 receives the reflected light after it illuminates the tongue or face, forming a spectral image corresponding to the 390nm LED bead group a. This process continues until the control switch illuminates the last group of 24 LED beads in the second group of 24 LED beads 1122 for two weeks, and the hyperspectral camera 12 receives the reflected light after it illuminates the tongue or face, forming a spectral image corresponding to the 940nm LED bead group n. This completes a full multispectral imaging process (which also includes the imaging processes of the structured light camera module 20 and the visible light camera module 30, as described below).

[0055] In one example, alternatively, the light source unit 11 may also include an annular reflector 113 disposed on the annular light source plate 111 and a light source cover plate 114 for protecting the lamp beads, electrical circuits, control chips, etc. inside the light source unit 11. The annular reflector 113 covers the side of the annular light source plate 111 where the lamp beads are disposed, and a coating film for improving the diffuse reflectivity of the light source is provided on the surface of the annular reflector 113. The light source cover plate 114 fixes the annular light source plate 111, at least one set of lamp bead groups 112, and the annular reflector 113 together.

[0056] In one example, preferably, a nano-97% high diffuse reflection coating (HDRC-V001) is sprayed onto the surface of the annular reflector 113 to form a coating film. This nano-97% high diffuse reflection coating is a white emulsion-like coating refined from high-reflectivity micro- and nano-material composites using water as a medium, with a total reflectance and diffuse reflectance as high as 98.2% and 97%, respectively. This coating film can improve luminous efficiency while making the reflected light uniform and soft, reducing glare and color difference or deviation of light in a wide-angle manner. It also provides dust and UV protection, extending its service life.

[0057] 3D structured light imaging technology and its structured light cameras can provide three-dimensional contour data of the target of interest. For tongue and facial diagnosis, the three-dimensional contour data of the subject's tongue and / or face (including the whole face and specific areas) obtained through 3D structured light imaging technology can digitize the contour data of the skin surface, facilitating further detailed analysis of minute changes on the skin surface through precise measurement to aid in diagnosis.

[0058] In one example, see Figure 5 The structure of a structured light camera module 20 is illustrated exemplarily. Combined with... Figure 2 and Figure 5 As shown, the structured light camera module 20 is disposed on the backlight side of the light source unit 11. Specifically, the structured light camera module 20 includes a projector 21 and at least one industrial camera 22 integrated with the projector 21. The lens direction of each of the at least one industrial camera 22 is in the same direction as the light emission direction of the light source unit 11.

[0059] In one example, alternatively, the structured light camera module 20 can be assembled using common projector equipment and common industrial-grade cameras. For example, it can be assembled using one 720p or higher high-definition Blu-ray industrial-grade DLP projector and two fixed-focus high-definition industrial cameras.

[0060] Specifically, the structured light camera module 20 operates as follows: The structured light camera module 20 incorporates a grating encoder, and the projector 21 projects a set of spatial orientation encoded patterns onto the target (the face and / or tongue of the person being sampled). Simultaneously, at least one industrial camera 22 is triggered to acquire an image of the face and / or tongue of the person being sampled, superimposed with the orientation encoded patterns. Then, the high-speed computing unit inside the structured light camera module 20 performs parallel decoding on the acquired images. By combining the pre-calibrated parameters of the projector 21 and at least one industrial camera 22, the three-dimensional shape and texture information of the surface of the face and / or tongue of the person being sampled can be reconstructed.

[0061] In particular, when using two industrial cameras 22, two sets of point cloud data about the subject's face and / or tongue can be acquired in a single capture. By fusing key information from the two sets of point cloud data, a more detailed 3D contour image of the subject's face and / or tongue, along with its image data, can be obtained.

[0062] Visible light imaging technology and visible light cameras can provide high-resolution color images. High-resolution color images allow for the precise capture of surface features such as tone and texture of the skin on the face and / or tongue of the subject.

[0063] In one example, specifically, such as Figure 2 As shown, the visible light camera module 30 includes at least one visible light camera 31 and a mounting bracket 32, a lens envelope 33, and a lens support 34 for fixing the at least one visible light camera 31. The at least one visible light camera 31 is fixedly mounted on the backlight side of the light source unit 11 by the mounting bracket 32, the lens envelope 33, and the lens support 34, and the lens direction of each visible light camera 31 is in the same direction as the light emission direction of the light source unit 11.

[0064] In one example, alternatively, a separate, assembled cover plate 42 is provided behind the opening end of the housing 40 of the acquisition device 100, that is, behind the backlight side of the light source unit 11. When the acquisition device 100 needs to replace its internal components, such as the multispectral camera module 10, the structured light camera module 20, and the visible light camera module 30, the cover plate 42 is removed to provide sufficient operating space inside the housing 40, facilitating equipment maintenance and debugging.

[0065] In one example, alternatively, a frame 43 (such as) can also be provided inside the housing 40. Figure 2 (As shown) is used to fix the multispectral camera module 10, the structured light camera module 20 and the visible light camera module 30 to the frame 43 by fasteners.

[0066] In one example, alternatively, a power supply module 60 is also provided inside the acquisition device 100 to power the multispectral camera module 10, the structured light camera module 20, and the visible light camera module 30. The power supply voltage can be adjusted by integrating a transformer inside the power supply module 60, depending on the voltage requirements of these modules.

[0067] The complete image acquisition process of the acquisition device 100 includes:

[0068] After starting the acquisition device 100, the multispectral camera module 10, the structured light camera module 20 and the visible light camera module 30 are initialized respectively. The current acquisition parameters are set according to the specific requirements of the current tongue diagnosis process.

[0069] During the current process of capturing images of the subject's face and / or tongue, regardless of whether the LEDs in the light source unit 11 are emitting light, the multispectral camera module 10 and the visible light camera module 30 are always in the acquisition state, continuously acquiring images at high speed. Specifically, the multispectral camera module 10 acquires images of biomarkers under the skin of the subject's face and / or tongue, while the visible light camera module 30 acquires color images of the surface features of the subject's face and / or tongue.

[0070] The LEDs in the light source section 11 are lit sequentially by the control switch on the control circuit board 13, with a lighting interval between each pair of adjacent groups of LEDs. That is, the previous group of LEDs is lit for a period of time, then turns off, and after a period of time, the next group of LEDs lights up, and so on.

[0071] During the waiting period of each group of LED beads, the structured light camera module 20 is activated to capture three-dimensional contour images of the surface of the subject's face and / or tongue.

[0072] In one example, see Figure 6 This example demonstrates a biomarker image of a subject's face obtained through a multispectral camera module 10. By capturing multiple spectral images of the subject's face in a single, concentrated capture, different spectral bands are obtained. The texture, skin tone, and blemishes of the same facial area appear differently in these different spectral images. By fusing these spectral images from different bands, more comprehensive information about the biomarkers beneath the facial skin can be obtained.

[0073] In one example, see Figure 7 This example demonstrates a three-dimensional contour image of a subject's tongue obtained through a structured light camera module 20. The fusion and reconstruction of point cloud data resulted in a three-dimensional morphology and rich texture information about the subject's tongue.

[0074] Multispectral imaging, 3D structured light imaging, and visible light imaging technologies are combined in a single acquisition device 100 for use in traditional Chinese medicine tongue diagnosis. By fusing multi-level and multi-dimensional image information, doctors can obtain more comprehensive, objective, and detailed judgment criteria for their diagnosis, enabling them to quickly and accurately acquire more potential information about the subject's physical condition.

[0075] The embodiments of this utility model provide a device for acquiring hyperspectral and structured light images for tongue diagnosis in traditional Chinese medicine, which has at least one or a portion of the following advantages:

[0076] (1) By integrating a hyperspectral camera, a structured light camera and a visible light camera into the same acquisition device, the face and tongue of the subject can be acquired at the same time, and biomarker images of multispectral imaging, three-dimensional contour images of structured light imaging and color images can be obtained simultaneously, providing objective, detailed and multi-dimensional tongue image data for TCM observation diagnosis to improve the efficiency and accuracy of TCM observation diagnosis.

[0077] (2) By combining hyperspectral cameras, structured light cameras and visible light cameras, the shortcomings of visible light cameras in capturing surface image information of the tongue and / or face of the subject can be effectively overcome, and the physiological changes of the tongue can be deeply captured based on the surface image information of the tongue, thereby obtaining multi-dimensional tongue image information data.

[0078] (3) By integrating a hyperspectral camera and a multi-wavelength light source, the biomarker images corresponding to different spectral bands of the same tongue or the same face can be obtained within a large wavelength range by adjusting the emission wavelength of the light source. This enables in-depth exploration of physiological characteristics such as blood vessels and lymph nodes under the skin of the face and tongue, which has significant guiding value for the discovery of potential diseases and early diagnosis of diseases.

[0079] (4) By setting and adjusting the wavelength of the lamp beads and arranging the lamp bead group in the light source section, the light source can be adapted to various tongue diagnosis requirements and multi-dimensional tongue image data can be obtained in the same acquisition device, thereby improving the imaging stability and image acquisition efficiency of the acquisition device.

[0080] (5) By adjusting the number of LED beads and the arrangement of LED bead groups, it can be adapted to most TCM observation diagnosis scenarios and tongue diagnosis requirements. While obtaining more objective and comprehensive tongue image information, it also reduces the difficulty of acquisition and equipment investment costs, and has broad application prospects.

[0081] (6) By using a structured light camera to perform three-dimensional contour imaging of the face and tongue, the face and tongue of the subject can be accurately modeled in three dimensions, providing rich information on subtle physiological changes from a structural information level, thereby improving the image acquisition sensitivity and accuracy of the acquisition device.

[0082] (7) By using the image data processing modules configured inside hyperspectral cameras, structured light cameras and visible light cameras to process the collected image information and image data, the diagnosis time of traditional Chinese medicine observation and the acquisition time of image data can be effectively shortened, greatly improving the efficiency of consultation, shortening the consultation time of the subject, and improving the quality of medical services.

[0083] While some embodiments of the general concept of this utility model have been shown and described, those skilled in the art will understand that changes may be made to these embodiments without departing from the principles and spirit of the general concept of this utility model, the scope of which is defined by the claims and their equivalents.

Claims

1. A device for acquiring hyperspectral and structured light images for tongue diagnosis in Traditional Chinese Medicine, characterized in that, The data acquisition device includes: A multispectral camera module for acquiring biomarker images of the inside of the tongue or face, the multispectral camera module including a light source and a hyperspectral camera for receiving the reflected light of different wavelengths when the light source emits light of different wavelengths to illuminate the tongue or face and reflection occurs, forming biomarker images of the same tongue or face in different spectral bands, the light source and the hyperspectral camera are integrated together, and the hyperspectral camera is disposed on the backlight side of the light source. Structured light camera module for acquiring three-dimensional contour images of the tongue or face surface; A visible light camera module for acquiring color images of surface features of the tongue or face.

2. The data acquisition device according to claim 1, characterized in that, The light source unit includes a ring light source plate and at least one set of lamp beads disposed on the ring light source plate; Each of the at least one group of LED beads includes a first group of LED beads for providing white light and a second group of LED beads for providing different wavelengths; The LEDs in each group of LEDs are arranged in a ring around the center of the annular light source plate.

3. The data acquisition device according to claim 2, characterized in that, The first LED group includes at least one LED for providing white light; At least one preset wavelength value is set in the second LED group, and at least one LED with a preset wavelength is set for each preset wavelength value; The range of the preset wavelength value is 390nm to 940nm; The LEDs in each group of LEDs are arranged evenly in ascending order of the preset wavelength value, starting with the LED that provides white light and moving counterclockwise or clockwise.

4. The data acquisition device according to claim 3, characterized in that, The number of LEDs in the first LED group is equal to the number of LEDs in each preset wavelength value in the second LED group.

5. The data acquisition device according to claim 2, characterized in that, The at least one group of LED beads refers to at least two groups of LED beads; Each of the at least two groups of LED beads is arranged after the previous group of LED beads is arranged on the annular light source plate, and then arranged on the side of the previous group of LED beads away from the center of the annular light source plate.

6. The data acquisition device according to claim 2, characterized in that, The lens of the hyperspectral camera is coaxially arranged with the ring light source plate; The lens of the hyperspectral camera is oriented in the same direction as the light emission direction of the light source.

7. The data acquisition device according to claim 2, characterized in that, The light source unit also includes a control circuit board integrated with the at least one group of LED beads and the hyperspectral camera; The control circuit board is equipped with a control switch for switching the lamps in the at least one group of lamp beads to light up or turn off.

8. The data acquisition device according to claim 2, characterized in that, The light source unit also includes an annular reflector disposed on the annular light source plate; The annular reflector is covered on the side of the annular light source plate where the LED beads are located; A coating is provided on the surface of the annular reflector to improve the diffuse reflectivity of the light source.

9. The data acquisition device according to any one of claims 1-8, characterized in that, The structured light camera module includes a projector and at least one industrial camera integrated with the projector; The structured light camera module is located on the backlight side of the light source. The lens direction of each of the at least one industrial cameras is the same as the light emission direction of the light source.

10. The data acquisition device according to claim 9, characterized in that, The acquisition device also includes a housing for fixing and mounting the multispectral camera module, the structured light camera module, and the visible light camera module; The housing has an opening at one end in the light emission direction of the light source, and a head bracket for fixing the position of the tongue or face is provided on the opening.

Images