Visible light image and infrared image fusion method for inspection diagnosis of traditional Chinese medicine

Abstract

The invention discloses a visible light image and infrared image fusion method for inspection diagnosis of traditional Chinese medicine, and the method comprises the steps: calibrating a camera model, so as to obtain an internal parameter matrix, an external parameter matrix and a distortion coefficient matrix of a visible light camera and an infrared camera; transforming the infrared image acquired by the infrared camera so as to enable the infrared image to coincide with the coordinate system of the visible light image acquired by the visible light camera; according to the visible light image and infrared image fusion method for the traditional Chinese medicine inspection diagnosis, the defects that in the prior art, doctors mainly judge based on naked eyes, the visible light image and the infrared image are overlapped, the infrared image and the visible light image in the overlapped image are corrected to form a matching relation, and an isotherm infrared image is extracted and displayed on the visible light image are overcome. The problem that the accuracy of a diagnosis result is affected by diagnosis errors easily caused by the inevitable influence of the environment, such as the brightness of light and the personal psychological condition of a doctor, in the diagnosis is solved.

Description

Technical Field

[0001] The present invention relates to the field of traditional Chinese medicine diagnosis, and in particular to a method for fusing visible light images and infrared images for traditional Chinese medicine visual diagnosis. Background Art

[0002] Traditional Chinese medicine carries the experience and theoretical knowledge of the ancient Chinese people in fighting against diseases. It is a medical theory system that has gradually formed and developed through long-term medical practice under the guidance of ancient naive materialism and spontaneous dialectical thinking. Traditional Chinese medicine explores the cause, nature and location of diseases through the four diagnostic methods of "observation, auscultation, inquiry and palpation". Among them, observing the patient's body shape, complexion, tongue body and tongue coating, and determining the location and nature of the disease based on the changes in shape and color is called inspection, which is used to diagnose changes in human physiology and pathology and is one of the important diagnostic information of the human body.

[0003] In the process of TCM diagnosis, doctors mainly rely on their naked eye judgment, which is inevitably affected by the environment, such as the brightness of the light and the doctor's personal psychological state. This leads to diagnostic errors, which in turn affects the accuracy of the diagnosis results.

[0004] Therefore, a method for fusing visible light and infrared images during use is provided, wherein the fused image has the characteristics of clear imaging quality of visible light images and retains clear details and texture features, and can also show the distribution changes of body surface temperature, thereby providing a strong diagnostic basis for Chinese medicine physicians and facilitating physicians to make diagnostic results quickly and accurately. A method for fusing visible light images and infrared images for Chinese medicine visual diagnosis is an urgent problem to be solved by the present invention. Summary of the invention

[0005] In view of the above technical problems, the purpose of the present invention is to overcome the problem that the existing Chinese medicine doctors mainly rely on the judgment of the naked eye, and the diagnosis is inevitably affected by the environment, such as the brightness of the light and the influence of the doctor's personal psychological condition, which leads to diagnostic errors in the diagnosis, thereby affecting the accuracy of the diagnosis results. Thus, a method for fusing visible light and infrared images during use is provided. The fused image has the characteristics of clear imaging quality of visible light images and clear retention of details and texture features, and can also show the distribution changes of body surface temperature, providing a strong diagnostic basis for Chinese medicine doctors, and facilitating doctors to make diagnostic results quickly and accurately. A visible light image and infrared image fusion method for Chinese medicine visual diagnosis is provided.

[0006] In order to achieve the above object, the present invention provides a method for fusing visible light images and infrared images for TCM visual diagnosis, the method comprising:

[0007] By calibrating the camera model, the intrinsic parameter matrix, extrinsic parameter matrix and distortion coefficient matrix of both the visible light camera and the infrared camera are obtained;

[0008] Transforming the infrared image acquired by the infrared camera according to the obtained intrinsic parameter matrix, extrinsic parameter matrix and distortion coefficient matrix so as to make the coordinate system of the infrared image acquired by the visible light camera coincide with that of the visible light image acquired by the visible light camera;

[0009] The infrared image and the visible light image in the overlapped image are corrected respectively to form a matching relationship.

[0010] The isotherm infrared image is extracted and displayed on the visible light image according to the matching relationship between the infrared image and the visible light image.

[0011] Preferably, the step of extracting the isotherm infrared image and displaying it on the visible light image according to the matching relationship between the infrared image and the visible light image comprises the following steps:

[0012] The isotherm values ​​are set according to the temperature data, image segmentation is performed in the temperature image, and isotherms of multiple temperatures are extracted;

[0013] The isotherm contours corresponding to the isotherm values ​​are extracted and marked on the infrared image to form a color infrared image;

[0014] The isotherm profile and the infrared image features are matched according to the feature points and descriptors to obtain a matching relationship;

[0015] The isotherm contours are transformed in position and marked in the visible light image to obtain the isotherm data of the visible light image.

[0016] Preferably, the monocular camera model includes: the relationship between the world coordinate system, the camera coordinate system and the image coordinate system; wherein,

[0017] The transformation formula between the camera coordinate system and the world coordinate system is:

[0018]

[0019] Among them, subscript w is the world coordinate system, subscript c is the camera coordinate system, R and T are the external parameters of the camera, and the external parameters R and T correspond to:

[0020]

[0021] The transformation formula between the camera coordinate system and the image pixel coordinate system is:

[0022]

[0023] Among them, f x 、fy , u0, v0 are the intrinsic parameters of the camera respectively; (u0, v0) is the coordinate of the camera optical center in the pixel coordinate system, (f x , f y ) is the pixel focal length, that is, the number of pixels per unit length, in pixels.

[0024] By combining the above internal and external parameters, we can get the transformation relationship between the world coordinate system and the pixel coordinate system:

[0025]

[0026] Preferably, the distortion coefficient matrix includes: a radial distortion matrix and a tangential distortion matrix, wherein:

[0027] The radial distortion matrix is:

[0028]

[0029] Where (x, y) is the coordinate of the uncorrected point, (x rad ,y rad ) are the coordinates of the corrected point;

[0030] The tangential distortion matrix is:

[0031]

[0032] Where (x, y) is the coordinate of the point of the uncalibrated camera, (x tan ,y tan ) is the coordinate of the point of the calibrated camera, r is the distance from the image pixel to the center of the image, that is, r 2 =x 2 +y 2 , therefore, the distortion coefficients obtained in the camera calibration process are five coefficients: k1, k2, k3, p1, and p2. When the distortion coefficients are known, the camera lens can be calibrated.

[0033] Preferably, the step of respectively correcting the infrared image and the visible light image in the overlapped image to form a matching relationship comprises the following steps:

[0034] Through the imaging principle of binocular stereo vision, the rotation and translation between the infrared camera and the visible light camera are calculated to obtain the transformation relationship from the infrared camera coordinate system to the visible light camera coordinate system;

[0035] According to the transformation relationship, the imaging planes of the two cameras are transformed into the same coordinate system to form a matching relationship.

[0036] Preferably, the visible light image and the infrared image are matched by a local stereo matching method to form a fused image of the region of interest.

[0037] Preferably, the calculation formula of the rotation amount and translation amount between the infrared camera and the visible light camera is:

[0038]

[0039] Among them, the subscript l is the left camera coordinate system, and the subscript r is the right camera coordinate system; the space transformation matrix Mlr is expressed as:

[0040]

[0041] Combined with the camera intrinsic parameter matrix, the transformation of the left and right camera pixel coordinate systems can be obtained.

[0042] Preferably, the manner of transforming the infrared image acquired by the infrared camera includes: rotation, translation and scaling.

[0043] Preferably, the fused image used for TCM visual diagnosis is obtained using any one of the visible light image and infrared image fusion methods for TCM visual diagnosis in claims 1-8.

[0044] According to the above technical solution, the method for fusing visible light images and infrared images for TCM visual diagnosis provided by the present invention has the following beneficial effects when used:

[0045] The present invention can establish a monocular camera model through binocular camera calibration to obtain the image coordinates of the infrared camera and the visible light camera, and the infrared image coordinates obtained by the infrared camera are transformed to coincide with the image coordinates obtained by the visible light camera, and the infrared image and the visible light image are corrected to form a matching relationship to obtain an accurate image, and the proposed infrared image isotherms are displayed in the visible light image according to the matching relationship to provide temperature information for the doctor's visual diagnosis, and the combination of the temperature information and the visible light image after the infrared image and the visible light image are coincident and corrected is applied to tongue diagnosis, facial diagnosis, and meridian acupoints, so that the doctor can make a diagnosis quickly and accurately, which plays an auxiliary role.

[0046] Other features and advantages of the present invention will be described in detail in the subsequent specific implementation mode; and the parts not involved in the present invention are the same as the prior art or can be implemented by using the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the following specific embodiments, they are used to explain the present invention but do not constitute a limitation of the present invention. In the accompanying drawings:

[0048] Figure 1 It is a principle block diagram of a method for fusing visible light images and infrared images for TCM visual diagnosis provided in a preferred embodiment of the present invention;

[0049] Figure 2 It is an imaging principle diagram of binocular stereoscopic vision of a method for fusing visible light images and infrared images for TCM visual diagnosis provided in a preferred embodiment of the present invention;

[0050] Figure 3 It is a principle diagram of the relationship between the internal parameter matrix of a camera for a method for fusing visible light images and infrared images for TCM visual diagnosis provided in a preferred embodiment of the present invention.

[0051] Description of Reference Numerals DETAILED DESCRIPTION

[0052] The specific implementation of the present invention is described in detail below in conjunction with the accompanying drawings. It should be understood that the specific implementation described here is only used to illustrate and explain the present invention, and is not used to limit the present invention.

[0053] like Figure 1 As shown, the present invention provides a method for fusing visible light images and infrared images for TCM visual diagnosis, the method comprising:

[0054] S1: Calibrate the camera model to obtain the intrinsic parameter matrix, extrinsic parameter matrix and distortion coefficient matrix of both the visible light camera and the infrared camera;

[0055] S2: transforming the infrared image acquired by the infrared camera according to the obtained intrinsic parameter matrix, extrinsic parameter matrix and distortion coefficient matrix so as to make the coordinate system of the infrared image acquired by the visible light camera coincide with that of the visible light image acquired by the visible light camera;

[0056] S3: Correct the infrared image and the visible light image in the overlapped image respectively to form a matching relationship.

[0057] S4: extracting the isotherm infrared image, and displaying it on the visible light image according to the matching relationship between the infrared image and the visible light image.

[0058] In the above scheme, the image quality obtained by the visible light camera is clear, the detailed texture features are clear, and the shape and color features of the patient's affected area can be restored. However, due to the influence of the light source in the shooting environment and the shadows caused by the photographed objects being easily blocked, the images taken by the visible light camera are difficult to produce good imaging quality in bad weather, at night, and when the ambient light source is insufficient. The infrared camera can make up for the problem of insufficient light intensity and can obtain good infrared images.

[0059] Therefore, a monocular camera model can be established through binocular camera calibration to obtain the image coordinates of the infrared camera and the visible light camera, and the infrared image coordinates obtained by the infrared camera are transformed to coincide with the image coordinates obtained by the visible light camera. The infrared image and the visible light image are corrected to form a matching relationship to obtain an accurate image, and the proposed infrared image isotherms are displayed in the visible light image according to the matching relationship to provide temperature information for the doctor's visual diagnosis. The temperature information and the visible light image after the infrared image and the visible light image are overlapped and corrected are combined and applied to tongue diagnosis, facial diagnosis, and meridian acupoints, so that the doctor can make a diagnosis quickly and accurately, which plays an auxiliary role.

[0060] In a preferred embodiment of the present invention, step S4 extracts the isotherm infrared image and displays it on the visible light image according to the matching relationship between the infrared image and the visible light image, including the following steps:

[0061] The isotherm values ​​are set according to the temperature data, image segmentation is performed in the temperature image, and isotherms of multiple temperatures are extracted;

[0062] The isotherm contours corresponding to the isotherm values ​​are extracted and marked on the infrared image to form a color infrared image;

[0063] The isotherm profile and the infrared image features are matched according to the feature points and descriptors to obtain a matching relationship;

[0064] The isotherm contours are transformed in position and marked in the visible light image to obtain the isotherm data of the visible light image.

[0065] In the above scheme, the isotherm contour is proposed by using the table lookup method to form a color infrared image, and it is displayed on the visible light image according to the matching relationship between the infrared image and the visible light image. This makes up for the fact that only the fusion of infrared image and visible light image is used to collect human body surface images, so that the diagnostic information that can be provided is single, and temperature information can be provided for human body inspection, which is convenient for doctors to make accurate diagnosis results for patients by combining the details, texture characteristics and temperature pathological characteristics displayed by the visible light image, thereby improving the accuracy of the diagnosis results.

[0066] In a preferred embodiment of the present invention, the monocular camera model includes: the relationship between the world coordinate system, the camera coordinate system and the image coordinate system; wherein,

[0067] The transformation formula between the camera coordinate system and the world coordinate system is:

[0068]

[0069] Among them, subscript w is the world coordinate system, subscript c is the camera coordinate system, R and T are the external parameters of the camera, and the external parameters R and T correspond to:

[0070]

[0071] The transformation formula between the camera coordinate system and the image pixel coordinate system is:

[0072]

[0073] Among them, f x 、f y , u0, v0 are the intrinsic parameters of the camera respectively; (u0, v0) is the coordinate of the camera optical center in the pixel coordinate system, (f x , f y ) is the pixel focal length, that is, the number of pixels per unit length, in pixels.

[0074] By combining the above internal and external parameters, we can get the transformation relationship between the world coordinate system and the pixel coordinate system:

[0075]

[0076] In the above scheme, according to Zhang Zhengyou's calibration method, the camera's intrinsic and extrinsic parameter matrix can be obtained. Since the positions of the infrared camera and the visible light camera are fixed and the positional relationship of the cameras is used in image matching, the intrinsic and extrinsic parameters of the two cameras must be saved and used to transform the infrared image.

[0077] In a preferred embodiment of the present invention, the distortion coefficient matrix includes: a radial distortion matrix and a tangential distortion matrix, wherein:

[0078] The radial distortion matrix is:

[0079]

[0080] Where (x, y) is the coordinate of the uncorrected point, (x rad ,y rad ) are the coordinates of the corrected point;

[0081] The tangential distortion matrix is:

[0082]

[0083] Where (x, y) is the coordinate of the point of the uncalibrated camera, (x tan ,y tan ) is the coordinate of the point of the calibrated camera, r is the distance from the image pixel to the center of the image, that is, r 2 =x 2 +y2 , is, Therefore, the distortion coefficients obtained in the camera calibration process are k1, k2, k3, p1, p2, where k1, k2, k3 are radial distortion parameters. p1, p2 are tangential distortion parameters. When the distortion coefficients are known, the camera lens can be calibrated.

[0084] In the above scheme, since the positions of the infrared and visible light cameras are fixed and the positional relationship of the cameras is used in image matching, the internal and external parameters of the cameras must be saved and used. The infrared image acquired by the infrared camera is transformed according to the internal parameter matrix and the distortion coefficient matrix to coincide with the coordinates of the visible light image.

[0085] In a preferred embodiment of the present invention, the step of respectively correcting the infrared image and the visible light image in the overlapped image to form a matching relationship comprises the following steps:

[0086] Through the imaging principle of binocular stereo vision, the rotation and translation between the infrared camera and the visible light camera are calculated to obtain the transformation relationship from the infrared camera coordinate system to the visible light camera coordinate system;

[0087] According to the transformation relationship, the imaging planes of the two cameras are transformed into the same coordinate system to form a matching relationship.

[0088] In the above scheme, if Figure 2 As shown in the figure, it is an imaging principle diagram of binocular stereo vision. Through the imaging principle of binocular stereo vision, the visible light camera and the infrared camera are calibrated simultaneously, and the calculation formula of the rotation and translation between the infrared camera and the visible light camera can be used to obtain the transformation relationship from the infrared camera coordinate system to the visible light camera coordinate system. In combination with the camera intrinsic parameter matrix, the transformation of the left and right camera pixel coordinate systems can be obtained.

[0089] Among them, the coordinate O l is the left camera coordinate system, that is, the image coordinates obtained by the infrared camera, coordinate O r is the right camera coordinate system, that is, the image coordinates obtained by the visible light camera, and the coordinates A (X, Y, Z) are the coordinates of the photographed point in the world coordinate system, that is, the coordinates O l and coordinates O r The coordinates after transformation and overlap, C l is the left camera pixel coordinate plane, C r is the right camera pixel coordinate plane, f l and f r are the focal length of the right camera, n r is the pixel point of A in the right camera pixel coordinate system, a r is the pixel coordinate of point A on the right camera, a l is the pixel coordinate of A in the left camera.

[0090] Different from the matching of two visible light cameras, the imaging principle of binocular stereo vision is used to obtain the transformation relationship between the infrared camera coordinate system and the visible light camera coordinate system, which overcomes the problem that the existing technology uses infrared cameras to image low texture and the features of the same-name points in the two images are inconsistent, which leads to the phenomenon of easy mismatching. In addition, without the constraints of prior conditions, for each pixel point of the template image, it is necessary to search and match among all the pixels of the entire image on the image to be registered, resulting in the problem that the process of finding matching points is inefficient and very time-consuming.

[0091] In a preferred embodiment of the present invention, the camera calibration result is used as a constraint condition, and the visible light image is matched with the infrared image through a local stereo matching method to form a fused image of the area of ​​interest. Local stereo matching is performed based on the constraint conditions obtained by transforming the internal and external parameters of the camera in order to improve shooting efficiency and accuracy.

[0092] In a preferred embodiment of the present invention, the calculation formula of the rotation and translation between the infrared camera and the visible light camera is:

[0093]

[0094] Among them, the subscript l is the left camera coordinate system, and the subscript r is the right camera coordinate system; the space transformation matrix Mlr is expressed as:

[0095]

[0096] Combined with the camera intrinsic parameter matrix, the constraint relationship between the left and right camera pixel coordinate systems can be obtained as a priori condition for matching, which can reduce the probability of false matching, reduce the range of image search during matching, and improve matching efficiency.

[0097] The purpose of epipolar constraint is to reduce the workload of searching for corresponding points, that is, to reduce the search from the entire image to the search on the epipolar line. Figure 3 As shown, there is a point P in space, the projection points are P1 and P2, and the optical centers are O1 and O2.

[0098] If the intrinsic parameter matrices of the left and right cameras are K1 and K2 respectively, and the extrinsic parameters are R and T. Let P1(u1, v1, 1) and P2(u1, v1, 1), then the conversion relationship is:

[0099]

[0100]

[0101] The normal vector of the plane PO1O2 is Figure 3 The camera coordinate system of camera 2 shown in is:

[0102]

[0103] in, Perpendicular to Pc2, we can get:

[0104]

[0105] In summary, we can get the polar line P2e2:

[0106]

[0107] Where TTTR is the eigenvalue matrix, is the basic matrix.

[0108] In the above scheme, accurate image feature matching can be performed based on feature points and descriptors. Thanks to the fact that the positions and shooting states of the two cameras are basically fixed, the image matching algorithm, which has been calibrated by the cameras and corrected to the same coordinate system, only needs to perform fine matching and fine-tuning in a small range, thereby saving calculation time and improving matching accuracy.

[0109] In a preferred embodiment of the present invention, the manner of transforming the infrared image acquired by the infrared camera includes: rotation, translation and scaling.

[0110] In a preferred embodiment of the present invention, the fused image used for TCM visual diagnosis is obtained using any one of the visible light image and infrared image fusion methods used for TCM visual diagnosis in claims 1-8.

[0111] In summary, the method for fusing visible light images and infrared images for TCM visual diagnosis provided by the present invention overcomes the problem in the prior art that doctors mainly rely on their judgments based on the naked eye, and the diagnosis is inevitably affected by the environment, such as the brightness of the light, and the influence of the doctor's personal psychological state, which leads to diagnostic errors in the diagnosis, thereby affecting the accuracy of the diagnosis results.

[0112] The preferred embodiments of the present invention are described in detail above in conjunction with the accompanying drawings. However, the present invention is not limited to the specific details in the above embodiments. Within the technical concept of the present invention, a variety of simple modifications can be made to the technical solution of the present invention, and these simple modifications all belong to the protection scope of the present invention.

[0113] It should also be noted that the various specific technical features described in the above specific embodiments can be combined in any suitable manner without contradiction. In order to avoid unnecessary repetition, the present invention will not further describe various possible combinations.

[0114] In addition, various embodiments of the present invention may be arbitrarily combined, and as long as they do not violate the concept of the present invention, they should also be regarded as the contents disclosed by the present invention.

Claims

1. A method for fusing visible light images and infrared images for TCM visual diagnosis, characterized in that: The method comprises: By calibrating the camera model, the intrinsic parameter matrix, extrinsic parameter matrix and distortion coefficient matrix of both the visible light camera and the infrared camera are obtained; Transforming the infrared image acquired by the infrared camera according to the obtained intrinsic parameter matrix, extrinsic parameter matrix and distortion coefficient matrix so as to make the coordinate system of the infrared image acquired by the visible light camera coincide with that of the visible light image acquired by the visible light camera; Correcting the infrared image and the visible light image in the overlapped image respectively to form a matching relationship; The isotherm infrared image is extracted and displayed on the visible light image according to the matching relationship between the infrared image and the visible light image.

2. The visible light image and infrared image fusion method for TCM visual diagnosis according to claim 1 is characterized in that: The step of extracting the isotherm infrared image and displaying it on the visible light image according to the matching relationship between the infrared image and the visible light image comprises the following steps: The isotherm values ​​are set according to the temperature data, image segmentation is performed in the temperature image, and isotherms of multiple temperatures are extracted; The isotherm contours corresponding to the isotherm values ​​are extracted and marked on the infrared image to form a color infrared image; The isotherm profile and the infrared image features are matched according to the feature points and descriptors to obtain a matching relationship; The isotherm contours are transformed in position and marked in the visible light image to obtain the isotherm data of the visible light image.

3. The method for fusing visible light images and infrared images for TCM visual diagnosis according to claim 1 is characterized in that: The monocular camera model includes: the relationship between the world coordinate system, the camera coordinate system and the image coordinate system; wherein, The transformation formula between the camera coordinate system and the world coordinate system is: Among them, subscript w is the world coordinate system, subscript c is the camera coordinate system, R and T are the external parameters of the camera, and the external parameters R and T correspond to: The transformation formula between the camera coordinate system and the image pixel coordinate system is: Among them, fx, fy, u0, and v0 are the intrinsic parameters of the camera respectively; (u0, v0) is the coordinate of the camera optical center in the pixel coordinate system, and (fx, fy) is the pixel focal length, that is, the number of pixels per unit length. By combining the above internal and external parameters, we can get the transformation relationship between the world coordinate system and the pixel coordinate system:

4. The method for fusing visible light images and infrared images for TCM visual diagnosis according to claim 1, characterized in that: The distortion coefficient matrix includes: a radial distortion matrix and a tangential distortion matrix, wherein: The radial distortion matrix is: Where (x, y) is the coordinate of the uncorrected point, and (xrad, yrad) is the coordinate of the corrected point; The tangential distortion matrix is: Among them, (x, y) is the coordinate of the point of the uncalibrated camera, (xtan, ytan) is the coordinate of the point of the calibrated camera, r is the distance from the image pixel to the center of the image, that is, r2=x2+y2, which is, Therefore, the distortion coefficients obtained in the camera calibration process are k1, k2, k3, p1, p2, where k1, k2, k3 are radial distortion parameters. p1, p2 are tangential distortion parameters. When the distortion coefficient is known, the camera lens can be calibrated.

5. The method for fusing visible light images and infrared images for TCM visual diagnosis according to claim 1, characterized in that: The step of respectively correcting the infrared image and the visible light image in the overlapped image to form a matching relationship comprises the following steps: Through the imaging principle of binocular stereo vision, the rotation and translation between the infrared camera and the visible light camera are calculated to obtain the transformation relationship from the infrared camera coordinate system to the visible light camera coordinate system; According to the transformation relationship, the imaging planes of the two cameras are transformed into the same coordinate system to form a matching relationship.

6. The visible light image and infrared image fusion method for TCM visual diagnosis according to claim 1 is characterized in that: The visible light image is matched with the infrared image through the local stereo matching method to form a fused image of the area of ​​interest.

7. The method for fusing visible light images and infrared images for TCM visual diagnosis according to claim 5, characterized in that: The calculation formula of the rotation and translation between the infrared camera and the visible light camera is: Among them, the subscript l is the left camera coordinate system, and the subscript r is the right camera coordinate system; the space transformation matrix Mlr is expressed as: Combined with the camera intrinsic parameter matrix, the transformation of the left and right camera pixel coordinate systems can be obtained.

8. The method for fusing visible light images and infrared images for TCM visual diagnosis according to claim 1, characterized in that: The ways of transforming the infrared image acquired by the infrared camera include: rotation, translation and scaling.

9. A fusion image for TCM visual diagnosis, characterized in that: The fused image used for TCM visual diagnosis is obtained using any of the visible light image and infrared image fusion methods used for TCM visual diagnosis in claims 1-8.

Images