TW201740871A - Method for reconstructing fundus image - Google Patents

Abstract

The invention provides a method for reconstructing fundus image including: identifying a plurality of component image data as an input of an iteration calculation; calculating a weight factor for respective component image data based on a first ratio. Said iteration calculation includes executing an enhancement calculation to generate a plurality of enhanced component image data and calculating a weight factor for respective enhanced component image data based on a second ratio; determining whether to end the iteration calculation, if not, the computed enhanced component image data being served as an input for the next iteration calculation. After the iteration calculation is ended, the method reconstructs the fundus image based on the plurality of enhanced component image data.

Description

Fundus image reconstruction method

The present invention relates to an image reconstruction method, and more particularly to a method for reconstructing a fundus image.

The epiretinal proliferative membrane or Epiretinal Membrane is a lesion that occurs at the fundus, which severely images the patient's vision. The fundus hyperplasia membrane can be properly treated, as long as it can diagnose the correct position of the proliferative membrane and completely remove it, it can improve the lost vision.

The discovery of the fundus hyperplasia membrane can be identified by fundus examination. A bottom eyepiece can be used to capture the back of the eye to obtain a fundus image. The fundus image records the appearance of the patient's retina, which is used to examine abnormalities caused by eye diseases and can also be used to track the progression of eye diseases. Clinicians can follow the patient's fundus image to understand the history of the patient's eye disease and make appropriate diagnosis and treatment. In particular, changes in the detail displayed by the fundus image may be related to a disease. For example, in the case of a colored fundus image, the abnormality displayed in the image or the particularly conspicuous transparent (white) area may be associated with the fundus hyperplasia film. related. That is, the abnormal white area in the image is an optical characteristic caused by a film formed at the fundus position or on the retina. The clinical staff can identify the proliferative membrane by regularly tracking the patient's fundus image. In a fundus image containing a proliferative membrane, a brighter image area and a darker image area should be included, The image area corresponds to the area of the fundus hyperplasia membrane. In practice, the fundus image taken through the general ophthalmoscope is difficult to allow the clinician to recognize the brighter and darker areas of the image without special image processing, so that accurate diagnosis and treatment cannot be given.

Therefore, in order to give patients with such eye diseases a more reliable and efficient fundus diagnosis, a tool is needed to improve the identification of image details and contrast.

The invention uses image processing as an identification for improving image detail and contrast, and is suitable for fundus images, especially fundus images related to fundus hyperplasia films. The present invention provides a method of image reconstruction that converts an unprocessed original image into a reconstructed image. A fundus image (initial image) taken by a lens is converted into a reconstructed image by the method provided by the present invention, which has the characteristics of contrast and/or pattern detail enhancement.

The method for reconstructing a fundus image is performed by at least one processor, comprising: receiving a color image data, wherein the image data is related to a fundus image; performing a iterative operation to obtain a plurality of enhanced component image data; The image data of the enhanced component is reconstructed to reconstruct the color image data.

The method, before performing the iterative operation, includes: obtaining a plurality of component image data as an input of the iterative operation according to the color image data. In general, fundus images contain color. The method provided by the present invention is to identify the plurality of component image data related to the image according to the color component of the received color image data, and each component image data corresponds to a color, and the color corresponding to the component image is different from the color Another color corresponding to another component image. For example, one component image may correspond to red, and another component image may correspond to blue. These component images represent the components of each color of the color image. The present invention utilizes these component images As an input to the iterative operation, and processed separately.

The iterative operation includes calculating a weight of each of the component image data based on a first ratio of the component image data. Each of the component image data has a different contribution in the color image, that is, each component image material may have different pixel values on corresponding pixels. This results in a proportional relationship between the component image data of the color image data. Based on such a proportional relationship, each of the component image data is subjected to a weighting operation. Based on such a proportional relationship, a plurality of weight values are generated, each of the equal weight values corresponding to each of the equal component images, and the weighting operation is performed based on such correspondence.

The iterative operation includes performing an enhancement operation to calculate a plurality of enhancement component image data, wherein each enhancement component image data is multiplied by a sum of respective weights based on other component image data. The other component image data is multiplied by a corresponding weight value. The sum of the weighted other component image data is the enhanced component image data. The color corresponding to the enhanced component image data is different from the color corresponding to the other component image data, and the other image materials respectively correspond to different colors. In other words, the component image data corresponding to one color is obtained by calculating the weighted sum of the component image data corresponding to the other colors.

The enhancement operation further includes calculating a respective enhancement weight of the enhancement component image data based on a second ratio of the enhancement component image data. As described above, the enhancement component image data also has a proportional relationship with each other, so that a plurality of weight values (herein referred to as enhancement weight values) can be further generated based on such relationships for the enhancement component image data for subsequent processing.

The iterative operation includes: based on the corresponding enhancement weight and the enhancement component For the average value of the data, the normalized image data of each of the enhanced components is normalized. The image data of the enhanced components obtained may make the image intensity corresponding to the image intensity too high, so the normalization operation related to the image intensity is performed to obtain an appropriate image intensity.

The iterative operation includes: determining whether to end the iterative operation, and if not, using the enhancement component image data of the normalization operation as the input of the iterative operation. The iterative operation is ended when the iterative operation, or the enhancement component images satisfy a particular condition. When the condition is not satisfied, the iterative operation is performed again, and the component image data is replaced with the normalization result as an input to which the iterative operation will be performed later. The flow of subsequent iterative operations is basically the same as the flow of the previous iterative operation. Ending the iterative operation, reconstructing the color image data based on the enhanced component image data, and the reconstructed color image data displays an image having a color and a detail different from the initial image.

These and other features and advantages of the present invention will be described in more detail in the description of the appended claims.

2‧‧‧Image capture unit

4‧‧‧ imaging unit

6‧‧‧Lighting unit

61‧‧‧Light source

62‧‧‧Optical components

8‧‧‧ camera unit

10‧‧‧Computer equipment

102‧‧‧Processor

104‧‧‧ storage unit

106‧‧‧Display unit

108‧‧‧Input interface

E‧‧‧ eyes

20‧‧‧ Input image

22‧‧‧Reconstruction of images

24‧‧‧Component image data

24r, 24g, 24b‧‧‧ component image data

26‧‧‧Intermediary reconstruction image

W _r , W _g , W _b ‧‧ ‧ weight value

300 to 320‧‧ steps

The first figure shows a system that is suitable for use in the fundus image reconstruction method of the present invention.

The second figure shows an input image and a reconstructed image thereof (in accordance with the method provided by the present invention).

The third figure shows the flow of the method of the invention.

The invention will be described more fully hereinafter with reference to the accompanying drawings, However, the subject matter of this claim can be embodied in many different forms, so The construction of the claimed subject matter is not limited to any of the exemplary embodiments disclosed in the specification; the specific embodiments are merely illustrative. As such, the present invention is intended to provide a broad and broad scope of the claimed subject matter. In addition, for example, the claimed subject matter can be embodied as a method, apparatus, or system. Thus, particular embodiments may take the form of, for example, a hardware, a soft body, a firmware, or any combination of these (known as not being a soft body).

The words "in one embodiment" used in the specification are not necessarily referring to the specific embodiments, and the "in other embodiments" used in the specification are not necessarily referring to the specific embodiments. It is intended that the subject matter, for example, be construed as a

The first figure illustrates a system for obtaining a fundus image of an eye E and its processing. The system includes an image capture device, an image capture (recording) device, and a processing and operation device. The image capturing device may be included in the image capturing device for capturing a clear fundus image. The processing and application device carries program instructions configured to perform the image reconstruction method of the present invention to process a received image. The processing and operation device receives the initial image data obtained by the image capturing device, and outputs a reconstructed image through the special weighting process provided by the present invention. The image capturing device and the image capturing device are not necessarily combined into a single capturing device, and the image capturing device can also be incorporated into the processing and operating device.

The photographing device may be a fundus camera dedicated to taking a fundus image. As shown in the first figure, an image capturing device of the system may include an image capturing unit 2 and an imaging unit 4. The image capturing unit 2 includes a plurality of optical elements including, for example, an objective, a semitransparent mirror, a focusing lens, and an aperture. The image capturing unit 2 is configured to form a space in the object space The surface is focused such that the bottom surface of an eye E overlaps the focused surface. The image capturing unit 2 can be combined with a lighting unit 6. The illumination device 6 includes a light source 61, a condenser, and other optical elements 62. A portion of the illumination unit 6 is included in the image capture unit 2, such as a common objective lens. The illumination unit 6 is configured to project light into the eyeball to illuminate the fundus region to provide sufficient light for the image capturing unit 2 to capture. Depending on the operation, the light source 61 can be selectively turned on. In the present invention, more lighting units can be included to meet different viewing needs.

The imaging unit 4 includes a plurality of optical elements including, for example, a mirror, a dichroic mirror, a relay lens, and the like. The imaging unit 4 is connected to the rear end of the image capturing unit 2 for receiving the light captured by the former and projecting to an imaging unit 8, which is included in the image capturing device. In other possible cases, the imaging unit 4 and the imaging unit 8 may be included in the image capturing device to capture the fundus image and output a color image data. A photographed fundus image is transmitted to the processing and application device. The processing and application unit may be a computer device 10 including at least one processor 102, a storage unit 104, a display unit 106, and an input interface 108. The fundus image of the photograph is stored in the storage unit 104 in the form of data. The storage unit 104 also stores a plurality of instructions for being read by the at least one processor 102 to perform various operations, including the operation of reconstructing the fundus image provided by the present invention. The storage unit 104 also stores the results of each iteration operation as a source of subsequent iterative operations or reconstructed images. The storage unit 104 is a memory that stores the color image data and intermediate data related to image processing (such as component image data and enhanced component image data). The intermediate data will be explained in the following content. One or more processed or unprocessed images may be displayed on the display unit 106 for viewing and comparison. The display unit 106 can be a display device, such as an LCD high-resolution screen, displaying a transparent area of the fundus image in the color image data after reconstruction (ie, a shadow) The part that is white in the middle, that is, the area where the fundus hyperplasia film may form). The input interface 108 is composed of a hardware and a software, such as an input keyboard, a touch device, and an operating program that interacts with the hardware. The input interface 108 is configured to provide interaction of a user or an operator with the computer device 10. Through the input interface 108, the computer device 10 can receive control parameters for performing the method of the present invention, such as a plurality of preset values or conditions regarding operations, which will be described later. The processor 104 can cause the color image data reconstructed by different iterations according to the operation of the input interface 108 (ie, mediate reconstruction of the image) on the display device.

The image reconstruction method of the present invention is not necessarily performed in the system of the first figure, and the color image data may be transmitted to other computers or servers for processing via other means, such as a network. The processor executing the method of the present invention may be one or more, and the processors may be present in a computer device or distributed among different computing devices.

The second figure shows an input image 20 (initial image) converted to a reconstructed image 22 by the method of the present invention. The input image 20 is displayed based on a color image material. The color image data is obtained by an image capturing device. The color image material can be the output of the image capture device and is generally unprocessed. The format of the color image data may be jpg, jpeg, bmp or png. The color image data is presented in a matrix, for example, a 512×512 pixel input image 20, and the color image data is also a 512×512 matrix, and each element in the matrix represents a pixel value. . The color image data and the component image data and the enhancement component image data of the subsequent calculations all include a plurality of pixel values. The color image data is composed of a plurality of component image data. The component image data is defined based on a color model selected from one of an RGB color model, a CMYK color model, and a HSI color model.

As shown in the second figure, first, the color image data related to the input image 20 (such as a fundus image) is received. The processor obtains a plurality of component image data 24 based on the color image data. The component image data 24 exemplified herein is obtained based on a three-primary color model, that is, a red portion 24r, a blue portion 24b, and a green portion 24g of the color image data, but those having ordinary knowledge in the field may also be based on three primary color models and other colors. The conversion between the models obtains other component image data based on the color mixing model or other component image data based on the HSI model. The component image data 24 is also represented in a matrix, such as a 512 x 512 matrix, and the elements of each matrix are pixel values associated with a color. In other words, the color image material is comprised of or consists of a superposition of the component image data 24. The initial image obtained by most image capturing devices generally forms corresponding data according to the components of its three primary colors, which is related to the configuration of the photosensitive elements. Therefore, it has been possible for a person skilled in the art to recognize the component image data of the three primary colors in the color image data.

The method of the invention comprises a weighting operation. The processor generates a plurality of weight values W _r , W _g , W _b (initial weights) according to a proportional relationship (first ratio) between the component image data 24r, 24g, and 24b, each of which corresponds to the previously identified Component image data 24r, 24g, 24b. The proportional relationship (first ratio) will be explained in the following.

The method of the present invention includes an iterative operation to enhance the transparent region of the fundus image in the color image data. The method of the present invention also includes more iterative operations to further strengthen the region. The iterative operation includes an enhancement operation and an enhancement weight operation. The identified component image data 24r, 24g, 24b and the calculated weight values W _r , W _g , W _b can be used as an input to the iterative operation (first iteration operation), respectively. The enhancement operation is performed to calculate a plurality of enhancement component image data (not shown), wherein each enhancement component image data is multiplied by respective weights based on other component image data (weight values W _r , W _g , W _b ) The sum of them. The enhanced operation will be described in detail later. The data dimension of the enhanced component image is the same as the component image data before the enhancement, that is, a 512×512 matrix.

The enhancement weight operation included in the iterative operation is based on a proportional relationship (second ratio) of the image data of the enhancement components, and the enhancement weights of the image data of the enhancement components are calculated, that is, a plurality of enhancement weight values are generated. Here, the reinforcement weight is different from the initial weight, and the reinforcement weight is obtained based on the reinforcement operation in the iterative operation; the initial weight is obtained based on the initial component image data.

The enhanced component image data may be an output of the iterative operation. The output is used as an input to the next iterative operation (second iteration operation), and the enhancement operation and the enhancement weight operation are repeated to obtain a new plurality of enhancement component image data as the next iteration. An input to the operation. These operations continue to repeat until the processor ends the iterative operation based on a result of the decision. After the processor ends the iterative operation, the color image data is reconstructed based on the latest enhanced component image data. The finally obtained enhancement component image data and the corresponding component image data of the color image data are superimposed on each other to generate the reconstructed image 22. Comparing the fundus images 20, 22 before and after reconstruction in the second figure, wherein the reconstructed image 22 has a higher brightness contrast, which helps to identify a bright region of the image 22 and a relatively dark region. In particular, the pattern details of the reconstructed image 22 are also more distinct due to enhancement.

The output of one or more iterative operations, i.e., the enhanced component image data, may be stored in storage unit 104 as in the first map system before the processor stops the continuous iterative operation. At the same time, one or more intermediaries reconstruct images 26 (based on the stored image data of the enhanced components) Built) can be stored together. The intermediate reconstructed image 26 is different from the reconstructed image 22 of the second map. The intermediate reconstruction image 26 is produced before the iterative operation has not stopped. The intermediate reconstruction images 26 can be invoked for display via a display device. Each intermediate reconstructed image 26 may be generated based on the last calculated computed component image data after every predetermined number of iterations, such as an intervening reconstructed image every 1000 iterations. Thus, as long as the iterative operation has not stopped, at least one intermediate reconstructed image 26 is available. The features such as contrast and brightness of the reconstructed image 26 exhibit a continuous change that can be used for other image processing, such as whether to continue the iterative operation as to whether to end or stop.

The third diagram is a flow of the method of the present invention, including steps 300 through 320, which are performed by at least one processor. For convenience of explanation, n in the figure represents the initial processing without the iterative operation, and n+1 represents the processing by the first iterative operation, and so on. The method begins in step 300 by receiving an initial image. The color image data, that is, the input image 20 of the second image, is received by an computing device or a computer, and the color image data is related to the fundus image. The initial image is taken from an image capture device and typically the color or pixel values are not processed. However, in other embodiments, the initial image may also be subjected to preliminary processing, such as compression of the image or normalization of pixel values.

Step 302: Identify, by the at least one processor, a color component included in the color image data, such as the foregoing three primary colors. Recognizing the three primary color components contained in each pixel value of the color image data, thereby obtaining a plurality of component image data, as described by the following equation: X _initial = r _n + g _n + b _n ...... 1), wherein X _{initial is} the color image data, r _n , g _n , b _n are component image data, and the component image data 24r, 24g, 24b based on the three primary color models are shown in the second figure. In other embodiments, other component image data may be identified from the color image data based on the CMYK model or the HSI model. The image data of the components have the same dimensions, such as 512×512. The component image data is also an input to subsequent iterative operations.

Step 304, generating an initial weight for the color component. A proportional relationship (first ratio) of the component image data is used to calculate the weighting of each of the component image data. The first ratio is the ratio of the mean values of the respective component image data. According to the first ratio, a plurality of initial weight values are generated. The weighting of the respective component image data, that is, an initial weight value corresponding to each component image data, is the sum of the mean values of the respective component image data divided by the mean values of all component image data, as described by the following equation: Where k represents one of the component image data, i = { r, g, b } represents all component image data, avg ( k ) represents the pixel mean of a component image data, Σ _i avg ( i ) represents all components The pixel mean of the image data, and W _k is a weight value associated with the component image data k , such as W _r , W _g , W _b calculated in the second figure. These weight values are used as an input to subsequent iterative operations.

Step 306, performing an iterative operation, where the iterative operation starts with an enhancement operation to generate a plurality of enhancement component image data (n+1), wherein each enhancement component image data is multiplied by respective component image data. The sum of the weights. Each of the enhancement component image data is computed based on at least two of the component image data subjected to the weighting operation, wherein at least two of the component image data (n) used for the enhancement operation correspond respectively Two different colors (for example, green, blue), and the enhanced component image data (n+1) calculated based on at least two of the component image data (n) corresponds to another color (for example, red), and the other One color is different from the two different colors. For example, the operation of the enhanced component image data (n+1) based on the three primary colors is as described in the following equation: Where r _n , g _n , b _n are the image data (matrices) of the components, W _rn , W _gn , W _bn are weight values (constants) corresponding to the image data of the components, r _{n +1} , g _{n +1} and b _{n +1} are the image data (matrices) of the enhancement components.

The iterative operation also includes an enhancement weighting operation, step 310, which is a weighting operation of the enhanced image data obtained by the operation. The weighting operation of step 310 is the same as the weighting operation of step 304, but the basis of the operation is different. Step 304 is based on the initial component image data (n), and step 308 is based on the enhancement component image data (n+1). Based on a proportional relationship (second ratio) of the enhanced component image data (n+1), the respective enhancement weights of the enhanced component image data (n+1) are calculated. A plurality of enhancement weight values W k _n+1 are generated, as described by the following equation: Where r _{n +1} , g _{n +1} , and b _{n +1} are the image data (matrices) of the enhancement components. The iterative operation can be performed after generating the enhanced component image data and the corresponding enhancement weight values.

The iterative operation also includes a normalization operation, step 312. A normalization operation is performed on each of the enhanced component image data based on the corresponding enhancement weight and a mean value of the enhancement component image data. The normalization operation is performed on the image data of the respective enhancement components, and the product of the original enhancement component image data minus the mean value of the original enhancement component image data plus 1 and the respective enhancement weights is calculated, and the calculation results are normalized. Enhanced component image data, as described by the following equation: r _{n +1} (normalized) = r _{n +1} - avg ( r _{n +1} ) × (1 + Wr _{n +1} ) (7), g _{n +1} (normalized)= g _{n +1} - avg ( g _{n +1} )×(1+ Wg _{n +1} ) (8), b _n+1 (normalized)=b _{n+ 1 -} avg(b _n+1 ) × (1 + Wb _n+1 ) (9). The enhanced component image data of the regularization operation can be used as an output of the iterative operation. In some embodiments, step 312 may be omitted, that is, the enhanced component image data is used as the output of the iterative operation.

Step 314, determining whether to end or stop the iterative operation, that is, whether to continue to strengthen the enhanced component image data and its enhancement weighting operation. If the iterative operation is not completed or stopped, the enhanced component image data of the normalization operation (step 312) is taken as the input of the iterative operation. The iterative operation is continued, and the process returns to step 306, and the input of the continuous iterative operation (n+2) includes the enhancement component image data (n+1) obtained from the foregoing step 308 and the enhancement weight obtained from step 310. Value (n+1).

In an embodiment, the determining whether to end the iterative operation is determining whether a number of iterations is reached, which may be a preset. When the continuous iterative operation satisfies the number of iterations, for example 10,000 times, the iteration operation at (n+9999) ends or stops, and proceeds to step 316. If it is determined that the number of iterations has not been reached, the enhanced component image data of the normalization operation is used as an input for continuing the iterative operation, and the iterative operation is performed. In addition, possible practices can also include manual operations. Work. For example, the operator can determine whether or not to perform several iterations in accordance with the observation of the intermediate reconstructed image 26 as shown in the second figure.

The iterative operation further includes reconstructing the color image data of the iteration number based on the enhanced image data obtained by the number of iterations for each preset number of iterations or a multiple thereof. Reconstruct the image. For example, it may be preset that when the number of iterations reaches 1000 or reaches a multiple of 1000, the color image data is reconstructed based on the enhanced image data obtained by the last iteration operation to obtain one or more intermediate reconstructions. Image and continue to perform iterative operations. As mentioned previously, the intermediate reconstructed images may present a continuous change in the initial image during processing. This can be provided to the operator or clinical staff as an observation.

In step 314, in other embodiments, determining whether to end the iterative operation is determining whether a difference in different operation results obtained by different iteration times is less than a critical condition. In a continuous iterative operation, when the difference between the enhancement component image data (normalization) of a certain iteration operation and the enhancement component image data (normalization) of the previous iteration operation is less than the critical condition, then the end Or stop the iterative operation and proceed to step 316. For example, based on an iterative operation, an overall pixel value difference between an intermediate reconstructed image and another intermediate reconstructed image obtained based on another previous iterative operation is obtained to determine whether it is less than the critical condition.

The bundled critical condition is a convergence condition, and the difference between the outputs of different iteration operations (ie, multiple mediation reconstructed images, or multiple enhancement component image data) exhibits a convergence tendency, that is, the convergence condition is satisfied, The generation will end or stop.

Step 316, based on the judgment of step 314, that is, whether the number of iterations is satisfied or whether the iteration result converges, the execution of the iterative operation is stopped, and the termination is enhanced. Step 318: reconstruct the color image data based on the enhanced component image data obtained by the last iterative operation. Reconstructing the color image data includes superimposing the enhanced component image data after the last iteration operation and the component image data of the corresponding color image data to generate a reconstructed image, as described in the following equation : X _final = r _final + g _final + b _final + X _initial ...... (10), where X _final is the reconstructed image data, r _final , g _final , b _final is the last time after the iteration operation stops The enhancement component image data obtained by the iterative operation is superimposed with the corresponding component images r _n , g _n , b _n , that is, r _final + r _n , g _final + g _n , b _final + b _n . Step 320: The processor outputs the reconstructed image (such as the second image reconstructed image 22) based on the reconstructed image data X _final , which can be displayed on the display device. The reconstructed image is different from the intermediate reconstructed image, where the reconstructed image is generated after the iteration operation is terminated or stopped. After the fundus image was reconstructed through the above steps, the area of the fundus hyperplasia film (whiteish) was more pronounced.

The above embodiment is exemplified by a three primary color model. In other embodiments, the three primary color models may also be replaced with CMYK models or HSI models. For the CMYK model, the above operation may further comprise a complementary operation on the color, for example, component image data including recognition to convert an input image data, as described by the following equation: X _initial = c + m + y + k . .....(11), c _n =255- c ......(12), m _n =255- m ......(13), y _n =255- y ... ...(14), k _n =255- k (15), where c , m , y, k are matrices of cyan, magenta, yellow, black, respectively, c _n , m _n , y _n , k _{n are the basis} for the conversion as an input to the iterative operation and the weighting calculation. In addition, for the HSI model, a linear relationship between the three primary color model and the HSI model is included in the above operation including a conversion operation. Those skilled in the art can appropriately adjust or modify the above-described operational flow based on usual knowledge to make the present invention applicable to other color models.

Although the foregoing invention has been described in some detail, it will be understood that Therefore, the above embodiments are intended to be illustrative only, and the invention is not limited to the details described herein, but may be modified in the field of the appended claims.

20‧‧‧ Input image

22‧‧‧Reconstruction of images

24‧‧‧Component image data

24r, 24g, 24b‧‧‧ component image data

26‧‧‧Intermediary reconstruction image

W _r , W _g , W _b ‧‧ ‧ weight value

Claims (15)

A fundus image reconstruction method is performed by at least one processor, comprising: receiving a color image data, wherein the image data relates to a fundus image; and obtaining a plurality of component image data (n) as a stack according to the color image data An input of the generation operation; obtaining a first ratio (W _n ) of the component image data based on the input, and calculating a weight of each of the component image data; performing the iterative operation, comprising: performing an enhancement operation to calculate a plurality of enhanced component image data (n+1), wherein each of the enhancement component image data is based on a sum of the weights of the other component image data and a second ratio based on the image data of the enhancement components, and the operation is performed Enhancement weighting (n+1) of each of the enhanced component image data; normalizing the image data of the enhanced component based on the corresponding enhancement weight and a mean value of the enhanced component image data; determining whether to end the iterative operation, If not completed, the normalized component image data of the normalization operation is used as the input of the iterative operation, and the stack is ended. After the generation operation, the color image data is reconstructed based on the enhanced component image data. For example, the method of claim 1, wherein the component image data is a pixel value (pixel Value). . The method of claim 1, wherein the first ratio is a ratio of respective mean values of the component image data, and the second ratio is a ratio of respective mean values of the enhancement component image data. For example, in the method of claim 3, wherein the weighting of the image data of the respective components is the sum of the mean values of the respective component image data divided by the mean values of the image data of all the components. For example, in the method of claim 3, the enhanced weighting of the image data of the respective enhancement components is the sum of the mean values of the respective enhancement component image data divided by the mean values of all the enhancement component image data. The method of claim 1, wherein the plurality of component image data is performed based on a color model selected from one of an RGB model, a CMYK model, and an HSI model. For example, in the method of claim 1, wherein the normalization operation is performed on the image data of the respective enhancement components, and the product of the original enhancement component image data minus the original enhancement component image data and the respective enhancement weights are calculated. The calculation results are taken as the image data of the respective enhancement components. The method of claim 1, wherein the determining whether to end the iterative operation is determining whether the number of iterations is reached. For example, in the method of claim 8, wherein the number of iterations is not reached, the normalized component image data of the normalization operation is used as the input of the iterative operation, and the iterative operation is performed. The method of claim 1, wherein the iterative operation further comprises reconstructing the number of iterations based on the enhanced component image data obtained by the number of iterations each time a predetermined number of iterations is reached Color image data. The method of claim 10, wherein the determining whether to end the iterative operation is determining whether a difference in different operation results obtained by different iteration times is less than a critical condition. The method of claim 1, wherein the reconstructing the color image data comprises superimposing the image data of the enhancement component and the component image data of the corresponding color image data after the completion of the iteration operation to generate A reconstruction of the image. A fundus image capturing device comprising: an image capturing device for capturing a fundus image; and an image capturing device for capturing the fundus image to output a color image data; a processor, based on the color image data, obtaining a plurality of component image data as an input of an iterative operation, the processor performing the iterative operation to enhance a transparent region of the fundus image in the color image data, The iterative operation includes an enhancement operation for computing a plurality of enhancement component image data, wherein each enhancement component image data is based on a sum of the respective component image data multiplied by respective weights, and a image based on the enhancement component image data The second ratio calculates the respective enhancement weights of the enhanced component image data, and after the processor ends the iterative operation, reconstructing the color image data based on the enhanced component image data. The device of claim 13 includes a memory that stores the color image data, the component image data, and the enhanced component image data, and a display device that displays the color after reconstruction The transparent area of the fundus image in the image data. The method of claim 14, wherein the processor reconstructs the number of iterations based on the image of the enhanced component obtained by the number of iterations each time a predetermined number of iterations is reached. The color image data, and the processor is configured to display the color image data reconstructed by different iterations according to an operation of the input interface to the display device.