Image pre-processing method and image processing apparatus for fundoscopic image

1. An image pre-processing method, comprising:

obtaining a region of interest from a fundoscopic image to generate a first image, wherein the region of interest is focused on an eyeball in the fundoscopic image;

performing a smoothing process on the first image to generate a second image;

comparing, for each pixel, a distance between value differences and a reference value, wherein the value differences are a first difference between a red channel value of the pixel and a neighboring pixel, a second difference between a green channel value of the pixel and the neighboring pixel, and a third difference between a blue channel value of the pixel and the neighboring pixel in the second image; and

increasing the value differences according to the distance to generate a third image in which at least one of the red channel value, the green channel value, and blue channel value of pixels of the second image is changed, comprising:

in response to the distance increasing, increasing a magnitude of an increase in the value differences;

in response to the distance reducing, reducing the magnitude of the increase in the value differences;

wherein the third image is used in pre-processing in at least one of a training phase and inference phase of a detection model based on a machine learning algorithm.

2. The image pre-processing method according to claim 1 , wherein obtaining the region of interest from the fundoscopic image comprises:

locating a center of the eyeball from the fundoscopic image; and

determining the region of interest according to the center.

3. The image pre-processing method according to claim 1 , wherein obtaining the region of interest from the fundoscopic image comprises:

finding a boundary of the eyeball from an outside of the fundoscopic image, wherein a lightness value on one side of the boundary of the eyeball is higher than the lightness value on the other side of the boundary of the eyeball; and

determining the region of interest according to the boundary of the eyeball.

4. The image pre-processing method according to claim 1 , wherein generating the first image comprises:

cutting out the region of interest from the fundoscopic image; and

adding a background color outside the region of interest to form the first image.

5. The image pre-processing method according to claim 1 , wherein the smoothing process is Gaussian blur, and performing the smoothing process on the first image comprises:

performing the Gaussian blur on the first image.

6. The image pre-processing method according to claim 1 , wherein increasing the value difference comprises:

increasing the value difference in proportion to the distance between the value differences and the reference value.

7. The image pre-processing method according to claim 1 , further comprising, after generating the third image:

inputting the third image to the detection model based on the machine learning algorithm.

8. An image processing apparatus, comprising:

a storage, storing a code; and

a processor, coupled to the storage, loading and executing the code to be configured to:

obtain a region of interest from a fundoscopic image to generate a first image, wherein the region of interest is focused on an eyeball in the fundoscopic image;

perform a smoothing process on the first image to generate a second image;

compare, for each pixel, a distance between value differences and a reference value, wherein the value differences are a first difference between a red channel value of the pixel and a neighboring pixel, a second difference between a green channel value of the pixel and the neighboring pixel, and a third difference between a blue channel value of the pixel and the neighboring pixel in the second image; and

increase the value differences according to the distance to generate a third image in which at least one of the red channel value, the green channel value, and blue channel value of pixels of the second image is changed, comprising:

in response to the distance increasing, increasing a magnitude of an increase in the value differences;

in response to the distance reducing, reducing the magnitude of the increase in the value differences;

wherein the third image is used in pre-processing in at least one of a training phase and inference phase of a detection model based on a machine learning algorithm.

9. The image processing apparatus according to claim 8 , wherein the processor is further configured to:

locate a center of the eyeball from the fundoscopic image; and

determine the region of interest according to the center.

10. The image processing apparatus according to claim 8 , wherein the processor is further configured to:

find a boundary of the eyeball from an outside to a center of the fundoscopic image, wherein a lightness value on one side of the boundary of the eyeball is higher than the lightness value on the other side of the boundary of the eyeball; and

determine the region of interest according to the boundary of the eyeball.

11. The image processing apparatus according to claim 8 , wherein the processor is further configured to:

cut out the region of interest from the fundoscopic image; and

add a background color outside the region of interest to form the first image.

12. The image processing apparatus according to claim 8 , wherein the smoothing process is Gaussian blur, and the processor is further configured to:

perform the Gaussian blur on the first image.

13. The image processing apparatus according to claim 8 , wherein the processor is further configured to:

increase the value differences in proportion to the distance between the value difference and the reference value.

14. The image processing apparatus according to claim 8 , wherein the processor is further configured to:

input the third image to the detection model based on the machine learning algorithm.