TWI639329B - Medical defogging image correction method - Google Patents

Abstract

A medical defogging image correction method is implemented by a processing unit, and includes the following steps: (A) converting a first image including a plurality of pixels and a second image obtained by performing the defogging process on the first image to Hue, saturation, and brightness color fields to obtain a plurality of first saturations of pixels associated with the first image and second saturations of pixels of the plurality of second images; (B) according to the first saturation Degree and the second saturation to obtain a saturation difference; (C) obtaining a correction value according to the first image and a threshold value; (D) obtaining a saturation according to the saturation difference value and the correction value Correcting value; and (E) correcting the second image according to the saturation correction value to obtain a third image. The image is applied to an environment with a large change in brightness by using a low sensitivity characteristic of saturation to the change of the light source.

Description

Medical defogging image correction method

The invention relates to an image data processing or generation, in particular to a medical defogging image correction method for laparoscopic images.

Laparoscopic surgery has been widely used in gastrointestinal, abdominal wall, endocrine and other operations in recent years. Unlike traditional open surgery surgeons who use a single large incision to enter the abdominal cavity for surgery, laparoscopic surgery requires only a small incision of 0.5 to 1.5 cm into each type of cannula, using special instruments and laparoscopic lenses. The tube enters the abdominal cavity and the surgeon views the laparoscopic image and performs the surgical procedure. Laparoscopic surgery allows surgeons to achieve the effects of traditional open surgery, and laparoscopic surgery has smaller wounds than traditional open surgery.

However, if the temperature of the laparoscopic lens is lower than the temperature in the abdominal cavity, after the laparoscopic lens enters the abdominal cavity, the heat in the abdominal cavity will quickly form a mist in the lens, which will blur the image on the display, thereby affecting the operation.

The existing method of removing image fog is to defogg the image first, and then correct the defogging image after obtaining the defogging image. However, the existing defogging image correction method is to transfer the defogging image to hue and saturation. In the color field of Hue (Saturation, Value, HSV), the image of the image is corrected to improve the defogging image. However, in laparoscopic surgery, the light source is provided by the laparoscope itself, and the cavity itself has no other light source. Therefore, when the laparoscopic movement or the movement of the object in the cavity (such as the instrument or tissue), the brightness of the overall image is very unstable, and the brightness of the image after the defrosting is easily affected by the change of the ambient brightness, so that the color shift occurs. The existing defogging image correction method is not suitable for images of environments where the light source varies greatly.

Accordingly, it is an object of the present invention to provide a medical defogging image correction method suitable for use in an image of a environment in which the brightness varies greatly.

Therefore, the medical defogging image correction method of the present invention is implemented by a processing unit and includes a step (A), a step (B), a step (C), a step (D), and a step (E). .

In the step (A), the processing unit converts a first image including a plurality of pixels and a second image obtained by the defogging process to the hue, saturation, and brightness color fields to obtain a plurality of pixels. a first saturation of pixels associated with the first image and a second saturation of pixels of the plurality of second images.

In step (B), the processing unit obtains a saturation difference value according to the first saturation and the second saturation.

In step (C), the processing unit obtains a correction value according to the first image and a threshold value.

In step (D), the processing unit obtains a saturation correction value based on the saturation difference value and the correction value.

In step (E), the processing unit corrects the second image according to the saturation correction value to obtain a third image.

The effect of the present invention is that the first image and the second image are converted into a hue, saturation, and brightness color field by the processing unit to obtain the first saturation and the second saturation, and utilize The low sensitivity characteristic of the saturation to the brightness, the second image is corrected according to the first saturation and the second saturation to obtain the third image without the color shift problem, and the image recognition degree is improved.

Referring to FIG. 1 , an image processing apparatus 100 for implementing an embodiment of the medical demisting image correction method of the present invention includes a storage unit 11 and a processing unit 12 electrically connected to the storage unit 11 and a laparoscopic device 200. .

The storage unit 11 stores a threshold, a first predetermined value, and a second predetermined value. Wherein the first predetermined value is greater than the second predetermined value.

The laparoscopic device 200 is used to photograph the inside of a human body to generate a first image including a plurality of pixels.

Referring to Figures 1 and 2, an example of how the image processing apparatus 100 implements the medical defogging image correction method of the present invention is illustrated.

In step S31, after the processing unit 12 receives the first image from the laparoscopic device 200, the processing unit 12 performs a defogging process on the first image to obtain a second image. It should be noted that, in this embodiment, the processing unit 12 obtains a pixel associated with the first image according to a Dark Channel Prior (DCP) method at a low intensity in at least one color channel. Dark channel image of pixel values. Then, according to the dark channel image, an atmospheric pixel value related to the global Atmospheric Light is obtained, wherein the atmospheric pixel value is a maximum value of the pixel values of the pixels of the dark channel image, and the processing unit 12 And according to the dark channel image and the atmospheric pixel value, a transmittance image related to the unscattered transmittance during the transmission of light in the atmosphere is obtained. Finally, the processing unit 12 obtains the second image according to the transmittance image and the atmospheric pixel value. However, in other embodiments, the processing unit 12 can utilize different defogging processes, and is not limited thereto.

In step S32, the processing unit 12 converts the first image and the second image into a Hue, Saturation, and Value (HSV) color field to obtain a plurality of correlations. a first saturation of a pixel of an image and a second saturation of a plurality of pixels of the second image.

In step S33, the processing unit 12 obtains a saturation difference value according to the first saturation and the second saturation. It should be noted that, in this embodiment, the saturation difference is an average of the first saturations of the pixels of the first image and an average of the second saturations of the pixels of the second image. a difference between the first difference of the difference between the maximum value and the minimum value of the first saturations of the pixels of the first image and the pixels of the second image. The difference between the second difference of the difference between the maximum value and the minimum value of the second saturation, but not limited thereto.

In step S34, the processing unit 12 obtains a correction value according to the first image and the threshold value stored by the storage unit 11.

It is to be noted that step S34 contains the following sub-steps.

In sub-step S341, the processing unit 12 sharpens and binarizes the first image edge to obtain a plurality of edge pixels, and adds the number of the edge pixels to obtain a correlation with the first image. Edge feature value.

In sub-step S342, the processing unit 12 determines whether the edge feature value is greater than the threshold value. When the processing unit 12 determines that the edge feature value is greater than the threshold value, sub-step S343 is performed, otherwise sub-step S344 is performed.

In sub-step S343, the processing unit 12 uses the first predetermined value stored in the storage unit 11 as the correction value.

In sub-step S344, the processing unit 12 uses the second predetermined value stored in the storage unit 11 as the correction value.

It is important to pay special attention to avoid too much color shift correction when the degree of fog is too low, or too much when the degree of fog is high, so that the saturation difference is not enough to make the color shift correction too small. The situation occurs. Therefore, in the embodiment, the edge sharpening degree of the first image is used as a reference for determining the degree of fogging. When the edge feature value is greater than the threshold value, the degree of fog is high, and thus the fog is used. The first predetermined value having a high degree is used as the correction value; and when the edge characteristic value is less than or equal to the threshold value, indicating that the degree of fog is low, the second predetermined value for the low degree of fog is used as the correction value.

In step S35, the processing unit 12 obtains a saturation correction value according to the saturation difference value and the correction value. It should be noted that, in this embodiment, the saturation correction value is a product of the saturation difference value and the correction value, but is not limited thereto.

In step S36, the processing unit 12 corrects the second image according to the saturation correction value to obtain a third image. It should be noted that, in this embodiment, the processing unit 12 subtracts the second saturation of each pixel of the second image from the saturation correction value to obtain the third image, but in other implementations. In the manner, the processing unit 12 may also add or multiply or divide the second saturation of each pixel of the second image with the saturation correction value, but not limited thereto.

In summary, the medical demisting image correcting method of the present invention converts the first image and the second image into a hue, saturation, and lightness color field by the processing unit 12 to obtain the first saturation and The second saturation, and using the low sensitivity characteristic of saturation to brightness, correcting the second image according to the first saturation and the second saturation to obtain the third image without color shift problem The image improves the visibility of the image, so the object of the present invention can be achieved.

However, the above is only the embodiment of the present invention, and the scope of the invention is not limited thereto, and all the simple equivalent changes and modifications according to the scope of the patent application and the patent specification of the present invention are still Within the scope of the invention patent.

100‧‧‧Image processing device

11‧‧‧ storage unit

12‧‧‧Processing unit

200‧‧‧ Laparoscopic device

S31~S36‧‧‧Steps

Sub-step S341~S344‧‧

Other features and effects of the present invention will be apparent from the following description of the drawings, wherein: Figure 1 is a block diagram illustrating an implementation of a medical defogging image correction method for practicing the present invention. FIG. 2 is a flow chart illustrating the embodiment; and FIG. 3 is a flowchart, and the sub-steps of step S34 of the embodiment are described with reference to FIG. 2.

Claims (9)

A medical defogging image correction method is implemented by a processing unit, and includes the following steps: (A) converting a first image including a plurality of pixels and a second image obtained by defogging the first image to Hue, saturation, and brightness color fields to obtain a plurality of first saturations of pixels associated with the first image and second saturations of pixels of the plurality of second images; (B) according to the first saturation Degree and the second saturation to obtain a saturation difference; (C) obtaining a correction value according to the first image and a threshold value; (D) obtaining a saturation according to the saturation difference value and the correction value Correcting value; and (E) correcting the second image according to the saturation correction value to obtain a third image. The medical defog image correction method according to claim 1, wherein in step (B), the saturation difference is an average value of the first saturations of the pixels of the first image and the second image The difference between the average values of the second saturations of the pixels. The medical defogging image correction method according to claim 1, wherein in step (B), the saturation difference is a difference between a maximum value and a minimum value of the first saturations of the pixels of the first image. A difference between a first difference and a second difference between a maximum value and a minimum value of the second saturations of the pixels of the second image. The medical defogging image correction method according to claim 1, wherein the step (C) includes the following substeps: (C-1) sharpening and binarizing the first image edge to obtain a correlation (C-2) determining whether the edge feature value is greater than the threshold value; (C-3) when determining that the edge feature value is greater than the threshold value, using a first predetermined value as the a correction value; and (C-4), when it is determined that the edge feature value is not greater than the threshold value, a second predetermined value is used as the correction value. The medical defogging image correction method according to claim 1, wherein in the step (D), the saturation correction value is a product of the saturation difference value and the correction value. The medical defog image correction method according to claim 1, wherein in step (E), the second saturation of each pixel of the second image is subtracted from the saturation correction value to obtain the first Three images. The medical defogging image correction method according to claim 1, wherein in step (E), the second saturation of each pixel of the second image is added to the saturation correction value to obtain the first Three images. The medical defogging image correction method according to claim 1, wherein in step (E), the second saturation of each pixel of the second image is multiplied by the saturation correction value to obtain the first Three images. The medical defogging image correction method according to claim 1, wherein in step (E), the second saturation of each pixel of the second image is divided by the saturation correction value to obtain the first Three images.